Informatics in Medicine Unlocked最新文献_第2页

A medical image captioning system for TeleOTIVA: Supporting SDGs-oriented cervical precancer screening in Indonesia TeleOTIVA的医学图像字幕系统：支持印尼面向可持续发展目标的宫颈癌前筛查

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2026-01-01 DOI: 10.1016/j.imu.2025.101719

Firdaus Firdaus , Siti Nurmaini , Rizki Ayunda Pratama , Elly Matul Imah , Muhammad Naufal Rachmatullah , Ade Iriani Sapitri , Annisa Darmawahyuni , Anggun Islami , Akhiar Wista Arum , Bambang Tutuko , Patiyus Agustiansyah , Rizal Sanif , Radiyati Umi Partan

Cervical cancer screening using Visual Inspection with Acetic Acid (VIA) remains a critical strategy in resource-limited settings. However, its effectiveness is often hindered by diagnostic variability arising from subjective interpretation. To address this challenge, we introduce TeleOTIVA, an AI-powered system designed to automatically detect and describe cervical lesions from VIA images. The system integrates YOLOv11-based lesion detection and segmentation with a Dense Residual Network and an embedding LSTM-based image captioning module, enabling it to generate clinically meaningful descriptions encompassing lesion borders, surface texture, and anatomical location. The performance of TeleOTIVA demonstrates promising results. Evaluations of the generated captions, compared to expert-annotated ground truth, yielded high scores across multiple metrics: BLEU (0.5711), METEOR (0.6726), and ROUGE-L (0.6929). These results indicate a high degree of n-gram similarity, semantic relevance, grammatical accuracy, and structural alignment with human-generated descriptions. In other words, the model not only mirrors expert-level vocabulary but also captures the clinical essence of VIA image interpretation. This synergy between advanced lesion detection and automated caption generation significantly enhances the accuracy, efficiency, and accessibility of cervical cancer screening. TeleOTIVA thus offers a powerful and scalable diagnostic aid, particularly impactful for improving early detection efforts in underserved and low-resource regions.

在资源有限的情况下，使用醋酸目视检查（VIA）进行宫颈癌筛查仍然是一种重要的策略。然而，其有效性往往受到主观解释引起的诊断可变性的阻碍。为了应对这一挑战，我们引入了TeleOTIVA，这是一种人工智能驱动的系统，旨在从VIA图像中自动检测和描述宫颈病变。该系统将基于yolov11的病变检测和分割与密集残差网络和基于嵌入lstm的图像标题模块相结合，使其能够生成包括病变边界、表面纹理和解剖位置在内的具有临床意义的描述。TeleOTIVA的性能显示出良好的效果。与专家注释的真实情况相比，对生成的字幕的评估在多个指标上获得了高分：BLEU（0.5711）、METEOR（0.6726）和ROUGE-L（0.6929）。这些结果表明，与人类生成的描述具有高度的n-gram相似性、语义相关性、语法准确性和结构一致性。换句话说，该模型不仅反映了专家级词汇，还捕捉到了VIA图像解释的临床本质。这种高级病变检测和自动字幕生成之间的协同作用显著提高了宫颈癌筛查的准确性、效率和可及性。因此，TeleOTIVA提供了一种强大且可扩展的诊断援助，对改善服务不足和资源匮乏地区的早期发现工作尤其有影响。

{"title":"A medical image captioning system for TeleOTIVA: Supporting SDGs-oriented cervical precancer screening in Indonesia","authors":"Firdaus Firdaus , Siti Nurmaini , Rizki Ayunda Pratama , Elly Matul Imah , Muhammad Naufal Rachmatullah , Ade Iriani Sapitri , Annisa Darmawahyuni , Anggun Islami , Akhiar Wista Arum , Bambang Tutuko , Patiyus Agustiansyah , Rizal Sanif , Radiyati Umi Partan","doi":"10.1016/j.imu.2025.101719","DOIUrl":"10.1016/j.imu.2025.101719","url":null,"abstract":"<div><div>Cervical cancer screening using Visual Inspection with Acetic Acid (VIA) remains a critical strategy in resource-limited settings. However, its effectiveness is often hindered by diagnostic variability arising from subjective interpretation. To address this challenge, we introduce TeleOTIVA, an AI-powered system designed to automatically detect and describe cervical lesions from VIA images. The system integrates YOLOv11-based lesion detection and segmentation with a Dense Residual Network and an embedding LSTM-based image captioning module, enabling it to generate clinically meaningful descriptions encompassing lesion borders, surface texture, and anatomical location. The performance of TeleOTIVA demonstrates promising results. Evaluations of the generated captions, compared to expert-annotated ground truth, yielded high scores across multiple metrics: BLEU (0.5711), METEOR (0.6726), and ROUGE-L (0.6929). These results indicate a high degree of n-gram similarity, semantic relevance, grammatical accuracy, and structural alignment with human-generated descriptions. In other words, the model not only mirrors expert-level vocabulary but also captures the clinical essence of VIA image interpretation. This synergy between advanced lesion detection and automated caption generation significantly enhances the accuracy, efficiency, and accessibility of cervical cancer screening. TeleOTIVA thus offers a powerful and scalable diagnostic aid, particularly impactful for improving early detection efforts in underserved and low-resource regions.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"60 ","pages":"Article 101719"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145921550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Automated identification of left ventricular hypertrophy using cardiac ultrasound imaging: A systematic review of artificial intelligence driven approaches 使用心脏超声成像自动识别左心室肥厚：人工智能驱动方法的系统回顾

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2026-01-01 DOI: 10.1016/j.imu.2025.101730

Jimcymol James , Anjan Gudigar , U. Raghavendra , Jyothi Samanth , M. Maithri , Aryaman Kaprekar , Mukund A. Prabhu , Massimo Salvi , Filippo Molinari , Edward J. Ciaccio , U. Rajendra Acharya

Left Ventricular Hypertrophy (LVH) is a significant cardiovascular risk marker that manifests in several clinical conditions, including Hypertension (HTN), Chronic Kidney Disease (CKD), and Hypertrophic Cardiomyopathy (HCM). This systematic review examines Artificial Intelligence (AI) approaches for the automated identification of these conditions using cardiac Ultrasound (US) imaging. Following the PRISMA guidelines, 37 relevant articles (7 reviews, 30 research papers) published between 2010 and 2025 were analysed. The analysis revealed three primary methodological approaches: feature learning pipelines, end-to-end Deep Learning (DL), and hybrid methods that combine both techniques. For CKD detection, only one study using cardiac US was identified, which achieved 99.09 % classification accuracy using Support Vector Machine (SVM) with steerable Gaussian filters and entropy features. HTN classification studies have demonstrated high performance across different approaches: traditional Machine Learning (ML) classifiers (decision trees with transform features: 99.11 %, weighted k-nearest neighbors: 98 %) and DL methods (Area Under Curve (AUC): 0.92–0.94). HCM studies ranged from binary classification (42.3 % of studies) to multi-class problems of increasing complexity (3-class: 38.4 %, 4-class: 11.5 %, 5-class: 7.6 %), with SVM achieving 95.2 % average sensitivity and DL models reaching an average AUC of 0.94. Current limitations include a predominant focus on binary classification problems, limited research on cardiac-based CKD detection, and a lack of standardized datasets. Future research directions include developing hybrid methodologies that combine traditional and DL approaches, creating standardized multimodal databases, implementing explainable AI techniques, and integrating Internet of Things technologies for continuous monitoring.

