Obesity, now the fifth leading global cause of death, has seen a dramatic rise in prevalence over the last forty years. It significantly increases the risk of diseases such as type 2 diabetes and cardiovascular disease. Early identification of obesity risk allows for preventative actions against obesity-related factors. Despite the existence of AI-based predictive models, developing a comprehensive obesity screening tool requires extensive cohort data.
Methods
A thorough review of 6,351 articles, focusing on AI predictions for obesity in cohort studies, was conducted up to March 2024 across databases including PubMed, Scopus, and Web of Science.
Results
Using the JBI checklist, 10 studies involving 411,580 participants were critically appraised. These cohorts varied in length and size, with half lasting 1–5 years and involving less than 5,000 participants. The data types were categorized into nine groups, with demographic (7 studies) and biomarker data (4 studies) being the most frequently used. Machine learning was predominantly used (95 % of studies), mostly employing supervised learning techniques. Algorithms like random forest (RF) (18 %), linear regression (18 %), and stochastic gradient boosting (GBM) (14 %) were common. Top-performing models were noted for k-means (accuracy of 0.977), artificial neural networks (AUC of 0.99), GBM (specificity of 0.95 and sensitivity of 0.65), RF (RMSE of 0.146), and least absolute shrinkage and selection operator (r-squared of 0.684).
Conclusion
Findings indicate that AI algorithms can predict obesity; however, further research is needed to assess their effectiveness in analyzing obesity-related data and examine most advanced AI methods. This review is a valuable resource for dietitians and researchers engaged in developing predictive models and intelligent clinical decision support systems using AI technology.
{"title":"Artificial intelligence-enabled obesity prediction: A systematic review of cohort data analysis","authors":"Sharareh Rostam Niakan Kalhori , Farid Najafi , Hajar Hasannejadasl , Soroush Heydari","doi":"10.1016/j.ijmedinf.2025.105804","DOIUrl":"10.1016/j.ijmedinf.2025.105804","url":null,"abstract":"<div><h3>Background</h3><div>Obesity, now the fifth leading global cause of death, has seen a dramatic rise in prevalence over the last forty years. It significantly increases the risk of diseases such as type 2 diabetes and cardiovascular disease. Early identification of obesity risk allows for preventative actions against obesity-related factors. Despite the existence of AI-based predictive models, developing a comprehensive obesity screening tool requires extensive cohort data.</div></div><div><h3>Methods</h3><div>A thorough review of 6,351 articles, focusing on AI predictions for obesity in cohort studies, was conducted up to March 2024 across databases including PubMed, Scopus, and Web of Science.</div></div><div><h3>Results</h3><div>Using the JBI checklist, 10 studies involving 411,580 participants were critically appraised. These cohorts varied in length and size, with half lasting 1–5 years and involving less than 5,000 participants. The data types were categorized into nine groups, with demographic (7 studies) and biomarker data (4 studies) being the most frequently used. Machine learning was predominantly used (95 % of studies), mostly employing supervised learning techniques. Algorithms like random forest (RF) (18 %), linear regression (18 %), and stochastic gradient boosting (GBM) (14 %) were common. Top-performing models were noted for k-means (accuracy of 0.977), artificial neural networks (AUC of 0.99), GBM (specificity of 0.95 and sensitivity of 0.65), RF (RMSE of 0.146), and least absolute shrinkage and selection operator (r-squared of 0.684).</div></div><div><h3>Conclusion</h3><div>Findings indicate that AI algorithms can predict obesity; however, further research is needed to assess their effectiveness in analyzing obesity-related data and examine most advanced AI methods. This review is a valuable resource for dietitians and researchers engaged in developing predictive models and intelligent clinical decision support systems using AI technology.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"196 ","pages":"Article 105804"},"PeriodicalIF":3.7,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143054380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-24DOI: 10.1016/j.ijmedinf.2025.105790
Hassan Bozorgmanesh, Patrik Rydén
Objective
In this paper, we implement and validate a set of optimization approaches that were applied on ambulance data from the Västerbotten county in Sweden collected 2018, with the objective to find the optimal placement of the ambulance stations (or stand-by positions) in Umeå, a municipality in the county with regards to median of response times for priority 1 alarms, the most urgent type of alarms (MRT1).
Methods
Here, we use data-driven approaches for optimizing the placement of ambulance stations. For a given allocation, i.e. placement of the stations, a large-scale simulation is conducted to estimate the allocation's MRT1. Since the inherent mechanism of the simulation function is very complex, the optimization problem has a black-box nature. We use two methods belonging to important classes for solving the problem of black-box optimization: GPS (smooth-free) and surrogate (smooth-based) methods. Both methods can be used on either local or global data and implemented using a one-by-one approach or an all-together approach. To study the mentioned methods and approaches, we consider several real-world scenarios pertaining to the placement of ambulance stations in Umeå municipality.
Results
Relocating the ambulance stations in Umeå can reduce MRT1 around 80-100 seconds in comparison with the current allocation. Using global data leads to better solutions with lower MRT1-values, although they demand more computational time. The results of GPS and surrogate methods are similar, but the surrogate method is less sensitive to the starting position. One-by-one approach is more effective and less time-consuming than the all-together approach.
