Digital Chinese Medicine最新文献_第8页

An interpretability model for syndrome differentiation of HBV-ACLF in traditional Chinese medicine using small-sample imbalanced data 利用小样本不平衡数据建立中药 HBV-ACLF 证候区分的可解释性模型

Q3 Medicine

Digital Chinese Medicine

Pub Date : 2024-06-01 Epub Date: 2024-11-01 DOI: 10.1016/j.dcmed.2024.09.005

Zhou Zhan , Peng Qinghua , Xiao Xiaoxia , Zou Beiji , Liu Bin , Guo Shuixia

<div><h3>Objective</h3><div>Clinical medical record data associated with hepatitis B-related acute-on-chronic liver failure (HBV-ACLF) generally have small sample sizes and a class imbalance. However, most machine learning models are designed based on balanced data and lack interpretability. This study aimed to propose a traditional Chinese medicine (TCM) diagnostic model for HBV-ACLF based on the TCM syndrome differentiation and treatment theory, which is clinically interpretable and highly accurate.</div></div><div><h3>Methods</h3><div>We collected medical records from 261 patients diagnosed with HBV-ACLF, including three syndromes: Yang jaundice (214 cases), Yang-Yin jaundice (41 cases), and Yin jaundice (6 cases). To avoid overfitting of the machine learning model, we excluded the cases of Yin jaundice. After data standardization and cleaning, we obtained 255 relevant medical records of Yang jaundice and Yang-Yin jaundice. To address the class imbalance issue, we employed the oversampling method and five machine learning methods, including logistic regression (LR), support vector machine (SVM), decision tree (DT), random forest (RF), and extreme gradient boosting (XGBoost) to construct the syndrome diagnosis models. This study used precision, F1 score, the area under the receiver operating characteristic (ROC) curve (AUC), and accuracy as model evaluation metrics. The model with the best classification performance was selected to extract the diagnostic rule, and its clinical significance was thoroughly analyzed. Furthermore, we proposed a novel multiple-round stable rule extraction (MRSRE) method to obtain a stable rule set of features that can exhibit the model’s clinical interpretability.</div></div><div><h3>Results</h3><div>The precision of the five machine learning models built using oversampled balanced data exceeded 0.90. Among these models, the accuracy of RF classification of syndrome types was 0.92, and the mean F1 scores of the two categories of Yang jaundice and Yang-Yin jaundice were 0.93 and 0.94, respectively. Additionally, the AUC was 0.98. The extraction rules of the RF syndrome differentiation model based on the MRSRE method revealed that the common features of Yang jaundice and Yang-Yin jaundice were wiry pulse, yellowing of the urine, skin, and eyes, normal tongue body, healthy sublingual vessel, nausea, oil loathing, and poor appetite. The main features of Yang jaundice were a red tongue body and thickened sublingual vessels, whereas those of Yang-Yin jaundice were a dark tongue body, pale white tongue body, white tongue coating, lack of strength, slippery pulse, light red tongue body, slimy tongue coating, and abdominal distension. This is aligned with the classifications made by TCM experts based on TCM syndrome differentiation and treatment theory.</div></div><div><h3>Conclusion</h3><div>Our model can be utilized for differentiating HBV-ACLF syndromes, which has the potential to be applied to generate other clinically i

目标与乙型肝炎相关的急性慢性肝衰竭（HBV-ACLF）相关的临床病历数据通常样本量较小，且存在类别不平衡的问题。然而，大多数机器学习模型都是基于平衡数据设计的，缺乏可解释性。本研究旨在提出一种基于中医辨证论治理论的 HBV-ACLF 中医诊断模型，该模型具有临床可解释性和高准确性：阳黄（214 例）、阳阴黄（41 例）和阴黄（6 例）。为了避免机器学习模型的过度拟合，我们排除了阴性黄疸的病例。经过数据标准化和清理后，我们获得了 255 份阳黄疸和阳阴黄疸的相关病历。为了解决类不平衡问题，我们采用了超采样方法和五种机器学习方法，包括逻辑回归（LR）、支持向量机（SVM）、决策树（DT）、随机森林（RF）和极梯度提升（XGBoost），来构建综合征诊断模型。本研究采用精确度、F1得分、接收者操作特征曲线下面积（AUC）和准确度作为模型评价指标。选择分类性能最佳的模型提取诊断规则，并深入分析其临床意义。此外，我们还提出了一种新颖的多轮稳定规则提取（MRSRE）方法，以获得稳定的规则特征集，从而展现模型的临床可解释性。在这些模型中，综合征类型 RF 分类的准确率为 0.92，而阳黄疸和阳阴黄疸两个类别的平均 F1 分数分别为 0.93 和 0.94。此外，AUC 为 0.98。基于 MRSRE 方法的射频综合征分型模型的提取规则显示，阳黄疸和阳阴黄疸的共同特征是脉细数，尿黄、肤黄、目黄，舌体正常，舌下血管健康，恶心、厌油、食欲不振。阳黄疸的主要特征是舌体红，舌下血管增粗，而阳阴黄疸的主要特征是舌体暗、舌体淡白、舌苔白、乏力、脉滑、舌体淡红、舌苔黏腻、腹胀。结论我们的模型可用于鉴别 HBV-ACLF 综合征，并有可能应用于生成其他临床可解释模型，在样本量较小且类群不平衡的临床数据上具有较高的准确性。

{"title":"An interpretability model for syndrome differentiation of HBV-ACLF in traditional Chinese medicine using small-sample imbalanced data","authors":"Zhou Zhan , Peng Qinghua , Xiao Xiaoxia , Zou Beiji , Liu Bin , Guo Shuixia","doi":"10.1016/j.dcmed.2024.09.005","DOIUrl":"10.1016/j.dcmed.2024.09.005","url":null,"abstract":"<div><h3>Objective</h3><div>Clinical medical record data associated with hepatitis B-related acute-on-chronic liver failure (HBV-ACLF) generally have small sample sizes and a class imbalance. However, most machine learning models are designed based on balanced data and lack interpretability. This study aimed to propose a traditional Chinese medicine (TCM) diagnostic model for HBV-ACLF based on the TCM syndrome differentiation and treatment theory, which is clinically interpretable and highly accurate.</div></div><div><h3>Methods</h3><div>We collected medical records from 261 patients diagnosed with HBV-ACLF, including three syndromes: Yang jaundice (214 cases), Yang-Yin jaundice (41 cases), and Yin jaundice (6 cases). To avoid overfitting of the machine learning model, we excluded the cases of Yin jaundice. After data standardization and cleaning, we obtained 255 relevant medical records of Yang jaundice and Yang-Yin jaundice. To address the class imbalance issue, we employed the oversampling method and five machine learning methods, including logistic regression (LR), support vector machine (SVM), decision tree (DT), random forest (RF), and extreme gradient boosting (XGBoost) to construct the syndrome diagnosis models. This study used precision, F1 score, the area under the receiver operating characteristic (ROC) curve (AUC), and accuracy as model evaluation metrics. The model with the best classification performance was selected to extract the diagnostic rule, and its clinical significance was thoroughly analyzed. Furthermore, we proposed a novel multiple-round stable rule extraction (MRSRE) method to obtain a stable rule set of features that can exhibit the model’s clinical interpretability.</div></div><div><h3>Results</h3><div>The precision of the five machine learning models built using oversampled balanced data exceeded 0.90. Among these models, the accuracy of RF classification of syndrome types was 0.92, and the mean F1 scores of the two categories of Yang jaundice and Yang-Yin jaundice were 0.93 and 0.94, respectively. Additionally, the AUC was 0.98. The extraction rules of the RF syndrome differentiation model based on the MRSRE method revealed that the common features of Yang jaundice and Yang-Yin jaundice were wiry pulse, yellowing of the urine, skin, and eyes, normal tongue body, healthy sublingual vessel, nausea, oil loathing, and poor appetite. The main features of Yang jaundice were a red tongue body and thickened sublingual vessels, whereas those of Yang-Yin jaundice were a dark tongue body, pale white tongue body, white tongue coating, lack of strength, slippery pulse, light red tongue body, slimy tongue coating, and abdominal distension. This is aligned with the classifications made by TCM experts based on TCM syndrome differentiation and treatment theory.</div></div><div><h3>Conclusion</h3><div>Our model can be utilized for differentiating HBV-ACLF syndromes, which has the potential to be applied to generate other clinically i","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"7 2","pages":"Pages 137-147"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Zuogui Jiangtang Jieyu Formula ameliorating hippocampal neuronal apoptosis in diabetic rats with depression by inhibiting JNK signaling pathway 左归姜汤解郁方通过抑制JNK信号通路改善糖尿病抑郁大鼠海马神经元凋亡