左心室肥厚（LVH）是一项重要的心血管危险标志物，在多种临床情况下均有表现，包括高血压（HTN）、慢性肾病（CKD）和肥厚性心肌病（HCM）。本系统综述研究了使用心脏超声（US）成像自动识别这些疾病的人工智能（AI）方法。根据PRISMA指南，我们分析了2010年至2025年间发表的37篇相关文章（7篇综述，30篇研究论文）。分析揭示了三种主要的方法方法：特征学习管道，端到端深度学习（DL），以及结合这两种技术的混合方法。对于CKD的检测，仅鉴定了一项使用心脏US的研究，该研究使用具有可操纵高斯滤波器和熵特征的支持向量机（SVM）实现了99.09%的分类准确率。HTN分类研究已经证明了不同方法的高性能：传统机器学习（ML）分类器（具有变换特征的决策树：99.11%，加权k近邻：98%）和深度学习方法（曲线下面积（AUC）： 0.92-0.94）。HCM的研究范围从二元分类（42.3%的研究）到日益复杂的多类问题（3类：38.4%，4类：11.5%，5类：7.6%），SVM的平均灵敏度达到95.2%，DL模型的平均AUC达到0.94。目前的限制包括主要关注二分类问题，基于心脏的CKD检测研究有限，以及缺乏标准化数据集。未来的研究方向包括开发结合传统和深度学习方法的混合方法，创建标准化的多模态数据库，实施可解释的人工智能技术，以及集成物联网技术进行持续监测。

{"title":"Automated identification of left ventricular hypertrophy using cardiac ultrasound imaging: A systematic review of artificial intelligence driven approaches","authors":"Jimcymol James , Anjan Gudigar , U. Raghavendra , Jyothi Samanth , M. Maithri , Aryaman Kaprekar , Mukund A. Prabhu , Massimo Salvi , Filippo Molinari , Edward J. Ciaccio , U. Rajendra Acharya","doi":"10.1016/j.imu.2025.101730","DOIUrl":"10.1016/j.imu.2025.101730","url":null,"abstract":"<div><div>Left Ventricular Hypertrophy (LVH) is a significant cardiovascular risk marker that manifests in several clinical conditions, including Hypertension (HTN), Chronic Kidney Disease (CKD), and Hypertrophic Cardiomyopathy (HCM). This systematic review examines Artificial Intelligence (AI) approaches for the automated identification of these conditions using cardiac Ultrasound (US) imaging. Following the PRISMA guidelines, 37 relevant articles (7 reviews, 30 research papers) published between 2010 and 2025 were analysed. The analysis revealed three primary methodological approaches: feature learning pipelines, end-to-end Deep Learning (DL), and hybrid methods that combine both techniques. For CKD detection, only one study using cardiac US was identified, which achieved 99.09 % classification accuracy using Support Vector Machine (SVM) with steerable Gaussian filters and entropy features. HTN classification studies have demonstrated high performance across different approaches: traditional Machine Learning (ML) classifiers (decision trees with transform features: 99.11 %, weighted k-nearest neighbors: 98 %) and DL methods (Area Under Curve (AUC): 0.92–0.94). HCM studies ranged from binary classification (42.3 % of studies) to multi-class problems of increasing complexity (3-class: 38.4 %, 4-class: 11.5 %, 5-class: 7.6 %), with SVM achieving 95.2 % average sensitivity and DL models reaching an average AUC of 0.94. Current limitations include a predominant focus on binary classification problems, limited research on cardiac-based CKD detection, and a lack of standardized datasets. Future research directions include developing hybrid methodologies that combine traditional and DL approaches, creating standardized multimodal databases, implementing explainable AI techniques, and integrating Internet of Things technologies for continuous monitoring.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"60 ","pages":"Article 101730"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145921553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Objective detection of Parkinson's disease motor states using Lasso-selected IMUs features 目的利用lasso选择imu特征检测帕金森病运动状态

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2026-01-01 DOI: 10.1016/j.imu.2026.101732

Mevludin Memedi

Background and objective

Machine learning (ML) models that use data captured from Inertial Measurement Units (IMUs) are widely applied in the clinical management of Parkinson's disease (PD). However, performance and interpretability of these models can be influenced by the selection of input features, especially when dealing with multi-dimensional data. This study investigates the performance of Lasso regularization in improving performance and simplicity of supervised and unsupervised ML models using IMUs data.

Methods

Data were collected using IMUs placed on the wrists and ankles of 19 patients (14 males and 5 females) with advanced PD (mean years with disease of 10 years). Participants performed different motor tests, and three movement disorder specialists rated the severity of motor states (Off and dyskinesia) on a Treatment Response Scale (TRS). Sensor data were processed, and features were reduced by Lasso regularization and used as inputs to Support Vector Machines (SVM) for classification and regression. In addition, clustering methods were employed to align the sensor data to clinical labels.

Results

Linear SVM correctly classified Off motor state from treatment-induced dyskinesia state with an accuracy of 93.9 % and 93.3 %, respectively. The correlation coefficient between the predicted TRS score derived by gaussian SVM and mean TRS score of the three specialists was 0.91. The clusters derived by the clustering algorithms separated well the instances when the patients were in Off and dyskinesia motor states.

Conclusions

Using Lasso regularization as a feature selection method coupled with ML models yielded good predictive performance when fusing multi-sensor and -activity data from IMUs. This approach can be used as a tool to objectively assess PD motor states and improve the management of the disease by individualizing treatments.

