International Journal of Medical Informatics最新文献

{"title":"Effectiveness of digital health interventions for chronic conditions management in European primary care settings: Systematic review and meta-analysis","authors":"Elisa Ambrosi ,&nbsp;Elisabetta Mezzalira ,&nbsp;Federica Canzan ,&nbsp;Chiara Leardini ,&nbsp;Giovanni Vita ,&nbsp;Giulia Marini ,&nbsp;Jessica Longhini","doi":"10.1016/j.ijmedinf.2025.105820","DOIUrl":"10.1016/j.ijmedinf.2025.105820","url":null,"abstract":"<div><h3>Background</h3><div>The past decade has seen rapid digitalization of healthcare, significantly transforming healthcare delivery. However, the impact of these technologies remains unclear, with notable gaps in evidence regarding their effectiveness, especially in primary care settings.</div></div><div><h3>Objective</h3><div>This systematic review assesses the effectiveness of digital health interventions versus interventions without digital components implemented over the last 10 years in European primary care settings for managing chronic diseases.</div></div><div><h3>Methods</h3><div>Following Cochrane guidelines, we conducted a systematic review with <em>meta</em>-analysis. We searched multiple databases for randomized controlled trials. Inclusion criteria encompassed studies on digital health interventions for chronic disease management in primary care settings in Europe, evaluating outcomes such as hospitalizations, quality of life, and clinical measures. Data extraction and quality assessment were independently conducted by two authors, with discrepancies resolved by a third author. The certainty of the evidence was judged according to the Grading of Recommendations, Assessment, Development, and Evaluation approach.</div></div><div><h3>Results</h3><div>From 9829 records, 23 studies were included, with most studies conducted in the UK and Spain. The most investigated conditions were type 2 diabetes and hypertension. Interventions mainly focused on patient monitoring, self-care education, and digital communication tools. The risk of bias was low to moderate for most studies. Meta-analyses showed no significant differences between digital health interventions and usual care for hospitalizations, depressive symptoms, anxiety, HbA1c, diastolic blood pressure, weight, or quality of life, except for a small improvement in systolic blood pressure.</div></div><div><h3>Conclusion</h3><div>Digital health interventions have not yet demonstrated substantial benefits over traditional care for chronic disease management in European primary care. While some improvements were noted, particularly in systolic blood pressure, the impact remains limited. Further research is needed to enhance the effectiveness of digital health interventions, address current methodological limitations, and explore tailored approaches for both specific patient populations and multimorbid populations.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"196 ","pages":"Article 105820"},"PeriodicalIF":3.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143350075","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}

{"title":"Deep learning and machine learning in CT-based COPD diagnosis: Systematic review and meta-analysis","authors":"Qian Wu,&nbsp;Hui Guo,&nbsp;Ruihan Li,&nbsp;Jinhuan Han","doi":"10.1016/j.ijmedinf.2025.105812","DOIUrl":"10.1016/j.ijmedinf.2025.105812","url":null,"abstract":"<div><h3>Background</h3><div>With advancements in medical technology and science, chronic obstructive pulmonary disease (COPD), one of the world’s three major chronic diseases, has seen numerous remarkable outcomes when combined with artificial intelligence, particularly in disease diagnosis. However, the diagnostic performance of these AI models still lacks comprehensive evidence. Therefore, this study quantitatively analyzed the diagnostic performance of AI models in CT images of COPD patients, aiming to promote the development of related research in the future.</div></div><div><h3>Methods</h3><div>PubMed, Cochrane Library, Web of Science, and Embase were retrieved up to September 1, 2024. The QUADAS-2 evaluation tool was used to assess the quality of the included studies. Meta-analysis of the included researches was performed using Stata18, RevMan 5.4, and Meta-Disc 1.4 software to merge sensitivity, specificity and plot a summary receiver operating characteristic curve (SROC). Heterogeneity was assessed using the Q statistic, and sources of inter-study heterogeneity were explored through <em>meta</em>-regression analysis.