Q3 Medicine

Digital Chinese Medicine

Pub Date : 2024-06-01 Epub Date: 2024-11-01 DOI: 10.1016/j.dcmed.2024.09.010

Zhao Hongqing , Mou Qingrui , Jiang Jiaqi , Zhu Xuan , Liu Zhuo , Wang Yuhong

<div><h3>Objective</h3><div>To investigate the effect of Zuogui Jiangtang Jieyu Formula (左归降糖解郁方, ZJJF) on hippocampal neuron apoptosis in diabetic rats with depression and to ascertain whether its mechanism involves the regulation of JNK signaling pathway.</div></div><div><h3>Methods</h3><div>(i) A total of 72 specific pathogen-free (SPF) grade male Sprague Dawley (SD) rats were randomly divided into six groups, with 12 rats in each group: control, model, metformin (Met, 0.18 g/kg) + fluoxetine (Flu, 1.8 mg/kg), and the high-, medium-, and low-ZJJF dosages (ZJJF-H, 20.52 g/kg; ZJJF-M, 10.26 g/kg; ZJJF-L, 5.13 g/kg) groups. All groups except control group were injected once via the tail vein with streptozotocin (STZ, 38 mg/kg) combined with 28 d of chronic unpredictable mild stress (CUMS) to establish diabetic rat models with depression. During the CUMS modeling period, treatments were administered via gavage, with control and model groups receiving an equivalent volume of distilled water for 28 d. The efficacy of ZJJF in reducing blood sugar and alleviating depression was evaluated by measuring fasting blood glucose, insulin, and glycated hemoglobin levels, along with behavioral assessments, including the open field test (OFT), forced swim test (FST), and sucrose preference test (SPT). Hippocampal tissue damage and neuronal apoptosis were evaluated using hematoxylin-eosin (HE) staining and terminal deoxynucleotidyl transferase-mediated dUTP nick-end labeling (TUNEL) staining. Apoptosis-related proteins Bax, Bcl-2, caspase-3, and the expression levels of JNK/Elk-1/c-fos signaling pathway were detected using Western blot and real-time quantitative polymerase chain reaction (RT-qPCR). (ii) To further elucidate the role of JNK signaling pathway in hippocampal neuronal apoptosis and the pharmacological effects of ZJJF, an additional 50 SPF grade male SD rats were randomly divided into five groups, with 10 rats in each group: control, model, SP600125 (SP6, a JNK antagonist, 10 mg/kg), ZJJF (20.52 g/kg), and ZJJF (20.52 g/kg) + Anisomycin (Aniso, a JNK agonist, 15 mg/kg) groups. Except for control group, all groups were established as diabetic rat models with depression, and treatments were administered via gavage for ZJJF and intraperitoneal injection for SP6 and Aniso for 28 d during the CUMS modeling period. Behavioral changes in rats were evaluated through the OFT, FST, and SPT, and hippocampal neuron damage and apoptosis were observed using HE staining, Nissl staining, TUNEL staining, and transmission electron microscopy (TEM). Changes in apoptosis-related proteins and JNK signaling pathway in the hippocampal tissues of rats were also analyzed.</div></div><div><h3>Results</h3><div>(i) ZJJF significantly reduced the high blood glucose, insulin, and glycated hemoglobin levels in model rats (<em>P</em> < 0.01). It increased autonomous activity and decreased despair-like behaviors (<em>P</em> < 0.01), improved the pathological damage of hippocam

目的研究左归降糖解郁方对糖尿病伴抑郁大鼠海马神经元凋亡的影响，并探讨其机制是否涉及JNK信号通路的调控。方法（i）将72只无特定病原体（SPF）级雄性Sprague Dawley（SD）大鼠随机分为6组，每组12只，分别为对照组、模型组、二甲双胍（Met，0.18 g/kg）+氟西汀（Flu，1.8 mg/kg）组、ZJJF高、中、低剂量组（ZJJF-H，20.52 g/kg；ZJJF-M，10.26 g/kg；ZJJF-L，5.13 g/kg）。除对照组外，其他各组均经尾部静脉注射一次链脲佐菌素（STZ，38 mg/kg），并给予28 d的慢性不可预知的轻度应激（CUMS），以建立糖尿病大鼠抑郁模型。通过测量空腹血糖、胰岛素和糖化血红蛋白水平，以及行为评估，包括开阔地试验（OFT）、强迫游泳试验（FST）和蔗糖偏好试验（SPT），评估了ZJJF降低血糖和缓解抑郁的功效。使用苏木精-伊红（HE）染色和末端脱氧核苷酸转移酶介导的 dUTP nick-end 标记（TUNEL）染色评估海马组织损伤和神经细胞凋亡。使用 Western 印迹和实时定量聚合酶链反应（RT-qPCR）检测凋亡相关蛋白 Bax、Bcl-2、caspase-3 和 JNK/Elk-1/c-fos 信号通路的表达水平。(ii) 为进一步阐明 JNK 信号通路在海马神经元凋亡中的作用及 ZJJF 的药理作用，将另外 50 只 SPF 级雄性 SD 大鼠随机分为 5 组，每组 10 只，分别为对照组、模型组、SP600125（SP6，一种 JNK 拮抗剂，10 mg/kg）组、ZJJF（20.52 g/kg）组、ZJJF（20.52 g/kg）+ Anisomycin（Aniso，一种 JNK 激动剂，15 mg/kg）组。除对照组外，其余各组均为糖尿病大鼠抑郁模型，在CUMS建模期间，ZJJF通过灌胃给药，SP6和Aniso通过腹腔注射给药，持续28天。通过OFT、FST和SPT评估大鼠的行为变化，并使用HE染色、Nissl染色、TUNEL染色和透射电子显微镜（TEM）观察海马神经元损伤和凋亡。结果(i) ZJJF能显著降低模型大鼠的高血糖、胰岛素和糖化血红蛋白水平（P < 0.01）。ZJJF能提高大鼠的自主活动能力，减少绝望样行为（P< 0.01），改善海马神经元的病理损伤，增加神经元核的数量（P< 0.01），减少机化细胞、空泡细胞和凋亡神经元的数量（分别为P< 0.05、P< 0.01和P< 0.01）。ZJJF 下调促凋亡蛋白 Bax 和 caspase-3 的表达水平（P <；0.01），上调抗凋亡蛋白 Bcl-2 的表达水平（P <；0.01），并显著抑制磷酸化 JNK（p-JNK）、Elk-1 和 c-fos 的过度表达（P <；0.01）。(ii) SP6 增加了模型大鼠的自主活动，减少了绝望时间（P <；0.05），但对蔗糖偏好无显著影响（P >；0.05）。它增加了海马神经元中 Nissl 体的数量（P <；0.01），降低了 Bax（P <；0.01）和 caspase-3 （P <；0.05）的蛋白表达水平，并减少了凋亡神经元的数量（P <；0.05）。SP6还能提高Bcl-2的表达水平（P <0.01），抑制p-JNK、Elk-1和c-fos的高表达水平（分别为P <0.01、P <0.01和P <0.05），表明糖尿病抑郁大鼠海马神经元凋亡与JNK信号通路的异常激活有关。与ZJJF组相比，ZJJF + Aniso组大鼠的蔗糖偏好下降（P < 0.05），绝望时间延长（P < 0.01），海马神经元损伤更为显著。该组还表现出 Bcl-2 表达水平下降（P < 0.01），Bax、caspase-3、p-JNK、Elk-1 和 c-fos 表达水平上升（P < 0.01、P < 0.05、P < 0.05、P < 0.01和P <0.05），表明ZJJF的抗抑郁作用、对神经元凋亡的改善作用以及对JNK信号分子的调控作用都可以通过特定的JNK激动剂逆转。结论ZJJF具有显著的降血糖作用，并通过抑制JNK信号通路的活化改善海马神经元的凋亡，是临床治疗糖尿病抑郁症的有效配方。

