Pub Date : 2024-07-24DOI: 10.1186/s12911-024-02592-2
Saman Enayati, Slobodan Vucetic
Background: Biomedical Relation Extraction (RE) is essential for uncovering complex relationships between biomedical entities within text. However, training RE classifiers is challenging in low-resource biomedical applications with few labeled examples.
Methods: We explore the potential of Shortest Dependency Paths (SDPs) to aid biomedical RE, especially in situations with limited labeled examples. In this study, we suggest various approaches to employ SDPs when creating word and sentence representations under supervised, semi-supervised, and in-context-learning settings.
Results: Through experiments on three benchmark biomedical text datasets, we find that incorporating SDP-based representations enhances the performance of RE classifiers. The improvement is especially notable when working with small amounts of labeled data.
Conclusion: SDPs offer valuable insights into the complex sentence structure found in many biomedical text passages. Our study introduces several straightforward techniques that, as demonstrated experimentally, effectively enhance the accuracy of RE classifiers.
背景:生物医学关系提取(RE)对于揭示文本中生物医学实体之间的复杂关系至关重要。然而,在标注示例较少的低资源生物医学应用中,训练关系提取分类器具有挑战性:我们探索了最短依赖路径(SDP)在帮助生物医学 RE 方面的潜力,尤其是在标注示例有限的情况下。在这项研究中,我们提出了在监督、半监督和上下文学习设置下创建单词和句子表示时使用 SDP 的各种方法:通过对三个基准生物医学文本数据集的实验,我们发现采用基于 SDP 的表示法可以提高 RE 分类器的性能。在处理少量标注数据时,这种改进尤为显著:SDP 为了解许多生物医学文本中的复杂句子结构提供了宝贵的见解。我们的研究介绍了几种简单直接的技术,实验证明,这些技术能有效提高 RE 分类器的准确性。
{"title":"Leveraging shortest dependency paths in low-resource biomedical relation extraction.","authors":"Saman Enayati, Slobodan Vucetic","doi":"10.1186/s12911-024-02592-2","DOIUrl":"10.1186/s12911-024-02592-2","url":null,"abstract":"<p><strong>Background: </strong>Biomedical Relation Extraction (RE) is essential for uncovering complex relationships between biomedical entities within text. However, training RE classifiers is challenging in low-resource biomedical applications with few labeled examples.</p><p><strong>Methods: </strong>We explore the potential of Shortest Dependency Paths (SDPs) to aid biomedical RE, especially in situations with limited labeled examples. In this study, we suggest various approaches to employ SDPs when creating word and sentence representations under supervised, semi-supervised, and in-context-learning settings.</p><p><strong>Results: </strong>Through experiments on three benchmark biomedical text datasets, we find that incorporating SDP-based representations enhances the performance of RE classifiers. The improvement is especially notable when working with small amounts of labeled data.</p><p><strong>Conclusion: </strong>SDPs offer valuable insights into the complex sentence structure found in many biomedical text passages. Our study introduces several straightforward techniques that, as demonstrated experimentally, effectively enhance the accuracy of RE classifiers.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11267752/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141757239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-23DOI: 10.1186/s12911-024-02611-2
Tuuli Turja, Milla Rosenlund, Virpi Jylhä, Hanna Kuusisto
Background: Previous studies have shown that shared decision-making (SDM) between a practitioner and a patient strengthens the ideal of treatment adherence. This study employed a multi-method approach to SDM in healthcare to reinforce the theoretical and methodological grounds of this argument. As the study design, self-reported survey items and experimental vignettes were combined in one electronic questionnaire. This technique aimed to analyze the effects of previous experiences and the current preferences regarding SDM on the intentions to follow-through with the medical recommendations.
Method: Using quantitative data collected from the members of the Finnish Pensioners' Federation (N = 1610), this study focused on the important and growing population of older adults as healthcare consumers. Illustrated vignettes were used in the evaluation of expected adherence to both vaccination and the treatment of an illness, depending on the decision-making style varying among the repeated scenarios. In a within-subjects study design, each study subject acted as their own control.
Results: The findings demonstrated that SDM correlates with expected adherence to a treatment and vaccination. Both the retrospective experiences and prospective aspirations of SDM in clinical encounters supported the patients' expected adherence to vaccination and treatment while decreasing the probability of pseudo-compliance. The association between SDM and expected adherence was not affected by the perceived health of the respondents. However, the associations among the expected adherence and decision-making styles were found to differ between the treatment and vaccination scenarios.
Conclusions: SDM enables expected treatment adherence among older adults. Thus, the multi-method study emphasizes the importance of SDM in various healthcare encounters. The findings further imply that SDM research benefits from questionnaires combining self-report methods and experimental study designs. Further cross-validation studies using various types of written and illustrated scenarios are encouraged.