背景与目的利用惯性测量单元（imu）数据采集的机器学习（ML）模型在帕金森病（PD）的临床管理中得到了广泛的应用。然而，这些模型的性能和可解释性可能会受到输入特征选择的影响，特别是在处理多维数据时。本研究探讨了Lasso正则化在使用imu数据提高有监督和无监督ML模型的性能和简单性方面的性能。方法对19例（男14例，女5例）晚期PD患者（平均患病时间为10年）进行腕、踝部imu采集数据。参与者进行不同的运动测试，三位运动障碍专家在治疗反应量表（TRS）上评估运动状态（关闭和运动障碍）的严重程度。对传感器数据进行处理，通过Lasso正则化对特征进行约简，并将其作为支持向量机（SVM）的输入进行分类和回归。此外，采用聚类方法将传感器数据与临床标签对齐。结果线性支持向量机对治疗引起的运动障碍状态和运动关闭状态的分类准确率分别为93.9%和93.3%。高斯支持向量机预测的TRS评分与三位专家的平均TRS评分的相关系数为0.91。由聚类算法得到的聚类能很好地分离出患者在运动障碍状态和运动障碍状态下的实例。结论将Lasso正则化作为特征选择方法与ML模型相结合，在融合多传感器和imu活动数据时具有良好的预测性能。这种方法可以作为客观评估PD运动状态的工具，并通过个体化治疗改善疾病的管理。

{"title":"Objective detection of Parkinson's disease motor states using Lasso-selected IMUs features","authors":"Mevludin Memedi","doi":"10.1016/j.imu.2026.101732","DOIUrl":"10.1016/j.imu.2026.101732","url":null,"abstract":"<div><h3>Background and objective</h3><div>Machine learning (ML) models that use data captured from Inertial Measurement Units (IMUs) are widely applied in the clinical management of Parkinson's disease (PD). However, performance and interpretability of these models can be influenced by the selection of input features, especially when dealing with multi-dimensional data. This study investigates the performance of Lasso regularization in improving performance and simplicity of supervised and unsupervised ML models using IMUs data.</div></div><div><h3>Methods</h3><div>Data were collected using IMUs placed on the wrists and ankles of 19 patients (14 males and 5 females) with advanced PD (mean years with disease of 10 years). Participants performed different motor tests, and three movement disorder specialists rated the severity of motor states (Off and dyskinesia) on a Treatment Response Scale (TRS). Sensor data were processed, and features were reduced by Lasso regularization and used as inputs to Support Vector Machines (SVM) for classification and regression. In addition, clustering methods were employed to align the sensor data to clinical labels.</div></div><div><h3>Results</h3><div>Linear SVM correctly classified Off motor state from treatment-induced dyskinesia state with an accuracy of 93.9 % and 93.3 %, respectively. The correlation coefficient between the predicted TRS score derived by gaussian SVM and mean TRS score of the three specialists was 0.91. The clusters derived by the clustering algorithms separated well the instances when the patients were in Off and dyskinesia motor states.</div></div><div><h3>Conclusions</h3><div>Using Lasso regularization as a feature selection method coupled with ML models yielded good predictive performance when fusing multi-sensor and -activity data from IMUs. This approach can be used as a tool to objectively assess PD motor states and improve the management of the disease by individualizing treatments.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"60 ","pages":"Article 101732"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145921549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Noise-Aware Undersampling for imbalanced medical data (NAUS) 不平衡医疗数据的噪声感知欠采样（NAUS）

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2026-01-01 DOI: 10.1016/j.imu.2026.101731

Zholdas Buribayev , Ainur Yerkos , Zhibek Zhetpisbay , Markus Wolfien

Advancements in medical research have increasingly relied on robust data analytics to support diagnostic and treatment decisions. However, data analysis still faces challenges when investigating datasets with severe class imbalance, often stemming from the rarity of certain conditions and uneven disease distributions. To address this issue, we propose the Noise-Aware Undersampling with Subsampling (NAUS) algorithm. NAUS integrates clustering, noise removal, and Tomek-link identification techniques to create refined subsamples that assess the significance of individual observations, while systematically removing redundant and noisy data. The proposed approach was evaluated on datasets related to chronic kidney disease, liver disease, heart disease and its performance was compared to that of traditional oversampling methods (e.g., SMOTE, ADASYN, LoRAS) and undersampling techniques (e.g., random undersampling, Tomek-links). Our experimental results, based on machine learning classifiers (e.g. Random Forest, LightGBM, and Multilayer Perceptron). Data visualization further confirmed that NAUS effectively mitigates class imbalance, making it a promising tool for enhancing the reliability of medical data analysis.

医学研究的进步越来越依赖于强大的数据分析来支持诊断和治疗决策。然而，在调查具有严重类别不平衡的数据集时，数据分析仍然面临挑战，通常源于某些疾病的罕见性和不均匀的疾病分布。为了解决这个问题，我们提出了带有子采样的噪声感知欠采样（NAUS）算法。NAUS集成了聚类、去噪和Tomek-link识别技术，以创建精细的子样本，评估个人观察的重要性，同时系统地去除冗余和噪声数据。在慢性肾病、肝病和心脏病相关的数据集上对所提出的方法进行了评估，并将其性能与传统的过采样方法（例如SMOTE、ADASYN、LoRAS）和欠采样技术（例如随机欠采样、Tomek-links）进行了比较。我们的实验结果，基于机器学习分类器（例如Random Forest， LightGBM和Multilayer Perceptron）。数据可视化进一步证实了NAUS有效缓解了类别不平衡，使其成为提高医疗数据分析可靠性的有前景的工具。

{"title":"Noise-Aware Undersampling for imbalanced medical data (NAUS)","authors":"Zholdas Buribayev , Ainur Yerkos , Zhibek Zhetpisbay , Markus Wolfien","doi":"10.1016/j.imu.2026.101731","DOIUrl":"10.1016/j.imu.2026.101731","url":null,"abstract":"<div><div>Advancements in medical research have increasingly relied on robust data analytics to support diagnostic and treatment decisions. However, data analysis still faces challenges when investigating datasets with severe class imbalance, often stemming from the rarity of certain conditions and uneven disease distributions. To address this issue, we propose the Noise-Aware Undersampling with Subsampling (NAUS) algorithm. NAUS integrates clustering, noise removal, and Tomek-link identification techniques to create refined subsamples that assess the significance of individual observations, while systematically removing redundant and noisy data. The proposed approach was evaluated on datasets related to chronic kidney disease, liver disease, heart disease and its performance was compared to that of traditional oversampling methods (e.g., SMOTE, ADASYN, LoRAS) and undersampling techniques (e.g., random undersampling, Tomek-links). Our experimental results, based on machine learning classifiers (e.g. Random Forest, LightGBM, and Multilayer Perceptron). Data visualization further confirmed that NAUS effectively mitigates class imbalance, making it a promising tool for enhancing the reliability of medical data analysis.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"60 ","pages":"Article 101731"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145921547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluating cultural impact on subject-independent EEG-based emotion recognition approaches 评估文化对独立于主体的基于脑电图的情感识别方法的影响