{"title":"Zuogui Jiangtang Jieyu Formula ameliorating hippocampal neuronal apoptosis in diabetic rats with depression by inhibiting JNK signaling pathway","authors":"Zhao Hongqing , Mou Qingrui , Jiang Jiaqi , Zhu Xuan , Liu Zhuo , Wang Yuhong","doi":"10.1016/j.dcmed.2024.09.010","DOIUrl":"10.1016/j.dcmed.2024.09.010","url":null,"abstract":"<div><h3>Objective</h3><div>To investigate the effect of Zuogui Jiangtang Jieyu Formula (左归降糖解郁方, ZJJF) on hippocampal neuron apoptosis in diabetic rats with depression and to ascertain whether its mechanism involves the regulation of JNK signaling pathway.</div></div><div><h3>Methods</h3><div>(i) A total of 72 specific pathogen-free (SPF) grade male Sprague Dawley (SD) rats were randomly divided into six groups, with 12 rats in each group: control, model, metformin (Met, 0.18 g/kg) + fluoxetine (Flu, 1.8 mg/kg), and the high-, medium-, and low-ZJJF dosages (ZJJF-H, 20.52 g/kg; ZJJF-M, 10.26 g/kg; ZJJF-L, 5.13 g/kg) groups. All groups except control group were injected once via the tail vein with streptozotocin (STZ, 38 mg/kg) combined with 28 d of chronic unpredictable mild stress (CUMS) to establish diabetic rat models with depression. During the CUMS modeling period, treatments were administered via gavage, with control and model groups receiving an equivalent volume of distilled water for 28 d. The efficacy of ZJJF in reducing blood sugar and alleviating depression was evaluated by measuring fasting blood glucose, insulin, and glycated hemoglobin levels, along with behavioral assessments, including the open field test (OFT), forced swim test (FST), and sucrose preference test (SPT). Hippocampal tissue damage and neuronal apoptosis were evaluated using hematoxylin-eosin (HE) staining and terminal deoxynucleotidyl transferase-mediated dUTP nick-end labeling (TUNEL) staining. Apoptosis-related proteins Bax, Bcl-2, caspase-3, and the expression levels of JNK/Elk-1/c-fos signaling pathway were detected using Western blot and real-time quantitative polymerase chain reaction (RT-qPCR). (ii) To further elucidate the role of JNK signaling pathway in hippocampal neuronal apoptosis and the pharmacological effects of ZJJF, an additional 50 SPF grade male SD rats were randomly divided into five groups, with 10 rats in each group: control, model, SP600125 (SP6, a JNK antagonist, 10 mg/kg), ZJJF (20.52 g/kg), and ZJJF (20.52 g/kg) + Anisomycin (Aniso, a JNK agonist, 15 mg/kg) groups. Except for control group, all groups were established as diabetic rat models with depression, and treatments were administered via gavage for ZJJF and intraperitoneal injection for SP6 and Aniso for 28 d during the CUMS modeling period. Behavioral changes in rats were evaluated through the OFT, FST, and SPT, and hippocampal neuron damage and apoptosis were observed using HE staining, Nissl staining, TUNEL staining, and transmission electron microscopy (TEM). Changes in apoptosis-related proteins and JNK signaling pathway in the hippocampal tissues of rats were also analyzed.</div></div><div><h3>Results</h3><div>(i) ZJJF significantly reduced the high blood glucose, insulin, and glycated hemoglobin levels in model rats (<em>P</em> < 0.01). It increased autonomous activity and decreased despair-like behaviors (<em>P</em> < 0.01), improved the pathological damage of hippocam","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"7 2","pages":"Pages 195-208"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The enlightenment of artificial intelligence large-scale model on the research of intelligent eye diagnosis in traditional Chinese medicine 人工智能大型模型对中医智能眼诊研究的启示

Q3 Medicine

Digital Chinese Medicine

Pub Date : 2024-06-01 Epub Date: 2024-11-01 DOI: 10.1016/j.dcmed.2024.09.001

Yuan Gao , Zixuan Wu , Boyang Sheng , Fu Zhang , Yong Cheng , Junfeng Yan , Qinghua Peng

Eye diagnosis is a method for inspecting systemic diseases and syndromes by observing the eyes. With the development of intelligent diagnosis in traditional Chinese medicine (TCM), artificial intelligence (AI) can improve the accuracy and efficiency of eye diagnosis. However, the research on intelligent eye diagnosis still faces many challenges, including the lack of standardized and precisely labeled data, multi-modal information analysis, and artificial intelligence models for syndrome differentiation. The widespread application of AI models in medicine provides new insights and opportunities for the research of eye diagnosis intelligence. This study elaborates on the three key technologies of AI models in the intelligent application of TCM eye diagnosis, and explores the implications for the research of eye diagnosis intelligence. First, a database concerning eye diagnosis was established based on self-supervised learning so as to solve the issues related to the lack of standardized and precisely labeled data. Next, the cross-modal understanding and generation of deep neural network models to address the problem of lacking multi-modal information analysis. Last, the building of data-driven models for eye diagnosis to tackle the issue of the absence of syndrome differentiation models. In summary, research on intelligent eye diagnosis has great potential to be applied the surge of AI model applications.

眼诊是通过观察眼睛来检查全身性疾病和综合征的一种方法。随着中医智能诊断的发展，人工智能（AI）可以提高眼科诊断的准确性和效率。然而，眼科智能诊断的研究仍面临诸多挑战，包括缺乏标准化和精确标记的数据、多模态信息分析以及用于综合征分型的人工智能模型。人工智能模型在医学领域的广泛应用为眼科诊断智能化研究提供了新的启示和机遇。本研究阐述了人工智能模型在中医眼科诊断智能化应用中的三大关键技术，并探讨了其对眼科诊断智能化研究的启示。首先，建立基于自监督学习的眼科诊断数据库，以解决缺乏标准化和精确标注数据的问题。其次，通过跨模态理解和生成深度神经网络模型，解决缺乏多模态信息分析的问题。最后，建立数据驱动的眼科诊断模型，解决缺乏综合征区分模型的问题。总之，智能眼科诊断研究大有可为，将掀起人工智能模型应用的热潮。

{"title":"The enlightenment of artificial intelligence large-scale model on the research of intelligent eye diagnosis in traditional Chinese medicine","authors":"Yuan Gao , Zixuan Wu , Boyang Sheng , Fu Zhang , Yong Cheng , Junfeng Yan , Qinghua Peng","doi":"10.1016/j.dcmed.2024.09.001","DOIUrl":"10.1016/j.dcmed.2024.09.001","url":null,"abstract":"<div><div>Eye diagnosis is a method for inspecting systemic diseases and syndromes by observing the eyes. With the development of intelligent diagnosis in traditional Chinese medicine (TCM), artificial intelligence (AI) can improve the accuracy and efficiency of eye diagnosis. However, the research on intelligent eye diagnosis still faces many challenges, including the lack of standardized and precisely labeled data, multi-modal information analysis, and artificial intelligence models for syndrome differentiation. The widespread application of AI models in medicine provides new insights and opportunities for the research of eye diagnosis intelligence. This study elaborates on the three key technologies of AI models in the intelligent application of TCM eye diagnosis, and explores the implications for the research of eye diagnosis intelligence. First, a database concerning eye diagnosis was established based on self-supervised learning so as to solve the issues related to the lack of standardized and precisely labeled data. Next, the cross-modal understanding and generation of deep neural network models to address the problem of lacking multi-modal information analysis. Last, the building of data-driven models for eye diagnosis to tackle the issue of the absence of syndrome differentiation models. In summary, research on intelligent eye diagnosis has great potential to be applied the surge of AI model applications.</div></div>","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"7 2","pages":"Pages 101-107"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Constitution identification model in traditional Chinese medicine based on multiple features 基于多重特征的中医体质辨识模型

Q3 Medicine

Digital Chinese Medicine

Pub Date : 2024-06-01 Epub Date: 2024-11-01 DOI: 10.1016/j.dcmed.2024.09.002

Anying Xu , Tianshu Wang , Tao Yang , Han Xiao , Xiaoyu Zhang , Ziyan Wang , Qi Zhang , Xiao Li , Hongcai Shang , Kongfa Hu

Objective

To construct a precise model for identifying traditional Chinese medicine (TCM) constitutions, thereby offering optimized guidance for clinical diagnosis and treatment planning, and ultimately enhancing medical efficiency and treatment outcomes.

Methods

First, TCM full-body inspection data acquisition equipment was employed to collect full-body standing images of healthy people, from which the constitutions were labelled and defined in accordance with the Constitution in Chinese Medicine Questionnaire (CCMQ), and a dataset encompassing labelled constitutions was constructed. Second, heat-suppression valve (HSV) color space and improved local binary patterns (LBP) algorithm were leveraged for the extraction of features such as facial complexion and body shape. In addition, a dual-branch deep network was employed to collect deep features from the full-body standing images. Last, the random forest (RF) algorithm was utilized to learn the extracted multifeatures, which were subsequently employed to establish a TCM constitution identification model. Accuracy, precision, and F1 score were the three measures selected to assess the performance of the model.

Results

It was found that the accuracy, precision, and F1 score of the proposed model based on multifeatures for identifying TCM constitutions were 0.842, 0.868, and 0.790, respectively. In comparison with the identification models that encompass a single feature, either a single facial complexion feature, a body shape feature, or deep features, the accuracy of the model that incorporating all the aforementioned features was elevated by 0.105, 0.105, and 0.079, the precision increased by 0.164, 0.164, and 0.211, and the F1 score rose by 0.071, 0.071, and 0.084, respectively.

Conclusion

The research findings affirmed the viability of the proposed model, which incorporated multifeatures, including the facial complexion feature, the body shape feature, and the deep feature. In addition, by employing the proposed model, the objectification and intelligence of identifying constitutions in TCM practices could be optimized.