Conclusion
The results confirm that relocating ambulance stations can lead to a significant decrease in MRT1 and it also can compensate for the loss of an ambulance resource partially. To reduce the dimensionality and the cost of optimization methods, it can be better to use one-by-one approach than all-together.
{"title":"Optimal placement of ambulance stations using data-driven direct and surrogate search methods","authors":"Hassan Bozorgmanesh, Patrik Rydén","doi":"10.1016/j.ijmedinf.2025.105790","DOIUrl":"10.1016/j.ijmedinf.2025.105790","url":null,"abstract":"<div><h3>Objective</h3><div>In this paper, we implement and validate a set of optimization approaches that were applied on ambulance data from the Västerbotten county in Sweden collected 2018, with the objective to find the optimal placement of the ambulance stations (or stand-by positions) in Umeå, a municipality in the county with regards to median of response times for priority 1 alarms, the most urgent type of alarms (MRT1).</div></div><div><h3>Methods</h3><div>Here, we use data-driven approaches for optimizing the placement of ambulance stations. For a given allocation, i.e. placement of the stations, a large-scale simulation is conducted to estimate the allocation's MRT1. Since the inherent mechanism of the simulation function is very complex, the optimization problem has a black-box nature. We use two methods belonging to important classes for solving the problem of black-box optimization: GPS (smooth-free) and surrogate (smooth-based) methods. Both methods can be used on either local or global data and implemented using a one-by-one approach or an all-together approach. To study the mentioned methods and approaches, we consider several real-world scenarios pertaining to the placement of ambulance stations in Umeå municipality.</div></div><div><h3>Results</h3><div>Relocating the ambulance stations in Umeå can reduce MRT1 around 80-100 seconds in comparison with the current allocation. Using global data leads to better solutions with lower MRT1-values, although they demand more computational time. The results of GPS and surrogate methods are similar, but the surrogate method is less sensitive to the starting position. One-by-one approach is more effective and less time-consuming than the all-together approach.</div></div><div><h3>Conclusion</h3><div>The results confirm that relocating ambulance stations can lead to a significant decrease in MRT1 and it also can compensate for the loss of an ambulance resource partially. To reduce the dimensionality and the cost of optimization methods, it can be better to use one-by-one approach than all-together.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"196 ","pages":"Article 105790"},"PeriodicalIF":3.7,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143069665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-23DOI: 10.1016/j.ijmedinf.2025.105786
Shan Chen , Yuanzhao Ding
Background
Coronavirus Disease 2019 (COVID-19), caused by the SARS-CoV-2 virus, emerged as a global health crisis in 2019, resulting in widespread morbidity and mortality. A persistent challenge during the pandemic has been the accuracy of reported epidemic data, particularly in underdeveloped regions with limited access to COVID-19 test kits and healthcare infrastructure. In the post-COVID era, this issue remains crucial. This study introduces a novel approach by leveraging machine learning to predict cases and uncover critical discrepancies, focusing on African regions where reported daily cases per million often deviate significantly from machine learning-predicted cases. These findings strongly suggest widespread underreporting of cases. By identifying these gaps, our research provides valuable insights for future pandemic preparedness, improving epidemic forecasting accuracy, data reliability, and response strategies to mitigate the impact of emerging global health crises.
Objective
This study aims to assess the reliability of reported COVID-19 incidence data globally, particularly in underdeveloped regions, and to identify discrepancies between reported and predicted cases using machine learning methodologies.
Methods
Data collected from March 2020 to September 2022 included demographic, healthcare, economic, and testing-related parameters. Several machine learning models—neural networks, decision trees, random forests, cross-validation, support vector machines, and logistic regression—were employed to predict COVID-19 incidence rates. Model performance was evaluated using testing accuracy metrics.
Results
Testing accuracy rates for the models were as follows: neural networks (65.50 %), decision trees (63.76 %), random forests (63.33 %), cross-validation (55.92 %), support vector machines (63.62 %), and logistic regression (64.70 %). Comparative analysis using neural networks revealed significant discrepancies between reported and predicted COVID-19 cases, particularly in numerous African countries. These results suggest a considerable volume of underreported cases in regions with limited testing capabilities.
Conclusion
This study highlights the critical need for improved data accuracy and reporting mechanisms, especially in resource-constrained regions. International organizations and policymakers must implement strategies to enhance testing capacity and data reliability to better understand and manage the global impact of the pandemic. Our work emphasizes the potential of machine learning to identify gaps in epidemic reporting, facilitating evidence-based interventions.
