International Journal of Medical Informatics最新文献

{"title":"Applying a statistical model-based AI method to identify prognostic factors for long-term cognitive decline in Alzheimer’s disease: Evidence from pooled placebo data of four phase III trials","authors":"Ryoichi Hanazawa ,&nbsp;Hiroyuki Sato ,&nbsp;Keisuke Suzuki ,&nbsp;Akihiro Hirakawa","doi":"10.1016/j.ijmedinf.2026.106337","DOIUrl":"10.1016/j.ijmedinf.2026.106337","url":null,"abstract":"<div><h3>Background</h3><div>Heterogeneity in the long-term progression of Alzheimer’s disease (AD) challenges the efficiency of clinical trials. Identifying long-term prognostic factors is critical for enhancing trial efficiency, although it has been limited by the lack of appropriate statistical approaches. We applied a recently developed statistical model-based AI method to identify the baseline prognostic factors for long-term cognitive decline in a clinical trial population.</div></div><div><h3>Methods</h3><div>We analyzed pooled placebo arm data (N = 1,597) from four Phase III trials in patients with mild-to-moderate AD. Long-term trajectories for the Mini-Mental State Examination (MMSE), 11- and 14-item versions of the Alzheimer’s Disease Assessment Scale-Cognitive subscale (ADAS-Cog11, ADAS-Cog14), and Clinical Dementia Rating-Sum of Boxes (CDR-SB) were predicted from their short-term data (≤80 weeks). Trajectories were compared between subgroups defined by six baseline factors (age, sex, <em>apolipoprotein E ε4</em> [<em>APOE ε4</em>] status, years of education, years from diagnosis, and years from disease onset) using the area under the curve (AUC).</div></div><div><h3>Results</h3><div>Longer years of education (≥13 years) was the most robust predictor associated with faster progression across all four outcomes (e.g., for 20-year ADAS-Cog11, AUC ratio, 1.11, p &lt; 0.001). Younger age (&lt;74 years) was associated with a faster decline in MMSE and ADAS-Cog scores, but not in CDR-SB. <em>APOE ε4</em> status, sex, years from diagnosis, and years from disease onset were not significantly associated with long-term progression.</div></div><div><h3>Conclusions</h3><div>Baseline educational level and age were significant prognostic factors of long-term cognitive decline. These findings will help optimize patient stratification in future clinical trials on AD.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"211 ","pages":"Article 106337"},"PeriodicalIF":4.1,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146190933","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":"Harmonizing patient-reported outcome measures for nasal complaints using traditional and machine learning methods","authors":"Miljan Jović ,&nbsp;Esther Hof ,&nbsp;Maryam Amir Haeri ,&nbsp;Jasper J. Hoorweg ,&nbsp;Stéphanie M. van den Berg","doi":"10.1016/j.ijmedinf.2026.106319","DOIUrl":"10.1016/j.ijmedinf.2026.106319","url":null,"abstract":"<div><h3>Background</h3><div>Nasal obstruction measurement instruments are widely used in the field of nasal surgery. There are various scales that measure nasal obstruction and they differ regarding the number of items, their wording, and the type of response options. In order to pool the data and analyze it together, it is necessary to harmonize it so that we can compare participants’ nasal obstruction scores irrespective of instrument they filled in. Data harmonization is still not used in the field of nasal obstruction assessment.</div></div><div><h3>The Aim</h3><div>The aim of this study was to find the best harmonization method in terms of predicting the scores on a target instrument based on the scores from another instrument as precise as possible in the case of four different nasal complaints instruments. A method was sought to find a transformation of scores on the NOSE, Utrecht-Q and SCHNOS that makes them equivalent to ENFAS scores.</div></div><div><h3>Methods</h3><div>A total of 1324 unique patients completed all four measurement instruments. We tried linear equating, Item Response Theory (IRT), and the following machine learning methods: linear regression, random forest regression, support vector machine regression, and neural network. We used the root-mean-square error (RMSE) of differences between predicted and observed scores to evaluate the quality of harmonization in 5-fold cross-validation.</div></div><div><h3>Results</h3><div>The ML methods gave overall the best results (the lowest RMSEs) and outperformed IRT (which is considered as a common choice for data harmonization in psychometrics).</div></div><div><h3>Conclusion</h3><div>The ML methods led to the best quality of the results, confirming their strong potential for data harmonization. This study shows that next to linear equating and IRT that are commonly used for data harmonization, we can also use ML methods for the same purpose and, by doing so, to even increase the quality of the harmonization in certain use cases.