International Journal Of Medical Informatics[JOURNAL]
Sun
200 papers
Fuzzy logic in respiratory medicine: a systematic review of predictive and diagnostic applications.
Kettle T, McKeever TM, Gonem S … +2 more , Figueredo G, Bogdanovica I
Int J Med Inform · 2026 Jun · PMID 41702270 · Publisher ↗
BACKGROUND: There is increasing interest in the use of artificial intelligence (AI) to assist with respiratory diagnosis and risk prediction. Fuzzy logic is a form of AI that has the advantage of being transparent and in...
BACKGROUND: There is increasing interest in the use of artificial intelligence (AI) to assist with respiratory diagnosis and risk prediction. Fuzzy logic is a form of AI that has the advantage of being transparent and interpretable, compared to alternatives such as deep neural networks. We systematically reviewed applications of fuzzy logic for outcome prediction in respiratory medicine. MATERIALS AND METHODS: We searched PubMed and IEEE Xplore from inception to November 2024 for studies which applied fuzzy logic to respiratory outcome prediction and diagnosis. Three reviewers independently screened titles and abstracts, then all five reviewers assessed full texts for eligibility. Risk of bias was assessed using PROBAST by three reviewers. We performed a narrative synthesis following the SWiM guidelines due to heterogeneity. RESULTS: From 982 records, 29 studies (1998-2024) met the inclusion criteria. Studies addressed asthma (n = 5), obstructive sleep apnoea (n = 8), lung cancer (n = 4) and a variety of other conditions. Mamdani-type systems were the most frequently used (69%). Performance varied dramatically, with sensitivity/specificity ranging from 69 to 100% and 19-100%, respectively. The studies which displayed the highest accuracy (>95%) incorporated well-defined clinical variables, particularly for asthma and tuberculosis. However, 69% of studies displayed high risk of bias, frequently due to inadequate validation. CONCLUSIONS: Fuzzy logic systems show potential as a transparent alternative to neural network-based machine learning for outcome prediction and diagnosis in respiratory medicine. However, clinical implementation is limited by frequent methodological limitations. Future research requires prospective validation studies and standardised reporting before fuzzy logic can enhance respiratory medicine.
PRE2DUP-R, advanced, open science method to estimate drug use periods for pharmacoepidemiology.
Vattulainen P, Tanskanen A, Taipale H
Int J Med Inform · 2026 Jun · PMID 41689954 · Publisher ↗
INTRODUCTION: Valid outcome estimation in pharmacoepidemiological studies requires accurate estimation of drug use periods. This estimation becomes more precise when person-specific drug use patterns are considered. PRE2...
INTRODUCTION: Valid outcome estimation in pharmacoepidemiological studies requires accurate estimation of drug use periods. This estimation becomes more precise when person-specific drug use patterns are considered. PRE2DUP is a method to estimate drug use periods from drug purchases, based on purchased amount, sliding average of daily dose, utilizing package-level parameters, hospital care periods and personal purchase regularity over time. Objective of this study was to develop openly shared R-package of PRE2DUP named PRE2DUP-R, to compare the drug use periods created by PRE2DUP and PRE2DUP-R, and to assess the impact of using package durations derived from the study population for single purchases. METHODS: PRE2DUP-R follows the same core principles as original PRE2DUP. The main change is forming blocks of purchases to which estimation of personal use pattern calculation is restricted to. We created drug use periods with PRE2DUP and PRE2DUP-R using the same data and guiding parameters and compared the difference in the number of drug use periods and total exposure time per person and drug. In addition, the impact of updating typical package durations with PRE2DUP-R estimated package durations from study population was assessed. RESULTS: The number of drug use periods created with PRE2DUP-R was slightly larger (mean number of periods per person and drug 2.01 vs 1.88, rate ratio (RR) 1.07, 95% CI 1.07-1.08) and total exposure time was shorter (∼4 days, 1,085 vs 1,089 days). Using data driven package durations led to slightly higher number of periods (RR 1.01, 95% CI 1.01-1.02), but exposure time reduced mean of 23.8 days compared to results with original parameters. CONCLUSION: PRE2DUP and PRE2DUP-R results differed slightly, but expectedly considering the restriction in calculation of personal pattern. Change in the results after updating typical package durations highlights the importance of thorough consideration on use patterns of single purchases.
Guideline-based, but not error-free: Multilingual risks in AI-powered patient counseling on gallstones.
Erdem O, Canbak T, Acar A … +3 more , Ceylan EM, Çakıt H, Başak F
Int J Med Inform · 2026 Jun · PMID 41689953 · Publisher ↗
BACKGROUND: Patients increasingly use large language models (LLMs) for health information, yet the guideline concordance and safety of patient-facing outputs-particularly across languages-remain uncertain. We evaluated t...