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2026-01-01 DOI: 10.1016/j.imu.2025.101728

Anshul Sheoran , Camilo E. Valderrama

Culture plays a crucial role in shaping emotional expression and recognition, influencing how individuals perceive and regulate emotions. Electroencephalography (EEG) can capture electrical activity associated with human emotion processing from the scalp. The electrical activity can be processed using deep learning models to predict emotional states. Two approaches can be employed to develop these deep learning models: subject-dependent and subject-independent. The subject-independent approach is more practical as it trains the model on data from some individuals and tests it on entirely different individuals, ensuring it generalizes well to new users. However, because of the high variability of EEG across individuals, the subject-independent approach tends to yield low performance. Recent studies suggest incorporating demographic information along with EEG signals is one way to overcome this issue. By using the subject-independent approach, this study investigates how cultural factors impact emotion prediction. Specifically, we used a stacking model that combines deep learning with multinomial logistic regression to predict positive, neutral, and negative emotions among 15 Chinese, 8 French, and 8 German subjects. Our approach achieved accuracies of 77.3% for Chinese subjects, 73% for French subjects, and 65% for German subjects, which are comparable to or exceed accuracies reported by previous studies. Our approach highlighted that incorporating cultural information increases the likelihood of predicting positive emotions for Chinese participants and negative emotions for Europeans. Moreover, French and German subjects exhibited similar neural patterns across all emotions, suggesting a more common cultural sharing between those subjects. Overall, our findings emphasize the importance of integrating cultural considerations into emotion recognition models. This inclusion not only improves emotion prediction accuracy for subject-independent approaches but also promotes inclusivity and ethical practices in emotion recognition systems.

文化在塑造情绪表达和识别方面起着至关重要的作用，影响着个体如何感知和调节情绪。脑电图（EEG）可以从头皮捕捉到与人类情感处理相关的电活动。脑电活动可以通过深度学习模型来预测情绪状态。可以采用两种方法来开发这些深度学习模型：主题依赖和主题独立。独立于主题的方法更实用，因为它根据来自某些个体的数据训练模型，并在完全不同的个体上进行测试，以确保它可以很好地推广到新用户。然而，由于脑电图在个体之间的高度可变性，独立于受试者的方法往往产生较低的性能。最近的研究表明，将人口统计信息与脑电图信号结合起来是克服这一问题的一种方法。本研究采用受试者独立的方法，探讨文化因素对情绪预测的影响。具体来说，我们使用了一个将深度学习与多项逻辑回归相结合的叠加模型来预测15名中国、8名法国和8名德国受试者的积极、中性和消极情绪。我们的方法在中文受试者中达到了77.3%的准确率，在法语受试者中达到了73%，在德语受试者中达到了65%，这与之前的研究报告的准确率相当或超过了这些准确率。我们的方法强调，结合文化信息增加了预测中国参与者积极情绪和欧洲参与者消极情绪的可能性。此外，法语和德语受试者在所有情绪上都表现出相似的神经模式，这表明这些受试者之间存在更普遍的文化共享。总的来说，我们的研究结果强调了将文化因素整合到情感识别模型中的重要性。这种包容不仅提高了独立于主体方法的情感预测准确性，而且促进了情感识别系统的包容性和伦理实践。

{"title":"Evaluating cultural impact on subject-independent EEG-based emotion recognition approaches","authors":"Anshul Sheoran , Camilo E. Valderrama","doi":"10.1016/j.imu.2025.101728","DOIUrl":"10.1016/j.imu.2025.101728","url":null,"abstract":"<div><div>Culture plays a crucial role in shaping emotional expression and recognition, influencing how individuals perceive and regulate emotions. Electroencephalography (EEG) can capture electrical activity associated with human emotion processing from the scalp. The electrical activity can be processed using deep learning models to predict emotional states. Two approaches can be employed to develop these deep learning models: subject-dependent and subject-independent. The subject-independent approach is more practical as it trains the model on data from some individuals and tests it on entirely different individuals, ensuring it generalizes well to new users. However, because of the high variability of EEG across individuals, the subject-independent approach tends to yield low performance. Recent studies suggest incorporating demographic information along with EEG signals is one way to overcome this issue. By using the subject-independent approach, this study investigates how cultural factors impact emotion prediction. Specifically, we used a stacking model that combines deep learning with multinomial logistic regression to predict positive, neutral, and negative emotions among 15 Chinese, 8 French, and 8 German subjects. Our approach achieved accuracies of 77.3% for Chinese subjects, 73% for French subjects, and 65% for German subjects, which are comparable to or exceed accuracies reported by previous studies. Our approach highlighted that incorporating cultural information increases the likelihood of predicting positive emotions for Chinese participants and negative emotions for Europeans. Moreover, French and German subjects exhibited similar neural patterns across all emotions, suggesting a more common cultural sharing between those subjects. Overall, our findings emphasize the importance of integrating cultural considerations into emotion recognition models. This inclusion not only improves emotion prediction accuracy for subject-independent approaches but also promotes inclusivity and ethical practices in emotion recognition systems.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"60 ","pages":"Article 101728"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145921548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A systematic review on computer vision-based methods for cervical cancer detection 基于计算机视觉的宫颈癌检测方法综述

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2025-12-16 DOI: 10.1016/j.imu.2025.101726

Hope Mbelwa , Judith Leo , Crispin Kahesa , Elizabeth Mkoba

Cervical cancer is a leading cause of mortality among women globally, especially in regions where access to timely screening remains a challenge. With such concerns, accurate detection of cervical lesions is essential for effective diagnosis and treatment. This review aimed to explore the application of computer vision-based methods for detecting cervical cancer, identifying their potential, setbacks and areas for future development. A comprehensive literature search across Scopus, IEEE Xplore, PubMed, and Google Scholar identified 96 relevant studies published between 2014 and August 2025. These studies applied computer vision methods including CNNs, Vision Transformers, and multimodal models to cervical cancer detection using Pap smear, colposcopy, and histopathology images. They were analyzed based on the techniques employed, datasets used, evaluation metrics adopted, and reported results. This review highlights significant advancements in the field, particularly in lesion classification, precise segmentation of affected regions, and accurate detection of cancerous regions. However, some challenges were identified, including limited image datasets with insufficiently distributed normal and abnormal cases, aggravated by privacy issues and accurate labeling of medical images, which is critical and rigorous, often leading to annotation inconsistencies. Lastly, this study revealed that integrating Natural Language Processing and Computer Vision can enhance cervical cancer diagnosis through multi-modal models that combine both clinical text and imaging data. Additionally, this study proposes the use of techniques like annotation-efficient learning to manage limited labeled datasets using methods such as semi-supervised and transfer learning as well as the use of federated learning to ensure privacy in computer-aided diagnostic systems.