{"title":"The feasibility of using machine learning to predict COVID-19 cases","authors":"Shan Chen , Yuanzhao Ding","doi":"10.1016/j.ijmedinf.2025.105786","DOIUrl":"10.1016/j.ijmedinf.2025.105786","url":null,"abstract":"<div><h3>Background</h3><div>Coronavirus Disease 2019 (COVID-19), caused by the SARS-CoV-2 virus, emerged as a global health crisis in 2019, resulting in widespread morbidity and mortality. A persistent challenge during the pandemic has been the accuracy of reported epidemic data, particularly in underdeveloped regions with limited access to COVID-19 test kits and healthcare infrastructure. In the post-COVID era, this issue remains crucial. This study introduces a novel approach by leveraging machine learning to predict cases and uncover critical discrepancies, focusing on African regions where reported daily cases per million often deviate significantly from machine learning-predicted cases. These findings strongly suggest widespread underreporting of cases. By identifying these gaps, our research provides valuable insights for future pandemic preparedness, improving epidemic forecasting accuracy, data reliability, and response strategies to mitigate the impact of emerging global health crises.</div></div><div><h3>Objective</h3><div>This study aims to assess the reliability of reported COVID-19 incidence data globally, particularly in underdeveloped regions, and to identify discrepancies between reported and predicted cases using machine learning methodologies.</div></div><div><h3>Methods</h3><div>Data collected from March 2020 to September 2022 included demographic, healthcare, economic, and testing-related parameters. Several machine learning models—neural networks, decision trees, random forests, cross-validation, support vector machines, and logistic regression—were employed to predict COVID-19 incidence rates. Model performance was evaluated using testing accuracy metrics.</div></div><div><h3>Results</h3><div>Testing accuracy rates for the models were as follows: neural networks (65.50 %), decision trees (63.76 %), random forests (63.33 %), cross-validation (55.92 %), support vector machines (63.62 %), and logistic regression (64.70 %). Comparative analysis using neural networks revealed significant discrepancies between reported and predicted COVID-19 cases, particularly in numerous African countries. These results suggest a considerable volume of underreported cases in regions with limited testing capabilities.</div></div><div><h3>Conclusion</h3><div>This study highlights the critical need for improved data accuracy and reporting mechanisms, especially in resource-constrained regions. International organizations and policymakers must implement strategies to enhance testing capacity and data reliability to better understand and manage the global impact of the pandemic. Our work emphasizes the potential of machine learning to identify gaps in epidemic reporting, facilitating evidence-based interventions.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"196 ","pages":"Article 105786"},"PeriodicalIF":3.7,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143048873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-23DOI: 10.1016/j.ijmedinf.2025.105806
Hussain Ahmad Madni , Rao Muhammad Umer , Silvia Zottin , Carsten Marr , Gian Luca Foresti
Background
Segmentation models for clinical data experience severe performance degradation when trained on a single client from one domain and distributed to other clients from different domain. Federated Learning (FL) provides a solution by enabling multi-party collaborative learning without compromising the confidentiality of clients' private data.
Methods
In this paper, we propose a cross-domain FL method for Weakly Supervised Semantic Segmentation (FL-W3S) of white blood cells in microscopic images. We perform model training on multiple clients with different data distributions to obtain a global aggregated model using only image-level class labels for semantic segmentation of white blood cells. A multi-class token transformer model learns the relationship between patch tokens and class tokens during collaborative learning and generates class-specific localization maps for mask predictions. To rectify the localization maps, we use patch-level pairwise affinity obtained from patch-to-patch transformer attention.
Results
We evaluate performance of the proposed semantic segmentation method on two different datasets of white blood cells from different domains. Our experimental results show that for two datasets, there is 2.56% and 1.39% increase in performance of the proposed method over existing state-of-the-art methods.
Conclusion
The combination of federated learning for collaborative model training while preserving data privacy, alongside white blood cell segmentation techniques for precise cell identification, enhances diagnostic accuracy and personalized treatment strategies in clinical applications, particularly in hematology and pathology. More specifically, it involves isolating white blood cell from blood smear for further analysis such as automated blood cell counting, morphological analysis, cell classification, disease diagnosis and monitoring.
{"title":"FL-W3S: Cross-domain federated learning for weakly supervised semantic segmentation of white blood cells","authors":"Hussain Ahmad Madni , Rao Muhammad Umer , Silvia Zottin , Carsten Marr , Gian Luca Foresti","doi":"10.1016/j.ijmedinf.2025.105806","DOIUrl":"10.1016/j.ijmedinf.2025.105806","url":null,"abstract":"<div><h3>Background</h3><div>Segmentation models for clinical data experience severe performance degradation when trained on a single client from one domain and distributed to other clients from different domain. Federated Learning (FL) provides a solution by enabling multi-party collaborative learning without compromising the confidentiality of clients' private data.</div></div><div><h3>Methods</h3><div>In this paper, we propose a cross-domain FL method for Weakly Supervised Semantic Segmentation (FL-W3S) of white blood cells in microscopic images. We perform model training on multiple clients with different data distributions to obtain a global aggregated model using only image-level class labels for semantic segmentation of white blood cells. A multi-class token transformer model learns the relationship between patch tokens and class tokens during collaborative learning and generates class-specific localization maps for mask predictions. To rectify the localization maps, we use patch-level pairwise affinity obtained from patch-to-patch transformer attention.</div></div><div><h3>Results</h3><div>We evaluate performance of the proposed semantic segmentation method on two different datasets of white blood cells from different domains. Our experimental results show that for two datasets, there is 2.56% and 1.39% increase in performance of the proposed method over existing state-of-the-art methods.</div></div><div><h3>Conclusion</h3><div>The combination of federated learning for collaborative model training while preserving data privacy, alongside white blood cell segmentation techniques for precise cell identification, enhances diagnostic accuracy and personalized treatment strategies in clinical applications, particularly in hematology and pathology. More specifically, it involves isolating white blood cell from blood smear for further analysis such as automated blood cell counting, morphological analysis, cell classification, disease diagnosis and monitoring.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"195 ","pages":"Article 105806"},"PeriodicalIF":3.7,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143034874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-23DOI: 10.1016/j.ijmedinf.2025.105808
Jiqing Li, Shuo Wu, Jianhua Gu
Background
Coronary heart disease (CHD) and depression frequently co-occur, significantly impacting patient outcomes. However, comprehensive health status assessment tools for this complex population are lacking. This study aimed to develop and validate an explainable machine learning model to evaluate overall health status in patients with comorbid CHD and depression.