BACKGROUND: Patients increasingly use large language models (LLMs) for health information, yet the guideline concordance and safety of patient-facing outputs-particularly across languages-remain uncertain. We evaluated three widely used LLM platforms (web interfaces) and their underlying default models for gallstone-related counseling in Turkish and English. METHODS: In this cross-sectional content analysis, 14 real-world, guideline-mappable patient questions were developed in Turkish and translated into semantically equivalent English. Each question was submitted once to ChatGPT (ChatGPT-4o mini), Gemini (Gemini 3-flash), and Perplexity (Sonar family; default free-tier routing at the time of testing) in both languages under standardized conditions, yielding 84 responses. Two blinded hepatobiliary surgeons independently rated each response using a prespecified 3-point guideline concordance scale (0-2) mapped to EASL 2016 gallstone guidelines and Tokyo Guidelines 2018 for acute cholecystitis; disagreements were adjudicated by a third surgeon. Within-model language differences were assessed with Wilcoxon signed-rank tests; between-model comparisons used Friedman tests. Full correctness (score = 2) was analyzed using Cochran's Q with McNemar post-hoc tests. Error types and response length were also examined. RESULTS: In English, model performance differed significantly, with ChatGPT and Gemini outperforming Perplexity (p < 0.01), while Turkish differences were not statistically significant. ChatGPT performed better in English than Turkish (p = 0.008). Error profiles were language-dependent: Turkish outputs more often showed under-explanation, whereas English outputs more frequently amplified risk. Perplexity demonstrated the highest overall error burden. . CONCLUSION: LLM responses to gallstone questions are often guideline-aligned but remain model- and language-sensitive, with clinically relevant safety risks. Multilingual evaluation standards are needed, and unsupervised reliance on LLMs for patient guidance-especially in low-resource languages-should be discouraged.
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.
Hanazawa R, Sato H, Suzuki K … +1 more , Hirakawa A
Int J Med Inform · 2026 May · PMID 41689882 · Publisher ↗
BACKGROUND: 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, althou...
BACKGROUND: 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. METHODS: 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, apolipoprotein E ε4 [APOE ε4] status, years of education, years from diagnosis, and years from disease onset) using the area under the curve (AUC). RESULTS: 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 < 0.001). Younger age (<74 years) was associated with a faster decline in MMSE and ADAS-Cog scores, but not in CDR-SB. APOE ε4 status, sex, years from diagnosis, and years from disease onset were not significantly associated with long-term progression. CONCLUSIONS: 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.
Success and failure of human-AI collaboration in clinical reasoning: An experimental study on challenging real-world cases.
Ong KT, Seo J, Kim H … +5 more , Kim J, Kim J, Kim S, Yeo J, Choi EY
Int J Med Inform · 2026 May · PMID 41689881 · Publisher ↗
BACKGROUND: While conversational human-AI collaboration (HAC) using large language models (LLM) has shown potential to enhance clinical reasoning, its effectiveness in highly specialized and challenging clinical scenario...
BACKGROUND: While conversational human-AI collaboration (HAC) using large language models (LLM) has shown potential to enhance clinical reasoning, its effectiveness in highly specialized and challenging clinical scenarios remains unclear. This study aimed to evaluate the effectiveness of HAC and analyzed the causes of its success and failure. METHODS: A crossover experimental study was conducted using 30 challenging cases from JAMA Ophthalmology. Thirty participants (10 board-certified ophthalmologist, 10 ophthalmology resident, and 10 senior medical students) completed the cases under two conditions: independent work (human-only) and collaboration through free-text conversation with Claude-3.5-Sonnet (HAC). Performance accuracy, along with self-rated confidence and cognitive burden, were assessed. HAC interaction logs were analyzed to evaluate the appropriateness of the LLM's accepting and arguing behaviors, which were categorized into six patterns. Sliding paired t-tests across incremental thresholds were used to assess how accuracy gains from HAC varied by task difficulty. RESULTS: HAC significantly improved mean accuracy compared to the human-only condition (from 0.45 to 0.60, P < 0.001), although 20% of participants showed a decline in performance and the mean remained below the LLM-only accuracy (0.70). HAC significantly increased confidence and reduced cognitive burden (both P < 0.001) in both successful and failed HAC. The appropriateness of LLM behaviors was substantially higher in successful HAC than in failed HAC (F1 score = 0.92 vs. 0.29, P < 0.001). In successful HAC, 92.6% followed the pattern LLM presents correct insight/human accepts, while 58.6% of failures involved LLM presents incorrect insight/human accepts. HAC improved accuracy significantly in tasks where the human-only correct response rate exceeded 47% (P < 0.05), but not below 30% (P ≥ 0.188). CONCLUSIONS: These findings suggest that HAC benefits complex clinical decisions in ophthalmology but remains limited by human, model, and task-level factors requiring further improvement.
