BMC Medical Informatics and Decision Making最新文献

{"title":"Machine learning-based prediction model for predicting the impact of insulin resistance on the risk of ischemic cardiomyopathy.","authors":"Tuersunjiang Naman, Hui Cheng, Xiao-Lin Yu, Zi-Tong Guo","doi":"10.1186/s12911-026-03693-w","DOIUrl":"10.1186/s12911-026-03693-w","url":null,"abstract":"<p><strong>Background: </strong>The triglyceride-to-high-density lipoprotein cholesterol (TG/HDL-C) ratio and triglyceride glucose-body mass (TyG-BMI) index are reliable indicators of insulin resistance (IR). This study investigated their association with ischemic cardiomyopathy (ICM) and developed a machine learning-based model for ICM risk prediction.</p><p><strong>Methods: </strong>In total, 1,603 subjects participated in this study. Univariable logistic regression analysis was conducted, and variables with P < 0.05 were selected for multivariable logistic regression to identify independent risk factors for ICM. Variables meeting this criterion were adopted to create eight machine learning models, from which the optimal model was selected. Using this best-performing model, SHAP values were visualized, and an online calculator was developed. The model was validated via a calibration plot and DCA.</p><p><strong>Results: </strong>Univariate and multivariate logistic regression analyses revealed that TyG-BMI, age, ejection fraction, TC/HDL-C, sex, HDL-C, TC, BMI, hemoglobin, diabetes, and hypertension were independent risk factors for ICM (P < 0.05). Based on these factors, SHAP visualization and an online calculator were developed. The calibration plot indicated strong alignment between the model's predicted and actual values, whereas the DCA demonstrated the model's clinical utility.</p><p><strong>Conclusion: </strong>The TyG-BMI and TC/HDL-C ratio independently predict ICM risk, with the XGB model identified as the most effective for ICM risk prediction, indicating substantial clinical applicability.</p><p><strong>Clinical trial registration number: </strong>Not applicable.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"26 1","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13523236/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148849859","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":"Decentralized rare disease studies in Germany: first results and hurdles of secondary use of patient data.","authors":"Michele Zoch, Christian Gierschner, Jens Weidner, Martin Sedlmayr, Gabriele Müller, Daniela Choukair, Georg F Hoffmann, Nicole Toepfner, Reinhard Berner, Fabian Prasser, Josef Schepers, Helge Hebestreit","doi":"10.1186/s12911-026-03688-7","DOIUrl":"10.1186/s12911-026-03688-7","url":null,"abstract":"<p><strong>Background: </strong>The research challenges associated with rare diseases is characterized by a scarcity of information as well as reliable data due to their low prevalence. The problem of the \"underpowered studies\" is stemmed from a small research community, limited study participants and scarce data. The German project \"Collaboration on Rare Diseases - Medical Informatics\" (CORD-MI), tackles these problems by improving research opportunities and patient care by employing innovative IT solutions for collaborative data use across 20 German university hospitals. One possibility was to conduct decentralized studies based on secondary data. Three studies based on four rare diseases served as examples: (1) Cystic Fibrosis (CF), (2) Phenylketonuria (PKU), and (3) Kawasaki Disease and Multisystem Inflammatory Syndrome in Children (MIS-C).</p><p><strong>Methods: </strong>All three decentralized studies were conducted using routine inpatient data from German university hospitals. For each use case, an interdisciplinary team defined research questions, created analysis scripts based on the Core Data Set of the Medical Informatics Initiative (MII), executed these locally at participating sites, and aggregated anonymized results for descriptive statistical analysis. A frequency threshold rule was applied to protect patient privacy. Study protocols and analysis scripts for data extraction and evaluation are publicly available, and the studies were reported in detail in accordance with the Reporting of Studies Conducted Using Observational Routinely-Collected Health Data (RECORD) Statement.</p><p><strong>Results: </strong>Results from up to 17 German university hospitals were achieved for all three decentralized studies. The challenges in the areas of health care process bias, inaccurate coding of rare diseases, difficult verification of study results, and loss of information due to masking of small study case numbers as well as imprecise definition of the cohorts are discussed.