宫颈癌是全球妇女死亡的主要原因，特别是在获得及时筛查仍然是一项挑战的区域。考虑到这些问题，准确检测宫颈病变对于有效的诊断和治疗至关重要。本文旨在探讨基于计算机视觉的宫颈癌检测方法的应用，确定其潜力，挫折和未来发展的领域。在Scopus、IEEE explore、PubMed和b谷歌Scholar上进行了全面的文献检索，确定了2014年至2025年8月期间发表的96项相关研究。这些研究将计算机视觉方法包括cnn、视觉变形器和多模态模型应用于宫颈涂片、阴道镜检查和组织病理学图像的宫颈癌检测。根据采用的技术、使用的数据集、采用的评估指标和报告的结果对它们进行分析。这篇综述强调了该领域的重大进展，特别是在病变分类、受影响区域的精确分割和癌变区域的准确检测方面。然而，也发现了一些挑战，包括图像数据集有限，正常和异常病例分布不足，隐私问题和医学图像的准确标记（这是至关重要和严格的）加剧了这些问题，往往导致注释不一致。最后，本研究表明，将自然语言处理和计算机视觉相结合，可以通过结合临床文本和图像数据的多模态模型来提高宫颈癌的诊断。此外，本研究提出使用注释高效学习等技术来管理有限的标记数据集，使用半监督和迁移学习等方法，以及使用联邦学习来确保计算机辅助诊断系统中的隐私。

{"title":"A systematic review on computer vision-based methods for cervical cancer detection","authors":"Hope Mbelwa , Judith Leo , Crispin Kahesa , Elizabeth Mkoba","doi":"10.1016/j.imu.2025.101726","DOIUrl":"10.1016/j.imu.2025.101726","url":null,"abstract":"<div><div>Cervical cancer is a leading cause of mortality among women globally, especially in regions where access to timely screening remains a challenge. With such concerns, accurate detection of cervical lesions is essential for effective diagnosis and treatment. This review aimed to explore the application of computer vision-based methods for detecting cervical cancer, identifying their potential, setbacks and areas for future development. A comprehensive literature search across Scopus, IEEE Xplore, PubMed, and Google Scholar identified 96 relevant studies published between 2014 and August 2025. These studies applied computer vision methods including CNNs, Vision Transformers, and multimodal models to cervical cancer detection using Pap smear, colposcopy, and histopathology images. They were analyzed based on the techniques employed, datasets used, evaluation metrics adopted, and reported results. This review highlights significant advancements in the field, particularly in lesion classification, precise segmentation of affected regions, and accurate detection of cancerous regions. However, some challenges were identified, including limited image datasets with insufficiently distributed normal and abnormal cases, aggravated by privacy issues and accurate labeling of medical images, which is critical and rigorous, often leading to annotation inconsistencies. Lastly, this study revealed that integrating Natural Language Processing and Computer Vision can enhance cervical cancer diagnosis through multi-modal models that combine both clinical text and imaging data. Additionally, this study proposes the use of techniques like annotation-efficient learning to manage limited labeled datasets using methods such as semi-supervised and transfer learning as well as the use of federated learning to ensure privacy in computer-aided diagnostic systems.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"60 ","pages":"Article 101726"},"PeriodicalIF":0.0,"publicationDate":"2025-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145788409","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Epic overhaul at a Canadian hospital: Pre-Post evaluation insights from physicians and medical residents 加拿大一家医院史诗般的大修：来自医生和住院医生的前后评估见解

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2025-12-16 DOI: 10.1016/j.imu.2025.101725

Mirou Jaana , Edward Riachy , Erika MacPhee , Heather Sherrard

Background

The implementation of Electronic Medical Records (EMRs) in hospitals offers potential benefits but often disrupts clinician workflows, affecting care delivery and outcomes.

Objective

This study evaluates physicians' and medical residents’ perspectives on the impacts of introducing a new Epic system at a Canadian academic hospital.

Methods

A pre-post evaluation design was conducted using physician and resident surveys before (T0) and 4- and 9-months post-implementation (T1, T2) that assessed technology use, satisfaction with training and system use, and EMR's perceived impact on care delivery, work practices and quality.

Results

Satisfaction with training and system use declined for both groups in the first four months (more sharply for residents) but several measures improved at T2 as users readjusted to the system. There was a significant increase in physicians’ daily computer use (4 h at T0 to 6 h at T1; P < .001). Limited early benefits of the Epic system were observed and a decline in perceived improvement in clinical documentation (P = .006 and .0012), order entry (P = .018 and .002) and patient safety (P = .044 and .024) were reported at T1 for physicians and residents, respectively. Although some medical practice/work indicators improved by 9 months for physicians, the changes were not statistically significant; these benefits were not observed for residents at T2. Medical training was not significantly affected by the new Epic system either immediately or later post implementation. At T1, 83% of physicians reported that the new system sometimes or often improved the quality of care, as opposed to only 33% of residents; no significant improvements were noted at 9 months post implementation by both groups.

Conclusions

Physicians and residents adapt differently to Epic and full system assimilation does not happen in one year. Early perceptions of Epic do not reflect its long-term potential, and meaningful benefits require prolonged stabilization periods for user satisfaction and efficiency gains. We caution hospital leaders not to rely heavily on a vendor-driven implementation, and recommend tailored training, rapid-cycle improvements, transparent communication, and monitoring of agreed-upon performance indicators to strengthen clinician engagement and support long-term success.