</div></div><div><h3>Results</h3><div>Twenty-two of 3280 identified studies were eligible. Meta-analysis was performed on 15 of these studies, encompassing a total of 22,817 patients for which statistical metrics were reported or could be calculated. Seven studies were based on deep learning (DL) model, three on machine learning (ML) model, and five on DL model with multiple-instance learning (MIL) mechanisms. One study evaluated both DL and ML models. The <em>meta</em>-analysis results showed that the pooled sensitivity of all DL and ML models was 86 % (95 %CI 78–91 %), specificity was 87 % (95 %CI 83–91 %), and area under the curve was 93 % (95 %CI 90–95 %). Subgroup analyses revealed no significant difference in diagnostic sensitivity and specificity between DL and ML models (sensitivity 82 % (95 %CI 76–87 %), 93 % (95 %CI 85–97 %); specificity 87 % (95 %CI 79–91 %), 84 % (95 %CI 79–88 %), and the DL model with MIL (sensitivity 87 % (95 %CI 61–96 %); specificity 89 % (95 %CI 78–95 %) improved the performance of DL model, but this improvement was not statistically significant (p &gt; 0.05).</div></div><div><h3>Conclusion</h3><div>Both DL and ML models for diagnosing COPD using CT images exhibited high accuracy. There was no significant difference in diagnostic efficacy between the two types of AI models, and the addition of the MIL mechanism may enhance the performance of the DL model.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"196 ","pages":"Article 105812"},"PeriodicalIF":3.7,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143076329","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}

{"title":"A deep learning model for QRS delineation in organized rhythms during in-hospital cardiac arrest","authors":"Jon Urteaga ,&nbsp;Andoni Elola ,&nbsp;Daniel Herráez ,&nbsp;Anders Norvik ,&nbsp;Eirik Unneland ,&nbsp;Abhishek Bhardwaj ,&nbsp;David Buckler ,&nbsp;Benjamin S. Abella ,&nbsp;Eirik Skogvoll ,&nbsp;Elisabete Aramendi","doi":"10.1016/j.ijmedinf.2025.105803","DOIUrl":"10.1016/j.ijmedinf.2025.105803","url":null,"abstract":"<div><h3>Background</h3><div>Cardiac arrest (CA) is the sudden cessation of heart function, typically resulting in loss of consciousness and cessation of pulse and breathing. The electrocardiogram (ECG) stands as an essential tool extensively utilized by clinicians, during CA treatment. Within the ECG, the QRS complex reflects the depolarization of the ventricles, yielding valuable perspectives on cardiac health and potential irregularities. The delineation of QRS complexes is crucial for obtaining that information, but classical algorithms have not been tested with CA rhythms.</div></div><div><h3>Objective</h3><div>This research aims to introduce a new deep learning-based model for accurately delineating QRS complexes in patients experiencing organized rhythms during in-hospital CA.</div></div><div><h3>Material and Methods</h3><div>Two databases have been employed, one comprising 332 episodes of in-hospital CA (151815 QRS complexes) and another consisting of 105 hemodynamically stable patients (112497 QRS complexes). The method comprises three stages: signal preprocessing for noise removal, windowing and sample classification with a U-Net model, and finally, the segmented windows are merged to complete the process.</div></div><div><h3>Results</h3><div>The proposed method exhibited mean (standard deviation) F1 score/Sensitivity/Specificity/intersection over union values of 97.03(8.28)/ 97.69(11.38)/96.47(9.92)/79.09(15.78), and a 8.56(11.62)<!--> <figure><img></figure> error for <span><math><mi>QR</mi><msub><mrow><mi>S</mi></mrow><mrow><mi>on</mi></mrow></msub></math></span>, and 25.11(25.86)<!--> <figure><img></figure> for <span><math><mi>QR</mi><msub><mrow><mi>S</mi></mrow><mrow><mi>off</mi></mrow></msub></math></span> instant delineation.</div></div><div><h3>Conclusions</h3><div>A precise delineator like this could support clinical practice by quantifying QRS features to enhance diagnostic accuracy and optimize treatment strategies.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"196 ","pages":"Article 105803"},"PeriodicalIF":3.7,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143076320","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}

{"title":"Individual risk and prognostic value prediction by interpretable machine learning for distant metastasis in neuroblastoma: A population-based study and an external validation","authors":"Shan Li ,&nbsp;Jinkui Wang ,&nbsp;Zhaoxia Zhang ,&nbsp;Chunnian Ren ,&nbsp;Dawei He","doi":"10.1016/j.ijmedinf.2025.105813","DOIUrl":"10.1016/j.ijmedinf.2025.105813","url":null,"abstract":"<div><h3>Purpose</h3><div>Neuroblastoma (NB) is a childhood malignancy with a poor prognosis and a propensity for distant metastasis (DM). We aimed to establish machine learning (ML) based model to accurately predict risk of DM and prognosis of NB patients with DM.