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"211 ","pages":"Article 106319"},"PeriodicalIF":4.1,"publicationDate":"2026-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146133655","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":"Explainable AI in Cardiology Diagnostics: A Systematic Review of Machine Learning, Meta-heuristic Optimization, and Clinical Text Mining for Coronary Artery Disease","authors":"Majdi Jaradat ,&nbsp;Mohammed Awad","doi":"10.1016/j.ijmedinf.2026.106321","DOIUrl":"10.1016/j.ijmedinf.2026.106321","url":null,"abstract":"<div><h3>Background</h3><div>This systematic review compiles evidence and examines how various artificial intelligence (AI) approaches, including machine learning (ML), natural language processing (NLP), <em>meta</em>-heuristic optimization, and explainable AI (XAI), are utilized to predict and diagnose coronary artery disease (CAD). We aim to identify the most commonly used models, evaluate their performance, and explore how interpretability and optimization enhance their usefulness in clinical practice.</div></div><div><h3>Method</h3><div>A thorough search was conducted across five major databases (PubMed, Scopus, IEEE Xplore, ACM Digital Library, and SpringerLink) to identify relevant studies published between January 2022 and August 2025, in accordance with the PRISMA guidelines. Dual independent reviewers performed study selection and data extraction. The quality of the included studies was evaluated using a checklist based on QUADAS-2. Data were collected on study characteristics, model types, validation methods, and performance metrics, which will be the cornerstone of the analysis.</div></div><div><h3>Results</h3><div>Sixty-one studies met the inclusion criteria. ML and deep learning models demonstrated strong performance and achieved high accuracy in benchmark datasets, but showed limited clinical validation. Transformer-based models (e.g., BioBERT, ClinicalBERT) showed high efficacy for medical text analysis, but require substantial data and computational resources. Meta-heuristic algorithms (e.g., Genetic Algorithms, Particle Swarm Optimization) effectively improved model efficiency but were rarely applied to unstructured clinical narratives. XAI tools (e.g., SHAP, LIME) improved model transparency, though most studies highlight a need for more rigorous evaluation.</div></div><div><h3>Conclusion</h3><div>Integrated ML, NLP, <em>meta</em>-heuristic optimization, and XAI hold significant promise in advancing the diagnosis of CAD by improving both accuracy and interpretability. However, challenges such as data scarcity, limited external validation, and a lack of standardized, clinician-centric explainability impede clinical adoption. Future research should focus on hybrid frameworks validated for large, diverse, and real-world datasets.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"211 ","pages":"Article 106321"},"PeriodicalIF":4.1,"publicationDate":"2026-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146137980","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":"Using causal rule mining to identify opportunities for value improvement in regional CABG care: A proof-of-concept study","authors":"Sophie van Heuveln ,&nbsp;Gijs J. van Steenbergen ,&nbsp;Mileen R.D. van de Kar ,&nbsp;Erwin S.H. Tan ,&nbsp;Mohamed A. Soliman-Hamad Veghel ,&nbsp;Rik Eshuis ,&nbsp;Lukas R.C. Dekker ,&nbsp;Dennis van Veghel","doi":"10.1016/j.ijmedinf.2026.106317","DOIUrl":"10.1016/j.ijmedinf.2026.106317","url":null,"abstract":"<div><h3>Objective</h3><div>To explore the potential of causal rule mining (CRM) as a complementary method to outcome monitoring in identifying plausible causal patterns that may explain undesired clinical outcomes or elevated care consumption in cardiac surgery.</div></div><div><h3>Methods</h3><div>In this proof-of-concept study, CRM was applied to data from 1,068 patients who underwent elective isolated coronary artery bypass grafting between January 2016 and March 2021 at a single heart center and its referral network in the Netherlands. Outcomes of interest included: 1-year and 120-day mortality, in-hospital stroke, 30-day deep sternal wound infection (DSWI), 30-day re-explorations, 1-year coronary reinterventions, event-free survival, 30-day emergency department (ED) visits, postoperative length of stay, and preoperative fractional flow reserve (FFR) testing. Causal rules were considered relevant if both the odds ratio (OR) and its 95 % confidence interval (CI) were &gt; 1. Identified rules were independently reviewed by clinical experts.</div></div><div><h3>Results</h3><div>CRM identified 114 significant rules. Five rules were rated as ‘new and interesting’ and two additional rules were included based on special interest. In follow-up discussions, clinical experts agreed that three rules warrant further clinical investigation: (1) the absence of fractional flow reserve (FFR) testing reducing the likelihood of coronary reintervention, (2) absence of red blood cell (RBC) transfusion during admission reducing the likelihood of 30-day re-explorations, and (3) RBC transfusion increasing the likelihood of 30-day re-explorations.