在医院实施电子病历（emr）提供了潜在的好处，但往往会扰乱临床医生的工作流程，影响医疗服务的提供和结果。目的本研究评估医生和住院医师对加拿大一家学术医院引入新的Epic系统的影响的看法。方法采用实施前（T0）和实施后4个月、9个月（T1、T2）的医师和住院医师调查进行前后评估设计，评估技术使用情况、培训和系统使用满意度，以及EMR对护理交付、工作实践和质量的感知影响。结果在前四个月，两组患者对培训和系统使用的满意度都有所下降（住院患者的满意度下降得更明显），但随着用户重新适应系统，在T2阶段有几项指标有所改善。医生每天使用电脑的时间显著增加（T0时为4小时，T1时为6小时；P < 0.001）。观察到Epic系统的早期益处有限，临床文献中感知到的改善有所下降（P = 0.006和P = 0.006）。0012)，订单输入(P = .018和。002)和患者安全(P = 0.044；在T1时，医生和住院医生分别报告了024例。虽然医生的一些医疗实践/工作指标提高了9个月，但变化没有统计学意义；T2的居民没有观察到这些益处。新的Epic系统对医疗训练没有明显的影响，无论是立即还是之后。在T1, 83%的医生报告说，新系统有时或经常提高护理质量，而只有33%的住院医生这样认为；两组在实施后9个月均未见明显改善。结论医师和住院医师对Epic的适应程度存在差异，并不是在一年内完全同化。早期对Epic的看法并没有反映出它的长期潜力，真正有意义的收益需要长期的稳定期来满足用户满意度和提高效率。我们提醒医院领导不要严重依赖供应商驱动的实施，并建议定制培训、快速周期改进、透明沟通和监测商定的绩效指标，以加强临床医生的参与并支持长期成功。

{"title":"Epic overhaul at a Canadian hospital: Pre-Post evaluation insights from physicians and medical residents","authors":"Mirou Jaana , Edward Riachy , Erika MacPhee , Heather Sherrard","doi":"10.1016/j.imu.2025.101725","DOIUrl":"10.1016/j.imu.2025.101725","url":null,"abstract":"<div><h3>Background</h3><div>The implementation of Electronic Medical Records (EMRs) in hospitals offers potential benefits but often disrupts clinician workflows, affecting care delivery and outcomes.</div></div><div><h3>Objective</h3><div>This study evaluates physicians' and medical residents’ perspectives on the impacts of introducing a new Epic system at a Canadian academic hospital.</div></div><div><h3>Methods</h3><div>A pre-post evaluation design was conducted using physician and resident surveys before (T0) and 4- and 9-months post-implementation (T1, T2) that assessed technology use, satisfaction with training and system use, and EMR's perceived impact on care delivery, work practices and quality.</div></div><div><h3>Results</h3><div>Satisfaction with training and system use declined for both groups in the first four months (more sharply for residents) but several measures improved at T2 as users readjusted to the system. There was a significant increase in physicians’ daily computer use (4 h at T0 to 6 h at T1; P < .<em>001</em>). Limited early benefits of the Epic system were observed and a decline in perceived improvement in clinical documentation (P = .<em>006</em> and <em>.0012)</em>, order entry (P = .<em>018</em> and <em>.002)</em> and patient safety (P = .<em>044</em> and <em>.024)</em> were reported at T1 for physicians and residents, respectively. Although some medical practice/work indicators improved by 9 months for physicians, the changes were not statistically significant; these benefits were not observed for residents at T2. Medical training was not significantly affected by the new Epic system either immediately or later post implementation. At T1, 83% of physicians reported that the new system sometimes or often improved the quality of care, as opposed to only 33% of residents; no significant improvements were noted at 9 months post implementation by both groups.</div></div><div><h3>Conclusions</h3><div>Physicians and residents adapt differently to Epic and full system assimilation does not happen in one year. Early perceptions of Epic do not reflect its long-term potential, and meaningful benefits require prolonged stabilization periods for user satisfaction and efficiency gains. We caution hospital leaders not to rely heavily on a vendor-driven implementation, and recommend tailored training, rapid-cycle improvements, transparent communication, and monitoring of agreed-upon performance indicators to strengthen clinician engagement and support long-term success.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"61 ","pages":"Article 101725"},"PeriodicalIF":0.0,"publicationDate":"2025-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146075004","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Comparative development and evaluation of multilayer fuzzy and adaptive neuro-fuzzy inference systems for early diagnosis of chronic kidney disease 多层模糊与自适应神经模糊推理系统在慢性肾脏疾病早期诊断中的比较开发与评价

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2025-12-13 DOI: 10.1016/j.imu.2025.101724

Arvind Sharma , Dalwinder Singh , Arun Singh , MVV Prasad Kantipudi , Saiprasd Potharaju , B. Suresh Babu

Chronic Kidney Disease (CKD) is a gradual yet life-threatening condition that often remains undetected until significant renal impairment has occurred. Early recognition is essential to slow its progression and reduce the risk of associated complications. Conventional diagnostic procedures have limitations; they are subjective and may be ineffective when symptoms take longer to manifest. In this paper, we propose and compare two intelligent diagnostic models—a Multilayer Fuzzy Inference System (MLFIS) and an Adaptive Neuro-Fuzzy Inference System (ANFIS)—that aim to diagnose early-stage CKD using clinical symptoms and laboratory indicators.

The model of MLFIS is constructed in dual form i.e. the first layer determines the probable presence of CKD, which is based on symptoms like hypertension, diabetes, and family history, and the second layer specifies the disease stage, which is done based on biochemical parameters attached with or without or increasing glomerular filtration rate, blood urea nitrogen, serum creatinine, albumin, and urinary pus cells. The ANFIS model, however, combines the strengths of both fuzzy logic and neural networks, providing automatic learning of diagnosis rules based on data, thereby increasing accuracy and flexibility.

The models had been constructed and benchmarked on a retrospective dataset consisting of 500 anonymised patient records retrieved from a publicly available resource, and then tested using standard performance measures. Although the ANFIS had a classification accuracy of 99.5 % which is a higher percentage than the 99.33 per cent accuracy of the MLFIS, the difference is not that great. Findings demonstrate the benchmarking performance of fuzzy and neuro-fuzzy systems for CKD staging, providing a foundation for future validation on hospital datasets. However, it is important to note that the high accuracies reported are based on a relatively small UCI dataset and should be interpreted as internal validation only. Broader clinical validation is necessary before deployment in real-world settings. The paper also compares these two systems and determines their performance based on current machine learning models. This study seeks to fill the gap between the laboratory-based diagnostic and real clinical practice by presenting a scalable and understandable solution to screening of CKD.