</div></div><div><h3>Methods</h3><div>We analyzed NB patients from the Surveillance, Epidemiology, and End Results (SEER) database between 2000 and 2020. Univariate and multivariate logistic analysis were employed to select meaning variables. Recursive Feature Elimination (RFE) method based on 6 ML algorithms was utilized in feature selection. To construct predictive model, 13 ML algorithms were evaluated by area under the operating characteristic curve (AUC), accuracy, sensitivity, specificity, precision, cross-entropy, Brier scores, Balanced Accuracy and F-beta score. An optimal ML model was constructed to predict DM, and the predictive results were explained by SHapley Additive exPlanations (SHAP) framework. Meanwhile, 101 ML algorithm combinations were developed to select the best model with highest C-index to predict prognosis of NB patients with DM.</div></div><div><h3>Results</h3><div>A total of 1,668 NB patients from SEER database was consecutively enrolled. We identified that tumor primary site, grade, surgery type, regional lymph nodes, radiotherapy and chemotherapy are significant risk factors for DM. CatBoost model was selected as the best prediction model, and AUC was 0.846 (95 %CI: [0.804,0.899]), 0.834 (95 %CI: [0.796,0.873]) and 0.813 (95 %CI: [0.776,0.852]) in training, internal test and external test sets, with 0.777 accuracy, 0.839 sensitivity, 0.72 specificity and 0.731 precision in training set. Grade, chemotherapy and radiotherapy had the greatest effects on DM according to SHAP results. For prognosis prediction, “RSF + GBM” algorithm was the best prognostic model with C-index of 0.656, 0.611 and 0.629 in training, internal test and external test sets.</div></div><div><h3>Conclusions</h3><div>Our ML models demonstrate excellent accuracy and reliability, offering more precise personalized metastasis diagnosis and prognostic prediction to NB patients.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"196 ","pages":"Article 105813"},"PeriodicalIF":3.7,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143191168","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}

{"title":"Healthcare information system support for leadership and management: Experiences of Finnish physician leaders by specialty from three cross-sectional surveys in 2014, 2017, and 2021","authors":"Tinja Lääveri ,&nbsp;Päivi Metsäniemi ,&nbsp;Timo Tuovinen ,&nbsp;Suvi Vainiomäki ,&nbsp;Jarmo Reponen","doi":"10.1016/j.ijmedinf.2025.105814","DOIUrl":"10.1016/j.ijmedinf.2025.105814","url":null,"abstract":"<div><h3>Introduction</h3><div>In addition to their role in patient care, health information systems (HISs) produce data for process and quality monitoring, resource management, and strategic planning. However, few studies have focused on physician leaders as end users of leadership and management information systems (LMISs).</div></div><div><h3>Objective</h3><div>The aim was to describe physician leaders’ experiences with LMISs by specialty group from three national usability-focused surveys.</div></div><div><h3>Methods</h3><div>The data were gathered via web-based questionnaires in 2014, 2017, and 2021 with 716, 728, and 831 physician leader respondents, respectively. The 2021 responses were compared across six specialty groups: operative, (non-surgical) medical, psychiatric, and diagnostic specialties, and general practice and occupational healthcare. Those not specialized or whose specialty was unknown formed the seventh group. Moreover, the results from the three study timepoints were compared within specialty groups.</div></div><div><h3>Results</h3><div>In 2021, 69.4%–84.2% indicated that they had to compile leadership and management data from several sources with 3.6%–23.7% finding this process easy. Furthermore, 3.7%–34.2% viewed that the available data supported research and innovation. Physician leaders in operative and diagnostic specialties and occupational healthcare appeared more satisfied with LMISs than did their colleagues in other specialties; for example, 41.9%–56.8% of these respondents considered that HISs help to monitor achieving the targets of their units, compared to 21.7%–34.5% in other specialties. Between the study years, the proportion of those content with LIMSs support for steering daily activities had increased, particularly in operative and medical specialties and general practice; otherwise, though overall improvements were modest.</div></div><div><h3>Conclusion</h3><div>Despite the wide availability of HISs and LMISs, their full potential to support physician leadership and management has not yet been fulfilled. Physician leaders working in diagnostic, operative, and occupational healthcare specialties appeared to derive the most benefit from LMISs.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"196 ","pages":"Article 105814"},"PeriodicalIF":3.7,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143076374","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}