</div></div><div><h3>Conclusion</h3><div>CRM helped identify potential explanations for certain outcomes and care consumption, providing structured input for hypothesis-driven quality improvement and supporting efforts to enhance patient value.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"211 ","pages":"Article 106317"},"PeriodicalIF":4.1,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146121141","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 of an interpretable machine learning model for predicting 4-year chronic kidney disease risk in elderly hypertensive patients","authors":"Panji Wang ,&nbsp;Yuan Meng ,&nbsp;Zhaowei Sun ,&nbsp;Jiaju Li ,&nbsp;Hailong Tao","doi":"10.1016/j.ijmedinf.2026.106320","DOIUrl":"10.1016/j.ijmedinf.2026.106320","url":null,"abstract":"<div><h3>Introduction</h3><div>Age and hypertension are key drivers of renal impairment, predisposing older hypertensive adults to faster kidney function decline and higher mortality. We aim to develop an interpretable machinelearning model to predict 4-year chronic kidney disease (CKD) risk in this population.</div></div><div><h3>Methods</h3><div>Our study incorporated 4,142 hypertensive patients from the Health and Retirement Study (HRS) 2010 and 2012 cohorts for model development and internal validation, with additional temporal validation performed within the HRS 2006 and 2008 cohorts. External validation was conducted using three distinct subcohorts derived from the China Health and Retirement Longitudinal Study (CHARLS) database. Feature selection was implemented through an integrated LASSO-Boruta algorithm, followed by model construction using eight machine learning approaches. Discriminative performance was rigorously evaluated through multiple metrics, including receiver operating characteristic (ROC) curve analysis, accuracy, sensitivity, specificity, and Brier score. The optimal model underwent interpretability analysis via SHapley Additive exPlanations (SHAP) to elucidate decision-making mechanisms and was subsequently deployed as a web-based clinical prediction tool.</div></div><div><h3>Results</h3><div>Using a combined LASSO–Boruta strategy, we identified nine routinely available predictors for model development. In the training set, SVM achieved the highest AUC (0.735), closely followed by XGBoost (0.734); notably, in the temporal validation cohort, XGBoost was the only model with an AUC &gt; 0.700 (0.702). Overall performance metrics derived from confusion matrices, together with Brier scores, suggested that XGBoost provided a favorable balance between sensitivity and specificity while maintaining acceptable probabilistic calibration. Calibration curves further suggested that XGBoost showed relatively stable agreement between predicted and observed risks across datasets, supporting its selection for subsequent SHAP-based interpretation and web deployment; SHAP identified age as the leading contributor to CKD risk.</div></div><div><h3>Conclusions</h3><div>We developed an interpretable model using routine clinical indicators to predict 4-year CKD risk in elderly hypertensive adults, with applicability across Asian and Caucasian populations.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"211 ","pages":"Article 106320"},"PeriodicalIF":4.1,"publicationDate":"2026-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146121129","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 personalized and complex mHealth intervention for the universal prevention of Perinatal mental Disorders in routine maternal Care: Design and development of e-Perinatal app","authors":"Company-Córdoba Rosalba ,&nbsp;Caffieri Alessia ,&nbsp;Barquero-Jimenez Carlos ,&nbsp;Cruz-Cabrera Roberto ,&nbsp;De-Juan-Iglesias Paula ,&nbsp;Gil-Cosano José J. ,&nbsp;Goossens Lennert ,&nbsp;Nieto-Casado Francisco J. ,&nbsp;Ureña-Lorenzo Amalia ,&nbsp;Gómez-Gómez Irene ,&nbsp;Motrico Emma","doi":"10.1016/j.ijmedinf.2026.106290","DOIUrl":"10.1016/j.ijmedinf.2026.106290","url":null,"abstract":"<div><h3>Background</h3><div>Perinatal Mental Disorders (PMDs) are common during pregnancy and the first postpartum year, with negative consequences for women, their partners, and infants, as well as broader societal costs. While numerous interventions have been developed to prevent PMDs, there remains a need for a universal, personalized, and cost-effective solution integrated into routine maternal care. The <em>e-Perinatal</em> study aimed to address this gap. This paper describes the design of the <em>e-Perinatal</em> intervention, delivered via a dedicated mobile health app.</div></div><div><h3>Methods</h3><div>Guided by the Medical Research Council framework, the <em>e-Perinatal</em> app integrates Self-Determination Theory, Normalization Process Theory, and Patient and Public Involvement perspectives. Existing evidence was reviewed, and stakeholders participated in the co-development of digital micro-interventions (DMs). A clinical rule-based algorithm was implemented to generate personalized recommendations across four pathways (1) weekly content delivery, (2) user preferences, (3) individual risk profile, and (4) PMD monitoring.