</p><p><strong>Conclusions: </strong>Naming the hurdles enables the identification of areas for improvements, which will be the base for the development of new approaches or adaptations of existing tools and methodologies for the future. Although adaptation would make an impact, the initial results already show that decentralized analyses based on secondary use of patient data can improve research and thus also the care for people with rare diseases.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"26 1","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13471175/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148719574","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 word and the way: strategies for domain-specific BERT pre-training in German medical NLP.","authors":"Henry He, Johann Frei, Raphael Schmitt","doi":"10.1186/s12911-026-03728-2","DOIUrl":"10.1186/s12911-026-03728-2","url":null,"abstract":"<p><strong>Background: </strong>Digital healthcare generates vast amounts of clinical texts that hold potential for AI-assisted applications. However, existing German biomedical language models either rely on older architectures or are trained on limited data, which may hinder their performance in real-world settings.</p><p><strong>Methods: </strong>To explore the impact of domain adaptation strategies in German clinical NLP, we developed a family of domain-specific RoBERTa-based language models, collectively referred to as ChristBERT (Clinical- and Healthcare-Related Issues and Subjects Tuned BERT). To address the lack of large-scale German clinical corpora, we curated a 13.5 GB dataset consisting of scientific publications, clinical texts, and health-related web content. Additionally, we employed data augmentation via translation of English clinical corpora. Three domain adaptation strategies were explored: continued pre-training, pre-training from scratch, and pre-training with domain-specific vocabulary adaptation.</p><p><strong>Results: </strong>The resulting models were evaluated on three medical named entity recognition and two text classification tasks. Our models consistently outperformed four existing general-purpose and medical German models on four out of five tasks. The results demonstrate that the choice of domain adaptation strategy significantly influences downstream task performance. Based on the empirical results, pre-training from scratch is effective for highly specialized clinical texts, whereas continued pre-training is suited for more commonly written medical texts.</p><p><strong>Conclusions: </strong>ChristBERT establishes a new state-of-the-art for German clinical language modeling. Our findings indicate that the optimal domain adaptation strategy is task-dependent and remains crucial, as adapted models consistently outperformed general-purpose language models in our experiments. To support further research and application in German medical NLP, all developed models are publicly released.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"26 1","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13449853/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148683448","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":"GERBEHRT: a BERT-based model tailored for German electronic health records - potential in chronic kidney disease prediction.","authors":"Anja Seidel, Edgar Steiger, Friedrich Alexander von Samson-Himmelstjerna, Lars Eric Kroll","doi":"10.1186/s12911-026-03733-5","DOIUrl":"10.1186/s12911-026-03733-5","url":null,"abstract":"<p><strong>Background: </strong>Chronic kidney disease (CKD) is a critical, progressive condition associated with high mortality and substantial healthcare costs. Early detection is essential, as it can slow disease progression and improve patient outcomes. With the increasing availability of large-scale electronic health records (EHRs), the question arises to what extent these data, when combined with machine-learning algorithms specifically tailored to EHR characteristics, can enhance personalized CKD risk prediction.</p><p><strong>Methods: </strong>We developed a transformer model adapted from BEHRT (Bidirectional Encoder Representations from Transformers for EHRs) and specifically tailored for German (GER) EHRs, which we refer to as GERBEHRT. GERBEHRT was pre-trained on outpatient claims data from more than 9 million statutorily insured patients and fine-tuned with nearly 1 million additional patients to predict CKD. The model incorporates EHR features not previously explored in BERT-based approaches and introduces an efficient method to represent multiple attributes per medical concept, such as diagnoses and medications. GERBEHRT was compared with more traditional models and predictions restricted to established risk factors, and the importance of its input features was assessed through an ablation study.