BackTracker: Machine learning to identify kinematic phenotypes for personalised exercise management in non-specific low back pain.
Liu Z, Hicks Y, Sheeran L
Int J Med Inform · 2026 May · PMID 41689880 · Publisher ↗
BACKGROUND: Low back pain (LBP) is a leading cause of global disability. Most cases are non-specific (NSLBP) and lack identifiable causes. Early active management is endorsed by clinical guidelines; however, exercises ar...
BACKGROUND: Low back pain (LBP) is a leading cause of global disability. Most cases are non-specific (NSLBP) and lack identifiable causes. Early active management is endorsed by clinical guidelines; however, exercises are rarely customised despite substantial variability in impairments. Existing classification systems can support targeted rehabilitation but require extensive clinical training and lengthy assessment procedures, limiting timely personalised care. OBJECTIVE: This study used AI methods to identify the two most common motor control impairments (MCIs)-flexion and extension patterns (FP/EP)-in NSLBP. The approach used spinal silhouettes extracted from movement videos to enable self-phenotyping and guide personalised exercise selection. METHODS: Data were collected from a research fellowship involving ninety NSLBP participants classified by an expert physiotherapist (LS) into FP or EP MCIs. Participants performed standard forward- and backward-bend tasks recorded in the sagittal plane. Pose estimation and instance segmentation techniques were applied to extract motion features and spine silhouettes. From each participant, a curated set of 80 black-and-white back images captured at specific bending angles was produced. These features were used to train a feedforward neural network. Model performance was assessed using five-fold cross-validation with accuracy, sensitivity, specificity, F1 score and AUC. RESULTS: The model achieved a diagnostic accuracy of 91.91% (95% CI 84.8-99.1) for backward-bend videos, exceeding reported inter-examiner agreement rates for trained physiotherapists. Robustness was supported by a mean AUC of 0.9422. Accuracy was lower for forward-bend images (86.69%), combined tasks (86.29%), or PROMs alone (63.82%). Adding PROMs to forward- or backward-bend tasks provided only modest improvements (66.32% and 71.62%, respectively). CONCLUSION: The model reliably distinguished between FP and EP NSLBP subgroups, demonstrating the potential of AI to support timely personalised rehabilitation. The integration of PROMs with motion features reduced classification accuracy, suggesting that self-reported outcomes may provide limited benefit when tailoring exercises to specific physical impairments.
Development of a Validation and Inspection Tool for Armband-based Lifelog data (VITAL) to facilitate the clinical use of wearable health data: A prototype and usability evaluation.
Im E, Kang S, Kim H
Int J Med Inform · 2026 May · PMID 41687288 · Publisher ↗
INTRODUCTION: The growing use of wearable devices has expanded the availability of health-related data. However, despite their potential to support clinical decision making, excessive data volume, inefficient processing...
INTRODUCTION: The growing use of wearable devices has expanded the availability of health-related data. However, despite their potential to support clinical decision making, excessive data volume, inefficient processing systems, limited interoperability, and concerns regarding data quality continue to hinder their practical use in clinical settings. To advance the clinical utilization of wearable health data, we developed the Validation and Inspection Tool for Armband-based Lifelog data (VITAL), a pipeline for data integration, visualization, and quality management, and evaluated its usability. METHODS: The development of VITAL followed a structured process comprising requirement gathering, system implementation, and usability evaluation. System requirements were identified through interviews with four clinicians. Wearable health data were collected from Samsung, Apple, Fitbit, and Xiaomi devices and integrated into a standardized dataframe at 10-minute intervals. The prototype focused on three core domains: physical activity, biometrics, and sleep. Data quality was operationalized using quantifiable metrics for completeness, recency, and plausibility to enable systematic evaluation. RESULTS: VITAL provides interactive visualization and integrated data quality management functions. Usability testing was conducted through individual interviews with seven clinicians, who completed task-based evaluations and a Unified Theory of Acceptance and Use of Technology (UTAUT) survey. All participants successfully completed the assigned tasks with minimal errors. The UTAUT results indicated favorable user acceptance, with mean scores of 4.20 for performance expectancy, 3.96 for effort expectancy, and 4.14 for intention to use. Interviews further highlighted strengths in visualization and usability, while also suggesting interface simplification and the inclusion of additional clinical data types, such as electrocardiograms and dietary information. CONCLUSION: VITAL demonstrated the feasibility of harmonizing, visualizing, and evaluating wearable health data for clinical use. These findings suggest that the tool is practical and valuable for supporting clinical workflows, warranting further large-scale studies to validate its effectiveness in real-world settings.