{"title":"Development and external validation of a machine learning model to predict the initial dose of vancomycin for targeting an area under the concentration–time curve of 400–600 mg∙h/L","authors":"Yun Woo Lee ,&nbsp;Ji-Hun Kim ,&nbsp;Jin Ju Park ,&nbsp;Hyejin Park ,&nbsp;Hyeonji Seo ,&nbsp;Yong Kyun Kim","doi":"10.1016/j.ijmedinf.2025.105817","DOIUrl":"10.1016/j.ijmedinf.2025.105817","url":null,"abstract":"<div><h3>Purpose</h3><div>To develop and validate a novel artificial intelligence model for predicting the initial empiric dose of vancomycin, with the aim of achieving an area under the concentration–time curve (AUC) of 400–600 mg∙h/L, using individual clinical data.</div></div><div><h3>Methods</h3><div>Machine learning models were developed and validated internally and externally using data from adult patients who received intravenous vancomycin treatment between November 2020 and June 2023, using records from July to September 2023, sourced from two hospitals. This study included 205, 44, and 35 patients in the training, internal validation, and external validation sets, respectively. The Random Forest, XGBoost, and Ensemble models were evaluated based on the mean squared error, root mean squared error, R-squared value, and accuracy (±20 % of the actual dose).</div></div><div><h3>Findings</h3><div>In internal validation, the Random Forest model achieved the highest 20% Accuracy at 56.8%, while the XGBoost model achieved 56.8% and Voting Ensemble models attained 54.5% accuracy. In external validation, the XGBoost model achieved the highest 20% Accuracy at 74.3%, followed by Random Forest and Voting Ensemble, both also achieving 74.3% accuracy. The estimated glomerular filtration rate was the most significant predictor in all models, with body weight, serum creatinine, height, and age also prominently influencing the XGBoost model’s predictions.</div></div><div><h3>Implications</h3><div>The proposed model is capable of accurately predicting the optimal dose of vancomycin, which could aid physicians in making more informed treatment decisions regarding early therapy, particularly when AUC estimation systems are not accessible or readily available in routine clinical practice.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"196 ","pages":"Article 105817"},"PeriodicalIF":3.7,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143082310","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}

{"title":"Machine learning to predict stroke risk from routine hospital data: A systematic review","authors":"William Heseltine-Carp ,&nbsp;Megan Courtman ,&nbsp;Daniel Browning ,&nbsp;Aishwarya Kasabe ,&nbsp;Michael Allen ,&nbsp;Adam Streeter ,&nbsp;Emmanuel Ifeachor ,&nbsp;Martin James ,&nbsp;Stephen Mullin","doi":"10.1016/j.ijmedinf.2025.105811","DOIUrl":"10.1016/j.ijmedinf.2025.105811","url":null,"abstract":"<div><h3>Purpose</h3><div>Stroke remains a leading cause of morbidity and mortality. Despite this, current risk stratification tools such as CHA₂DS₂-VASc and QRISK3 are of limited accuracy, particularly in those without a diagnosis of atrial-fibrillation. Hence, there is a need for more accurate stroke risk prediction models. Machine-learning (ML) may provide a solution to this by leveraging existing routine hospital databases to build accurate stroke risk prediction models and identify novel risk factors for stroke.</div></div><div><h3>Aims</h3><div>In this systematic review we appraise current research using ML to predict stroke risk from routine hospital data. Based on these findings we then highlight common methodological limitations and recommendations for future research.</div></div><div><h3>Methods</h3><div>In this review we identify 49 original research (38 in the general population and 11 in AF specific populations) articles from the PUBMED database from January-2013 to December-2024 using ML and routine hospital data to predict the risk of stroke.</div></div><div><h3>Results</h3><div>ML models were able to accurately predict stroke risk in both AF specific and general populations, with AUCs ranging from 0.64 to 0.99. Where tested, ML also consistently outperformed traditional risk stratification tool, such as CHA₂DS₂-VASc. ML also appeared useful in identifying several novel risk factors from electrocardiogram, laboratory test and echocardiography data.</div><div>However, the quality of datasets were often limited, there was a high suspicion of overfitting and models often lacked calibration, external validation and explainability analysis.</div></div><div><h3>Conclusion</h3><div>Whilst ML has shown great potential in stroke prediction and identifying novel risk factors for stroke, improvements in study methodology is required prior to integration of ML into routine healthcare. Future research should adhere to the EQUATOR guidance on prediction models and encourage interdisciplinary collaboration between computer scientists and clinicians. Further prospective RCTs are also required to validate models in the clinical setting and the identify barriers of integrating ML into routine healthcare.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"196 ","pages":"Article 105811"},"PeriodicalIF":3.7,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143226666","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}