Methods
Utilizing data from the 2021–2022 Behavioral Risk Factor Surveillance System, we developed and externally validated machine learning models to predict overall health status, defined as having both poor physical and mental health for ≥ 14 days in the past 30 days. Eleven machine learning algorithms were evaluated, including artificial neural networks, support vector machines, and ensemble methods. The SHapley Additive exPlanations (SHAP) method was employed to enhance model interpretability. Model performance was assessed using discrimination, calibration, and decision curve analysis.
Results
The study included 9,747 participants in the derivation cohort and 8,394 in the external validation cohort. Among the eleven algorithms evaluated, an optimized XGBoost model with eight key features demonstrated balanced performance. SHAP analysis revealed that employment status, physical activity, income, and age were the most influential predictors. The model maintained good discrimination (AUC 0.712, 95% CI 0.703–0.721 in derivation; AUC 0.711, 95% CI 0.701–0.721 in validation), calibration and clinical utility across both cohorts.
Conclusion
Our explainable machine learning model provides a novel, comprehensive approach to assessing health status in patients with comorbid CHD and depression, offering valuable insights for personalized management strategies.
{"title":"Explainable machine learning model for assessing health status in patients with comorbid coronary heart disease and depression: Development and validation study","authors":"Jiqing Li, Shuo Wu, Jianhua Gu","doi":"10.1016/j.ijmedinf.2025.105808","DOIUrl":"10.1016/j.ijmedinf.2025.105808","url":null,"abstract":"<div><h3>Background</h3><div>Coronary heart disease (CHD) and depression frequently co-occur, significantly impacting patient outcomes. However, comprehensive health status assessment tools for this complex population are lacking. This study aimed to develop and validate an explainable machine learning model to evaluate overall health status in patients with comorbid CHD and depression.</div></div><div><h3>Methods</h3><div>Utilizing data from the 2021–2022 Behavioral Risk Factor Surveillance System, we developed and externally validated machine learning models to predict overall health status, defined as having both poor physical and mental health for ≥ 14 days in the past 30 days. Eleven machine learning algorithms were evaluated, including artificial neural networks, support vector machines, and ensemble methods. The SHapley Additive exPlanations (SHAP) method was employed to enhance model interpretability. Model performance was assessed using discrimination, calibration, and decision curve analysis.</div></div><div><h3>Results</h3><div>The study included 9,747 participants in the derivation cohort and 8,394 in the external validation cohort. Among the eleven algorithms evaluated, an optimized XGBoost model with eight key features demonstrated balanced performance. SHAP analysis revealed that employment status, physical activity, income, and age were the most influential predictors. The model maintained good discrimination (AUC 0.712, 95% CI 0.703–0.721 in derivation; AUC 0.711, 95% CI 0.701–0.721 in validation), calibration and clinical utility across both cohorts.</div></div><div><h3>Conclusion</h3><div>Our explainable machine learning model provides a novel, comprehensive approach to assessing health status in patients with comorbid CHD and depression, offering valuable insights for personalized management strategies.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"196 ","pages":"Article 105808"},"PeriodicalIF":3.7,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143061533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-22DOI: 10.1016/j.ijmedinf.2025.105802
Francesco Masciulli , Anna Corti , Alessia Lindemann , Katia Chiappetta , Mattia Loppini , Valentina D.A. Corino
Background
Existing deep learning studies for the automated detection of hip prosthesis failure only consider the last available radiographic image. However, using longitudinal data is thought to improve the prediction, by combining temporal and spatial components. The aim of this study is to develop artificial intelligence models for predicting hip implant failure from multiple subsequent plain radiographs.
Methods
A cohort of 224 patients was considered for model development and a balanced cohort of 14 patients was used for external validation. A sequence of two or three anteroposterior radiographic images per patient was considered to track the prosthesis over time. A combination of a convolutional neural network (CNN) and a recurrent section was used. For the CNN, a pretrained autoencoder, a pretrained RadImageNet DenseNet and a pretrained custom DenseNet were considered. The recurrent section was implemented using either a single Gated Recurrent Unit (GRU) layer or a Long Short-Term Memory block.
Results
Considering 3 images as input provided a positive predictive value (PPV) of 0.966 and an f1 score of 0.933 on the validation set. Regarding the 2-image models, using the postoperative and the last image resulted in PPV of 0.933 and f1 score of 0.918, whereas using the second-to-last image with the post-operative one reached a PPV of 0.882 and f1 score of 0.923. On the external validation set, the 3-image model reached an accuracy of 0.786.
