BMC Medical Informatics and Decision Making最新文献

{"title":"Artificial intelligence for pediatric rare disease diagnosis: a multimethod study integrating published evidence and clinician interviews.","authors":"Jungang Zhao, Jiawei Luo, Qiu Li, Yaolong Chen","doi":"10.1186/s12911-026-03718-4","DOIUrl":"10.1186/s12911-026-03718-4","url":null,"abstract":"<p><strong>Background: </strong>Pediatric rare diseases are highly heterogeneous and are frequently associated with missed or delayed diagnosis, creating substantial burden for patients, families, and clinicians. Although artificial intelligence (AI), including large language model-enabled approaches, has shown potential for diagnostic support, translation into real-world pediatric care remains limited. A key gap is the mismatch between metric-centric evidence reporting and clinician-defined implementation needs. To address this, we integrated published evidence with clinician perspectives to derive an implementation-oriented evidence-to-requirements framework for AI-assisted pediatric rare-disease diagnosis.</p><p><strong>Methods: </strong>We used a convergent multimethod design with two complementary evidence sources. First, we conducted a PRISMA-ScR scoping review of four databases (PubMed, Embase, Web of Science, and Scopus) from inception to December 2025 and included 28 original studies on AI-assisted pediatric rare-disease diagnosis. Second, we conducted semi-structured interviews with 21 pediatric clinicians from 15 departments at a tertiary children's hospital in Chongqing, China, and analyzed transcripts using inductive thematic analysis. We then integrated findings side-by-side to identify convergences, divergences, and translational gaps.</p><p><strong>Results: </strong>The scoping review showed rapid movement toward multimodal and LLM-enabled approaches across several diagnostic task types, including screening or cohort identification, phenotyping, differential diagnostic support, and variant or gene prioritization. Translation-oriented evidence remained uneven, with limited prospective evaluation and inconsistent reporting of fairness, safety, and deployment context. Interview analysis identified four recurrent themes: diagnosis as time-pressured puzzle-solving; AI as a cognitive extender rather than replacement; trust dependent on traceable evidence and transparent reasoning; and demand for structured, actionable outputs with low workflow burden. Integrated analysis revealed a persistent implementation gap between metric-centric publication practices and clinician-defined requirements for real-world adoption.</p><p><strong>Conclusions: </strong>This scoping review and qualitative interview study does not establish clinical effectiveness of AI-assisted diagnosis. Instead, it identifies implementation requirements that may guide future development and evaluation, including representative multicenter data, prospective validation, evidence traceability, actionability, safety, fairness, and workflow fit. Main limitations include restriction to English-language studies, reliance on umbrella rare-disease terminology, possible missed studies among unscreened records after ASReview-assisted screening, and a single-institution clinician interview sample.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13640077/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148535358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reducing overconfident errors in clinical prediction models.","authors":"Henry Bayly, Yorghos Tripodis, Steven Lenio, Prasad Patil","doi":"10.1186/s12911-026-03681-0","DOIUrl":"10.1186/s12911-026-03681-0","url":null,"abstract":"<p><p>Machine Learning (ML) models are increasingly being used in clinical workflows. Evaluation of these models tends to focus on global performance metrics, which can obscure error patterns and lead to bias in clinical decision making. Here, we propose Proximal Error-Based Confidence Adjustment (PECA), a framework designed explicitly to improve the safety of ML predictions by reducing a model's confidence in regions of the feature space associated with historical prediction errors. Rather than optimizing global metrics alone, PECA targets confident misclassifications by attenuating prediction confidence proportional to similarity with previously observed errors. Across extensive simulations, PECA reduced the rate at which a model made confident misclassifications while preserving the overall predictive ability of the model. We applied this framework to a clinical trial enrollment workflow for Alzheimer's disease and demonstrated consistent results with the simulations while also demonstrating superior statistical power compared to baseline models. The results of this paper suggest that taming a model's tendency to predict overconfidently using historical error patterns may be a critical step towards safer and more reliable ML systems for digital public health.