Integrating semantic retrieval and chain-of-thought reasoning in small language models for SNOMED CT normalization.
López-Úbeda P, Martín-Noguerol T, Luna A
Int J Med Inform · 2026 May · PMID 41678976 · Publisher ↗
BACKGROUND AND OBJECTIVE: Breast lesion biopsy assessment generates a high volume of pathology reports, posing a significant workload for pathologists. Standardized coding systems such as SNOMED CT Morphological codes en...
BACKGROUND AND OBJECTIVE: Breast lesion biopsy assessment generates a high volume of pathology reports, posing a significant workload for pathologists. Standardized coding systems such as SNOMED CT Morphological codes enable consistent documentation, facilitate accurate data sharing, support clinical decision-making, and allow automated quality control. This study aims to evaluate systems that assist pathologists in normalizing and classifying free-text pathology reports to SNOMED CT Morphological codes, providing a short list of candidate codes for selection. METHODS: We used 2,718 breast biopsy pathology reports from over 20 hospitals, reported by nine expert pathologists in total. A normalization pipeline combining Small Language Models (SLMs) with semantic retrieval was evaluated to map free-text reports to SNOMED CT Morphological codes. Three strategies were evaluated: zero-shot prompting, Chain-of-Thought (CoT) with retrieval-augmented generation (RAG), and RAG combined with CoT, each generating a short list of candidate codes for pathologist selection. The strategies were assessed using ranking-oriented metrics adapted to the multi-label setting, including Hit@K, Mean Reciprocal Rank (MRR), Normalized Discounted Cumulative Gain (nDCG@K), and Recall@K, which measure both the presence and ranking of correct codes within the top-K predictions. Additionally, out-of-vocabulary (OOV) metrics were reported. RESULTS: The RAG + CoT strategy achieved the highest performance, with Hit@5 scores of 70.97% for LLaMA and 72.11% for Gemma and demonstrated a strong concentration of correct codes at Rank 1. CoT + RAG improved over zero-shot prompting but tended to place correct codes at lower ranks. CONCLUSION: Integrating SLMs with RAG and CoT provides an effective tool to support pathologists in coding breast biopsy pathology reports. By offering a short, curated list of SNOMED CT Morphological codes, the system enhances clinical workflow, improves data quality, and supports both prospective and retrospective analyses.
A systematic review of the causes of morbidity data quality issues.
Yan S, Dickson J, Cheong B … +2 more , Grain H, Oldroyd J
Int J Med Inform · 2026 May · PMID 41671617 · Publisher ↗
BACKGROUND: The quality of hospital morbidity data collected with the International Classification of Diseases is unknown. A systematic review of the causes of morbidity data quality issues is urgently needed. OBJECTIVES...
BACKGROUND: The quality of hospital morbidity data collected with the International Classification of Diseases is unknown. A systematic review of the causes of morbidity data quality issues is urgently needed. OBJECTIVES: We aimed to systematically identify and investigate the root causes of issues associated with hospital morbidity data collected using the International Classification of Diseases 10th edition, Australian Modification (ICD-10-AM) and Australian Classification of Health Interventions (ACHI). METHODS: This review included studies related to morbidity data collection issues arising from using ICD-10-AM and ACHI from Scopus, Embase, Medline and other data sources from 2017 to January 2025 in English. The quality of included studies was assessed using SQUIRE and STROBE checklists. A narrative synthesis was undertaken with themes and sub-categories of issues identified. The review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 Statement. RESULTS: Fifty-two studies were included, 37 from Australia, 3 from Canada, 2 each from Ireland and New Zealand, and 1 each from France, Germany, Turkey, US. Four themes were identified: 1) quality issues in standards, 2) technology, 3) education and training, and 4) issues related to clinical practice. There exists ambiguity in standards due to optional guidelines in data processing and jurisdictional differences. The standards do not provide sufficient granularity for precise disease identification. The standards are not capable of linking complex diagnostic, causal and procedural relationships and are leading to technical and other categories of issues. The complexity of issues associated with the standard leads to insufficient training resources for staff worldwide. Fragmented information structure and changes in clinical documentation rules lead to inconsistent coding. INTERPRETATION: The root causes of the morbidity data collection errors are mainly associated with the quality of the standards. Further research is needed to address the root causes of morbidity data quality issues, including the structure of data capture systems and the use of more consistent approaches to standards writing, such as those applied by the International Organisation for Standardisation (ISO), which is not investigated by this research.
Machine learning models for identifying urinary incontinence in women with a history of hysterectomy using basic demographic and clinical characteristics: A cross-sectional study.
Liu L, Chen W, Li L … +1 more , Zhang P
Int J Med Inform · 2026 May · PMID 41671616 · Publisher ↗
BACKGROUND: Urinary incontinence (UI) in women with a history of hysterectomy represents a significant global health concern. It is crucial to clarify the association between hysterectomy for benign indications and UI to...