{"title":"Shared decision-making endorses intention to follow through treatment or vaccination recommendations: a multi-method survey study among older adults.","authors":"Tuuli Turja, Milla Rosenlund, Virpi Jylhä, Hanna Kuusisto","doi":"10.1186/s12911-024-02611-2","DOIUrl":"10.1186/s12911-024-02611-2","url":null,"abstract":"<p><strong>Background: </strong>Previous studies have shown that shared decision-making (SDM) between a practitioner and a patient strengthens the ideal of treatment adherence. This study employed a multi-method approach to SDM in healthcare to reinforce the theoretical and methodological grounds of this argument. As the study design, self-reported survey items and experimental vignettes were combined in one electronic questionnaire. This technique aimed to analyze the effects of previous experiences and the current preferences regarding SDM on the intentions to follow-through with the medical recommendations.</p><p><strong>Method: </strong>Using quantitative data collected from the members of the Finnish Pensioners' Federation (N = 1610), this study focused on the important and growing population of older adults as healthcare consumers. Illustrated vignettes were used in the evaluation of expected adherence to both vaccination and the treatment of an illness, depending on the decision-making style varying among the repeated scenarios. In a within-subjects study design, each study subject acted as their own control.</p><p><strong>Results: </strong>The findings demonstrated that SDM correlates with expected adherence to a treatment and vaccination. Both the retrospective experiences and prospective aspirations of SDM in clinical encounters supported the patients' expected adherence to vaccination and treatment while decreasing the probability of pseudo-compliance. The association between SDM and expected adherence was not affected by the perceived health of the respondents. However, the associations among the expected adherence and decision-making styles were found to differ between the treatment and vaccination scenarios.</p><p><strong>Conclusions: </strong>SDM enables expected treatment adherence among older adults. Thus, the multi-method study emphasizes the importance of SDM in various healthcare encounters. The findings further imply that SDM research benefits from questionnaires combining self-report methods and experimental study designs. Further cross-validation studies using various types of written and illustrated scenarios are encouraged.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11264447/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141751167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-23DOI: 10.1186/s12911-024-02602-3
Andrea Campagner, Frida Milella, Giuseppe Banfi, Federico Cabitza
Background: The frequency of hip and knee arthroplasty surgeries has been rising steadily in recent decades. This trend is attributed to an aging population, leading to increased demands on healthcare systems. Fast Track (FT) surgical protocols, perioperative procedures designed to expedite patient recovery and early mobilization, have demonstrated efficacy in reducing hospital stays, convalescence periods, and associated costs. However, the criteria for selecting patients for FT procedures have not fully capitalized on the available patient data, including patient-reported outcome measures (PROMs).
Methods: Our study focused on developing machine learning (ML) models to support decision making in assigning patients to FT procedures, utilizing data from patients' self-reported health status. These models are specifically designed to predict the potential health status improvement in patients initially selected for FT. Our approach focused on techniques inspired by the concept of controllable AI. This includes eXplainable AI (XAI), which aims to make the model's recommendations comprehensible to clinicians, and cautious prediction, a method used to alert clinicians about potential control losses, thereby enhancing the models' trustworthiness and reliability.
Results: Our models were trained and tested using a dataset comprising 899 records from individual patients admitted to the FT program at IRCCS Ospedale Galeazzi-Sant'Ambrogio. After training and selecting hyper-parameters, the models were assessed using a separate internal test set. The interpretable models demonstrated performance on par or even better than the most effective 'black-box' model (Random Forest). These models achieved sensitivity, specificity, and positive predictive value (PPV) exceeding 70%, with an area under the curve (AUC) greater than 80%. The cautious prediction models exhibited enhanced performance while maintaining satisfactory coverage (over 50%). Further, when externally validated on a separate cohort from the same hospital-comprising patients from a subsequent time period-the models showed no pragmatically notable decline in performance.
Conclusions: Our results demonstrate the effectiveness of utilizing PROMs as basis to develop ML models for planning assignments to FT procedures. Notably, the application of controllable AI techniques, particularly those based on XAI and cautious prediction, emerges as a promising approach. These techniques provide reliable and interpretable support, essential for informed decision-making in clinical processes.