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13670849/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148535354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Explainable machine learning model for early prediction of ICU death in chronic heart failure with pulmonary infection.","authors":"Yihai Zhai, Bingbing Wei, Danxiu Lan, Siying Lv, Liqin Mo","doi":"10.1186/s12911-026-03682-z","DOIUrl":"10.1186/s12911-026-03682-z","url":null,"abstract":"<p><strong>Objective: </strong>To develop and validate a machine learning model for predicting ICU mortality in CHF patients with pulmonary infection.</p><p><strong>Methods: </strong>Clinical data were extracted from the MIMIC-IV database, and ICU mortality within 15 days was defined as the primary endpoint. Patients were stratified into HFrEF, HFmrEF, and HFpEF based on left ventricular ejection fraction. Six models were constructed-logistic regression, random forest, light gradient boosting machine, extreme gradient boosting (XGBoost), multilayer perceptron, and k-nearest neighbor-and optimized using cross-validated grid search. Predictive performance was evaluated using accuracy, precision, recall, F1-score, AUC, Brier score, Youden index, and calibration slope. Model interpretability was assessed using SHAP and LIME. External validation was conducted using the eICU-CRD database.</p><p><strong>Results: </strong>A total of 1308 patients were included, with an ICU mortality of 15.98%. Among all models, XGBoost achieved the best balance of discrimination and calibration (AUC 0.968; calibration slope 1.070), and retained useful but attenuated discrimination in external testing (AUC 0.718). SHAP analysis identified lactic acid, white blood cell count, prior diagnosis of hypertension, serum potassium, and pre-existing diabetes mellitus as the five most influential predictors of the outcome. Subgroup analyses further demonstrated distinct pathophysiological trajectories associated with mortality: HFrEF predominantly exhibited hemodynamic instability, impaired tissue perfusion, and electrolyte disturbances; in contrast, HFpEF were more frequently associated with chronic metabolic-inflammatory dysregulation and coagulopathy.</p><p><strong>Conclusion: </strong>The XGBoost-based model provides interpretable prediction of ICU mortality in CHF patients with pulmonary infection. Phenotype-specific interpretability analysis further suggested that mortality risk mechanisms differ between heart failure subtypes, supporting more individualized risk assessment and management in critically ill CHF patients.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13670780/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148535334","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A scoping review on artificial intelligence-based tools for cardiovascular disease risk prediction.","authors":"Shrivanshi Pai, Rekha Subramanian, Lakshmi Krishnan, Denny John, Tejashree Subramanya, Sanjay Kinra, Prabhdeep Kaur","doi":"10.1186/s12911-026-03699-4","DOIUrl":"10.1186/s12911-026-03699-4","url":null,"abstract":"<p><strong>Background: </strong>Cardiovascular disease (CVD) is a leading cause of death worldwide, making early risk prediction essential for improving outcomes. Although artificial intelligence (AI) models promise to improve predictions, questions remain about interpretability, the reliability of risk factors, and the need for cross-validation. This scoping review examined the extent, types, and reporting quality of studies that used AI-based prognostic models to predict CVD risk in individuals without established CVD.</p><p><strong>Methods: </strong>A systematic search of PubMed, IEEE Xplore, Web of Science, Scopus, and Google Scholar identified 6,710 records. Screening and data extraction followed the PRISMA-ScR framework and JBI Guidelines for Scoping Reviews. Included studies were evaluated against the TRIPOD-AI reporting checklist. The review protocol was registered with the Open Science Framework (OSF: https://osf.io/8nq6s/ ).</p><p><strong>Results: </strong>Thirty studies met the inclusion criteria; all published after 2017. Most studies utilized existing models on large datasets, predominantly leveraging unimodal clinical data and established machine learning algorithms such as Random Forests and Support Vector Machines. Twenty-four of the 30 studies used unimodal approaches, and the six multimodal studies demonstrated consistently strong performance, but they rest on a small, heterogeneous set of studies. Twelve studies conducted direct comparisons with traditional risk scores such as the Framingham Risk Score, showing comparable or modestly improved discrimination, although methodological heterogeneity limits the strength of these conclusions. External validation was reported in only seven studies, and calibration (agreement between the predicted and observed event rates) was not reported in any of the 30 included studies. Sensitivity, which determines a model's ability to identify truly high-risk individuals, was the least reported metric, appearing in only four studies, and no study reported a decision curve analysis.