Conclusion
This study demonstrated the potential of the developed models, based on a series of plain radiographs, to predict hip prosthesis failure.
{"title":"Hip prosthesis failure prediction through radiological deep sequence learning","authors":"Francesco Masciulli , Anna Corti , Alessia Lindemann , Katia Chiappetta , Mattia Loppini , Valentina D.A. Corino","doi":"10.1016/j.ijmedinf.2025.105802","DOIUrl":"10.1016/j.ijmedinf.2025.105802","url":null,"abstract":"<div><h3>Background</h3><div>Existing deep learning studies for the automated detection of hip prosthesis failure only consider the last available radiographic image. However, using longitudinal data is thought to improve the prediction, by combining temporal and spatial components. The aim of this study is to develop artificial intelligence models for predicting hip implant failure from multiple subsequent plain radiographs.</div></div><div><h3>Methods</h3><div>A cohort of 224 patients was considered for model development and a balanced cohort of 14 patients was used for external validation. A sequence of two or three anteroposterior radiographic images per patient was considered to track the prosthesis over time. A combination of a convolutional neural network (CNN) and a recurrent section was used. For the CNN, a pretrained autoencoder, a pretrained RadImageNet DenseNet and a pretrained custom DenseNet were considered. The recurrent section was implemented using either a single Gated Recurrent Unit (GRU) layer or a Long Short-Term Memory block.</div></div><div><h3>Results</h3><div>Considering 3 images as input provided a positive predictive value (PPV) of 0.966 and an f1 score of 0.933 on the validation set. Regarding the 2-image models, using the postoperative and the last image resulted in PPV of 0.933 and f1 score of 0.918, whereas using the second-to-last image with the post-operative one reached a PPV of 0.882 and f1 score of 0.923. On the external validation set, the 3-image model reached an accuracy of 0.786.</div></div><div><h3>Conclusion</h3><div>This study demonstrated the potential of the developed models, based on a series of plain radiographs, to predict hip prosthesis failure.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"196 ","pages":"Article 105802"},"PeriodicalIF":3.7,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143069648","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-22DOI: 10.1016/j.ijmedinf.2025.105801
Wei Feng , Honghan Wu , Hui Ma , Yuechuchu Yin , Zhenhuan Tao , Shan Lu , Xin Zhang , Yun Yu , Cheng Wan , Yun Liu
Background
Depression and anxiety are prevalent mental health conditions among individuals with type 2 diabetes mellitus (T2DM), who exhibit unique vulnerabilities and etiologies. However, existing approaches fail to fully utilize regional heterogeneous electronic health record (EHR) data. Integrating this data can provide a more comprehensive understanding of depression and anxiety in T2DM patients, leading to more personalized treatment strategies.
Objective
This study aims to develop and validate a deep learning model, the Regional EHR for Depression and Anxiety Prediction Model (REDAPM), using regional EHR data to predict depression and anxiety in patients with T2DM.
Methods
A case-control development and validation study was conducted using regional EHR data from the Nanjing Health Information Center (NHIC). Two retrospective, matched (1:3) datasets were constructed from the full cohort for the model's internal and external validation. These two datasets were selected from the NHIC data of 2020 and 2022, respectively. The REDAPM incorporates both structured and unstructured EHR data, capturing the temporal dependency of clinical events. The performance of REDAPM was compared to a set of baseline models, evaluated using the area under the receiver operating characteristic curve (ROC-AUC) and the area under the precision-recall curve (PR-AUC). Subgroup, ablation, and interpretation analyses were conducted to identify relevant clinical features available from EHRs.
Results
The internal and external validation datasets comprised 24,724 and 34,340 patients, respectively. The REDAPM outperformed baseline models in both datasets, achieving ROC-AUC scores of 0.9029±0.008 and 0.7360±0.005, and PR-AUC scores of 0.8124±0.011 and 0.5504±0.009. Ablation and subgroup experiments confirmed the significant contribution of patients' medical history text to the model's performance. Integrated gradient score analysis identified the predictive importance of other mental disorders.
Conclusion
The REDAPM effectively leverages the heterogeneous characteristics of regional EHR data, demonstrating strong predictive performance for depression onset in diabetic patients. It also shows potential for discovering significant clinical features, indicating considerable promise for clinical utility.