方法首先，利用中医全身检查数据采集设备采集健康人的全身站立图像，并根据中医体质问卷（CCMQ）对体质进行标注和定义，构建包含标注体质的数据集。其次，利用热抑制阀（HSV）色彩空间和改进的局部二元模式（LBP）算法提取面部肤色和体形等特征。此外，还采用了双分支深度网络从全身站立图像中收集深度特征。最后，利用随机森林（RF）算法对提取的多特征进行学习，进而建立中医体质识别模型。结果发现，所提出的基于多特征的中医体质识别模型的准确率、精确度和 F1 分数分别为 0.842、0.868 和 0.790。与只包含单一面色特征、体形特征或深层特征的识别模型相比，包含上述所有特征的模型的准确度分别提高了 0.105、0.105 和 0.079，精确度分别提高了 0.164、0.164 和 0.164。结论研究结果证实了所提出模型的可行性，该模型包含了多种特征，包括面部肤色特征、身体形状特征和深层特征。此外，通过使用所提出的模型，可以优化中医实践中体质辨识的客观化和智能化。

{"title":"Constitution identification model in traditional Chinese medicine based on multiple features","authors":"Anying Xu , Tianshu Wang , Tao Yang , Han Xiao , Xiaoyu Zhang , Ziyan Wang , Qi Zhang , Xiao Li , Hongcai Shang , Kongfa Hu","doi":"10.1016/j.dcmed.2024.09.002","DOIUrl":"10.1016/j.dcmed.2024.09.002","url":null,"abstract":"<div><h3>Objective</h3><div>To construct a precise model for identifying traditional Chinese medicine (TCM) constitutions, thereby offering optimized guidance for clinical diagnosis and treatment planning, and ultimately enhancing medical efficiency and treatment outcomes.</div></div><div><h3>Methods</h3><div>First, TCM full-body inspection data acquisition equipment was employed to collect full-body standing images of healthy people, from which the constitutions were labelled and defined in accordance with the Constitution in Chinese Medicine Questionnaire (CCMQ), and a dataset encompassing labelled constitutions was constructed. Second, heat-suppression valve (HSV) color space and improved local binary patterns (LBP) algorithm were leveraged for the extraction of features such as facial complexion and body shape. In addition, a dual-branch deep network was employed to collect deep features from the full-body standing images. Last, the random forest (RF) algorithm was utilized to learn the extracted multifeatures, which were subsequently employed to establish a TCM constitution identification model. Accuracy, precision, and F1 score were the three measures selected to assess the performance of the model.</div></div><div><h3>Results</h3><div>It was found that the accuracy, precision, and F1 score of the proposed model based on multifeatures for identifying TCM constitutions were 0.842, 0.868, and 0.790, respectively. In comparison with the identification models that encompass a single feature, either a single facial complexion feature, a body shape feature, or deep features, the accuracy of the model that incorporating all the aforementioned features was elevated by 0.105, 0.105, and 0.079, the precision increased by 0.164, 0.164, and 0.211, and the F1 score rose by 0.071, 0.071, and 0.084, respectively.</div></div><div><h3>Conclusion</h3><div>The research findings affirmed the viability of the proposed model, which incorporated multifeatures, including the facial complexion feature, the body shape feature, and the deep feature. In addition, by employing the proposed model, the objectification and intelligence of identifying constitutions in TCM practices could be optimized.</div></div>","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"7 2","pages":"Pages 108-119"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572373","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep learning-based recognition of stained tongue coating images 基于深度学习的染色舌苔图像识别

Q3 Medicine

Digital Chinese Medicine

Pub Date : 2024-06-01 Epub Date: 2024-11-01 DOI: 10.1016/j.dcmed.2024.09.004

Liqin Zhong , Guojiang Xin , Qinghua Peng , Ji Cui , Lei Zhu , Hao Liang

Objective

To build a dataset encompassing a large number of stained tongue coating images and process it using deep learning to automatically recognize stained tongue coating images.

Methods

A total of 1 001 images of stained tongue coating from healthy students at Hunan University of Chinese Medicine and 1 007 images of pathological (non-stained) tongue coating from hospitalized patients at The First Hospital of Hunan University of Chinese Medicine with lung cancer, diabetes, and hypertension were collected. The tongue images were randomized into the training, validation, and testing datasets in a 7 : 2 : 1 ratio. A deep learning model was constructed using the ResNet50 for recognizing stained tongue coating in the training and validation datasets. The training period was 90 epochs. The model’s performance was evaluated by its accuracy, loss curve, recall, F1 score, confusion matrix, receiver operating characteristic (ROC) curve, and precision-recall (PR) curve in the tasks of predicting stained tongue coating images in the testing dataset. The accuracy of the deep learning model was compared with that of attending physicians of traditional Chinese medicine (TCM).

Results

The training results showed that after 90 epochs, the model presented an excellent classification performance. The loss curve and accuracy were stable, showing no signs of overfitting. The model achieved an accuracy, recall, and F1 score of 92%, 91%, and 92%, respectively. The confusion matrix revealed an accuracy of 92% for the model and 69% for TCM practitioners. The areas under the ROC and PR curves were 0.97 and 0.95, respectively. Conclusion: The deep learning model constructed using ResNet50 can effectively recognize stained coating images with greater accuracy than visual inspection of TCM practitioners. This model has the potential to assist doctors in identifying false tongue coating and preventing misdiagnosis.

方法收集湖南中医药大学健康学生的染色舌苔图像1001张，以及湖南中医药大学附属第一医院肺癌、糖尿病、高血压等住院病人的病理（非染色）舌苔图像1007张。舌苔图像按 7 : 2 : 1 的比例随机分为训练集、验证集和测试集。使用 ResNet50 构建了一个深度学习模型，用于识别训练和验证数据集中的染色舌苔。训练周期为 90 个历元。在预测测试数据集中染色舌苔图像的任务中，通过准确率、损失曲线、召回率、F1 分数、混淆矩阵、接收器操作特征曲线（ROC）和精度-召回曲线（PR）来评估模型的性能。结果训练结果表明，经过 90 个历元的训练后，模型的分类性能非常出色。损失曲线和准确率都很稳定，没有过拟合的迹象。模型的准确率、召回率和 F1 分数分别为 92%、91% 和 92%。混淆矩阵显示，模型的准确率为 92%，中医的准确率为 69%。ROC 和 PR 曲线下的面积分别为 0.97 和 0.95。结论使用 ResNet50 构建的深度学习模型能有效识别染色涂层图像，其准确率高于中医目测。该模型有望帮助医生识别虚假舌苔，防止误诊。

{"title":"Deep learning-based recognition of stained tongue coating images","authors":"Liqin Zhong , Guojiang Xin , Qinghua Peng , Ji Cui , Lei Zhu , Hao Liang","doi":"10.1016/j.dcmed.2024.09.004","DOIUrl":"10.1016/j.dcmed.2024.09.004","url":null,"abstract":"<div><h3>Objective</h3><div>To build a dataset encompassing a large number of stained tongue coating images and process it using deep learning to automatically recognize stained tongue coating images.</div></div><div><h3>Methods</h3><div>A total of 1 001 images of stained tongue coating from healthy students at Hunan University of Chinese Medicine and 1 007 images of pathological (non-stained) tongue coating from hospitalized patients at The First Hospital of Hunan University of Chinese Medicine with lung cancer, diabetes, and hypertension were collected. The tongue images were randomized into the training, validation, and testing datasets in a 7 : 2 : 1 ratio. A deep learning model was constructed using the ResNet50 for recognizing stained tongue coating in the training and validation datasets. The training period was 90 epochs. The model’s performance was evaluated by its accuracy, loss curve, recall, F1 score, confusion matrix, receiver operating characteristic (ROC) curve, and precision-recall (PR) curve in the tasks of predicting stained tongue coating images in the testing dataset. The accuracy of the deep learning model was compared with that of attending physicians of traditional Chinese medicine (TCM).</div></div><div><h3>Results</h3><div>The training results showed that after 90 epochs, the model presented an excellent classification performance. The loss curve and accuracy were stable, showing no signs of overfitting. The model achieved an accuracy, recall, and F1 score of 92%, 91%, and 92%, respectively. The confusion matrix revealed an accuracy of 92% for the model and 69% for TCM practitioners. The areas under the ROC and PR curves were 0.97 and 0.95, respectively. <strong>Conclusion</strong>: The deep learning model constructed using ResNet50 can effectively recognize stained coating images with greater accuracy than visual inspection of TCM practitioners. This model has the potential to assist doctors in identifying false tongue coating and preventing misdiagnosis.</div></div>","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"7 2","pages":"Pages 129-136"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Antidepressant effects of Yuanzhi (Polygalae Radix) extract on chronic unpredictable mild stress-induced depression in rats: modulation of the NLRP3 inflammasome and NF-κB pathway 远志提取物对慢性不可预知轻度应激诱导的大鼠抑郁症的抗抑郁作用：NLRP3炎性体和NF-κB通路的调节作用

Q3 Medicine

Digital Chinese Medicine

Pub Date : 2024-06-01 Epub Date: 2024-11-01 DOI: 10.1016/j.dcmed.2024.09.009

Yuzhen Chen , Yongzhi Zhao , Yiwen Zhang , Fang Chen , Muhammad Iqbal Choudhary , Xinmin Liu , Ning Jiang