BACKGROUND: Urinary incontinence (UI) in women with a history of hysterectomy represents a significant global health concern. It is crucial to clarify the association between hysterectomy for benign indications and UI to avoid unnecessary surgery. OBJECTIVE: This study aimed to develop a machine learning (ML) model to identify factors associated with UI in women with a history of hysterectomy. METHODS: We analyzed 2021 patients from the National Health and Nutrition Examination Survey (NHANES) database who underwent hysterectomy for benign indications as our derivation cohort. Thirteen demographic and clinical features were evaluated: age, educational, anthropometric measurements (height, weight, waist), medical history diabetes mellitus (DM), and reproductive history. Six ML algorithms were employed: logistic regression (LR), naïve Bayes (NB), multilayer perceptron (MLP), extreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM). External validation was performed on a cohort consisting of 556 patients from the Second Qilu Hospital of Shandong University. To improve interpretability, the predictive process was graphically illustrated employing a nomogram and SHapley Additive exPlanations (SHAP). Finally, the model was deployed as an online clinical decision support platform for applications. RESULTS: A comparison of receiver operating characteristic (ROC) curves using LR as the reference model revealed no statistically significant differences across the six ML algorithms. In the internal validation cohorts, the models achieved area-under-the-curve (AUC) values of 0.753-0.763 and accuracies between 0.627 and 0.664. This predictive performance was sustained in the external-validation cohort, with AUC values ranging from 0.702 to 0.718 and accuracies ranging from 0.661 to 0.697. CONCLUSION: Our findings demonstrated that ML models could effectively identify UI in women with a history of hysterectomy. This approach, facilitated by the nomogram and online tool, enhanced the feasibility and accessibility of identifying women at risk.
The state of standardized musculoskeletal terminology for healthcare reuse:A scoping review.
Wassell M, Butler-Henderson K, McCann P … +4 more , Pollard H, Arabi S, Wang W, Verspoor K
Int J Med Inform · 2026 May · PMID 41666757 · Publisher ↗
OBJECTIVE: Standardizing terminology offers opportunities for improved communication and care outcomes. With increasing adoption of clinical terminologies, questions remain about whether they adequately capture the scope...
OBJECTIVE: Standardizing terminology offers opportunities for improved communication and care outcomes. With increasing adoption of clinical terminologies, questions remain about whether they adequately capture the scope of musculoskeletal (MSK) primary care practice. This scoping review examines global development efforts on MSK-relevant standardized terminology and its implementation in clinical practice. METHODS: A scoping review was conducted of 6 databases to May 2025. Identified studies (n = 3668) were included (n = 60) if they addressed standardized terminology relevant to the MSK primary care professions of chiropractic, osteopathy, and physiotherapy. Data were extracted on use cases, documentation of MSK information, alignment with national interoperability standards, and implementation status. RESULTS: Global development efforts span diverse MSK domains across condition types. Five studies achieved consensus around domain-specific terms (including tendinopathies, groin pain, and weight-bearing rehabilitation); in contrast, many studies developed extensive clinical terminology sets. Most studies (82.4%) address the development of terminologies, with few yet addressing how they have been implemented into clinical practice (2.7%). Analysis revealed MSK clinicians require documentation beyond existing core interoperability data groups, including 1) function and movement, 2) pain characteristics, 3) psychosocial factors, 4) social determinants of health (environmental factors and participation barriers), 5) intervention effectiveness and clinical outcomes, and 6) person-centered factors. Multiple barriers emerged, including technical (EHR integration, cognitive burden), workflow (time requirements, clinical value), professional (training, profession-specific terminology), and knowledge gaps (impact on care quality). CONCLUSION: Extensive terminology development has begun yet gaps exist between development and clinical adoption. Terms evolve as research evolves; therefore, MSK professions should actively engage with interoperability groups to establish hierarchical ontologies that incorporate the identified data groups and balance standardization at higher conceptual levels with flexible lexicons to enable terminology growth over time. Establishing feedback mechanisms with EHR vendors to minimize clinicians' cognitive burden will accelerate adoption and maximize clinical value.
The effect of artificial intelligence-assisted pulmonary rehabilitation on exercise capacity: A systematic review and meta-analysis.
Cinkavuk E, Calik E, Vardar-Yagli N
Int J Med Inform · 2026 May · PMID 41655523 · Publisher ↗
INTRODUCTION: Artificial intelligence (AI) technologies are increasingly being integrated into pulmonary rehabilitation (PR) to improve individualization, real-time monitoring, and adherence in individuals with chronic r...