慢性肾脏疾病（CKD）是一种渐进但危及生命的疾病，通常在发生重大肾脏损害之前未被发现。早期识别对于减缓其进展和减少相关并发症的风险至关重要。传统的诊断程序有局限性；它们是主观的，当症状需要较长时间才能显现时，它们可能无效。在本文中，我们提出并比较了两种智能诊断模型-多层模糊推理系统（MLFIS）和自适应神经模糊推理系统(ANFIS) -旨在通过临床症状和实验室指标诊断早期CKD。MLFIS模型采用双重形式构建，第一层根据高血压、糖尿病、家族史等症状判断是否存在CKD，第二层根据肾小球滤过率、血尿素氮、血清肌酐、白蛋白、尿脓细胞等生化指标有无升高来确定疾病分期。然而，ANFIS模型结合了模糊逻辑和神经网络的优势，提供了基于数据的诊断规则的自动学习，从而提高了准确性和灵活性。这些模型是在一个回顾性数据集上构建的，该数据集由500个从公共资源中检索的匿名患者记录组成，然后使用标准性能指标进行测试。虽然ANFIS的分类准确率为99.5%，高于MLFIS的99.33%，但差异并不大。研究结果证明了模糊和神经模糊系统对CKD分期的基准性能，为未来在医院数据集上的验证提供了基础。然而，值得注意的是，报告的高准确性是基于相对较小的UCI数据集，应该只解释为内部验证。在实际应用之前，需要进行更广泛的临床验证。本文还比较了这两种系统，并基于当前的机器学习模型确定了它们的性能。本研究旨在通过提出一种可扩展且可理解的CKD筛查解决方案来填补实验室诊断与实际临床实践之间的空白。

{"title":"Comparative development and evaluation of multilayer fuzzy and adaptive neuro-fuzzy inference systems for early diagnosis of chronic kidney disease","authors":"Arvind Sharma , Dalwinder Singh , Arun Singh , MVV Prasad Kantipudi , Saiprasd Potharaju , B. Suresh Babu","doi":"10.1016/j.imu.2025.101724","DOIUrl":"10.1016/j.imu.2025.101724","url":null,"abstract":"<div><div>Chronic Kidney Disease (CKD) is a gradual yet life-threatening condition that often remains undetected until significant renal impairment has occurred. Early recognition is essential to slow its progression and reduce the risk of associated complications. Conventional diagnostic procedures have limitations; they are subjective and may be ineffective when symptoms take longer to manifest. In this paper, we propose and compare two intelligent diagnostic models—a Multilayer Fuzzy Inference System (MLFIS) and an Adaptive Neuro-Fuzzy Inference System (ANFIS)—that aim to diagnose early-stage CKD using clinical symptoms and laboratory indicators.</div><div>The model of MLFIS is constructed in dual form i.e. the first layer determines the probable presence of CKD, which is based on symptoms like hypertension, diabetes, and family history, and the second layer specifies the disease stage, which is done based on biochemical parameters attached with or without or increasing glomerular filtration rate, blood urea nitrogen, serum creatinine, albumin, and urinary pus cells. The ANFIS model, however, combines the strengths of both fuzzy logic and neural networks, providing automatic learning of diagnosis rules based on data, thereby increasing accuracy and flexibility.</div><div>The models had been constructed and benchmarked on a retrospective dataset consisting of 500 anonymised patient records retrieved from a publicly available resource, and then tested using standard performance measures. Although the ANFIS had a classification accuracy of 99.5 % which is a higher percentage than the 99.33 per cent accuracy of the MLFIS, the difference is not that great. Findings demonstrate the benchmarking performance of fuzzy and neuro-fuzzy systems for CKD staging, providing a foundation for future validation on hospital datasets. However, it is important to note that the high accuracies reported are based on a relatively small UCI dataset and should be interpreted as internal validation only. Broader clinical validation is necessary before deployment in real-world settings. The paper also compares these two systems and determines their performance based on current machine learning models. This study seeks to fill the gap between the laboratory-based diagnostic and real clinical practice by presenting a scalable and understandable solution to screening of CKD.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"60 ","pages":"Article 101724"},"PeriodicalIF":0.0,"publicationDate":"2025-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145788410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Review of machine learning models in short- and long-term glucose forecasting and hypoglycemia classification 短期和长期血糖预测和低血糖分类中的机器学习模型综述

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2025-12-08 DOI: 10.1016/j.imu.2025.101723

Beyza Cinar , Louisa van den Boom , Maria Maleshkova

Type 1 Diabetes (T1D) is a chronic autoimmune disorder that requires lifelong insulin therapy. A common side effect is hypoglycemia, characterized by decreased blood glucose levels (BGL) below 70 mg/dL. Diabetes care can be optimized using machine learning (ML) models that can predict and alert patients to potential glycemic abnormalities. The ML models can be classified into regression-based, in which glucose levels are forecasted, and classification-based, in which adverse events are classified. This review analyzes the performance of ML models applied to T1D and compares these in terms of short- and long-term prediction horizons (PHs), defined as 15–120 min and 3 to more than 24 h, respectively. This review investigates: 1) How much in advance can glucose values or a hypoglycemic event be accurately predicted? 2) Which ML methods have the best performance? 3) Which factors impact the performance? And 4) Does personalization increase performance? The results indicate that 1) a PH of up to 1 h provides the best results. 2) Conventional ML methods yield the best results for classification and deep learning (DL) for regression. A single model cannot adequately classify across multiple PHs. 3) The model performance is influenced by multivariate datasets and the input sequence length (ISL). 4) Finally, personal data enhances performance, but due to limited data quality, population-based models are preferred.

1型糖尿病（T1D）是一种需要终身胰岛素治疗的慢性自身免疫性疾病。常见的副作用是低血糖，其特征是血糖水平（BGL）降至70 mg/dL以下。糖尿病护理可以使用机器学习（ML）模型进行优化，该模型可以预测并提醒患者潜在的血糖异常。ML模型可以分为基于回归的模型（预测葡萄糖水平）和基于分类的模型（对不良事件进行分类）。本文分析了应用于T1D的ML模型的性能，并在短期和长期预测范围（ph）方面进行了比较，分别定义为15-120分钟和3至24小时以上。本文综述了以下问题：1)血糖值或低血糖事件可以提前多少准确预测？2)哪种ML方法性能最好？3)哪些因素影响绩效？4)个性化是否能提高性能？结果表明：1)PH为1 h时效果最好。2)传统的机器学习方法在分类和深度学习（DL）回归方面的效果最好。单个模型不能对多个ph值进行充分的分类。3)模型性能受多元数据集和输入序列长度（ISL）的影响。4)最后，个人数据增强了性能，但由于数据质量有限，基于人口的模型更受青睐。