</p><p><strong>Results: </strong>In a test cohort of 3.7 million patients with 1.5% CKD positives, GERBEHRT achieved an area under the receiver operating characteristic curve (AUROC) of 87.9% and an average precision (AVPR) of 11.4% for the three-year prediction of incident moderate-to-severe CKD, outperforming risk-factor-based models (AUROC/AVPR: 83.6/6.4%) and more traditional algorithms using the full EHR (AUROC/AVPR: 86.9/10.1%).</p><p><strong>Conclusions: </strong>Predicting moderate-to-severe CKD based on real-world EHRs remains challenging. However, our proposed architecture was able to make more accurate predictions than traditional approaches and feature sets, underscoring the importance of comprehensive EHR utilization and the potential of tailored deep learning models for personalized CKD risk prediction and targeted patient screening.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"26 1","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13445917/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148677398","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":"Correction: Diagnostic performance of machine learning and deep learning algorithms for thyroid cancer metastasis: a systematic review and meta-analysis.","authors":"Mohammad Amouzadeh Lichahi, Saeid Anvari, Hossein Hemmati, Ervin Zadgari, Maryam Jafari, Seyedeh Mohadeseh Mosavi Mirkalaie, Mohaya Farzin, Amirhossein Larijani","doi":"10.1186/s12911-026-03708-6","DOIUrl":"10.1186/s12911-026-03708-6","url":null,"abstract":"","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"26 1","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13393856/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148560482","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":"Based on the middle ear negative pressure and multimodal data to construct and externally validate the predictive model for pediatric obstructive sleep apnea.","authors":"Simin Zhu, Yewen Shi, Yanuo Zhou, Lina Ma, Yonglong Su, Zitong Wang, Chendi Lu, Zine Cao, Xiaoxin Niu, Yushan Xie, Zihan Xia, Huanhuan Chang, Yuqi Yuan, Jiayi Yang, Rui Lu, Haiqin Liu, Xiaoyong Ren, Wei Hou","doi":"10.1186/s12911-026-03696-7","DOIUrl":"https://doi.org/10.1186/s12911-026-03696-7","url":null,"abstract":"<p><strong>Purpose: </strong>The aim of this study was to analyze negative middle ear pressure in children with obstructive sleep apnea (OSA) and establish and evaluate predictive models according to these findings.</p><p><strong>Methods: </strong>This retrospective study involved 931 children: 715 with OSA and 216 controls. Demographic, clinical, lateral head radiograph, and tympanometry data were collected. These characteristics of children with OSA were analyzed, with a particular focus on exploring the value of middle ear-related parameters for the diagnosis of pediatric OSA. Additionally, a logistic regression model incorporating optimal indicators was developed to predict pediatric OSA. The model was visualized via a nomogram and evaluated for discrimination, calibration, clinical effectiveness and external validation.</p><p><strong>Results: </strong>Children with OSA were younger and exhibited longer soft palates, larger tonsils and adenoids than non-OSA children. Additionally, children with OSA presented higher acoustic admittance (AC) and resonance frequency (RF), lower middle ear pressure (MEP), and narrower pressure gradient (PG) than non-OSA children. The external auditory canal volume (ECV), MEP, and PG were identified as independent predictors of childhood OSA. We constructed a foundational prediction model for childhood OSA (Model 0, AUC = 0.845, 95% CI: 0.813-0.878), and then added each tympanometric indicator to the model individually. After incorporating MEP into the model (Model 4), the AUC increased by 0.022 (p < 0.05).</p><p><strong>Conclusions: </strong>Based on a large sample size and multivariate analysis of factors associated with pediatric OSA, we developed a predictive model incorporating middle ear negative pressure for pediatric OSA, which may assist clinicians in diagnosing pediatric OSA in complex clinical settings.