<div><h3>Objective</h3><div>To investigate the antidepressant effects of Yuanzhi (Polygalae Radix, PR) aqueous extract on chronic unpredictable mild stress (CUMS)-induced depression rat models and the underlying mechanisms.</div></div><div><h3>Methods</h3><div>A total of 40 male Sprague Dawley (SD) rats were randomly divided into control, model, low dose of PR (PR-L, 0.5 g/kg), high dose of PR (PR-H, 1 g/kg), and fluoxetine (10 mg/kg) groups, with 8 rats in each group. Except for the rats in control group, those in the other four groups underwent CUMS-induced depression modeling. PR and fluoxetine were administered intragastrically once daily, 30 min prior to the CUMS procedure, for 14 consecutive days until the behavioral tests were performed. After CUMS modeling, the sucrose preference test (SPT), open field test (OFT), novelty-suppressed feeding test (NSFT), forced swim test (FST), and tail suspension test (TST) were employed to assess the pharmacological effects of PR on the mitigation of depressive-like behaviors in rat models. Additionally, the enzyme-linked immunosorbent assay (ELISA) was utilized to quantify the serum levels of tumor necrosis factor (TNF)-<em>α</em>, interleukin (IL)-6, and IL-1<em>β</em> in the rats. Western blot analysis was also conducted to evaluate the protein expression levels of nuclear factor kappa-B (NF-<em>κ</em>B), inducible nitric oxide synthase (iNOS), cyclooxygenase-2 (COX-2), nucleotide-binding oligomerization domain (NOD)-like receptor family pyrin domain containing 3 (NLRP3), apoptosis-associated speck-like protein containing caspase recruitment domain (ASC), and caspase-1 in the hippocampal tissues of the rats. Immunofluorescence staining was performed to observe the morphological changes in ionized calcium-binding adapter molecule 1 positive (Iba-1<sup>+</sup>) cells in the dentate gyrus (DG) of rats with CUMS-induced depression.</div></div><div><h3>Results</h3><div>(i) Treatment with PR-H and fluoxetine resulted in significant enhancements in both the total distance and time the rats moved during tests (<em>P</em> < 0.01 and <em>P</em> < 0.05, respectively). Post-administration of PR-H and fluoxetine also led to statistically significant increase in sucrose preference among rats (<em>P</em> < 0.05). Besides, PR-L, PR-H, and fluoxetine treatment markedly decreased the latency of ingestion (<em>P</em> < 0.05, <em>P</em> < 0.05, and <em>P</em> < 0.01, respectively). As observed from the FST, PR-L, PR-H, and fluoxetine presented antidepressant effects on rats with CUMS-induced depression, leading to the reduction in time of their immobility (<em>P</em> < 0.05, <em>P</em> < 0.01, and <em>P</em> < 0.01, respectively). The results of TST indicated reduced immobility time in rats receiving PR-H and fluoxetine treatment as well (<em>P</em> < 0.01). (ii) Rats in model group showed an increase in the levels of Iba-1<sup>+</sup> microglia in their left and right brains in comparison w

方法将40只雄性Sprague Dawley（SD）大鼠随机分为对照组、模型组、低剂量远志（PR-L，0.5 g/kg）组、高剂量远志（PR-H，1 g/kg）组和氟西汀（10 mg/kg）组，每组8只。除对照组大鼠外，其余四组大鼠均接受 CUMS 诱导的抑郁模型试验。在 CUMS 过程开始前 30 分钟胃内注射 PR 和氟西汀，连续 14 天，直到进行行为测试。在 CUMS 建模后，采用蔗糖偏好试验 (SPT)、开阔地试验 (OFT)、新奇抑制喂食试验 (NSFT)、强迫游泳试验 (FST) 和尾悬试验 (TST) 评估 PR 对缓解大鼠抑郁样行为模型的药理作用。此外，还利用酶联免疫吸附试验 (ELISA) 对大鼠血清中的肿瘤坏死因子 (TNF)-α、白细胞介素 (IL)-6 和 IL-1β 水平进行了定量分析。此外，还进行了 Western 印迹分析，以评估大鼠海马组织中核因子卡巴-B（NF-κB）、诱导型一氧化氮合酶（iNOS）、环氧化酶-2（COX-2）、核苷酸结合寡聚化结构域（NOD）样受体家族含 pyrin 结构域 3（NLRP3）、含 caspase 招募结构域的凋亡相关斑点样蛋白（ASC）和 caspase-1 的蛋白表达水平。结果(i) PR-H和氟西汀能显著提高大鼠在测试中移动的总距离和时间（分别为P < 0.01和P < 0.05）。给药 PR-H 和氟西汀后，大鼠对蔗糖的偏好也有统计学意义的增加（P < 0.05）。此外，PR-L、PR-H 和氟西汀能显著降低大鼠的摄食潜伏期（分别为 P < 0.05、P < 0.05 和 P < 0.01）。从 FST 中观察到，PR-L、PR-H 和氟西汀对 CUMS 诱导的抑郁大鼠有抗抑郁作用，导致其不动时间缩短（分别为 P < 0.05、P < 0.01 和 P < 0.01）。TST结果显示，接受PR-H和氟西汀治疗的大鼠不动时间也缩短了（P < 0.01）。(ii) 与对照组相比，模型组大鼠左右脑中 Iba-1+ 小胶质细胞的含量增加（P < 0.01）。然而，这种增加在 PR 处理后被抵消（P < 0.01）。使用 PR-L、PR-H 和氟西汀治疗可显著降低炎症因子（TNF-α、IL-1β 和 IL-6，P < 0.01）的水平。此外，PR-L 和 PR-H 能有效对抗 NLRP3、ASC 和 caspase-1 水平的升高，并显著下调磷酸化 p65（p-p65）、COX-2 和 iNOS 在大鼠海马中的表达水平（P < 0.01）。总之，这些研究结果表明，PR 部分通过调节 NLRP3 和 NF-κB 信号通路对 CUMS 诱导的抑郁症大鼠发挥抗抑郁作用。

{"title":"Antidepressant effects of Yuanzhi (Polygalae Radix) extract on chronic unpredictable mild stress-induced depression in rats: modulation of the NLRP3 inflammasome and NF-κB pathway","authors":"Yuzhen Chen , Yongzhi Zhao , Yiwen Zhang , Fang Chen , Muhammad Iqbal Choudhary , Xinmin Liu , Ning Jiang","doi":"10.1016/j.dcmed.2024.09.009","DOIUrl":"10.1016/j.dcmed.2024.09.009","url":null,"abstract":"<div><h3>Objective</h3><div>To investigate the antidepressant effects of Yuanzhi (Polygalae Radix, PR) aqueous extract on chronic unpredictable mild stress (CUMS)-induced depression rat models and the underlying mechanisms.</div></div><div><h3>Methods</h3><div>A total of 40 male Sprague Dawley (SD) rats were randomly divided into control, model, low dose of PR (PR-L, 0.5 g/kg), high dose of PR (PR-H, 1 g/kg), and fluoxetine (10 mg/kg) groups, with 8 rats in each group. Except for the rats in control group, those in the other four groups underwent CUMS-induced depression modeling. PR and fluoxetine were administered intragastrically once daily, 30 min prior to the CUMS procedure, for 14 consecutive days until the behavioral tests were performed. After CUMS modeling, the sucrose preference test (SPT), open field test (OFT), novelty-suppressed feeding test (NSFT), forced swim test (FST), and tail suspension test (TST) were employed to assess the pharmacological effects of PR on the mitigation of depressive-like behaviors in rat models. Additionally, the enzyme-linked immunosorbent assay (ELISA) was utilized to quantify the serum levels of tumor necrosis factor (TNF)-<em>α</em>, interleukin (IL)-6, and IL-1<em>β</em> in the rats. Western blot analysis was also conducted to evaluate the protein expression levels of nuclear factor kappa-B (NF-<em>κ</em>B), inducible nitric oxide synthase (iNOS), cyclooxygenase-2 (COX-2), nucleotide-binding oligomerization domain (NOD)-like receptor family pyrin domain containing 3 (NLRP3), apoptosis-associated speck-like protein containing caspase recruitment domain (ASC), and caspase-1 in the hippocampal tissues of the rats. Immunofluorescence staining was performed to observe the morphological changes in ionized calcium-binding adapter molecule 1 positive (Iba-1<sup>+</sup>) cells in the dentate gyrus (DG) of rats with CUMS-induced depression.</div></div><div><h3>Results</h3><div>(i) Treatment with PR-H and fluoxetine resulted in significant enhancements in both the total distance and time the rats moved during tests (<em>P</em> < 0.01 and <em>P</em> < 0.05, respectively). Post-administration of PR-H and fluoxetine also led to statistically significant increase in sucrose preference among rats (<em>P</em> < 0.05). Besides, PR-L, PR-H, and fluoxetine treatment markedly decreased the latency of ingestion (<em>P</em> < 0.05, <em>P</em> < 0.05, and <em>P</em> < 0.01, respectively). As observed from the FST, PR-L, PR-H, and fluoxetine presented antidepressant effects on rats with CUMS-induced depression, leading to the reduction in time of their immobility (<em>P</em> < 0.05, <em>P</em> < 0.01, and <em>P</em> < 0.01, respectively). The results of TST indicated reduced immobility time in rats receiving PR-H and fluoxetine treatment as well (<em>P</em> < 0.01). (ii) Rats in model group showed an increase in the levels of Iba-1<sup>+</sup> microglia in their left and right brains in comparison w","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"7 2","pages":"Pages 184-194"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572914","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrative analysis of bone-formation associated genes and immune cell infiltration in osteoporosis, and the prediction of active ingredients in targeted traditional Chinese medicine 骨质疏松症中骨形成相关基因与免疫细胞浸润的整合分析及靶向中药有效成分预测