{"title":"Human-centred AI for emergency cardiac care: Evaluating RAPIDx AI with PROLIFERATE_AI","authors":"Maria Alejandra Pinero de Plaza ,&nbsp;Kristina Lambrakis ,&nbsp;Fernando Marmolejo-Ramos ,&nbsp;Alline Beleigoli ,&nbsp;Mandy Archibald ,&nbsp;Lalit Yadav ,&nbsp;Penelope McMillan ,&nbsp;Robyn Clark ,&nbsp;Michael Lawless ,&nbsp;Erin Morton ,&nbsp;Jeroen Hendriks ,&nbsp;Alison Kitson ,&nbsp;Renuka Visvanathan ,&nbsp;Derek P. Chew ,&nbsp;Carlos Javier Barrera Causil","doi":"10.1016/j.ijmedinf.2025.105810","DOIUrl":"10.1016/j.ijmedinf.2025.105810","url":null,"abstract":"<div><h3>Background</h3><div>Chest pain diagnosis in emergency care is hindered by overlapping cardiac and non-cardiac symptoms, causing diagnostic uncertainty. Artificial Intelligence, such as RAPIDx AI, aims to enhance accuracy through clinical and biochemical data integration, but its adoption relies on addressing usability, explainability, and seamless workflow integration without disrupting care.</div></div><div><h3>Objective</h3><div>Evaluate RAPIDx AI’s integration into clinical workflows, address usability barriers, and optimise its adoption in emergencies.</div></div><div><h3>Methods</h3><div>The PROLIFERATE_AI framework was implemented across 12 EDs (July 2022–January 2024) with 39 participants: 15 experts co-designed a survey via Expert Knowledge Elicitation (EKE), applied to 24 ED clinicians to assess RAPIDx AI usability and adoption. Bayesian inference, using priors, estimated comprehension, emotional engagement, usage, and preference, while Monte Carlo simulations quantified uncertainty and variability, generating posterior means and 95% bootstrapped confidence intervals. Qualitative thematic analysis identified barriers and optimisation needs, with data triangulated through the PROLIFERATE_AI scoring system to rate RAPIDx AI’s performance by user roles and demographics.</div></div><div><h3>Results</h3><div>Registrars exhibited the highest comprehension (median: 0.466, 95 % CI: 0.41–0.51) and preference (median: 0.458, 95 % CI: 0.41–0.48), while residents/interns scored the lowest in comprehension (median: 0.198, 95 % CI: 0.17–0.26) and emotional engagement (median: 0.112, 95 % CI: 0.09–0.14). Registered nurses showed strong emotional engagement (median: 0.379, 95 % CI: 0.35–0.45). Novice users faced usability and workflow integration barriers, while experienced clinicians suggested automation and streamlined workflows. RAPIDx AI scored “Good Impact,” excelling with trained users but requiring targeted refinements for novices.</div></div><div><h3>Conclusion</h3><div>RAPIDx AI enhances diagnostic accuracy and efficiency for experienced users, but usability challenges for novices highlight the need for targeted training and interface refinements. The PROLIFERATE_AI framework offers a robust methodology for evaluating and scaling AI solutions, addressing the evolving needs of sociotechnical systems.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"196 ","pages":"Article 105810"},"PeriodicalIF":3.7,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143082311","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}

{"title":"EHR-ML: A data-driven framework for designing machine learning applications with electronic health records","authors":"Yashpal Ramakrishnaiah ,&nbsp;Nenad Macesic ,&nbsp;Geoffrey I. Webb ,&nbsp;Anton Y. Peleg ,&nbsp;Sonika Tyagi","doi":"10.1016/j.ijmedinf.2025.105816","DOIUrl":"10.1016/j.ijmedinf.2025.105816","url":null,"abstract":"<div><h3>Objective</h3><div>The healthcare landscape is experiencing a transformation with the integration of Artificial Intelligence (AI) into traditional analytic workflows. However, its integration faces challenges resulting in a crisis of generalisability. Key obstacles include; 1) Insufficient consideration of local contextual factors, such as institution-specific data formats, practices, and protocols, which can lead to variability in clinical practices across different institutions. 2) ad-hoc data preparation and design of machine learning strategies. 