</div></div><div><h3>Results</h3><div>The <em>e-Perinatal</em> app includes: 1) DMs focused on psychological, physical activity, and healthy lifestyle domains; 2) a personalized recommendation engine; 3) a social support section; 4) mental health monitoring; 5) an ‘SOS’ button for assistance; and 6) an appointment reminder tool. In total, 332 evidence-based DMs were developed for women and their partners and delivered in text, audio, and video formats. A clinical rule-based algorithm tailors recommendations according to user characteristics and perinatal stage, employing adaptive content filtering to optimize personalization.</div></div><div><h3>Conclusion</h3><div>the <em>e-Perinatal</em> app is a personalized mHealth intervention to<!--> <!-->prevent PMDs within routine maternal care. The intervention combines evidence-based strategies, personalized recommendations, and adaptive digital content to prevent PMDs. Future research will assess effectiveness, implementation, and real-world impact of <em>e-Perinatal</em> intervention for PMD prevention.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"211 ","pages":"Article 106290"},"PeriodicalIF":4.1,"publicationDate":"2026-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146133643","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":"Navigating illness in a virtual world: the role of immersive technology across chronic care continuum – A scoping review","authors":"Ramakrishna Dantu ,&nbsp;Mohammad Murad ,&nbsp;Kirti Sharma ,&nbsp;Kirti Dutta ,&nbsp;Laura Cravens-Ray","doi":"10.1016/j.ijmedinf.2026.106311","DOIUrl":"10.1016/j.ijmedinf.2026.106311","url":null,"abstract":"<div><div>Immersive technologies offer promising capabilities for chronic disease management, but their implementation and specific applications across the chronic care continuum remain limited. This study examines how immersive technologies are being utilized across various chronic disease contexts through a scoping review. Using a comprehensive mapping of literature published between 1995 and 2024, we identified 2,012 relevant articles from major databases using WHO and CDC-defined chronic disease keywords and finally focused on 127 studies for detailed manual review.</div><div>Our approach combined text analytics (BERTopic modelling) with manual synthesis. This methodology revealed eight key themes where immersive technologies are being applied: medical procedures, training and education for healthcare professionals, substance use disorder therapy, cognitive rehabilitation, physical rehabilitation, exergaming and biofeedback, navigation and spatial therapy, and pain, stress, and anxiety management. These themes reflect the growing use of immersive technologies to support diverse activities in chronic care settings.</div><div>The findings highlight the breadth of immersive technology applications across multiple points in chronic care. Our study introduces a thematic framework for understanding immersive applications in healthcare and identifies research directions and opportunities for future investigation. Future research should explore long-term integration into clinical workflows, as well as inclusivity and adoption across diverse populations.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"211 ","pages":"Article 106311"},"PeriodicalIF":4.1,"publicationDate":"2026-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146115036","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":"Patient engagement and performance expectancy towards epilepsy digital health interventions: systematic literature review and meta-analysis","authors":"Tolesa Fanta Jilcha ,&nbsp;Peter Richard Christopher Leeson ,&nbsp;Khin Than Win","doi":"10.1016/j.ijmedinf.2026.106306","DOIUrl":"10.1016/j.ijmedinf.2026.106306","url":null,"abstract":"<div><h3>Background</h3><div>Digital Health is currently showing promising results in reducing patient and caregiver suffering that arise from misconceptions.</div></div><div><h3>Objective</h3><div>To synthesize existing evidence on Perceived Usefulness, interest in use and willingness to use towards Epilepsy Digital Health Interventions.</div></div><div><h3>Method</h3><div>Databases were searched for studies reporting on the outcomes of interest by using a comprehensive search strategy. Studies published in English from January 2015 to September 2025 were included. The Newcastle-Ottawa Quality Assessment Scale was employed to evaluate the quality of included studies. Stata version 19 was used to compute a pooled proportion using a random-effects model. Heterogeneity was assessed using the Cochrane chi-square and the index of heterogeneity test. Sensitivity tests and subgroup analyses were performed. Publication bias was examined by funnel plots and Egger’s test.