背景:近几十年来,髋关节和膝关节置换手术的频率一直在稳步上升。造成这一趋势的原因是人口老龄化,导致对医疗保健系统的需求增加。快速通道(FT)手术方案是一种围手术期程序,旨在加快患者的康复和早期活动,在缩短住院时间、缩短疗养期和降低相关费用方面具有显著疗效。然而,选择患者进行快速手术的标准并没有充分利用现有的患者数据,包括患者报告的结果指标(PROMs):我们的研究重点是利用患者自我报告的健康状况数据,开发机器学习(ML)模型,以支持将患者分配到急诊手术的决策。这些模型专门用于预测最初被选中进行 FT 的患者的潜在健康状况改善情况。我们的方法侧重于受可控人工智能概念启发的技术。这包括可解释人工智能(XAI)和谨慎预测,前者旨在使临床医生能够理解模型的建议,后者用于提醒临床医生注意潜在的控制损失,从而提高模型的可信度和可靠性:我们使用一个数据集对模型进行了训练和测试,该数据集由 IRCCS Ospedale Galeazzi-Sant'Ambrogio 的 FT 项目收治的 899 名患者的个人记录组成。在训练和选择超参数后,使用单独的内部测试集对模型进行了评估。可解释模型的性能与最有效的 "黑盒 "模型(随机森林)相当,甚至更好。这些模型的灵敏度、特异性和阳性预测值(PPV)均超过 70%,曲线下面积(AUC)超过 80%。谨慎的预测模型在保持令人满意的覆盖率(超过 50%)的同时,还表现出更高的性能。此外,在对同一医院的另一批患者(包括随后一段时间的患者)进行外部验证时,模型的性能没有出现实际意义上的明显下降:我们的研究结果表明,以 PROMs 为基础开发 ML 模型来规划 FT 手术的分配是有效的。值得注意的是,应用可控人工智能技术,特别是基于 XAI 和谨慎预测的技术,是一种很有前途的方法。这些技术可提供可靠且可解释的支持,对临床过程中的知情决策至关重要。
{"title":"Second opinion machine learning for fast-track pathway assignment in hip and knee replacement surgery: the use of patient-reported outcome measures.","authors":"Andrea Campagner, Frida Milella, Giuseppe Banfi, Federico Cabitza","doi":"10.1186/s12911-024-02602-3","DOIUrl":"10.1186/s12911-024-02602-3","url":null,"abstract":"<p><strong>Background: </strong>The frequency of hip and knee arthroplasty surgeries has been rising steadily in recent decades. This trend is attributed to an aging population, leading to increased demands on healthcare systems. Fast Track (FT) surgical protocols, perioperative procedures designed to expedite patient recovery and early mobilization, have demonstrated efficacy in reducing hospital stays, convalescence periods, and associated costs. However, the criteria for selecting patients for FT procedures have not fully capitalized on the available patient data, including patient-reported outcome measures (PROMs).</p><p><strong>Methods: </strong>Our study focused on developing machine learning (ML) models to support decision making in assigning patients to FT procedures, utilizing data from patients' self-reported health status. These models are specifically designed to predict the potential health status improvement in patients initially selected for FT. Our approach focused on techniques inspired by the concept of controllable AI. This includes eXplainable AI (XAI), which aims to make the model's recommendations comprehensible to clinicians, and cautious prediction, a method used to alert clinicians about potential control losses, thereby enhancing the models' trustworthiness and reliability.</p><p><strong>Results: </strong>Our models were trained and tested using a dataset comprising 899 records from individual patients admitted to the FT program at IRCCS Ospedale Galeazzi-Sant'Ambrogio. After training and selecting hyper-parameters, the models were assessed using a separate internal test set. The interpretable models demonstrated performance on par or even better than the most effective 'black-box' model (Random Forest). These models achieved sensitivity, specificity, and positive predictive value (PPV) exceeding 70%, with an area under the curve (AUC) greater than 80%. The cautious prediction models exhibited enhanced performance while maintaining satisfactory coverage (over 50%). Further, when externally validated on a separate cohort from the same hospital-comprising patients from a subsequent time period-the models showed no pragmatically notable decline in performance.</p><p><strong>Conclusions: </strong>Our results demonstrate the effectiveness of utilizing PROMs as basis to develop ML models for planning assignments to FT procedures. Notably, the application of controllable AI techniques, particularly those based on XAI and cautious prediction, emerges as a promising approach. These techniques provide reliable and interpretable support, essential for informed decision-making in clinical processes.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11267678/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141751174","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-22DOI: 10.1186/s12911-024-02607-y
Zahra Mohammadzadeh, Mehdi Shokri, Hamid Reza Saeidnia, Marcin Kozak, Agostino Marengo, Brady D Lund, Marcel Ausloos, Nasrin Ghiasi
Experts are currently investigating the potential applications of the metaverse in healthcare. The metaverse, a groundbreaking concept that arose in the early 21st century through the fusion of virtual reality and augmented reality technologies, holds promise for transforming healthcare delivery. Alongside its implementation, the issue of digital professionalism in healthcare must be addressed. Digital professionalism refers to the knowledge and skills required by healthcare specialists to navigate digital technologies effectively and ethically. This study aims to identify the core principles of digital professionalism for the use of metaverse in healthcare. This study utilized a qualitative design and collected data through semi-structured online interviews with 20 medical information and health informatics specialists from various countries (USA, UK, Sweden, Netherlands, Poland, Romania, Italy, Iran). Data analysis was conducted using the open coding method, wherein concepts (codes) related to the themes of digital professionalism for the metaverse in healthcare were assigned to the data. The analysis was performed using the MAXQDA software (VER BI GmbH, Berlin, Germany). The study revealed ten fundamental principles of digital professionalism for the metaverse in healthcare: Privacy and Security, Informed Consent, Trust and Integrity, Accessibility and Inclusion, Professional Boundaries, Evidence-Based Practice, Continuous Education and Training, Collaboration and Interoperability, Feedback and Improvement, and Regulatory Compliance. As the metaverse continues to expand and integrate itself into various industries, including healthcare, it becomes vital to establish principles of digital professionalism to ensure ethical and responsible practices. Healthcare professionals can uphold these principles to maintain ethical standards, safeguard patient privacy, and deliver effective care within the metaverse.
