Journal of Medical Systems最新文献

{"title":"Mapping Rare Disease Registries in Brazil: Situational Analysis and Proposal for National Unification.","authors":"Filipe Andrade Bernardi, Bibiana Mello de Oliveira, Natan Monsores de Sá, Domingos Alves, Têmis Maria Félix","doi":"10.1007/s10916-026-02442-w","DOIUrl":"10.1007/s10916-026-02442-w","url":null,"abstract":"<p><p>Rare disease registries in Brazil remain fragmented across federal, state, and local initiatives, limiting the availability of reliable epidemiological information to support diagnosis, care planning, research, and public policy. This study aimed to map existing rare disease registry entities and registry-related initiatives in Brazil and to propose practical guidelines for their unification into an integrated national registry. We conducted a descriptive, exploratory mapping study combining a structured literature search with documentary analysis of public policies, health information systems, registry portals, institutional reports, and legislative documents related to rare diseases in Brazil. PRISMA-S was used to report the search component, and a PRISMA-style flow diagram documented source identification and selection. We identified a rapidly evolving legislative landscape, including federal bills proposing a national monitoring system or registry and recent state-level statutes related to identification and observatories. Using an expanded, auditability-oriented inventory definition, we mapped 28 registry entities and registry-related initiatives. Of these, 24 are implemented, three are legislative proposals, and one is under development. Among the 24 implemented initiatives, 16 are national or multicentre, Brazil-based initiatives; three are state-level; four are regional/local; and one is a transnational registry with documented participation of a Brazilian cohort. Registry creation and registry-related activity accelerated after 2018, particularly between 2020 and 2026. We conclude that Brazil exhibits substantial data fragmentation across uncoordinated systems. A unified approach should integrate epidemiological data from existing networks, state notification systems, specialised hospital registries, and technology appraisal information under coordinated governance, while embedding privacy-by-design and information security safeguards.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13385086/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148520543","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":"Recent Advances in AI for Automated ICD Coding: A Systematic Literature Review.","authors":"Abdul Rehman Khalid, Haider Ali, Kounen Fathima, Kouayep Sonia Carole, Hee-Cheol Kim","doi":"10.1007/s10916-026-02429-7","DOIUrl":"10.1007/s10916-026-02429-7","url":null,"abstract":"<p><p>International Classification of Diseases (ICD) codes enable correct billing, insurance reimbursement, and healthcare analytics. However, manual coding is time-consuming, expensive, and error-prone, creating bottlenecks in clinical workflow and limiting scalability. Artificial intelligence (AI) has emerged as a promising solution for automated ICD code assignment from unstructured clinical text. This systematic review explores the current state of automated ICD coding research, examining models applied to diverse clinical documents including discharge summaries, electronic health records, nursing notes, and pathology reports. Following PRISMA guidelines, we searched six databases for studies published between 2019 and 2024, selecting 54 relevant studies from 4,280 initial citations. Our analysis reveals the use of diverse datasets, preprocessing techniques, and feature extraction methods, alongside a clear evolution from traditional machine learning to deep learning approaches, with substantial architectural diversity across convolutional, recurrent, transformer, and hybrid models. Performance varies considerably across dataset configurations, with models achieving higher accuracy on frequent code subsets compared to full label spaces. However, critical gaps persist: overreliance on single-language, single-institution datasets limits generalizability; difficulties in predicting rare codes remain unresolved; lack of model interpretability undermines clinical trust; and inconsistent evaluation protocols hinder meaningful comparison. To address these challenges, we propose a 5P evidence-grounded research agenda: Population Diversity, Performance Robustness, Prediction of Rare Codes, Provenance Transparency, and Practical Integration. These findings underscore AI's potential to transform ICD coding while highlighting the need for standardized benchmarks, rigorous external validation, multilingual datasets, and explainable architectures to enable equitable and effective deployment in real-world healthcare systems.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13375852/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148471162","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 Digital Cueing Intervention for Parkinsonian Gait: Laboratory-Based Clinical Validation and Acute Gait Responses.","authors":"Conor Wall, Victoria Hetherington, Rodrigo Vitorio, Peter McMeekin, Richard Walker, Jason Moore, Rosie Morris, Yunus Celik, Alan Godfrey","doi":"10.1007/s10916-026-02441-x","DOIUrl":"10.1007/s10916-026-02441-x","url":null,"abstract":"<p><p>Falls are common in people with Parkinson's (PwP). There is a need for a scalable, pragmatic, personalisable, and single device intervention to improve gait characteristics related to fall risk. CuePD is an app-only approach to deliver personalised auditory cues to retrain gait in PwP. This study aimed to clinically validate and evaluate effectiveness of CuePD in PwP and to explore their perceptions of CuePD. Sixty/60 PwP performed cued walks via metronome, instrumental