{"title":"Deep learning based prediction of depression and anxiety in patients with type 2 diabetes mellitus using regional electronic health records","authors":"Wei Feng , Honghan Wu , Hui Ma , Yuechuchu Yin , Zhenhuan Tao , Shan Lu , Xin Zhang , Yun Yu , Cheng Wan , Yun Liu","doi":"10.1016/j.ijmedinf.2025.105801","DOIUrl":"10.1016/j.ijmedinf.2025.105801","url":null,"abstract":"<div><h3>Background</h3><div>Depression and anxiety are prevalent mental health conditions among individuals with type 2 diabetes mellitus (T2DM), who exhibit unique vulnerabilities and etiologies. However, existing approaches fail to fully utilize regional heterogeneous electronic health record (EHR) data. Integrating this data can provide a more comprehensive understanding of depression and anxiety in T2DM patients, leading to more personalized treatment strategies.</div></div><div><h3>Objective</h3><div>This study aims to develop and validate a deep learning model, the Regional EHR for Depression and Anxiety Prediction Model (REDAPM), using regional EHR data to predict depression and anxiety in patients with T2DM.</div></div><div><h3>Methods</h3><div>A case-control development and validation study was conducted using regional EHR data from the Nanjing Health Information Center (NHIC). Two retrospective, matched (1:3) datasets were constructed from the full cohort for the model's internal and external validation. These two datasets were selected from the NHIC data of 2020 and 2022, respectively. The REDAPM incorporates both structured and unstructured EHR data, capturing the temporal dependency of clinical events. The performance of REDAPM was compared to a set of baseline models, evaluated using the area under the receiver operating characteristic curve (ROC-AUC) and the area under the precision-recall curve (PR-AUC). Subgroup, ablation, and interpretation analyses were conducted to identify relevant clinical features available from EHRs.</div></div><div><h3>Results</h3><div>The internal and external validation datasets comprised 24,724 and 34,340 patients, respectively. The REDAPM outperformed baseline models in both datasets, achieving ROC-AUC scores of 0.9029±0.008 and 0.7360±0.005, and PR-AUC scores of 0.8124±0.011 and 0.5504±0.009. Ablation and subgroup experiments confirmed the significant contribution of patients' medical history text to the model's performance. Integrated gradient score analysis identified the predictive importance of other mental disorders.</div></div><div><h3>Conclusion</h3><div>The REDAPM effectively leverages the heterogeneous characteristics of regional EHR data, demonstrating strong predictive performance for depression onset in diabetic patients. It also shows potential for discovering significant clinical features, indicating considerable promise for clinical utility.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"196 ","pages":"Article 105801"},"PeriodicalIF":3.7,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143076333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-22DOI: 10.1016/j.ijmedinf.2025.105807
Chen Chen , Wenkang Zhang , Yang Pan , Zhen Li
<div><h3>Background</h3><div>Acute ischemic stroke (AIS) is a clinical disorder caused by nontraumatic cerebrovascular disease with a high incidence, mortality, and disability rate. Most stroke survivors are left with speech and physical impairments, and emotional problems. Despite technological advances and improved treatment options, death and disability after stroke remain a major problem. Our research aims to develop interpretable hybrid machine learning (ML) models to accurately predict three-month unfavorable outcomes in patients with AIS.</div></div><div><h3>Methods</h3><div>Within the framework of this analysis, the model was trained using data from 731 cases in the dataset and subsequently validated using data from both internal and external validation datasets. A total of 25 models (including ML and deep learning models) were initially employed, along with 14 evaluation metrics, and the results were subjected to cluster analysis to objectively validate the model’s effectiveness and assess the similarity of evaluation metrics. For the final model evaluation, 10 metrics selected after metric screening and calibration analysis were utilized to evaluate model performance, while clinical decision analysis, cost curve analysis, and model fairness analysis were applied to assess the clinical applicability of the model. Nested cross-validation and optimal hyperparameter search were employed to determine the best hyperparameter for the ML models. The SHAP diagram is utilized to provide further visual explanations regarding the importance of features and their interaction effects, ultimately leading to the establishment of a practical AIS three-month prognostic prediction platform.</div></div><div><h3>Results</h3><div>The frequencies of unfavorable outcomes in the internal dataset and external validation dataset were 389 / 1045 (37.2 %) and 161 / 411 (39.2 %), respectively. Through cluster analysis of the results of 14 evaluation metrics across 25 models and a comparison of clinical applicability, 12 ML models were ultimately selected for further analysis. The findings revealed that XGBoost and CatBoost performed the best. Further ensemble modeling of these two models and adjustment of decision thresholds using cost curves resulted in the final model performing as follows on the internal validation set: PRAUC of 0.856 (0.801, 0.902), ROCAUC of 0.856 (0.801, 0.901), specificity of 0.879 (0.797, 0.953), balanced accuracy of 0.840 (0.763, 0.912) and MCC of 0.678 (0.591, 0.760). Similarly, the model exhibited excellent performance on the external validation set, with a PRAUC of 0.823 (0.775, 0.872), ROCAUC of 0.842 (0.801, 0.890), specificity of 0.888 (0.822, 0.920), balanced accuracy of 0.814 (0.751, 0.869) and MCC of 0.639 (0.546, 0.721). In terms of the important features of AIS three-month outcomes, albumin ranked highest, followed by FBG, BMI, Scr, WBC, and age, while gender exhibited significant interactions with other indicators. Ultimately, b