Q3 Medicine

Digital Chinese Medicine

Pub Date : 2024-06-01 Epub Date: 2024-11-01 DOI: 10.1016/j.dcmed.2024.09.007

Kai Wang , Ping Dong , Hongzhang Guo

<div><h3>Objective</h3><div>To explore the differential expression and mechanisms of bone formation-related genes in osteoporosis (OP) leveraging bioinformatics and machine learning methodologies, and to predict the active ingredients of targeted traditional Chinese medicine (TCM) herbs.</div></div><div><h3>Methods</h3><div>The Gene Expression Omnibus (GEO) and GeneCards databases were employed to conduct a comprehensive screening of genes and disease-associated loci pertinent to the pathogenesis of OP. The R package was utilized as the analytical tool for the identification of differentially expressed genes. Least absolute shrinkage and selection operator (LASSO) logistic regression analysis and support vector machine-recursive feature elimination (SVM-RFE) algorithm were employed in defining the genetic signature specific to OP. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses for the selected pivotal genes were conducted. The cell-type identification by estimating relative subsets of RNA transcripts (CIBERSORT) algorithm was leveraged to examine the infiltration patterns of immune cells, with Spearman’s rank correlation analysis utilized to assess the relationship between the expression levels of the genes and the presence of immune cells. Coremine Medical Database was used to screen out potential TCM herbs for the treatment of OP. Comparative Toxicogenomics Database (CTD) was employed for forecasting the TCM active ingredients targeting the key genes. AutoDock Vina 1.2.2 and GROMACS 2020 softwares were employed to conclude analysis results, facilitating the exploration of binding affinity and conformational dynamics between the TCM active ingredients and their biological targets.</div></div><div><h3>Results</h3><div>Ten genes were identified by intersecting the results from the GEO and GeneCards databases. Through the application of LASSO regression and SVM-RFE algorithm, four pivotal genes were selected: coat protein (<em>CP</em>), kallikrein 3 (<em>KLK3</em>), polymerase <em>γ</em> (<em>POLG</em>), and transient receptor potential vanilloid 4 (<em>TRPV4</em>). GO and KEGG pathway enrichment analyses revealed that these trait genes were predominantly engaged in the regulation of defense response activation, maintenance of cellular metal ion balance, and the production of chemokine ligand 5. These genes were notably associated with signaling pathways such as ferroptosis, porphyrin metabolism, and base excision repair. Immune infiltration analysis showed that key genes were highly correlated with immune cells. Macrophage M0, M1, M2, and resting dendritic cell were significantly different between groups, and there were significant differences between different groups (<em>P</em> < 0.05). The interaction counts of resveratrol, curcumin, and quercetin with <em>KLK3</em> were 7, 3, and 2, respectively. It shows that the interactions of resveratrol, curcumin, and quercetin with <em>KLK3</em> were

目的利用生物信息学和机器学习方法探索骨质疏松症（OP）中骨形成相关基因的差异表达及其机制，并预测靶向中药（TCM）的有效成分。方法利用基因表达总库（GEO）和基因卡片数据库对与OP发病机制相关的基因和疾病相关位点进行全面筛选。利用 R 软件包作为分析工具来鉴定差异表达基因。采用最小绝对收缩和选择算子（LASSO）逻辑回归分析和支持向量机-递归特征消除（SVM-RFE）算法来定义 OP 的特异性遗传特征。对选定的关键基因进行了基因本体（GO）和京都基因组百科全书（KEGG）通路富集分析。通过估算 RNA 转录本的相对子集（CIBERSORT）算法进行细胞类型鉴定，以检查免疫细胞的浸润模式，并利用斯皮尔曼秩相关分析评估基因表达水平与免疫细胞存在之间的关系。利用 Coremine 医学数据库筛选出治疗 OP 的潜在中草药。比较毒物基因组学数据库（CTD）用于预测针对关键基因的中药活性成分。利用AutoDock Vina 1.2.2和GROMACS 2020软件总结分析结果，有助于探索中药活性成分与其生物靶标之间的结合亲和力和构象动力学。通过应用LASSO回归和SVM-RFE算法，选出了四个关键基因：衣壳蛋白（CP）、allikrein 3（KLK3）、聚合酶γ（POLG）和瞬时受体位点类香草素4（TRPV4）。GO 和 KEGG 通路富集分析表明，这些性状基因主要参与调控防御反应激活、维持细胞金属离子平衡和产生趋化因子配体 5。这些基因明显与信号通路有关，如铁蛋白沉积、卟啉代谢和碱基切除修复。免疫浸润分析表明，关键基因与免疫细胞高度相关。巨噬细胞M0、M1、M2和静息树突状细胞在组间有显著差异，不同组间差异显著（P <0.05）。白藜芦醇、姜黄素和槲皮素与 KLK3 的相互作用次数分别为 7、3 和 2。这表明白藜芦醇、姜黄素和槲皮素与 KLK3 的相互作用是实质性的。结论包括 CP、KLK3、POLG 和 TRPV4 在内的关键基因具有显著的预后价值，在 OP 的诊断评估中发挥着重要作用。中药中的天然化合物白藜芦醇、姜黄素和槲皮素显示出有效调节骨形成基因 KLK3 的潜力。这项研究为解释 OP 的发病机制和开发临床药物提供了科学依据。

{"title":"Integrative analysis of bone-formation associated genes and immune cell infiltration in osteoporosis, and the prediction of active ingredients in targeted traditional Chinese medicine","authors":"Kai Wang , Ping Dong , Hongzhang Guo","doi":"10.1016/j.dcmed.2024.09.007","DOIUrl":"10.1016/j.dcmed.2024.09.007","url":null,"abstract":"<div><h3>Objective</h3><div>To explore the differential expression and mechanisms of bone formation-related genes in osteoporosis (OP) leveraging bioinformatics and machine learning methodologies, and to predict the active ingredients of targeted traditional Chinese medicine (TCM) herbs.</div></div><div><h3>Methods</h3><div>The Gene Expression Omnibus (GEO) and GeneCards databases were employed to conduct a comprehensive screening of genes and disease-associated loci pertinent to the pathogenesis of OP. The R package was utilized as the analytical tool for the identification of differentially expressed genes. Least absolute shrinkage and selection operator (LASSO) logistic regression analysis and support vector machine-recursive feature elimination (SVM-RFE) algorithm were employed in defining the genetic signature specific to OP. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses for the selected pivotal genes were conducted. The cell-type identification by estimating relative subsets of RNA transcripts (CIBERSORT) algorithm was leveraged to examine the infiltration patterns of immune cells, with Spearman’s rank correlation analysis utilized to assess the relationship between the expression levels of the genes and the presence of immune cells. Coremine Medical Database was used to screen out potential TCM herbs for the treatment of OP. Comparative Toxicogenomics Database (CTD) was employed for forecasting the TCM active ingredients targeting the key genes. AutoDock Vina 1.2.2 and GROMACS 2020 softwares were employed to conclude analysis results, facilitating the exploration of binding affinity and conformational dynamics between the TCM active ingredients and their biological targets.</div></div><div><h3>Results</h3><div>Ten genes were identified by intersecting the results from the GEO and GeneCards databases. Through the application of LASSO regression and SVM-RFE algorithm, four pivotal genes were selected: coat protein (<em>CP</em>), kallikrein 3 (<em>KLK3</em>), polymerase <em>γ</em> (<em>POLG</em>), and transient receptor potential vanilloid 4 (<em>TRPV4</em>). GO and KEGG pathway enrichment analyses revealed that these trait genes were predominantly engaged in the regulation of defense response activation, maintenance of cellular metal ion balance, and the production of chemokine ligand 5. These genes were notably associated with signaling pathways such as ferroptosis, porphyrin metabolism, and base excision repair. Immune infiltration analysis showed that key genes were highly correlated with immune cells. Macrophage M0, M1, M2, and resting dendritic cell were significantly different between groups, and there were significant differences between different groups (<em>P</em> < 0.05). The interaction counts of resveratrol, curcumin, and quercetin with <em>KLK3</em> were 7, 3, and 2, respectively. It shows that the interactions of resveratrol, curcumin, and quercetin with <em>KLK3</em> were ","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"7 2","pages":"Pages 160-170"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572912","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Tongue image feature correlation analysis in benign lung nodules and lung cancer 良性肺结节和肺癌的舌头图像特征相关性分析

Q3 Medicine

Digital Chinese Medicine

Pub Date : 2024-06-01 Epub Date: 2024-11-01 DOI: 10.1016/j.dcmed.2024.09.003

Yulin Shi , Jiayi Liu , Yi Chun , Lingshuang Liu , Jiatuo Xu

Objective

To analyze the differences in the correlation of tongue image indicators among patients with benign lung nodules and lung cancer.