and vocal music personalised to their baseline walking speed (cadence). PwP chose music from e.g., pop, rock genres. Cued walks were +10% on baseline cadence. We examined effectiveness of each cue and any carryover effects across non-cued walks. CuePD clinical validation (e.g., intraclass correlation coefficients, ICC_(2,1)) was established against a reference standard. CuePD effectiveness was examined via improvement (e.g., standardised response means) of gait characteristics indicative of fall risk (stride length, walking speed, step time coefficient of variation). CuePD quantified fall relevant mean gait characteristics against a reference system with good-to-excellent agreement (ICC_(2,1) 0.849 - 0.986), though agreement was poor for several variability and asymmetry measures. Vocal music was the most preferred cue type, improving gait characteristics by increasing stride length (7cm, SRM of 0.873) and gait speed (0.115 m/s, SRM of 1.264), while reducing stride time coefficient of variation (-0.418%, SRM of-0.505). CuePD received positive feedback and is an app-only approach that is clinically valid to quantify mean gait characteristics and has demonstrated acute improvements in gait characteristics related to fall risk. Findings suggest that the personalised approach may have pragmatic utility beyond the lab, but ecological validity needs to be established.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13356047/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148421657","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":"Exploring the Potential of Ambient AI for Inpatient Documentation: A Qualitative Study with Junior Doctors.","authors":"Aisling Bracken, Sean Whelehan, Anita Rose Babu, Khalid Merghani, Eoin Sheehan, Iain Feeley","doi":"10.1007/s10916-026-02437-7","DOIUrl":"10.1007/s10916-026-02437-7","url":null,"abstract":"<p><p>Clinical documentation is essential for safe and effective patient care but places a substantial clerical burden on doctors, particularly those early in training. Ambient artificial intelligence (AI) systems, which passively capture clinical conversations and generate structured notes, have demonstrated promise in outpatient and primary care settings. However, their use in inpatient ward rounds remains largely unexplored. Semi-structured interviews were conducted with ten postgraduate year one doctors following participation in simulated orthopaedic ward rounds incorporating an ambient AI scribe (Heidi Health, Melbourne, Australia). The topic guide was informed by Normalisation Process Theory (NPT) to explore participants' understanding of AI-assisted documentation workflows, the work they anticipated would be required at individual, team, and system levels for implementation, and their appraisal of the potential benefits, risks, and practical challenges of future use. Data were analysed collaboratively by two researchers using reflexive thematic analysis with a hybrid inductive-deductive approach. Seven themes were identified and mapped across the four NPT constructs. Coherence was reflected in participants' understanding of ambient AI as a way to reduce documentation burden, support patient-centred records, and improve accessibility. Cognitive participation was evident in their recognition that implementation would require individual engagement, including review and approval of AI-generated outputs. Collective action captured the practical work required to adapt ward round behaviours, redistribute documentation tasks, manage consent, and address infrastructure, access, and governance requirements. Reflexive monitoring was demonstrated through participants' appraisal of anticipated benefits, including potential for improved clinical engagement, multidisciplinary communication, and real-time capture of complex conversations, balanced against risks of clinical misrepresentation, cultural resistance, and privacy concerns. Through simulated exposure, participants made sense of ambient AI scribes as a potentially valuable addition to inpatient documentation workflows, anticipating effects on efficiency, communication, and patient-centred documentation. However, they also identified individual, team, and organisational work required for implementation, including workflow adaptation, consent processes, data privacy, access controls, infrastructure, and real-world appraisal in clinical settings.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13342209/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148404903","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":"Automatic Sleep Staging Using Cardiorespiratory Signals: A Systematic Review of Methodologies and Performance.","authors":"Wanlin Chen, Xinhui He, Jing Zheng, Shulin Chen, Xiang Tian","doi":"10.1007/s10916-026-02435-9","DOIUrl":"10.1007/s10916-026-02435-9","url":null,"abstract":"<p><p>Cardiorespiratory-based methods offer promising alternatives to traditional PSG for longitudinal sleep monitoring, holding significant systemic medical value for scalable sleep health management. This systematic review synthesizes methodological frameworks and performance outcomes of automatic sleep staging using cardiorespiratory signals. Four databases were searched and a total of 35 studies published since 2010 were identified. The analysis revealed that cardiorespiratory signal-based sleep staging achieved a practically meaningful accuracy of 70%, with no significant performance differences observed among signal modalities (cardiac signals, cardiorespiratory signals, or cardiac/cardiorespiratory signals combined with other non-EEG modalities) or between modeling algorithms (traditional machine learning vs. deep learning). However, we identified significant methodological heterogeneity and several critical model failure modes that hinder clinical translation, including the widespread lack of external validation, consistently poor classification of the N1 sleep stage, and limited generalization across diverse patient populations. To realize the technology's potential, future research must establish consensus-driven methodological guidelines and rigorously validate algorithms on large, demographically and clinically diverse datasets. These advances are essential for integrating cardiorespiratory-based sleep staging into healthcare systems as a scalable tool for population-level screening, longitudinal monitoring, and tiered clinical decision support.