INTRODUCTION: Artificial intelligence (AI) technologies are increasingly being integrated into pulmonary rehabilitation (PR) to improve individualization, real-time monitoring, and adherence in individuals with chronic respiratory diseases. However, their clinical impact on exercise capacity remains unclear. This systematic review and meta-analysis aimed to evaluate the effectiveness of AI-supported PR programs compared to usual care in improving exercise capacity and respiratory function in adults with chronic respiratory diseases. METHODS: This systematic review and meta-analysis followed PRISMA guidelines and was registered with PROSPERO (ID: CRD420251075622). A comprehensive search was conducted across five electronic databases (PubMed, Web of Science, Scopus, Cochrane Central Register of Controlled Trials (CENTRAL) and PEDro) from inception to July 2025. Statistical analyses for the meta-analysis were conducted using RevMan 5.4. RESULTS: Three eligible RCTs with a total of 456 participants were included. Pooled analysis showed a significant improvement in 6-minute walk distance (6MWD) after AI-assisted PR group compared to control (MD: 22.08 m; 95% CI: 4.96-39.20; p = 0.01). Moderate heterogeneity was observed (I = 40%). No meta-analysis was conducted for respiratory function due to insufficient pre-post data. Risk of bias was generally low, though participant blinding was absent in all studies. Methodological quality was good, with a mean PEDro score of 6.0 ± 0.82. CONCLUSION: AI-supported PR can significantly improve exercise capacity in individuals with chronic respiratory diseases. Despite promising results, high-quality studies in different pulmonary patient groups are needed to address existing limitations, particularly regarding standardization, cost-effectiveness, and clinical integration of AI-technology.
Large language models as second reviewers for medical errors in real-world internal medicine reports: a prospective comparative study of open- and closed-source models.
Skrabic R, Viculin I, Boban Z … +4 more , Kumric M, Vilovic M, Vrdoljak J, Bozic J
Int J Med Inform · 2026 May · PMID 41655522 · Publisher ↗
OBJECTIVE: Preventable errors in clinical documentation and decision-making remain a major threat to patient safety, yet the role of open-source large language models (LLMs) as practical "second reviewers" in general Int...
OBJECTIVE: Preventable errors in clinical documentation and decision-making remain a major threat to patient safety, yet the role of open-source large language models (LLMs) as practical "second reviewers" in general Internal Medicine remains unclear. METHODS: We prospectively assembled 102 real-world Emergency Internal Medicine reports (de-identified) and either inserted or confirmed realistic errors across four categories (diagnostics/investigations, medication/therapy, process/communication/follow-up, other). Three LLMs (open-source Deepseek-v3-r1 and GPT-OSS-120b, and closed-source OpenAI-o3) were prompted with a uniform system instruction to (i) localize the predefined error and (ii) recommend corrections. Two blinded Internal Medicine specialists independently graded outputs for error localization (0-1) and recommendation quality (Likert 1-4); disagreements were resolved analytically, and analyses used the more conservative rater. Three human clinicians independently reviewed subsets of the same cases to provide a comparator. RESULTS: Using the conservative rater, correct error localization was 72.5% (74/102; 95% CI 63.2-80.3) for Deepseek-v3-r1, 79.2% (80/101; 95% CI 70.3-86.0) for o3, and 65.7% (67/102; 95% CI 56.1-74.2) for GPT-OSS-120b (Cochran's Q p = 0.033). Pairwise McNemar tests favored o3 over GPT-OSS-120b (p = 0.020; Holm-adjusted p = 0.060); other contrasts were not significant. Recommendation quality was high for all models (median 4/4), with mean ± SD scores of 3.73 ± 0.49 for Deepseek-v3-r1, 3.65 ± 0.64 for o3, and 3.51 ± 0.73 for GPT-OSS-120b. Inter-rater agreement was excellent for GPT-OSS-120b (κ = 0.94 for detection; κ_w = 0.85 for quality), substantial for Deepseek-v3-r1 (κ = 0.75; κ_w = 0.47), and lower for o3 (κ = 0.31; κ_w = 0.14). All models frequently flagged additional clinically useful issues (≥99% of reports). CONCLUSION: In real-world Internal Medicine reports with realistic, expert-defined errors, state-of-the-art open-source LLMs approached the performance of a leading closed model and clearly outperformed clinicians in error detection, while providing predominantly guideline-concordant corrective recommendations. Given their advantages for privacy, customizability, and potential local deployment, open models represent credible candidates for privacy-preserving "second-reviewer" support in Internal Medicine. Prospective, workflow-embedded trials that also quantify specificity on error-free notes, alert burden, and patient outcomes are now warranted.
Explainable AI in Cardiology Diagnostics: A Systematic Review of Machine Learning, Meta-heuristic Optimization, and Clinical Text Mining for Coronary Artery Disease.