{"title":"An interpretable hybrid machine learning approach for predicting three-month unfavorable outcomes in patients with acute ischemic stroke","authors":"Chen Chen , Wenkang Zhang , Yang Pan , Zhen Li","doi":"10.1016/j.ijmedinf.2025.105807","DOIUrl":"10.1016/j.ijmedinf.2025.105807","url":null,"abstract":"<div><h3>Background</h3><div>Acute ischemic stroke (AIS) is a clinical disorder caused by nontraumatic cerebrovascular disease with a high incidence, mortality, and disability rate. Most stroke survivors are left with speech and physical impairments, and emotional problems. Despite technological advances and improved treatment options, death and disability after stroke remain a major problem. Our research aims to develop interpretable hybrid machine learning (ML) models to accurately predict three-month unfavorable outcomes in patients with AIS.</div></div><div><h3>Methods</h3><div>Within the framework of this analysis, the model was trained using data from 731 cases in the dataset and subsequently validated using data from both internal and external validation datasets. A total of 25 models (including ML and deep learning models) were initially employed, along with 14 evaluation metrics, and the results were subjected to cluster analysis to objectively validate the model’s effectiveness and assess the similarity of evaluation metrics. For the final model evaluation, 10 metrics selected after metric screening and calibration analysis were utilized to evaluate model performance, while clinical decision analysis, cost curve analysis, and model fairness analysis were applied to assess the clinical applicability of the model. Nested cross-validation and optimal hyperparameter search were employed to determine the best hyperparameter for the ML models. The SHAP diagram is utilized to provide further visual explanations regarding the importance of features and their interaction effects, ultimately leading to the establishment of a practical AIS three-month prognostic prediction platform.</div></div><div><h3>Results</h3><div>The frequencies of unfavorable outcomes in the internal dataset and external validation dataset were 389 / 1045 (37.2 %) and 161 / 411 (39.2 %), respectively. Through cluster analysis of the results of 14 evaluation metrics across 25 models and a comparison of clinical applicability, 12 ML models were ultimately selected for further analysis. The findings revealed that XGBoost and CatBoost performed the best. Further ensemble modeling of these two models and adjustment of decision thresholds using cost curves resulted in the final model performing as follows on the internal validation set: PRAUC of 0.856 (0.801, 0.902), ROCAUC of 0.856 (0.801, 0.901), specificity of 0.879 (0.797, 0.953), balanced accuracy of 0.840 (0.763, 0.912) and MCC of 0.678 (0.591, 0.760). Similarly, the model exhibited excellent performance on the external validation set, with a PRAUC of 0.823 (0.775, 0.872), ROCAUC of 0.842 (0.801, 0.890), specificity of 0.888 (0.822, 0.920), balanced accuracy of 0.814 (0.751, 0.869) and MCC of 0.639 (0.546, 0.721). In terms of the important features of AIS three-month outcomes, albumin ranked highest, followed by FBG, BMI, Scr, WBC, and age, while gender exhibited significant interactions with other indicators. Ultimately, b","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"196 ","pages":"Article 105807"},"PeriodicalIF":3.7,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143369806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-22DOI: 10.1016/j.ijmedinf.2025.105794
Simon Lewerenz , Anne Moen , Henrique Martins
Introduction
In the WHO European Region, 44 of 53 reporting Member States (MS) have a national digital health strategy (NDHS) or policy. Their formulation is heterogenous and evolving and should best reflect public common interest. This research aims to explore how a public value approach improves the relevance of digital health policies and services, increasing their capacity to better serve the diverse range of societal interests. It utilises the guiding values within the French NDHS as an example before discussing other digital health policies such as the European Heath Data Space.
Methods
Three homogenous focus group discussions were conducted in November and December 2023. Each focus group separately gathered distinct stakeholders: public clients, health professionals, private sector. 19 participants were included in the study. Data collection comprised live polling and semi-structured discussion. Results were analysed considering the pre-defined stakeholder groups and the values discussed during the study.
Results
Findings reveal both technical and cultural challenges in digital health that highlight the need for adaptable frameworks across different contexts. Stakeholder insights informed a framework classifying public values into democratic and managerial categories, suggesting themes that may be relevant to digital health strategies in other national and regional settings.
Discussion
Public value is discussed as a multidimensional concept, and the plurality of its perceptions give basis for tailored approaches to serve different value-beneficiaries comprehensively. We propose this values-based approach as a systematic model for supra-, sub-, and national scales and additional policy topics, beyond digital health strategies.
Conclusion
The study suggests that using a public value lens considering multiple perceptions is valuable for advancing digital health policy in a responsible and ethical manner. Such an approach could promote wider governance of and adoption of digital health. To evolve the framework, application in multiple and large ecosystems at different levels should be considered.