</div></div><div><h3>Result</h3><div>Overall, 6041 studies were found from databases. After a step-by-step screening, 23 studies were included in this review. The total number of participants was 6703 with a sample size ranges from 12 to 1168. The pooled proportions of Perceived Usefulness, interest to use, and willingness to use Digital Health were 0.66 (0.58, 0.75), 0.69 (0.50, 0.88), and 0.75 (0.66, 0.83), respectively. In this review, Sensitivity tests indicated that none of the included studies exerted extreme influence on the pooled prevalence; and Funnel plots and Egger’s test (p ≤ 0.772) showed no evidence of publication bias.</div></div><div><h3>Conclusion</h3><div>In this review<strong>,</strong> 66% of respondents perceive Digital Health as useful; 69% were interested in using Digital Health, and 75% were willing to engage with Digital Health. Most of the studies were from high-income countries, with no studies found from developing countries. This review emphasizes the importance of focusing on the user’s perceptions, their interest and willingness to use Digital Health Interventions. It also stresses the need for further studies in low-income countries.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"211 ","pages":"Article 106306"},"PeriodicalIF":4.1,"publicationDate":"2026-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146081744","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":"Bridging performance and uncertainty: Cautionary notes on machine learning and large language models in TBI prognostication","authors":"Hasan Nawaz Tahir ,&nbsp;Anfal Khan ,&nbsp;Muhammad Yousaf ,&nbsp;Shahnila Javed ,&nbsp;Mursala Tahir ,&nbsp;Yousaf Ali","doi":"10.1016/j.ijmedinf.2026.106315","DOIUrl":"10.1016/j.ijmedinf.2026.106315","url":null,"abstract":"","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"210 ","pages":"Article 106315"},"PeriodicalIF":4.1,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146081165","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":"Smart insurance analytics: A novel ensemble feature selection approach to unlock health insurance coverage predictions in Sierra Leone","authors":"David B. Olawade ,&nbsp;Augustus Osborne ,&nbsp;Afeez A. Soladoye ,&nbsp;Olaitan E. Oluwadare ,&nbsp;Emmanuel O. Awogbindin ,&nbsp;Ojima Z. Wada","doi":"10.1016/j.ijmedinf.2026.106313","DOIUrl":"10.1016/j.ijmedinf.2026.106313","url":null,"abstract":"<div><h3>Background</h3><div>Predicting health insurance uptake remains a critical challenge for policymakers and insurance providers seeking to optimise coverage strategies and resource allocation. In Sierra Leone, health insurance uptake remains extremely low, and understanding determinants is vital for universal health coverage goals.</div></div><div><h3>Objective</h3><div>To develop and evaluate an innovative ensemble feature selection methodology for health insurance uptake prediction, establishing new performance benchmarks through systematic comparison of multiple machine learning algorithms using comprehensive validation strategies.</div></div><div><h3>Methods</h3><div>This study employed supervised machine learning to predict health insurance uptake among 15,574 women using data from the 2019 Sierra Leone Demographic and Health Survey (SLDHS). We implemented an ensemble feature selection approach that requires consensus across Adaptive Ant Colony Optimisation, Recursive Feature Elimination, and Backwards Elimination techniques. Seven algorithms were systematically compared: Logistic Regression, Support Vector Machines, K-Nearest Neighbors, Random Forest, Gradient Boosting, XGBoost, and LightGBM. SMOTE addressed class imbalance, whilst validation employed nested 5-fold cross-validation, 10-fold cross-validation, and hold-out testing to prevent information leakage.</div></div><div><h3>Results</h3><div>Random Forest achieved exceptional performance with 0.9973 accuracy, 0.9973 precision, 0.9973 recall, 0.9973 F1-score, and perfect 1.0000 ROC AUC on hold-out testing. XGBoost delivered comparable results with 0.9914 across all metrics and 0.9998 ROC AUC. Backward Feature Elimination consistently yielded superior results across ensemble methods. However, the near-perfect performance warrants cautious interpretation and requires external validation to confirm generalizability.</div></div><div><h3>Conclusions</h3><div>This research establishes new performance benchmarks for health insurance prediction, significantly exceeding existing literature, which has direct implications for health insurance policy and practice in Sierra Leone. The innovative ensemble feature selection methodology provides a robust framework for enhancing prediction accuracy across healthcare applications, offering immediate practical value for stakeholders. Future work should prioritize external validation, explainability analysis, and temporal stability assessment to ensure practical deployment readiness.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"211 ","pages":"Article 106313"},"PeriodicalIF":4.1,"publicationDate":"2026-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146115071","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}