</p><p><strong>Conclusion: </strong>AI-based CVD risk prediction tools show promise but have critical gaps in validation, calibration reporting, and clinical utility assessment, which currently preclude clinical deployment. Future research should prioritize external validation across diverse populations, mandatory reporting of calibration and sensitivity alongside discrimination metrics, as well as the adoption of reporting standards and appraisal tools such as Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis + Artificial Intelligence (TRIPOD + AI) or Prediction Model Risk of Bias Assessment Tool + Artificial Intelligence (PROBAST + AI) to improve transparency and reproducibility.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13663111/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148497132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interpretable, internally validated prognostic modelling of cumulative clinical pregnancy in women with diminished ovarian reserve.","authors":"Huimei Wu, Qianyi Huang, Yu Long, Li Jiang, Lidan Liu","doi":"10.1186/s12911-026-03709-5","DOIUrl":"10.1186/s12911-026-03709-5","url":null,"abstract":"<p><strong>Objective: </strong>To develop and internally validate an interpretable prognostic model for cumulative clinical pregnancy in women with diminished ovarian reserve (DOR), and to explore, as a hypothesis-generating secondary aim, whether protocol-associated pregnancy rates differ across model-defined baseline-prognosis risk strata.</p><p><strong>Design: </strong>Retrospective cohort study.</p><p><strong>Setting: </strong>A single tertiary reproductive medicine center.</p><p><strong>Patients: </strong>1,251 oocyte-retrieval cycles in women with DOR (AMH ≤ 1.1 ng/mL) at a single tertiary centre, January 2019-July 2024. Each record is one retrieval cycle; no patient identifier was available.</p><p><strong>Methods: </strong>From 37 candidate predictors, random-forest selection (training set only) retained eight; six algorithms were compared for discrimination (AUC, DeLong), calibration (slope, intercept, Brier) and clinical utility (decision-curve analysis), with SHAP for interpretability. Discrimination was further assessed by out-of-time validation (train ≤2022, test 2023-2024). Within model-defined risk strata, protocols were compared (chi-square/Fisher; bootstrap CIs; FDR and Bonferroni correction), with a pre-treatment-variable-only sensitivity analysis.</p><p><strong>Results: </strong>A parsimonious logistic regression gave the highest test AUC (0.739, 95% CI 0.688-0.790; Brier 0.200), not significantly better than more complex algorithms (DeLong p>0.10), and held up on out-of-time validation (AUC 0.726). The five most influential predictors (SHAP) were embryo quality, female age, male age, estradiol and AMH. In the exploratory analysis, low-probability cycles showed no protocol differences; among high-probability cycles only one association survived correction (long-acting GnRH-agonist fresh transfer vs HRT frozen transfer; absolute difference +48%, 95% CI 28-67%; FDR p=0.002), persisting in the baseline-only analysis.</p><p><strong>Conclusions: </strong>In women with DOR, an interpretable logistic-regression model provided moderate, internally and temporally validated discrimination for cumulative clinical pregnancy at the pre-transfer decision point, though calibration drifted over time and warrants recalibration before use. The single protocol-related association is hypothesis-generating only. The model is best regarded as a pre-transfer prognostic counselling tool, not a basis for protocol selection, and requires prospective external validation.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13662997/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148497188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AMIUgraph: analysis and modeling of interactions for utility-driven benchmarking of graph-based models in healthcare.","authors":"Paolo Sorino, Alessandro De Bellis, Daniele Malitesta, Domenico Lofù, Caterina Bonfiglio, Rossella Donghia, Gianluigi Giannelli, Antonio Ferrara, Fedelucio Narducci, Tommaso Di Noia, Eugenio Di Sciascio","doi":"10.1186/s12911-026-03717-5","DOIUrl":"10.1186/s12911-026-03717-5","url":null,"abstract":"<p><strong>Background: </strong>Graph-based machine learning approaches, including Knowledge Graph Embedding (KGE) methods and Graph Neural Networks (GNNs), have emerged as powerful tools for modeling complex biomedical data. However, a systematic and clinically grounded comparison of these approaches across heterogeneous healthcare graphs, accounting for both predictive performance and real-world deployment constraints, is still lacking.