专家们目前正在研究元宇宙在医疗保健领域的潜在应用。元宇宙是 21 世纪初通过融合虚拟现实和增强现实技术而产生的一个突破性概念,有望改变医疗保健服务的提供方式。在实施这一概念的同时,还必须解决医疗保健领域的数字专业化问题。数字专业精神指的是医疗保健专家有效、合乎道德地驾驭数字技术所需的知识和技能。本研究旨在确定在医疗保健领域使用元数据的数字专业精神的核心原则。本研究采用定性设计,通过对来自不同国家(美国、英国、瑞典、荷兰、波兰、罗马尼亚、意大利和伊朗)的 20 名医疗信息和健康信息学专家进行半结构化在线访谈收集数据。数据分析采用开放式编码法,将与医疗保健领域元宇宙数字化专业化主题相关的概念(代码)分配到数据中。分析使用 MAXQDA 软件(VER BI GmbH,德国柏林)进行。这项研究揭示了医疗保健领域元网络数字专业精神的十项基本原则:隐私与安全、知情同意、信任与诚信、可及性与包容性、专业界限、循证实践、持续教育与培训、协作与互操作性、反馈与改进以及监管合规。随着元宇宙不断扩展并融入包括医疗保健在内的各行各业,建立数字专业原则以确保合乎道德和负责任的实践变得至关重要。医疗保健专业人员可以坚持这些原则,以维护道德标准、保护患者隐私,并在元宇宙中提供有效的医疗服务。
{"title":"Principles of digital professionalism for the metaverse in healthcare","authors":"Zahra Mohammadzadeh, Mehdi Shokri, Hamid Reza Saeidnia, Marcin Kozak, Agostino Marengo, Brady D Lund, Marcel Ausloos, Nasrin Ghiasi","doi":"10.1186/s12911-024-02607-y","DOIUrl":"https://doi.org/10.1186/s12911-024-02607-y","url":null,"abstract":"Experts are currently investigating the potential applications of the metaverse in healthcare. The metaverse, a groundbreaking concept that arose in the early 21st century through the fusion of virtual reality and augmented reality technologies, holds promise for transforming healthcare delivery. Alongside its implementation, the issue of digital professionalism in healthcare must be addressed. Digital professionalism refers to the knowledge and skills required by healthcare specialists to navigate digital technologies effectively and ethically. This study aims to identify the core principles of digital professionalism for the use of metaverse in healthcare. This study utilized a qualitative design and collected data through semi-structured online interviews with 20 medical information and health informatics specialists from various countries (USA, UK, Sweden, Netherlands, Poland, Romania, Italy, Iran). Data analysis was conducted using the open coding method, wherein concepts (codes) related to the themes of digital professionalism for the metaverse in healthcare were assigned to the data. The analysis was performed using the MAXQDA software (VER BI GmbH, Berlin, Germany). The study revealed ten fundamental principles of digital professionalism for the metaverse in healthcare: Privacy and Security, Informed Consent, Trust and Integrity, Accessibility and Inclusion, Professional Boundaries, Evidence-Based Practice, Continuous Education and Training, Collaboration and Interoperability, Feedback and Improvement, and Regulatory Compliance. As the metaverse continues to expand and integrate itself into various industries, including healthcare, it becomes vital to establish principles of digital professionalism to ensure ethical and responsible practices. Healthcare professionals can uphold these principles to maintain ethical standards, safeguard patient privacy, and deliver effective care within the metaverse.","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":null,"pages":null},"PeriodicalIF":3.5,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141744450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-22DOI: 10.1186/s12911-024-02595-z
Ya Wu, Danmeng Dong, Lijie Zhu, Zihong Luo, Yang Liu, Xiaoyun Xie
Diabetic peripheral neuropathy (DPN) and lower extremity arterial disease (LEAD) are significant contributors to diabetic foot ulcers (DFUs), which severely affect patients’ quality of life. This study aimed to develop machine learning (ML) predictive models for DPN and LEAD and to identify both shared and distinct risk factors. This retrospective study included 479 diabetic inpatients, of whom 215 were diagnosed with DPN and 69 with LEAD. Clinical data and laboratory results were collected for each patient. Feature selection was performed using three methods: mutual information (MI), random forest recursive feature elimination (RF-RFE), and the Boruta algorithm to identify the most important features. Predictive models were developed using logistic regression (LR), random forest (RF), and eXtreme Gradient Boosting (XGBoost), with particle swarm optimization (PSO) used to optimize their hyperparameters. The SHapley Additive exPlanation (SHAP) method was applied to determine the importance of risk factors in the top-performing models. For diagnosing DPN, the XGBoost model was most effective, achieving a recall of 83.7%, specificity of 86.8%, accuracy of 85.4%, and an F1 score of 83.7%. On the other hand, the RF model excelled in diagnosing LEAD, with a recall of 85.7%, specificity of 92.9%, accuracy of 91.9%, and an F1 score of 82.8%. SHAP analysis revealed top five critical risk factors shared by DPN and LEAD, including increased urinary albumin-to-creatinine ratio (UACR), glycosylated hemoglobin (HbA1c), serum creatinine (Scr), older age, and carotid stenosis. Additionally, distinct risk factors were pinpointed: decreased serum albumin and lower lymphocyte count were linked to DPN, while elevated neutrophil-to-lymphocyte ratio (NLR) and higher D-dimer levels were associated with LEAD. This study demonstrated the effectiveness of ML models in predicting DPN and LEAD in diabetic patients and identified significant risk factors. Focusing on shared risk factors may greatly reduce the prevalence of both conditions, thereby mitigating the risk of developing DFUs.