3) manual subjective adjustment of design parameters resulting in sub-optimal performance. 4) EHR specific challenges regarding data biases affecting the model outcomes and unique intermittent temporal nature of the data necessitating specialised handling 5) lack of cross-institutional data validations.</div></div><div><h3>Methods</h3><div>To address these challenges, EHR-ML, provides an easy to use structured framework for designing optimum machine learning applications in a data-driven manner. The framework supports ingestion of local institutional electronic health records (EHRs) and process standardisation. The study design and parameter optimisation is done in a fully data-driven evidence-based approach. It seamlessly integrating with existing quality control tools. To handle the unique characteristics of the EHR data, it offers customisable ensemble models. It enables the acquisition of EHR data from diverse systems and harmonise them into common formats following international standards.</div></div><div><h3>Results</h3><div>The effectiveness of the EHR-ML is demonstrated through a series of case studies. These studies highlight its capability to develop high-performance models in a fully automated manner, consistently surpassing the performance of traditional methodologies. Furthermore, they exhibited strong generalisability across diverse healthcare settings.</div></div><div><h3>Discussion and Conclusion</h3><div>EHR-ML enhances the clinical relevance and accuracy of predictive models by incorporating local context into machine learning applications. Additionally, by providing an user-friendly fully-automated framework, it facilitates rapid hypothesis testing aimed to generate localised biomedical knowledge.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"196 ","pages":"Article 105816"},"PeriodicalIF":3.7,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143076356","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}

{"title":"Tackling the small imbalanced horizontal dataset regressions by Stability Selection and SMOGN: a case study of ventilation-free days prediction in the pediatric intensive care unit and the importance of PRISM","authors":"Milad Rad ,&nbsp;Alireza Rafiei ,&nbsp;Jocelyn Grunwell ,&nbsp;Rishikesan Kamaleswaran","doi":"10.1016/j.ijmedinf.2025.105809","DOIUrl":"10.1016/j.ijmedinf.2025.105809","url":null,"abstract":"<div><h3>Objective</h3><div>The regression of small imbalanced horizontal datasets is an important problem in bioinformatics due to rare but vital data points impacting model performance. Most clinical studies suffer from imbalance in their distribution which impacts the learning ability of regression or classification models. The imbalance once combined with the small number of samples reduces the prediction performance. An improvement in the trainability of small imbalanced datasets hugely improves the potency of current prediction models that rely on a small set of valuable expensive samples.</div></div><div><h3>Materials and methods</h3><div>A method called Stability Selection has been used to overcome the high dimensionality problem, which arises when the sample sizes are relatively small compared to the number of features. The method was used to improve the performance of the Synthetic Minority Over-Sampling Technique for Regression with Gaussian Noise (SMOGN), an imbalance removal algorithm. To test the new pipeline, a small imbalanced cohort of pediatric ICU patients was used to predict the number of Ventilator-Free Days (VFD) a patient may experience for an admission period of 28 days due to respiratory illnesses.</div></div><div><h3>Results</h3><div>Our model demonstrated its effectiveness by overcoming label imbalance while predicting almost all the non-surviving patients in the test dataset using Stability Selection before applying SMOGN. Our study also highlighted the importance of Pediatrics Risk of Mortality (PRISM) as a powerful VFD predictor if combined with other clinical features.</div></div><div><h3>Conclusion</h3><div>This paper shows how a hybrid strategy of Stability Selection, SMOGN, and regression can improve the outcome of highly imbalanced datasets and reduce the probability of highly expensive false negative detections in severe acute respiratory disease syndrome cases. The proposed modeling pipeline can reduce the overall VFD regression error but is also expandable to other regressable features. We also showed the importance of PRISM as a strong VFD predictor.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"196 ","pages":"Article 105809"},"PeriodicalIF":3.7,"publicationDate":"2025-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143082312","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}