</p><p><strong>Methods: </strong>We introduce AMIUGraph, a comprehensive benchmarking framework for healthcare link prediction that integrates real-world clinical data with external biomedical knowledge bases. AMIUGraph evaluates eight state-of-the-art models, of which four are knowledge graph embedding (KGE) methods DistMult, CP, ComplEx, and ConvE and four are graph neural network (GNN) architectures GCN, GraphSAGE, GAT, and GIN. The models are evaluated across three heterogeneous bipartite graphs representing Patients-Diseases, Diseases-Drugs, and Drugs-Targets interactions. Models are assessed under both transductive and inductive learning settings using accuracy, AUC, precision, recall, F1-score, and training time as evaluation metrics.</p><p><strong>Results: </strong>Experimental results show that model performance is strongly influenced by graph structure and sparsity. GNNs consistently achieve superior predictive performance on sparse interaction graphs, particularly for Diseases-Drugs and Drugs-Targets prediction tasks. In contrast, KGE models demonstrate competitive accuracy with substantially lower computational costs in inductive clinical scenarios involving unseen patients. These trends are especially relevant in clinically realistic settings characterized by multimorbidity, such as gastrointestinal and liver diseases, where frequent patient updates and complex therapeutic interactions are common.</p><p><strong>Conclusion: </strong>AMIUGraph provides a clinically grounded and utility-driven benchmarking framework that jointly evaluates KGE and GNN models across multiple healthcare graph types and learning settings. The findings offer practical guidance for selecting graph-based models in medical decision-support systems, including applications in gastrointestinal healthcare, while promoting transparency and reproducibility through the public release of all datasets, protocols, and code.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13663255/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148497156","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Users' opinions on the use of electronic health records at the Upper East Regional Hospital, Ghana: a qualitative study.","authors":"Joseph Owusu-Marfo, Mark Anthony Azongo, Jonathan Kissi","doi":"10.1186/s12911-026-03714-8","DOIUrl":"10.1186/s12911-026-03714-8","url":null,"abstract":"<p><strong>Background: </strong>The use of technology in healthcare to manage patient records, guide diagnosis, and make referrals is termed electronic healthcare. An electronic health record system called Lightwave Health Information Management System (LHIMS) was implemented in 2021 at Bolgatanga Regional Hospital (BRH). This study evaluated the opinion of users on the use of LHIMS among healthcare workers, focusing on the extent to which its use has enhanced the main dimensions of clinical work.</p><p><strong>Method: </strong>A qualitative research design was employed to explore healthcare providers' experiences with the LHIMS. Purposive sampling was employed to recruit eleven (11) participants comprising nurses and doctors who had at least two years of experience using the LHIMS. An interview guide was used to facilitate in-depth, face-to-face interviews with all participants.</p><p><strong>Results: </strong>Healthcare providers expressed overall satisfaction with LHIMS, citing its time-saving features, efficiency, data security, cost-effectiveness, and ease of use. Users reported receiving support from IT personnel, experienced colleagues, and stable network systems; however, challenges included inadequate staff training, documentation difficulties among nurse midwives, limited computer availability, insufficient user manuals, and frequent power interruptions.</p><p><strong>Conclusion: </strong>The study found that most LHIMS users were satisfied with the system, particularly its user-friendly interface and efficiency in managing and synchronizing patient data. To enhance system performance and sustain user satisfaction, the hospital should ensure uninterrupted power supply, provide mandatory training for new staff, integrate a comprehensive user manual into the LHIMS platform, and supply adequate computer resources to support effective use.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13656486/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148469056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Context-agnostic machine learning for Parkinson's disease motor symptom detection using wearable sensors.","authors":"Konstantina-Maria Giannakopoulou, Panagiotis Tsakanikas, Ioanna Roussaki","doi":"10.1186/s12911-026-03665-0","DOIUrl":"10.1186/s12911-026-03665-0","url":null,"abstract":"<p><strong>Background: </strong>Parkinson's disease is a rapidly growing neurodegenerative disorder with various motor and non-motor symptoms, affecting millions of people worldwide. These symptoms demonstrate significant medication-related fluctuations and inter-patient variability, highlighting the need for personalized management. Objective longitudinal symptom monitoring through wearable sensors and machine learning can support individualized care. However, to date, most approaches have been tested in lab-constrained environments. This study aims to develop a modular pipeline to automatically detect three cardinal Parkinson's disease motor symptoms, tremor, bradykinesia, and levodopa-induced dyskinesia in more realistic scenarios.