糖尿病周围神经病变(DPN)和下肢动脉疾病(LEAD)是导致糖尿病足溃疡(DFUs)的重要因素,严重影响患者的生活质量。本研究旨在开发针对 DPN 和 LEAD 的机器学习 (ML) 预测模型,并识别共同和不同的风险因素。这项回顾性研究纳入了 479 名糖尿病住院患者,其中 215 人被诊断为 DPN,69 人被诊断为 LEAD。研究人员收集了每位患者的临床数据和实验室结果。采用三种方法进行特征选择:互信息(MI)、随机森林递归特征消除(RF-RFE)和 Boruta 算法,以确定最重要的特征。使用逻辑回归(LR)、随机森林(RF)和极梯度提升(XGBoost)开发了预测模型,并使用粒子群优化(PSO)来优化其超参数。应用SHAPLE Additive exPlanation(SHAP)方法来确定风险因素在表现最佳的模型中的重要性。在诊断 DPN 方面,XGBoost 模型最为有效,其召回率为 83.7%,特异性为 86.8%,准确率为 85.4%,F1 得分为 83.7%。另一方面,RF 模型在诊断 LEAD 方面表现出色,召回率为 85.7%,特异性为 92.9%,准确率为 91.9%,F1 得分为 82.8%。SHAP分析显示了DPN和LEAD共有的五大关键风险因素,包括尿白蛋白与肌酐比值(UACR)升高、糖化血红蛋白(HbA1c)升高、血清肌酐(Scr)升高、年龄增大和颈动脉狭窄。此外,还发现了一些不同的风险因素:血清白蛋白降低和淋巴细胞计数减少与 DPN 有关,而中性粒细胞与淋巴细胞比率(NLR)升高和 D-二聚体水平升高与 LEAD 有关。这项研究证明了 ML 模型在预测糖尿病患者 DPN 和 LEAD 方面的有效性,并确定了重要的风险因素。关注共同的风险因素可能会大大降低这两种疾病的发病率,从而降低罹患 DFU 的风险。
{"title":"Interpretable machine learning models for detecting peripheral neuropathy and lower extremity arterial disease in diabetics: an analysis of critical shared and unique risk factors","authors":"Ya Wu, Danmeng Dong, Lijie Zhu, Zihong Luo, Yang Liu, Xiaoyun Xie","doi":"10.1186/s12911-024-02595-z","DOIUrl":"https://doi.org/10.1186/s12911-024-02595-z","url":null,"abstract":"Diabetic peripheral neuropathy (DPN) and lower extremity arterial disease (LEAD) are significant contributors to diabetic foot ulcers (DFUs), which severely affect patients’ quality of life. This study aimed to develop machine learning (ML) predictive models for DPN and LEAD and to identify both shared and distinct risk factors. This retrospective study included 479 diabetic inpatients, of whom 215 were diagnosed with DPN and 69 with LEAD. Clinical data and laboratory results were collected for each patient. Feature selection was performed using three methods: mutual information (MI), random forest recursive feature elimination (RF-RFE), and the Boruta algorithm to identify the most important features. Predictive models were developed using logistic regression (LR), random forest (RF), and eXtreme Gradient Boosting (XGBoost), with particle swarm optimization (PSO) used to optimize their hyperparameters. The SHapley Additive exPlanation (SHAP) method was applied to determine the importance of risk factors in the top-performing models. For diagnosing DPN, the XGBoost model was most effective, achieving a recall of 83.7%, specificity of 86.8%, accuracy of 85.4%, and an F1 score of 83.7%. On the other hand, the RF model excelled in diagnosing LEAD, with a recall of 85.7%, specificity of 92.9%, accuracy of 91.9%, and an F1 score of 82.8%. SHAP analysis revealed top five critical risk factors shared by DPN and LEAD, including increased urinary albumin-to-creatinine ratio (UACR), glycosylated hemoglobin (HbA1c), serum creatinine (Scr), older age, and carotid stenosis. Additionally, distinct risk factors were pinpointed: decreased serum albumin and lower lymphocyte count were linked to DPN, while elevated neutrophil-to-lymphocyte ratio (NLR) and higher D-dimer levels were associated with LEAD. This study demonstrated the effectiveness of ML models in predicting DPN and LEAD in diabetic patients and identified significant risk factors. Focusing on shared risk factors may greatly reduce the prevalence of both conditions, thereby mitigating the risk of developing DFUs.","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":null,"pages":null},"PeriodicalIF":3.5,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141744451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To develop and validate machine learning models for predicting coronary artery disease (CAD) within a Taiwanese cohort, with an emphasis on identifying significant predictors and comparing the performance of various models. This study involved a comprehensive analysis of clinical, demographic, and laboratory data from 8,495 subjects in Taiwan Biobank (TWB) after propensity score matching to address potential confounding factors. Key variables included age, gender, lipid profiles (T-CHO, HDL_C, LDL_C, TG), smoking and alcohol consumption habits, and renal and liver function markers. The performance of multiple machine learning models was evaluated. The cohort comprised 1,699 individuals with CAD identified through self-reported questionnaires. Significant differences were observed between CAD and non-CAD individuals regarding demographics and clinical features. Notably, the Gradient Boosting model emerged as the most accurate, achieving an AUC of 0.846 (95% confidence interval [CI] 0.819–0.873), sensitivity of 0.776 (95% CI, 0.732–0.820), and specificity of 0.759 (95% CI, 0.736–0.782), respectively. The accuracy was 0.762 (95% CI, 0.742–0.782). Age was identified as the most influential predictor of CAD risk within the studied dataset. The Gradient Boosting machine learning model demonstrated superior performance in predicting CAD within the Taiwanese cohort, with age being a critical predictor. These findings underscore the potential of machine learning models in enhancing the prediction accuracy of CAD, thereby supporting early detection and targeted intervention strategies. Not applicable.