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148547897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Provider perspectives of clinical decision support for chronic kidney disease management: a cross-sectional study.","authors":"Robert Goldberg, Henry Li, Cory E Goldstein, Kevin Yau, Shannon M Ruzycki, Maoliosa Donald, Meghan J Elliott, Brenda R Hemmelgarn, Matthew T James, Pietro Ravani, Neesh Pannu, Derek Chew, Dilaram Acharya, Tyrone G Harrison","doi":"10.1186/s12911-026-03721-9","DOIUrl":"https://doi.org/10.1186/s12911-026-03721-9","url":null,"abstract":"<p><strong>Background: </strong>Chronic kidney disease (CKD) affects approximately one in ten adults globally. Multiple studies have identified underuse of effective therapies in eligible patients with CKD despite guideline endorsement. Clinical decision support (CDS) may increase confidence in prescribing recommended medications, but how end-users perceive it is unknown.</p><p><strong>Objectives: </strong>To evaluate clinician-reported perspectives and acceptability of CDS elements for ambulatory CKD management and inform the development of a CKD-specific CDS intervention.</p><p><strong>Methods: </strong>Eligible participants for this electronic cross-sectional study were prescribing clinicians from Alberta, Canada, that practiced in ambulatory care settings, including physicians, nurse practitioners, and pharmacists. The survey presented examples of a proposed CDS' content and format, and collected information on clinician demographics, CKD workflows, perceptions of CDS design, perceived acceptability and clinical utility. Knowledge, comfort, and prescribing patterns were examined for renin-angiotensin system inhibitors (RASi), statins, sodium-glucose cotransporter-2 inhibitors (SGLT2i), glucagon-like peptide-1 receptor agonists (GLP-1RA), and non-steroidal mineralocorticoid receptor agonists (nsMRA). Participant comfort prescribing each medication class was compared using mean paired differences before and after viewing the proposed CDS.</p><p><strong>Results: </strong>Between May and June 2025, 137 clinicians engaged with the survey, 131 completed demographics and 111 completed all survey elements. Most were nephrologists (n = 42; 32%) or general internal medicine specialists (n = 36; 27%). Overall, 88 (79%) supported CDS integration. RASi had the highest self-reported comfort with prescribing followed by statins, SGLT2i, GLP-1RA, and nsMRA. Clinicians reported higher comfort prescribing GLP-1RA and nsMRA with CDS support (median +1 on 9-point scale; p < 0.001), but no change for RASi, statins, and SGLT2i. Participants with low baseline comfort (≤6 on 9-point Likert scale) had statistically significant improvements in comfort with CDS for GLP-1RA and nsMRA (p < 0.05), but no change was observed for those with high baseline comfort.</p><p><strong>Conclusions: </strong>Clinicians support CDS integration to enhance CKD care in ambulatory settings. The proposed CDS increased perceived prescribing confidence, particularly for GLP-1RA and nsMRA.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":" ","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148547890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI-assisted decision support for sickle cell disease severity stratification using routine blood tests: a systematic review and meta-analysis.","authors":"Naif Taleb Ali, Mansour Abdulnabi H Mehdi, Radfan Saleh Abdullah, Gamila Saleh Ali, Hana Mohsen Ali, Ali N M Gubran, Nazeh Mohammed Al-Abd","doi":"10.1186/s12911-026-03679-8","DOIUrl":"https://doi.org/10.1186/s12911-026-03679-8","url":null,"abstract":"<p><strong>Background: </strong>Stratifying sickle cell disease (SCD) severity remains challenging, particularly in resource-limited settings. Artificial intelligence (AI) models using routine complete blood count (CBC) parameters have been proposed as accessible tools for risk stratification; however, their overall performance and clinical applicability remain uncertain.</p><p><strong>Methods: </strong>We conducted a PRISMA-DTA 2020-compliant systematic review and meta-analysis (PROSPERO: CRD420251078389) including 60 studies (25,354 patients across 15 countries, 2010-2025). AI models based on CBC parameters were evaluated against heterogeneous reference standards, including clinical severity classifications and event-based outcomes. Risk of bias was assessed using QUADAS-2 and PROBAST-AI. Pooled estimates were generated using hierarchical summary receiver operating characteristic (HSROC) models.