{"title":"Review of machine learning models in short- and long-term glucose forecasting and hypoglycemia classification","authors":"Beyza Cinar , Louisa van den Boom , Maria Maleshkova","doi":"10.1016/j.imu.2025.101723","DOIUrl":"10.1016/j.imu.2025.101723","url":null,"abstract":"<div><div>Type 1 Diabetes (T1D) is a chronic autoimmune disorder that requires lifelong insulin therapy. A common side effect is hypoglycemia, characterized by decreased blood glucose levels (BGL) below 70 mg/dL. Diabetes care can be optimized using machine learning (ML) models that can predict and alert patients to potential glycemic abnormalities. The ML models can be classified into regression-based, in which glucose levels are forecasted, and classification-based, in which adverse events are classified. This review analyzes the performance of ML models applied to T1D and compares these in terms of short- and long-term prediction horizons (PHs), defined as 15–120 min and 3 to more than 24 h, respectively. This review investigates: 1) How much in advance can glucose values or a hypoglycemic event be accurately predicted? 2) Which ML methods have the best performance? 3) Which factors impact the performance? And 4) Does personalization increase performance? The results indicate that 1) a PH of up to 1 h provides the best results. 2) Conventional ML methods yield the best results for classification and deep learning (DL) for regression. A single model cannot adequately classify across multiple PHs. 3) The model performance is influenced by multivariate datasets and the input sequence length (ISL). 4) Finally, personal data enhances performance, but due to limited data quality, population-based models are preferred.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"60 ","pages":"Article 101723"},"PeriodicalIF":0.0,"publicationDate":"2025-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145735871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

3D SPECT-based machine learning approach to early Parkinson’s diagnosis 基于3D spect的机器学习方法在帕金森早期诊断中的应用

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2025-12-08 DOI: 10.1016/j.imu.2025.101722

Jihad Boucherouite, Abdelilah Jilbab, Atman Jbari

Purpose:

Dopamine transporter binding measurements in the striatum play a critical role in identifying dopaminergic deficits in Parkinson’s disease (PD), particularly during early stages. Using 3D SPECT imaging data from the PPMI database (928 subjects), we developed an automated feature extraction pipeline that captures subtle morphological changes characteristic of early neurodegeneration.

Approach:

Our methodology involved a sub-volume from each 3D SPECT scan and applied several image processing techniques to each slice. Unlike approaches relying on external datasets or derived features, we focused exclusively on direct geometric and shape features. We extracted 30 novel discriminative features, including volumetric measures, global thresholds, circularity, compactness, and curvature, with rigorous statistical validation using parametric tests (t-tests, ANOVA). The top 19 features, prioritized through MRMR to eliminate redundancy, were used to train and evaluate 34 machine learning classifiers.

Results:

For binary classification (Healthy Control (HC) vs. early PD), our Medium Gaussian SVM achieved excellent testing performance (98.56% accuracy, 98.81% precision), significantly higher than recent state-of-the-art approaches. Meanwhile, for three-class classification (HC, PD stage 1, and PD stage 2), the Subspace Discriminant Ensemble achieved the highest accuracy of 76.26%, solving a critical real-world scenario.

Conclusions:

This stage-aware approach advances the field by enabling automatic bilateral analysis of the striatum and accurate classification of early-stage PD, potentially supporting earlier clinical intervention. It also addresses a critical gap in the literature where most methods focus solely on binary classification (HC vs. PD) without capturing disease progression.

目的：纹状体多巴胺转运体结合测量在识别帕金森病（PD）的多巴胺能缺陷中起关键作用，特别是在早期阶段。利用来自PPMI数据库（928名受试者）的3D SPECT成像数据，我们开发了一种自动特征提取管道，可以捕获早期神经变性的细微形态学变化特征。方法：我们的方法涉及每个3D SPECT扫描的子体积，并对每个切片应用几种图像处理技术。与依赖外部数据集或衍生特征的方法不同，我们专注于直接的几何和形状特征。我们提取了30个新的判别特征，包括体积度量、全局阈值、圆度、紧度和曲率，并使用参数检验（t检验、方差分析）进行了严格的统计验证。通过MRMR对前19个特征进行优先排序以消除冗余，用于训练和评估34个机器学习分类器。结果：对于二分类（健康对照与早期PD），我们的中高斯支持向量机获得了出色的测试性能（98.56%的准确率，98.81%的精密度），显著高于目前最先进的方法。同时，对于三类分类（HC、PD阶段1和PD阶段2），子空间判别集成（Subspace Discriminant Ensemble）的准确率最高，达到76.26%，解决了一个关键的现实场景。结论：这种阶段感知方法通过实现纹状体的自动双侧分析和早期PD的准确分类，推动了该领域的发展，可能支持早期临床干预。它还解决了文献中大多数方法仅关注二元分类（HC与PD）而不捕获疾病进展的关键空白。

{"title":"3D SPECT-based machine learning approach to early Parkinson’s diagnosis","authors":"Jihad Boucherouite, Abdelilah Jilbab, Atman Jbari","doi":"10.1016/j.imu.2025.101722","DOIUrl":"10.1016/j.imu.2025.101722","url":null,"abstract":"<div><h3>Purpose:</h3><div>Dopamine transporter binding measurements in the striatum play a critical role in identifying dopaminergic deficits in Parkinson’s disease (PD), particularly during early stages. Using 3D SPECT imaging data from the PPMI database (928 subjects), we developed an automated feature extraction pipeline that captures subtle morphological changes characteristic of early neurodegeneration.</div></div><div><h3>Approach:</h3><div>Our methodology involved a sub-volume from each 3D SPECT scan and applied several image processing techniques to each slice. Unlike approaches relying on external datasets or derived features, we focused exclusively on direct geometric and shape features. We extracted 30 novel discriminative features, including volumetric measures, global thresholds, circularity, compactness, and curvature, with rigorous statistical validation using parametric tests (t-tests, ANOVA). The top 19 features, prioritized through MRMR to eliminate redundancy, were used to train and evaluate 34 machine learning classifiers.</div></div><div><h3>Results:</h3><div>For binary classification (Healthy Control (HC) vs. early PD), our Medium Gaussian SVM achieved excellent testing performance (98.56% accuracy, 98.81% precision), significantly higher than recent state-of-the-art approaches. Meanwhile, for three-class classification (HC, PD stage 1, and PD stage 2), the Subspace Discriminant Ensemble achieved the highest accuracy of 76.26%, solving a critical real-world scenario.</div></div><div><h3>Conclusions:</h3><div>This stage-aware approach advances the field by enabling automatic bilateral analysis of the striatum and accurate classification of early-stage PD, potentially supporting earlier clinical intervention. It also addresses a critical gap in the literature where most methods focus solely on binary classification (HC vs. PD) without capturing disease progression.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"60 ","pages":"Article 101722"},"PeriodicalIF":0.0,"publicationDate":"2025-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145697959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0