{"title":"Using machine learning-based algorithms to construct cardiovascular risk prediction models for Taiwanese adults based on traditional and novel risk factors","authors":"Chien-Hsiang Cheng, Bor-Jen Lee, Oswald Ndi Nfor, Chih-Hsuan Hsiao, Yi-Chia Huang, Yung-Po Liaw","doi":"10.1186/s12911-024-02603-2","DOIUrl":"https://doi.org/10.1186/s12911-024-02603-2","url":null,"abstract":"To develop and validate machine learning models for predicting coronary artery disease (CAD) within a Taiwanese cohort, with an emphasis on identifying significant predictors and comparing the performance of various models. This study involved a comprehensive analysis of clinical, demographic, and laboratory data from 8,495 subjects in Taiwan Biobank (TWB) after propensity score matching to address potential confounding factors. Key variables included age, gender, lipid profiles (T-CHO, HDL_C, LDL_C, TG), smoking and alcohol consumption habits, and renal and liver function markers. The performance of multiple machine learning models was evaluated. The cohort comprised 1,699 individuals with CAD identified through self-reported questionnaires. Significant differences were observed between CAD and non-CAD individuals regarding demographics and clinical features. Notably, the Gradient Boosting model emerged as the most accurate, achieving an AUC of 0.846 (95% confidence interval [CI] 0.819–0.873), sensitivity of 0.776 (95% CI, 0.732–0.820), and specificity of 0.759 (95% CI, 0.736–0.782), respectively. The accuracy was 0.762 (95% CI, 0.742–0.782). Age was identified as the most influential predictor of CAD risk within the studied dataset. The Gradient Boosting machine learning model demonstrated superior performance in predicting CAD within the Taiwanese cohort, with age being a critical predictor. These findings underscore the potential of machine learning models in enhancing the prediction accuracy of CAD, thereby supporting early detection and targeted intervention strategies. Not applicable.","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":null,"pages":null},"PeriodicalIF":3.5,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141744453","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-22DOI: 10.1186/s12911-024-02604-1
Asghar Ali Shah, Ali Daud, Amal Bukhari, Bader Alshemaimri, Muhammad Ahsan, Rehmana Younis
Genes, expressed as sequences of nucleotides, are susceptible to mutations, some of which can lead to cancer. Machine learning and deep learning methods have emerged as vital tools in identifying mutations associated with cancer. Thyroid cancer ranks as the 5th most prevalent cancer in the USA, with thousands diagnosed annually. This paper presents an ensemble learning model leveraging deep learning techniques such as Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs), and Bi-directional LSTM (Bi-LSTM) to detect thyroid cancer mutations early. The model is trained on a dataset sourced from asia.ensembl.org and IntOGen.org, consisting of 633 samples with 969 mutations across 41 genes, collected from individuals of various demographics. Feature extraction encompasses techniques including Hahn moments, central moments, raw moments, and various matrix-based methods. Evaluation employs three testing methods: self-consistency test (SCT), independent set test (IST), and 10-fold cross-validation test (10-FCVT). The proposed ensemble learning model demonstrates promising performance, achieving 96% accuracy in the independent set test (IST). Statistical measures such as training accuracy, testing accuracy, recall, sensitivity, specificity, Mathew's Correlation Coefficient (MCC), loss, training accuracy, F1 Score, and Cohen's kappa are utilized for comprehensive evaluation.
{"title":"DEL-Thyroid: deep ensemble learning framework for detection of thyroid cancer progression through genomic mutation","authors":"Asghar Ali Shah, Ali Daud, Amal Bukhari, Bader Alshemaimri, Muhammad Ahsan, Rehmana Younis","doi":"10.1186/s12911-024-02604-1","DOIUrl":"https://doi.org/10.1186/s12911-024-02604-1","url":null,"abstract":"Genes, expressed as sequences of nucleotides, are susceptible to mutations, some of which can lead to cancer. Machine learning and deep learning methods have emerged as vital tools in identifying mutations associated with cancer. Thyroid cancer ranks as the 5th most prevalent cancer in the USA, with thousands diagnosed annually. This paper presents an ensemble learning model leveraging deep learning techniques such as Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs), and Bi-directional LSTM (Bi-LSTM) to detect thyroid cancer mutations early. The model is trained on a dataset sourced from asia.ensembl.org and IntOGen.org, consisting of 633 samples with 969 mutations across 41 genes, collected from individuals of various demographics. Feature extraction encompasses techniques including Hahn moments, central moments, raw moments, and various matrix-based methods. Evaluation employs three testing methods: self-consistency test (SCT), independent set test (IST), and 10-fold cross-validation test (10-FCVT). The proposed ensemble learning model demonstrates promising performance, achieving 96% accuracy in the independent set test (IST). Statistical measures such as training accuracy, testing accuracy, recall, sensitivity, specificity, Mathew's Correlation Coefficient (MCC), loss, training accuracy, F1 Score, and Cohen's kappa are utilized for comprehensive evaluation.","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":null,"pages":null},"PeriodicalIF":3.5,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141744454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-19DOI: 10.1186/s12911-024-02593-1
Ting Cheng, Dongdong Yu, Jun Tan, Shaojun Liao, Li Zhou, Wenwei OuYang, Zehuai Wen
Background: The risk assessment for survival in heart failure (HF) remains one of the key focuses of research. This study aims to develop a simple and feasible nomogram model for survival in HF based on the Heart Failure-A Controlled Trial Investigating Outcomes of Exercise TraiNing (HF-ACTION) to support clinical decision-making.
Methods: The HF patients were extracted from the HF-ACTION database and randomly divided into a training cohort and a validation cohort at a ratio of 7:3. Multivariate Cox regression was used to identify and integrate significant prognostic factors to form a nomogram, which was displayed in the form of a static nomogram. Bootstrap resampling (resampling = 1000) and cross-validation was used to internally validate the model. The prognostic performance of the model was measured by the concordance index (C-index), calibration curve, and the decision curve analysis.
Results: There were 1394 patients with HF in the overall analysis. Seven prognostic factors, which included age, body mass index (BMI), sex, diastolic blood pressure (DBP), exercise duration, peak exercise oxygen consumption (peak VO2), and loop diuretic, were identified and applied to the nomogram construction based on the training cohort. The C-index of this model in the training cohort was 0.715 (95% confidence interval (CI): 0.700, 0.766) and 0.662 (95% CI: 0.646, 0.752) in the validation cohort. The area under the ROC curve (AUC) value of 365- and 730-day survival is (0.731, 0.734) and (0.640, 0.693) respectively in the training cohort and validation cohort. The calibration curve showed good consistency between nomogram-predicted survival and actual observed survival. The decision curve analysis (DCA) revealed net benefit is higher than the reference line in a narrow range of cutoff probabilities and the result of cross-validation indicates that the model performance is relatively robust.