</p><p><strong>Results: </strong>The pooled area under the curve (AUC) was 0.87 (95% CI: 0.84-0.90), with sensitivity 0.83 (0.79-0.86) and specificity 0.85 (0.81-0.88). Performance varied by setting, with higher accuracy in high-income countries (AUC 0.90) compared with low- and middle-income settings (AUC 0.82; p < 0.001). Red cell distribution width and platelet count were consistently identified as important predictors. However, substantial heterogeneity in outcome definitions and reference standards limits interpretability.</p><p><strong>Conclusions: </strong>AI models using routine CBC parameters demonstrate promising analytical performance for SCD risk stratification. However, the absence of a universally accepted severity gold standard, variability in outcome definitions, and differences across healthcare settings limit direct clinical applicability. These findings support cautious prospective validation and clinical utility assessment before consideration of broader real-world implementation.</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":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148535322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clinical decision support system for child and adolescent mental health services: a formative usability study.","authors":"Carolyn E Clausen, Dipendra Pant, Roman Koposov, Øystein Nytrø, Bennett Leventhal, Stian Lydersen, Odd Sverre Westbye, Thomas Brox Røst, Norbert Skokauskas","doi":"10.1186/s12911-026-03720-w","DOIUrl":"https://doi.org/10.1186/s12911-026-03720-w","url":null,"abstract":"<p><strong>Background: </strong>Child and adolescent mental disorders are creating significant demands on Norway's general and specialized health services. Addressing these demands requires innovative approaches to increase workforce numbers and effectiveness. The Individualized Digital Decision Assist System (IDDEAS) is a Clinical Decision Support System (CDSS) for child and adolescent mental health services in Norway. IDDEAS 1.0 is a guidelines-based prototype with attention-deficit/hyperactivity disorder (ADHD) as the first model clinical paradigm. IDDEAS 1.0 is the focus of a formative usability study to examine clinicians' information processing needs and their perceptions of the acceptability, functionality and ease of interactions with user interface (UI) and user-experience (UX).</p><p><strong>Methods: </strong>In collaboration with the Norwegian Association for Child and Adolescent Mental Health (N-BUP) a provisional list of practitioners in child and adolescent mental health services (CAMHS) was compiled for recruitment of potential participants. Child and adolescent psychologists and psychiatrists (n = 68) completed IDDEAS formative usability testing. Study participants also completed a think-aloud protocol in which they verbalized their thoughts about the experience in real time while assessing hypothetical patient case vignettes. By observing these representative, potential IDDEAS users, developers gain insight from their interactions with the prototype. A self-developed display and functional ease-of-use questionnaire, as well as the IDDEAS modified system usability scale and user engagement scales, were completed. All qualitative data were analyzed using both protocol analysis and content analysis.</p><p><strong>Results: </strong>Examination of the formative usability identified a participant appreciation of the side-by-side guideline/patient view, simplistic UI presentation, and alignment with their diagnostic routines. 89% of usability comments informed next-step improvements pinpointing forced linear navigation, ADHD focused prototype, and ambiguous prompts. This resulted in proposed enhancements centered on dynamic criteria selection, optional guideline choice, individualized content, and seamless electronic health records integration.</p><p><strong>Conclusion: </strong>The scenario-based exploration of the IDDEAS 1.0 prototype allowed CAMHS clinicians to offer honest reflections about receiving decision-support, and what they might potentially need for such support to enhance their clinical decision-making and information processing at the point of care. Functional adjustments in IDDEAS were recommended, with a focus on workflow cohesion and individualized adaptability for optimal ease of use and personalized patient care.</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":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148535375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"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":"https://doi.org/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":"","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":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}