Jaradat M, Awad M
Int J Med Inform · 2026 May · PMID 41653696 · Publisher ↗
BACKGROUND: This systematic review compiles evidence and examines how various artificial intelligence (AI) approaches, including machine learning (ML), natural language processing (NLP), meta-heuristic optimization, and...
BACKGROUND: This systematic review compiles evidence and examines how various artificial intelligence (AI) approaches, including machine learning (ML), natural language processing (NLP), meta-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. METHOD: 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. RESULTS: 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. CONCLUSION: Integrated ML, NLP, meta-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.
Case-based reasoning for clinical trial recruitment tools in oncology: When you need patients to find patients.
Guillotel LA, Lesimple T, Zekri O … +2 more , Cuggia M, Campillo-Gimenez B
Int J Med Inform · 2026 May · PMID 41653695 · Publisher ↗
BACKGROUND: Patient recruitment for clinical trials remains a major challenge, with 86% of trials failing to meet enrollment targets on time. In over 77% of cases, recruitment difficulties stem from matching problems bet...
BACKGROUND: Patient recruitment for clinical trials remains a major challenge, with 86% of trials failing to meet enrollment targets on time. In over 77% of cases, recruitment difficulties stem from matching problems between trials and patients. Case-Based Reasoning (CBR) offers a distinct patient-to-patient approach by determining eligibility through comparison with previously enrolled patients, yet this methodology remains underexplored in contemporary oncology trial matching despite its potential advantages. OBJECTIVE: To compare the performance of two CBR approaches-random forest (RF) and target patient similarity (TPS)-in predicting patient eligibility for recent oncology clinical trials using real-world electronic health record data. METHODS: We selected three breast cancer clinical trials (2019-2022) from our institutional registry. Patient data were extracted from our clinical data warehouse, including structured data (laboratory results, diagnosis codes, procedures, treatments) and unstructured clinical narratives processed using natural language processing. For each trial, we trained RF classifiers and TPS models using repeated hold-out validation (25 splits, 70/30 train-test). Performance was evaluated using discriminative metrics (AUC, positive precision, recall, F1-score) and ranking metrics (P@5, P@10, MAP, MRR, NDCG@5, NDCG@10). We analyzed model performance across varying numbers of eligible patients in training datasets (2 to 70% of the total number of eligible patients). RESULTS: Both approaches demonstrated strong discriminative performance across three trials, with average AUCs of 84.1 % for RF and 76.4 % for TPS, driven primarily by high recall (82.3 % and 77.7 %, respectively). However, positive precision remained low (13.3 % and 9.9 %), reflecting high false-positive rates due to class imbalance. RF showed superior ranking performance, particularly for the trial with the largest eligible cohort (n = 542; P@5 = 78.6 %, MRR = 88.0 %), compared to TPS (P@5 = 47.9 %, MRR = 69.2 %). Both approaches reached performance plateaus with only around 10 eligible patients in training datasets. Variable importance analysis revealed that treatment-related features, diagnostic codes, and procedures were consistently the most important predictors, with relevant patterns identified even with minimal training data. CONCLUSIONS: CBR approaches can effectively support patient pre-screening for oncology clinical trials, with RF demonstrating moderately superior performance over TPS. Both methods show robust discriminative performance with small training datasets, though ranking performance varies substantially across trials. Our findings suggest that CBR approaches may benefit from integration with query-based or prompt-based methods during early recruitment phases when training data is scarce.
Digital literacy training within interventions to support older adults with cardiovascular disease in using technologies: a systematic review.
Rush KL, Seaton CL, Ross R … +6 more , Robertson T, Louloudi AI, Loewen P, Haase KR, Jakobi J, Janke R
Int J Med Inform · 2026 May · PMID 41650700 · Publisher ↗
BACKGROUND: Advancement in digitalization in the health sector have created numerous opportunities for cardiovascular disease (CVD) self-management but also challenges, especially for older adults with lower digital heal...