Conclusions: This study created a nomogram prognostic model for survival in HF based on a large American population, which can provide additional decision information for the risk prediction of HF.
{"title":"Development a nomogram prognostic model for survival in heart failure patients based on the HF-ACTION data.","authors":"Ting Cheng, Dongdong Yu, Jun Tan, Shaojun Liao, Li Zhou, Wenwei OuYang, Zehuai Wen","doi":"10.1186/s12911-024-02593-1","DOIUrl":"10.1186/s12911-024-02593-1","url":null,"abstract":"<p><strong>Background: </strong>The risk assessment for survival in heart failure (HF) remains one of the key focuses of research. This study aims to develop a simple and feasible nomogram model for survival in HF based on the Heart Failure-A Controlled Trial Investigating Outcomes of Exercise TraiNing (HF-ACTION) to support clinical decision-making.</p><p><strong>Methods: </strong>The HF patients were extracted from the HF-ACTION database and randomly divided into a training cohort and a validation cohort at a ratio of 7:3. Multivariate Cox regression was used to identify and integrate significant prognostic factors to form a nomogram, which was displayed in the form of a static nomogram. Bootstrap resampling (resampling = 1000) and cross-validation was used to internally validate the model. The prognostic performance of the model was measured by the concordance index (C-index), calibration curve, and the decision curve analysis.</p><p><strong>Results: </strong>There were 1394 patients with HF in the overall analysis. Seven prognostic factors, which included age, body mass index (BMI), sex, diastolic blood pressure (DBP), exercise duration, peak exercise oxygen consumption (peak VO<sub>2</sub>), and loop diuretic, were identified and applied to the nomogram construction based on the training cohort. The C-index of this model in the training cohort was 0.715 (95% confidence interval (CI): 0.700, 0.766) and 0.662 (95% CI: 0.646, 0.752) in the validation cohort. The area under the ROC curve (AUC) value of 365- and 730-day survival is (0.731, 0.734) and (0.640, 0.693) respectively in the training cohort and validation cohort. The calibration curve showed good consistency between nomogram-predicted survival and actual observed survival. The decision curve analysis (DCA) revealed net benefit is higher than the reference line in a narrow range of cutoff probabilities and the result of cross-validation indicates that the model performance is relatively robust.</p><p><strong>Conclusions: </strong>This study created a nomogram prognostic model for survival in HF based on a large American population, which can provide additional decision information for the risk prediction of HF.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11264587/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141726917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-18DOI: 10.1186/s12911-024-02601-4
Thirumalesu Kudithi, J Balajee, R Sivakami, T R Mahesh, E Mohan, Suresh Guluwadi
Background: Generalized Joint Hyper-mobility (GJH) can aid in the diagnosis of Ehlers-Danlos Syndrome (EDS), a complex genetic connective tissue disorder with clinical features that can mimic other disease processes. Our study focuses on developing a unique image-based goniometry system, the HybridPoseNet, which utilizes a hybrid deep learning model.
Objective: The proposed model is designed to provide the most accurate joint angle measurements in EDS appraisals. Using a hybrid of CNNs and HyperLSTMs in the pose estimation module of HybridPoseNet offers superior generalization and time consistency properties, setting it apart from existing complex libraries.
Methodology: HybridPoseNet integrates the spatial pattern recognition prowess of MobileNet-V2 with the sequential data processing capability of HyperLSTM units. The system captures the dynamic nature of joint motion by creating a model that learns from individual frames and the sequence of movements. The CNN module of HybridPoseNet was trained on a large and diverse data set before the fine-tuning of video data involving 50 individuals visiting the EDS clinic, focusing on joints that can hyperextend. HyperLSTMs have been incorporated in video frames to avoid any time breakage in joint angle estimation in consecutive frames. The model performance was evaluated using Spearman's coefficient correlation versus manual goniometry measurements, as well as by the human labeling of joint position, the second validation step.
Outcome: Preliminary findings demonstrate HybridPoseNet achieving a remarkable correlation with manual Goniometric measurements: thumb (rho = 0.847), elbows (rho = 0.822), knees (rho = 0.839), and fifth fingers (rho = 0.896), indicating that the newest model is considerably better. The model manifested a consistent performance in all joint assessments, hence not requiring selecting a variety of pose-measuring libraries for every joint. The presentation of HybridPoseNet contributes to achieving a combined and normalized approach to reviewing the mobility of joints, which has an overall enhancement of approximately 20% in accuracy compared to the regular pose estimation libraries. This innovation is very valuable to the field of medical diagnostics of connective tissue diseases and a vast improvement to its understanding.