</p><p><strong>Methods: </strong>The proposed approach was evaluated on three datasets: the Levodopa Response Study and two newly introduced ALAMEDA datasets, containing tri-axial wrist accelerometer data collected with commercial wearable devices during clinical assessments and activities of daily living. For each symptom, separate context-agnostic models were developed using 92 hand-crafted features. Multiple segmentation window lengths and preprocessing techniques, including resampling and dimensionality reduction, alongside various machine learning models, including logistic regression, k-nearest neighbor, multilayer perceptron, support vector machine, decision tree, AdaBoost, and random forest, were explored. Statistical significance between configurations was assessed with the Wilcoxon signed-rank test. Model interpretability was investigated using Shapley additive explanations to identify highly influential predictors and assess their physiological relevance.</p><p><strong>Results: </strong>In the Levodopa Response Study dataset, tremor, bradykinesia, and dyskinesia detection reached 0.664, 0.636, and 0.443 area under the precision-recall curve, respectively, demonstrating scalability in high-complexity settings and revealing physiologically meaningful patterns. When evaluated on the ALAMEDA datasets, tremor and dyskinesia detection achieved 0.879 and 0.648 area under the precision-recall curve, highlighting strong model and feature generalizability. Across symptoms, longer segmentation windows and random forest classifiers performed better, while synthetic oversampling and principal component analysis showed limited impact.</p><p><strong>Conclusions: </strong>Automated Parkinson's disease symptom detection is feasible in more realistic, free-living conditions, with only a slight performance decrease despite substantially increased complexity. With carefully selected features and pipeline components, the objective, unobtrusive monitoring of motor symptoms can support personalized, evidence-based treatment suggestions, eventually improving patients' quality of life.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13660283/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148469086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The consultant's guide: evidence-based digital transformation framework for healthcare institutions in developing and resource-constrained economies.","authors":"Uchechukwu Solomon Onyeabor, Okechukwu Onwuasoigwe, Wilfred Okwudili Okenwa, Omolade Ayoola Lasebikan, Thorsten Schaaf, Niels Pinkwart, Felix Balzer","doi":"10.1186/s12911-026-03713-9","DOIUrl":"10.1186/s12911-026-03713-9","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Digital transformation is increasingly reshaping healthcare delivery worldwide; however, the adoption of digital health systems in developing and resource-constrained economies remains constrained by infrastructural limitations, poor alignment with clinical workflows, inadequate user involvement, and resistance to organizational change. Many digital healthcare initiatives in these settings continue to experience implementation and sustainability challenges, partly due to the absence of context-specific and evidence-based transformation models. Consequently, this study aimed to develop a customized evidence-based digital transformation framework to support the sustainable adoption of digital healthcare systems within tertiary and university teaching hospitals in developing economies.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This study emerged from a prolonged mixed-methods doctoral research project conducted across three tertiary healthcare institutions in southeastern Nigeria: the University of Nigeria Teaching Hospital (UNTH), ESUT Teaching Hospital (ESUTTH), and the National Orthopaedic Hospital Enugu (NOHE). The research involved close to 600 stakeholders, including doctors, nurses, medical records officers, patients, and clinical consultants. Data were collected through structured questionnaires, qualitative interviews, participatory co-design interactions, observational methods, usability testing, and iterative system evaluations. The study adopted an agile human-centered software engineering and participatory development approach to guide the design, implementation, and evaluation of the proposed TUMERIC digital healthcare support system and the resulting transformation framework.