Methods

From July 1, 2020 to March 31, 2022, clinical information of lung cancer patients and benign lung nodules patients was collected at the Oncology Department of Longhua Hospital Affiliated to Shanghai University of Traditional Chinese Medicine and the Physical Examination Center of Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine, respectively. We obtained tongue images from patients with benign lung nodules and lung cancer using the TFDA-1 digital tongue diagnosis instrument, and analyzed these images with the TDAS V2.0 software. The extracted indicators included color space parameters in the Lab system for both the tongue body (TB) and tongue coating (TC) (TB/TC-L, TB/TC-a, and TB/TC-b), textural parameters [TB/TC-contrast (CON), TB/TC-angular second moment (ASM), TB/TC-entropy (ENT), and TB/TC-MEAN], as well as TC parameters (perAll and perPart). The bivariate correlation of TB and TC features was analyzed using Pearson’s or Spearman’s correlation analysis, and the overall correlation was analyzed using canonical correlation analysis (CCA).

Results

Samples from 307 patients with benign lung nodules and 276 lung cancer patients were included after excluding outliers and extreme values. Simple correlation analysis indicated that the correlation of TB-L with TC-L, TB-b with TC-b, and TB-b with perAll in lung cancer group was higher than that in benign nodules group. Moreover, the correlation of TB-a with TC-a, TB-a with perAll, and the texture parameters of the TB (TB-CON, TB-ASM, TB-ENT, and TB-MEAN) with the texture parameters of the TC (TC-CON, TC-ASM, TC-ENT, and TC-MEAN) in benign nodules group was higher than lung cancer group. CCA further demonstrated a strong correlation between the TB and TC parameters in lung cancer group, with the first and second pairs of typical variables in benign nodules and lung cancer groups indicating correlation coefficients of 0.918 and 0.817 (P < 0.05), and 0.940 and 0.822 (P < 0.05), respectively.

Conclusion

Benign lung nodules and lung cancer patients exhibited differences in correlation in the L, a, and b values of the TB and TC, as well as the perAll value of the TC, and the texture parameters (TB/TC-CON, TB/TC-ASM, TB/TC-ENT, and TB/TC-MEAN) between the TB and TC. Additionally, there were differences in the overall correlation of the TB and TC between the two groups. Objective tongue diagnosis indicators can effectively assist in the diagnosis of benign lung nodules and lung cancer, thereby providing a scientific basis for the early detection, diagnosis, and treatment of lung cancer.

方法 2020年7月1日至2022年3月31日，分别在上海中医药大学附属龙华医院肿瘤科和上海中医药大学附属曙光医院体检中心收集肺癌患者和肺良性结节患者的临床资料。我们使用 TFDA-1 数字舌象诊断仪获取了肺良性结节和肺癌患者的舌象图像，并使用 TDAS V2.0 软件对这些图像进行了分析。提取的指标包括舌体（TB）和舌苔（TC）在Lab系统中的色彩空间参数（TB/TC-L、TB/TC-a和TB/TC-b）、纹理参数[TB/TC-对比度（CON）、TB/TC-角秒矩（ASM）、TB/TC-熵（ENT）和TB/TC-MEAN]以及TC参数（perAll和perPart）。结果在剔除异常值和极端值后，纳入了 307 名良性肺结节患者和 276 名肺癌患者的样本。简单相关分析表明，肺癌组 TB-L 与 TC-L、TB-b 与 TC-b 和 TB-b 与 perAll 的相关性高于良性结节组。此外，良性结节组中 TB-a 与 TC-a、TB-a 与 perAll 以及 TB 纹理参数（TB-CON、TB-ASM、TB-ENT 和 TB-MEAN）与 TC 纹理参数（TC-CON、TC-ASM、TC-ENT 和 TC-MEAN）的相关性也高于肺癌组。CCA 进一步表明肺癌组的 TB 和 TC 参数之间具有很强的相关性，良性结节组和肺癌组的第一对和第二对典型变量的相关系数分别为 0.918 和 0.817（P < 0.05），以及 0.940 和 0.822（P < 0.结论良性肺结节和肺癌患者在 TB 和 TC 的 L 值、a 值和 b 值、TC 的 perAll 值以及 TB 和 TC 之间的纹理参数（TB/TC-CON、TB/TC-ASM、TB/TC-ENT 和 TB/TC-MEAN）的相关性方面存在差异。此外，两组 TB 和 TC 的总体相关性也存在差异。客观的舌诊指标能有效辅助诊断肺部良性结节和肺癌，从而为肺癌的早期发现、诊断和治疗提供科学依据。

{"title":"Tongue image feature correlation analysis in benign lung nodules and lung cancer","authors":"Yulin Shi , Jiayi Liu , Yi Chun , Lingshuang Liu , Jiatuo Xu","doi":"10.1016/j.dcmed.2024.09.003","DOIUrl":"10.1016/j.dcmed.2024.09.003","url":null,"abstract":"<div><h3>Objective</h3><div>To analyze the differences in the correlation of tongue image indicators among patients with benign lung nodules and lung cancer.</div></div><div><h3>Methods</h3><div>From July 1, 2020 to March 31, 2022, clinical information of lung cancer patients and benign lung nodules patients was collected at the Oncology Department of Longhua Hospital Affiliated to Shanghai University of Traditional Chinese Medicine and the Physical Examination Center of Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine, respectively. We obtained tongue images from patients with benign lung nodules and lung cancer using the TFDA-1 digital tongue diagnosis instrument, and analyzed these images with the TDAS V2.0 software. The extracted indicators included color space parameters in the Lab system for both the tongue body (TB) and tongue coating (TC) (TB/TC-L, TB/TC-a, and TB/TC-b), textural parameters [TB/TC-contrast (CON), TB/TC-angular second moment (ASM), TB/TC-entropy (ENT), and TB/TC-MEAN], as well as TC parameters (perAll and perPart). The bivariate correlation of TB and TC features was analyzed using Pearson’s or Spearman’s correlation analysis, and the overall correlation was analyzed using canonical correlation analysis (CCA).</div></div><div><h3>Results</h3><div>Samples from 307 patients with benign lung nodules and 276 lung cancer patients were included after excluding outliers and extreme values. Simple correlation analysis indicated that the correlation of TB-L with TC-L, TB-b with TC-b, and TB-b with perAll in lung cancer group was higher than that in benign nodules group. Moreover, the correlation of TB-a with TC-a, TB-a with perAll, and the texture parameters of the TB (TB-CON, TB-ASM, TB-ENT, and TB-MEAN) with the texture parameters of the TC (TC-CON, TC-ASM, TC-ENT, and TC-MEAN) in benign nodules group was higher than lung cancer group. CCA further demonstrated a strong correlation between the TB and TC parameters in lung cancer group, with the first and second pairs of typical variables in benign nodules and lung cancer groups indicating correlation coefficients of 0.918 and 0.817 (<em>P</em> < 0.05), and 0.940 and 0.822 (<em>P</em> < 0.05), respectively.</div></div><div><h3>Conclusion</h3><div>Benign lung nodules and lung cancer patients exhibited differences in correlation in the L, a, and b values of the TB and TC, as well as the perAll value of the TC, and the texture parameters (TB/TC-CON, TB/TC-ASM, TB/TC-ENT, and TB/TC-MEAN) between the TB and TC. Additionally, there were differences in the overall correlation of the TB and TC between the two groups. Objective tongue diagnosis indicators can effectively assist in the diagnosis of benign lung nodules and lung cancer, thereby providing a scientific basis for the early detection, diagnosis, and treatment of lung cancer.</div></div>","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"7 2","pages":"Pages 120-128"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Intelligent question answering system for traditional Chinese medicine based on BSG deep learning model: taking prescription and Chinese materia medica as examples 基于 BSG 深度学习模型的中药智能问题解答系统：以处方和本草为例

Q3 Medicine

Digital Chinese Medicine

Pub Date : 2024-03-01 Epub Date: 2024-07-02 DOI: 10.1016/j.dcmed.2024.04.006

Ran Li , Gao Ren , Junfeng Yan , Beiji Zou , Qingping Liu

Objective

To construct a traditional Chinese medicine (TCM) knowledge base using knowledge graph based on deep learning methods, and to explore the application of joint models in intelligent question answering systems for TCM.

Methods

Textbooks Prescriptions of Chinese Materia Medica and Chinese Materia Medica were applied to construct a comprehensive knowledge graph serving as the foundation for the intelligent question answering system. In the study, a BERT+Slot-Gated (BSG) deep learning model was applied for the identification of TCM entities and question intentions presented by users in their questions. Answers retrieved from the knowledge graph based on the identified entities and intentions were then returned to the user. The Flask framework and BSG model were utilized to develop the intelligent question answering system of TCM.

Results

A TCM knowledge map encompassing 3 149 entities and 6 891 relational triples based on the prescriptions and Chinese materia medica was drawn. In the question answering test assisted by a question corpus, the F1 value for recognizing entities when answering 20 types of TCM questions was 0.996 9, and the accuracy rate for identifying intentions was 99.75%. This indicates that the system is both feasible and practical. Users can interact with the system through the WeChat Official Account platform.

Conclusion

The BSG model proposed in this paper achieved good results in experiments by increasing the vector dimension, indicating the effectiveness of the joint model method and providing new research ideas for the implementation of intelligent question answering systems in TCM.