{"title":"Hybridized deep learning goniometry for improved precision in Ehlers-Danlos Syndrome (EDS) evaluation.","authors":"Thirumalesu Kudithi, J Balajee, R Sivakami, T R Mahesh, E Mohan, Suresh Guluwadi","doi":"10.1186/s12911-024-02601-4","DOIUrl":"10.1186/s12911-024-02601-4","url":null,"abstract":"<p><strong>Background: </strong>Generalized Joint Hyper-mobility (GJH) can aid in the diagnosis of Ehlers-Danlos Syndrome (EDS), a complex genetic connective tissue disorder with clinical features that can mimic other disease processes. Our study focuses on developing a unique image-based goniometry system, the HybridPoseNet, which utilizes a hybrid deep learning model.</p><p><strong>Objective: </strong>The proposed model is designed to provide the most accurate joint angle measurements in EDS appraisals. Using a hybrid of CNNs and HyperLSTMs in the pose estimation module of HybridPoseNet offers superior generalization and time consistency properties, setting it apart from existing complex libraries.</p><p><strong>Methodology: </strong>HybridPoseNet integrates the spatial pattern recognition prowess of MobileNet-V2 with the sequential data processing capability of HyperLSTM units. The system captures the dynamic nature of joint motion by creating a model that learns from individual frames and the sequence of movements. The CNN module of HybridPoseNet was trained on a large and diverse data set before the fine-tuning of video data involving 50 individuals visiting the EDS clinic, focusing on joints that can hyperextend. HyperLSTMs have been incorporated in video frames to avoid any time breakage in joint angle estimation in consecutive frames. The model performance was evaluated using Spearman's coefficient correlation versus manual goniometry measurements, as well as by the human labeling of joint position, the second validation step.</p><p><strong>Outcome: </strong>Preliminary findings demonstrate HybridPoseNet achieving a remarkable correlation with manual Goniometric measurements: thumb (rho = 0.847), elbows (rho = 0.822), knees (rho = 0.839), and fifth fingers (rho = 0.896), indicating that the newest model is considerably better. The model manifested a consistent performance in all joint assessments, hence not requiring selecting a variety of pose-measuring libraries for every joint. The presentation of HybridPoseNet contributes to achieving a combined and normalized approach to reviewing the mobility of joints, which has an overall enhancement of approximately 20% in accuracy compared to the regular pose estimation libraries. This innovation is very valuable to the field of medical diagnostics of connective tissue diseases and a vast improvement to its understanding.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11264507/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141723165","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-16DOI: 10.1186/s12911-024-02599-9
HongYuan Lu, XinMiao Feng, Jing Zhang
This research study demonstrates an efficient scheme for early detection of cardiorespiratory complications in pandemics by Utilizing Wearable Electrocardiogram (ECG) sensors for pattern generation and Convolution Neural Networks (CNN) for decision analytics. In health-related outbreaks, timely and early diagnosis of such complications is conclusive in reducing mortality rates and alleviating the burden on healthcare facilities. Existing methods rely on clinical assessments, medical history reviews, and hospital-based monitoring, which are valuable but have limitations in terms of accessibility, scalability, and timeliness, particularly during pandemics. The proposed scheme commences by deploying wearable ECG sensors on the patient's body. These sensors collect data by continuously monitoring the cardiac activity and respiratory patterns of the patient. The collected raw data is then transmitted securely in a wireless manner to a centralized server and stored in a database. Subsequently, the stored data is assessed using a preprocessing process which extracts relevant and important features like heart rate variability and respiratory rate. The preprocessed data is then used as input into the CNN model for the classification of normal and abnormal cardiorespiratory patterns. To achieve high accuracy in abnormality detection the CNN model is trained on labeled data with optimized parameters. The performance of the proposed scheme is evaluated and gauged using different scenarios, which shows a robust performance in detecting abnormal cardiorespiratory patterns with a sensitivity of 95% and specificity of 92%. Prominent observations, which highlight the potential for early interventions include subtle changes in heart rate variability and preceding respiratory distress. These findings show the significance of wearable ECG technology in improving pandemic management strategies and informing public health policies, which enhances preparedness and resilience in the face of emerging health threats.
{"title":"Early detection of cardiorespiratory complications and training monitoring using wearable ECG sensors and CNN.","authors":"HongYuan Lu, XinMiao Feng, Jing Zhang","doi":"10.1186/s12911-024-02599-9","DOIUrl":"10.1186/s12911-024-02599-9","url":null,"abstract":"<p><p>This research study demonstrates an efficient scheme for early detection of cardiorespiratory complications in pandemics by Utilizing Wearable Electrocardiogram (ECG) sensors for pattern generation and Convolution Neural Networks (CNN) for decision analytics. In health-related outbreaks, timely and early diagnosis of such complications is conclusive in reducing mortality rates and alleviating the burden on healthcare facilities. Existing methods rely on clinical assessments, medical history reviews, and hospital-based monitoring, which are valuable but have limitations in terms of accessibility, scalability, and timeliness, particularly during pandemics. The proposed scheme commences by deploying wearable ECG sensors on the patient's body. These sensors collect data by continuously monitoring the cardiac activity and respiratory patterns of the patient. The collected raw data is then transmitted securely in a wireless manner to a centralized server and stored in a database. Subsequently, the stored data is assessed using a preprocessing process which extracts relevant and important features like heart rate variability and respiratory rate. The preprocessed data is then used as input into the CNN model for the classification of normal and abnormal cardiorespiratory patterns. To achieve high accuracy in abnormality detection the CNN model is trained on labeled data with optimized parameters. The performance of the proposed scheme is evaluated and gauged using different scenarios, which shows a robust performance in detecting abnormal cardiorespiratory patterns with a sensitivity of 95% and specificity of 92%. Prominent observations, which highlight the potential for early interventions include subtle changes in heart rate variability and preceding respiratory distress. These findings show the significance of wearable ECG technology in improving pandemic management strategies and informing public health policies, which enhances preparedness and resilience in the face of emerging health threats.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11250964/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141626068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}