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The findings demonstrated generally positive institutional readiness toward digital transformation, with over 70% of participating healthcare professionals indicating support for future digital initiatives within their institutions. Usability evaluations of the implemented TUMERIC system also demonstrated high levels of user acceptance and perceived usability among clinicians and patients. Qualitative findings further highlighted the importance of aligning digital systems with existing clinical workflows, involving end users throughout the development lifecycle, and addressing infrastructural and organizational constraints during implementation. These findings informed the development of the proposed evidence-based digital transformation framework tailored to resource-constrained healthcare environments.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusion: &lt;/strong&gt;The study demonstrates that agile human-centered and participatory design approaches can support the development and adoption of context-appropriate digital healthcare systems in developing economies. The proposed framework provides an empirically informed model that may assist healthcare institutions and policymakers in planning and implementing more sustainable and user-ali","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13659990/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148469126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Contrastive explainable AI in healthcare: a systematic review of trends, benefits, research gaps, and future directions.","authors":"Samuele Pe, Antonino Angi, Cristian Izquierdo, Enea Parimbelli, Machteld Johanna Boonstra, Folkert Wouter Asselbergs, Karim Lekadir","doi":"10.1186/s12911-026-03697-6","DOIUrl":"10.1186/s12911-026-03697-6","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Contrastive eXplainable Artificial Intelligence (cXAI) has emerged as a promising approach to align machine learning explanations with human reasoning. Unlike classical XAI, which addresses questions such as \"Why P?\", contrastive explanations explicitly consider alternatives, answering \"Why P, rather than Q?\". By making the implicit comparison explicit and focusing only on features that distinguish between outcomes, cXAI has been argued to provide more cognitively aligned, less ambiguous, and more actionable explanations than classical XAI. Moreover, in the context of healthcare, this comparative structure closely mirrors clinicians' abductive reasoning in differential diagnosis and treatment selection. Our purpose is to systematically examine how contrastive explanations have been developed and applied in healthcare; emphasize the related benefits; identify current trends, research gaps, and future directions.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We conducted a systematic literature review of studies published from 2018 onward, following the PRISMA 2020 guidelines. Five scientific databases (IEEE Xplore, Scopus, PubMed, ACM Digital Library, and SpringerLink) were queried using structured search strings, complemented by an AI-assisted search using the Elicit tool. Eligible studies focused on the development or application of contrastive explanation techniques in healthcare-related machine learning tasks. Extracted information included data modalities, AI models, contrastive methods, visualization techniques, and validation strategies.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Only 18 studies met the eligibility criteria, reflecting the relative novelty of the field, while also indicating that the translation of cXAI into healthcare applications is still at an early stage. Most works focused on tabular data and medical imaging, while physiological signals and video/volumetric data were notably underrepresented. Contrastive Explanation Method (CEM) was the most frequently employed approach. Visualization methods for explanations predominantly relied on heatmaps or feature-importance displays, with textual explanations mainly used in studies involving patients or lay users. Importantly, only a small number of studies reported empirical evaluations involving end users, indicating a lack of rigorous validation.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;cXAI offers a clinically aligned and cognitively coherent approach to explainability in healthcare by explicitly framing decisions in relation to meaningful alternatives. Despite its strong conceptual suitability, its adoption in real-world medical settings remains limited, with underexplored modalities and scarce user-centered validation. Advancing cXAI in healthcare will require (i) rigorous clinical assessment of explanations and systematic collection of user feedback and (ii) the development of multimodal, human-centered explanation frameworks. Through these efforts, cXAI can evolve from ","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13656352/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148454774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}