BACKGROUND: Advancement in digitalization in the health sector have created numerous opportunities for cardiovascular disease (CVD) self-management but also challenges, especially for older adults with lower digital health literacy. Reviews have examined impacts of digital health technology interventions on health outcomes without examining the role of training provided. The aim of this review is to synthesize evidence about the impacts of digital literacy training (DLT) and its characteristics as a component of digital interventions related to cardiovascular health on patient reported outcome and experience measures among older adults with CVD. METHODS: In accordance with the 2020 Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, a search of MEDLINE, EMBASE, CINAHL, and PsycINFO databases for articles published between inception to March 31, 2025 was conducted. Empirical studies reporting digital health technology training with adults (M age 60 + years) with CVD were eligible for inclusion. Articles included were quality-rated using the Mixed Methods Appraisal Tool. Data were extracted according to the DLT and health technologies alongside patient-reported outcome (i.e technology- and health-related) and experience measures. RESULTS: Of the 56 included studies (totaling 7698 participants), DLT varied considerably, with 51 describing in-person training. Two studies (totaling 519 participants) examined the role of training with positive impacts on technology- and health-related outcomes. In many of the remaining studies, positive technology-related outcomes were evident but could not be linked back to DLT separate from the overall intervention. In studies (n = 10) where training was evaluated, feedback from patients largely affirmed the training was needed. DISCUSSION: The collective evidence suggests DLT overall is useful and needed in digital interventions for older adults with CVD. More work is needed to elucidate the distinct role of DLT characteristics and to determine for whom and under what conditions DLT impacts health and technology-related outcomes. REGISTRATION: The protocol for this review was registered Aug 12, 2024 in Open Science Framework (OSF) (See: https://osf.io/unhd9).
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.
Rosalba CC, Alessia C, Carlos BJ … +8 more , Roberto CC, Paula DJ, José J GC, Lennert G, Francisco J NC, Amalia UL, Irene GG, Emma M
Int J Med Inform · 2026 May · PMID 41650699 · Publisher ↗
BACKGROUND: 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 numerou...
BACKGROUND: 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 e-Perinatal study aimed to address this gap. This paper describes the design of the e-Perinatal intervention, delivered via a dedicated mobile health app. METHODS: Guided by the Medical Research Council framework, the e-Perinatal 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. RESULTS: The e-Perinatal 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. CONCLUSION: the e-Perinatal app is a personalized mHealth intervention toprevent 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 e-Perinatal intervention for PMD prevention.
Harmonizing patient-reported outcome measures for nasal complaints using traditional and machine learning methods.
Jović M, Hof E, Haeri MA … +2 more , Hoorweg JJ, van den Berg SM
Int J Med Inform · 2026 May · PMID 41650698 · Publisher ↗
BACKGROUND: 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, a...
BACKGROUND: 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. THE AIM: 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. METHODS: 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. RESULTS: 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). CONCLUSION: 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.
Clinical-radiological machine learning model for non-invasive diagnosis and stratification of peripheral artery disease: a multicenter study.
Hou B, Qiao J, Ran Z … +4 more , Li Y, Huang Z, Luo X, Li X
Int J Med Inform · 2026 May · PMID 41650697 · Publisher ↗
BACKGROUND AND OBJECTIVE: Peripheral artery disease (PAD) is an atherosclerotic disorder prevalent in the elderly that leads to peripheral function decline and body composition changes. Current diagnostic approaches lack...
BACKGROUND AND OBJECTIVE: Peripheral artery disease (PAD) is an atherosclerotic disorder prevalent in the elderly that leads to peripheral function decline and body composition changes. Current diagnostic approaches lack sensitivity for early PAD detection and staging. This study aimed to develop and validate machine learning (ML) models of clinical and CT-based radiological features to improve PAD diagnosis and severity stratification. METHODS: A retrospective multicenter study was conducted using data from two institutions. Clinical and radiological features (including volumetric body composition and muscle texture parameters extracted from calf and thigh segments) were analyzed. Participants were randomly divided into training (70%) and test (30%) sets, stratified by PAD status. Models with different ML algorithms were developed and compared. Model interpretability was assessed with Shapley additive explanation (SHAP) analysis, and performance was evaluated through receiver operating characteristic analysis, Hosmer-Lemeshow testing, Brier score and calibration curves. RESULTS: This study comprised 342 participants, divided into training (n = 176), test set (n = 76) from Institute 1, external validation (n = 90) from Institute 2. Three models were developed: clinical model (CM), radiological model (RM), and combined clinical-radiological model (CRM). The calf-based CRM using random forest algorithm achieved area under the curves of 0.871 (training), 0.870 (test), and 0.828 (validation), demonstrating good calibration (p ≥ 0.05) and the low Brier score. SHAP analysis visually interpreted feature contributions toward PAD diagnosis and staging. CONCLUSIONS: The CRM model effectively integrated calf-derived radiological and clinical features into a noninvasive, interpretable tool for PAD diagnosis and severity stratification, demonstrating strong clinical applicability.
Development of an interpretable machine learning model for predicting 4-year chronic kidney disease risk in elderly hypertensive patients.
Wang P, Meng Y, Sun Z … +2 more , Li J, Tao H
Int J Med Inform · 2026 May · PMID 41638116 · Publisher ↗
INTRODUCTION: 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 mo...
INTRODUCTION: 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. METHODS: 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. RESULTS: 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 > 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. CONCLUSIONS: 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.
About
- Frequency
- Sun
- Papers found
- 200
- RSS feed
- Subscribe