方法应用《本草纲目》和《中华本草》构建综合知识图谱，作为智能答疑系统的基础。研究中，应用了BERT+Slot-Gated（BSG）深度学习模型来识别用户提问中提出的中医实体和问题意图。然后，根据识别出的实体和意图从知识图谱中检索出的答案将返回给用户。结果绘制出了包含 3 149 个实体和 6 891 个关系三元组的中医知识图谱。在问题语料库辅助的问题解答测试中，回答 20 种中医问题时，识别实体的 F1 值为 0.996 9，识别意图的准确率为 99.75%。这表明该系统既可行又实用。用户可以通过微信官方账号平台与系统进行交互。结论本文提出的 BSG 模型通过增加向量维度，在实验中取得了良好的效果，表明了联合模型方法的有效性，为中医智能答题系统的实现提供了新的研究思路。

{"title":"Intelligent question answering system for traditional Chinese medicine based on BSG deep learning model: taking prescription and Chinese materia medica as examples","authors":"Ran Li , Gao Ren , Junfeng Yan , Beiji Zou , Qingping Liu","doi":"10.1016/j.dcmed.2024.04.006","DOIUrl":"https://doi.org/10.1016/j.dcmed.2024.04.006","url":null,"abstract":"<div><h3>Objective</h3><p>To construct a traditional Chinese medicine (TCM) knowledge base using knowledge graph based on deep learning methods, and to explore the application of joint models in intelligent question answering systems for TCM.</p></div><div><h3>Methods</h3><p>Textbooks <em>Prescriptions of Chinese Materia Medica</em> and <em>Chinese Materia Medica</em> were applied to construct a comprehensive knowledge graph serving as the foundation for the intelligent question answering system. In the study, a BERT+Slot-Gated (BSG) deep learning model was applied for the identification of TCM entities and question intentions presented by users in their questions. Answers retrieved from the knowledge graph based on the identified entities and intentions were then returned to the user. The Flask framework and BSG model were utilized to develop the intelligent question answering system of TCM.</p></div><div><h3>Results</h3><p>A TCM knowledge map encompassing 3 149 entities and 6 891 relational triples based on the prescriptions and Chinese materia medica was drawn. In the question answering test assisted by a question corpus, the F1 value for recognizing entities when answering 20 types of TCM questions was 0.996 9, and the accuracy rate for identifying intentions was 99.75%. This indicates that the system is both feasible and practical. Users can interact with the system through the WeChat Official Account platform.</p></div><div><h3>Conclusion</h3><p>The BSG model proposed in this paper achieved good results in experiments by increasing the vector dimension, indicating the effectiveness of the joint model method and providing new research ideas for the implementation of intelligent question answering systems in TCM.</p></div>","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"7 1","pages":"Pages 47-55"},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589377724000247/pdfft?md5=a22431df2b6bfa13b9ef1cab13e2e4d5&pid=1-s2.0-S2589377724000247-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141485189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Differences in pulse manifestations at Cunkou based on simplified modeling of tactile sensing 基于触觉感应简化模型的村口脉冲表现差异

Q3 Medicine

Digital Chinese Medicine

Pub Date : 2024-03-01 Epub Date: 2024-07-02 DOI: 10.1016/j.dcmed.2024.04.004

S.H.I. Yubing , Y.A.N.G. Hongyi , Y.E.O. Joon Hock

Objective

In the theories of pulse disgnosis in traditional Chinese medicine (TCM), it is emphasized that pulse manifestations at the radial artery within the wrist (called Cunkou) signify the physiological and pathological conditions of different internal organs in the human body. However, different opinions exist among researchers about the objectiveness of the pulse diagnosis technique. Some researchers mentioned that no significant differences were observed in pulse manifestations at various Cunkou areas, hence there might be some difficulty in evaluating the status of different organs through checking pulse manifestations at Cunkou. This research aims to analyze the pulse response at Cunkou from the aspect of the characteristics of tactile sensing, thus to give a preliminary explanation to the above question.

Methods

This research utilized the Weber-Fechner law to model the tactile sensing as a dynamic low-pass signal filter with varying bandwidths under different compression levels during pulse diagnosis. The model was applied to analyzing the clinical data collected previously by our group. The arterial pressures measured invasively with equipment from 14 patients with aorta coarctation were processed to simulate different pulse manifestations at Cun, Guan, and Chi positions of Cunkou when different compression levels were applied.

Results

Due to the characteristics of tactile sensing, significant variations were observed in pulse manifestations at different pulse-depths under the application of changing compression levels; while no such changes in pulse manifestations were observed from the employment of transducer only, without tactile sensing involved. The results explained why different understandings on pulse manifestations were formed between direct pulse-taking technique in TCM and modern sphygmography using transducers. The features of pulse manifestations at Cunkou, using direct pulse-taking technique but at different depths, superficial, middle, and deep positions, respectively, predicted by the developed tactile sensing model were in line with those described in TCM pulse theories.

Conclusion

Based on the developed tactile sensing model, this study preliminarily explains the phenomenon that pulse manifestation at Cunkou changes in response to the compression force applied during TCM pulse-taking. Integrating the tactile sensing model with the study of TCM pulse diagnosis opens a new chapter for visualizing and quantitatively interpreting pulse manifestations. This not only expands the scope of pulse diagnosis study effectively, but also provide a scientific basis for further technical upgrading and optimization of existing pulse diagnosis equipment.

目的中医脉诊理论强调，腕部桡动脉（称为 "桡动脉"）的脉象表现标志着人体不同脏腑的生理和病理状况。然而，对于脉诊技术的客观性，研究者们存在不同的看法。有研究者提到，不同 "存口 "部位的脉象表现没有明显差异，因此通过检查 "存口 "的脉象表现来评估不同器官的状况可能存在一定困难。方法本研究利用韦伯-费希纳（Weber-Fechner）定律，将触觉感应建模为脉诊过程中不同压缩水平下带宽变化的动态低通信号滤波器。该模型被用于分析我们小组之前收集的临床数据。结果由于触觉传感的特性，在不同的压力下，不同脉深的脉搏表现有明显的变化；而只使用传感器而不使用触觉传感时，脉搏表现则没有这种变化。这些结果解释了为什么中医的直接把脉技术和使用传感器的现代血压计对脉搏表现形成了不同的理解。本研究基于所建立的触觉传感模型，初步解释了中医把脉时，脉搏表现随按压力的变化而变化的现象。将触觉传感模型与中医脉诊研究相结合，为脉象表现的可视化和定量解读揭开了新的篇章。这不仅有效拓展了脉诊的研究范围，也为现有脉诊设备的进一步技术升级和优化提供了科学依据。

{"title":"Differences in pulse manifestations at Cunkou based on simplified modeling of tactile sensing","authors":"S.H.I. Yubing , Y.A.N.G. Hongyi , Y.E.O. Joon Hock","doi":"10.1016/j.dcmed.2024.04.004","DOIUrl":"https://doi.org/10.1016/j.dcmed.2024.04.004","url":null,"abstract":"<div><h3>Objective</h3><p>In the theories of pulse disgnosis in traditional Chinese medicine (TCM), it is emphasized that pulse manifestations at the radial artery within the wrist (called Cunkou) signify the physiological and pathological conditions of different internal organs in the human body. However, different opinions exist among researchers about the objectiveness of the pulse diagnosis technique. Some researchers mentioned that no significant differences were observed in pulse manifestations at various Cunkou areas, hence there might be some difficulty in evaluating the status of different organs through checking pulse manifestations at Cunkou. This research aims to analyze the pulse response at Cunkou from the aspect of the characteristics of tactile sensing, thus to give a preliminary explanation to the above question.</p></div><div><h3>Methods</h3><p>This research utilized the Weber-Fechner law to model the tactile sensing as a dynamic low-pass signal filter with varying bandwidths under different compression levels during pulse diagnosis. The model was applied to analyzing the clinical data collected previously by our group. The arterial pressures measured invasively with equipment from 14 patients with aorta coarctation were processed to simulate different pulse manifestations at Cun, Guan, and Chi positions of Cunkou when different compression levels were applied.</p></div><div><h3>Results</h3><p>Due to the characteristics of tactile sensing, significant variations were observed in pulse manifestations at different pulse-depths under the application of changing compression levels; while no such changes in pulse manifestations were observed from the employment of transducer only, without tactile sensing involved. The results explained why different understandings on pulse manifestations were formed between direct pulse-taking technique in TCM and modern sphygmography using transducers. The features of pulse manifestations at Cunkou, using direct pulse-taking technique but at different depths, superficial, middle, and deep positions, respectively, predicted by the developed tactile sensing model were in line with those described in TCM pulse theories.</p></div><div><h3>Conclusion</h3><p>Based on the developed tactile sensing model, this study preliminarily explains the phenomenon that pulse manifestation at Cunkou changes in response to the compression force applied during TCM pulse-taking. Integrating the tactile sensing model with the study of TCM pulse diagnosis opens a new chapter for visualizing and quantitatively interpreting pulse manifestations. This not only expands the scope of pulse diagnosis study effectively, but also provide a scientific basis for further technical upgrading and optimization of existing pulse diagnosis equipment.</p></div>","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"7 1","pages":"Pages 29-39"},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589377724000223/pdfft?md5=b7c42f620580affd1cad2c5b27fa558c&pid=1-s2.0-S2589377724000223-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141485186","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0