{"title":"Public value and digital health: The example of guiding values in the national digital health strategy of France","authors":"Simon Lewerenz , Anne Moen , Henrique Martins","doi":"10.1016/j.ijmedinf.2025.105794","DOIUrl":"10.1016/j.ijmedinf.2025.105794","url":null,"abstract":"<div><h3>Introduction</h3><div>In the WHO European Region, 44 of 53 reporting Member States (MS) have a national digital health strategy (NDHS) or policy. Their formulation is heterogenous and evolving and should best reflect public common interest. This research aims to explore how a public value approach improves the relevance of digital health policies and services, increasing their capacity to better serve the diverse range of societal interests. It utilises the guiding values within the French NDHS as an example before discussing other digital health policies such as the European Heath Data Space.</div></div><div><h3>Methods</h3><div>Three homogenous focus group discussions were conducted in November and December 2023. Each focus group separately gathered distinct stakeholders: public clients, health professionals, private sector. 19 participants were included in the study. Data collection comprised live polling and semi-structured discussion. Results were analysed considering the pre-defined stakeholder groups and the values discussed during the study.</div></div><div><h3>Results</h3><div>Findings reveal both technical and cultural challenges in digital health that highlight the need for adaptable frameworks across different contexts. Stakeholder insights informed a framework classifying public values into democratic and managerial categories, suggesting themes that may be relevant to digital health strategies in other national and regional settings.</div></div><div><h3>Discussion</h3><div>Public value is discussed as a multidimensional concept, and the plurality of its perceptions give basis for tailored approaches to serve different value-beneficiaries comprehensively. We propose this values-based approach as a systematic model for supra-, sub-, and national scales and additional policy topics, beyond digital health strategies.</div></div><div><h3>Conclusion</h3><div>The study suggests that using a public value lens considering multiple perceptions is valuable for advancing digital health policy in a responsible and ethical manner. Such an approach could promote wider governance of and adoption of digital health. To evolve the framework, application in multiple and large ecosystems at different levels should be considered.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"196 ","pages":"Article 105794"},"PeriodicalIF":3.7,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143043394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-21DOI: 10.1016/j.ijmedinf.2025.105795
Renata Savian Colvero de Oliveira , Sharon Nabwire , Heta Merikallio , Markku Savolainen , Janne Hukkanen , Harri Oinas-Kukkonen
Background
Studies have demonstrated that interventions targeting weight loss and body mass index (BMI) reduction can be successful, although the specific factors that influence their effectiveness are still unclear. Behavior change support systems (BCSS) are an approach that aims to help users in their efforts to modify their behavior. A useful tool for assessing BCSS is the Persuasive Systems Design model (PSD), where different features and postulates can be employed. However, it is unknown whether the grouping of software features and design principles, along with behavioral traits, provide a better combination to achieve effective BMI reduction.
Objective
This study investigates the impact of PSD features, postulates behind the design, and behavioral traits on BMI reduction after six months of utilizing a mobile health behavior change support system (mHBCSS).
Methods
We examined a subset of 96 individuals from a randomized controlled trial using a mHBCSS for a period of six months. Data was analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM).
Results
We found that 15.3 % in the variance of BMI reduction was explained by the ability of setting goals. Furthermore, users who perceive a system as highly persuasive are more likely to establish goals (R2 = 0.207). Among PSD features, Dialogue Support and Primary Task Support explained 54.9 % of the variance in Perceived Persuasiveness. In addition, both Dialogue Support and Credibility Support have a mutual effect on Primary Task Support (R2 = 0.685). Finally, the system’s unobtrusiveness explained 41.1 % of the variance in Dialogue Support.
Conclusion
PSD framework and behavior change theories provide significant influence on BMI reduction. Setting a clear and organized objective assists individuals in successfully pursuing their intended results. The findings of this study can help developers and health professionals decide which PSD features and postulates to include to make mHBCSS interventions targeting BMI reduction more effective.
{"title":"Behind the software: The impact of Unobtrusiveness, Goal Setting and persuasive features on BMI","authors":"Renata Savian Colvero de Oliveira , Sharon Nabwire , Heta Merikallio , Markku Savolainen , Janne Hukkanen , Harri Oinas-Kukkonen","doi":"10.1016/j.ijmedinf.2025.105795","DOIUrl":"10.1016/j.ijmedinf.2025.105795","url":null,"abstract":"<div><h3>Background</h3><div>Studies have demonstrated that interventions targeting weight loss and body mass index (BMI) reduction can be successful, although the specific factors that influence their effectiveness are still unclear. Behavior change support systems (BCSS) are an approach that aims to help users in their efforts to modify their behavior. A useful tool for assessing BCSS is the Persuasive Systems Design model (PSD), where different features and postulates can be employed. However, it is unknown whether the grouping of software features and design principles, along with behavioral traits, provide a better combination to achieve effective BMI reduction.</div></div><div><h3>Objective</h3><div>This study investigates the impact of PSD features, postulates behind the design, and behavioral traits on BMI reduction after six months of utilizing a mobile health behavior change support system (mHBCSS).</div></div><div><h3>Methods</h3><div>We examined a subset of 96 individuals from a randomized controlled trial using a mHBCSS for a period of six months. Data was analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM).</div></div><div><h3>Results</h3><div>We found that 15.3 % in the variance of BMI reduction was explained by the ability of setting goals. Furthermore, users who perceive a system as highly persuasive are more likely to establish goals (R<sup>2</sup> = 0.207). Among PSD features, Dialogue Support and Primary Task Support explained 54.9 % of the variance in Perceived Persuasiveness. In addition, both Dialogue Support and Credibility Support have a mutual effect on Primary Task Support (R<sup>2</sup> = 0.685). Finally, the system’s unobtrusiveness explained 41.1 % of the variance in Dialogue Support.</div></div><div><h3>Conclusion</h3><div>PSD framework and behavior change theories provide significant influence on BMI reduction. Setting a clear and organized objective assists individuals in successfully pursuing their intended results. The findings of this study can help developers and health professionals decide which PSD features and postulates to include to make mHBCSS interventions targeting BMI reduction more effective.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"196 ","pages":"Article 105795"},"PeriodicalIF":3.7,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143043382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号