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148396888","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":"Security Analysis of a Federated Learning Framework for Medical Image-to-Image Translation.","authors":"Ciro Benito Raggio, Lina Bucher, Oliver Blanck, Francesco Cicone, Paolo Zaffino, Maria Francesca Spadea","doi":"10.1007/s10916-026-02436-8","DOIUrl":"10.1007/s10916-026-02436-8","url":null,"abstract":"<p><p>Federated Learning (FL) emerged as a privacy-preserving paradigm for collaborative training of deep learning models across institutions without sharing patient data. This approach has been applied to complex tasks such as medical image-to-image (I2I) translation, including MRI-to-synthetic CT (sCT) generation. However, existing federated I2I frameworks often assume privacy preservation as an inherent property of FL rather than a requirement to be explicitly validated, leaving their robustness to representative adversarial threat scenarios largely unexplored. In this study, we evaluated the vulnerability of a federated MRI-to-sCT translation framework (FedSynthCT-Brain) to three representative attack classes: Deep Leakage from Gradients (DLG), Federated Membership Inference Attack (FedMIA), and data poisoning. The efficacy of corresponding defense mechanisms, such as Secure Aggregation (SecAgg) and Byzantine-robust median aggregation (FedMedian), were assessed. DLG enabled only the recovery of coarse anatomical structures, with no clinically identifiable details (SSIM ≤ 0.16, PSNR ≤ 11 dB) across clients, suggesting limited vulnerability under the evaluated DLG setting. In contrast, FedMIA achieved high membership discrimination, with AUC scores between 0.92 and 0.99, revealing a critical privacy vulnerability. The introduction of SecAgg reduced AUC values to near-random levels (0.23-0.56) across all centers without impacting synthesis quality. Under high-noise poisoning, the standard federated averaging (FedAvg) aggregation rendered the federation inoperative, while FedMedian restored performance close to the no-poisoning baseline in most scenarios, with significant residual degradation in specific center configurations. At low noise levels, the advantage of FedMedian was less consistent, as low-level noise injection may be indistinguishable from natural heterogeneity across centers, potentially enabling stealthy degradation. These findings demonstrate that federated I2I translation frameworks are not inherently secure and require explicit, multi-layered evaluation. As FL is increasingly adopted in clinical workflows, our results underscore the necessity of integrating cryptographic, algorithmic, and infrastructural safeguards for secure deployment.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13332882/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148387245","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 to: Designing Operating Rooms as an Integrated Socio-Technical Ecosystem: Practical Lessons from a High-Volume Tertiary Center.","authors":"Dina Orkin, Ofir Morag, Hadas Moshonov-Cohavi, Tania Fishman, Gad Segal","doi":"10.1007/s10916-026-02439-5","DOIUrl":"https://doi.org/10.1007/s10916-026-02439-5","url":null,"abstract":"","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148387237","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-enabled clinical decision support in breast cancer care: a blinded multicenter benchmarking study comparing medically specialized with a general-purpose system.","authors":"Jonas Freudenberg, Johannes Knitza, Niklas Gremke, Niklas Amann, Thomas M Deutsch, Nikolas Tauber, Kerstin Muras, Zoe S Oftring, Tobias Engler, Alexander Englisch, Stefan Lukac, Adriano Fabi, André S Alves, Kristin Reinhardt, Markus Wallwiener, Moritz Kuhlmann, Jonathan Bamberger, Uwe Wagner, Sebastian Kuhn, Sebastian Griewing","doi":"10.1007/s10916-026-02434-w","DOIUrl":"10.1007/s10916-026-02434-w","url":null,"abstract":"<p><p>Medically specialized AI systems that have obtained regulatory clearance as medical devices can be deployed for patient-specific clinical decision support under defined compliance requirements. However, it remains unclear whether medical specialization and regulatory status translate into higher-quality breast cancer treatment recommendations than those produced by a general-purpose large language model (LLM). This blinded, multicenter study compared the performance of two medically specialized AI systems with a general-purpose model in breast cancer care. Two medically specialized (Prof. Valmed and OpenEvidence) and one general-purpose system (ChatGPT-5 Thinking) were prompted to generate treatment plans for 20 standardized breast cancer patient cases. Outputs were rated and ranked by blinded, board-certified breast cancer specialists from seven university breast cancer centers for safety, guideline adherence, medical adequacy, completeness, overall quality, and logical coherence. Statistical analyses comprised descriptive statistics, inter-rater reliability assessment, non-parametric performance comparisons of rating and ranking outcomes, and correlation analyses. Mean (± standard deviation) processing time for ChatGPT-5 Thinking (159 ± 58 s) was more than fourfold higher than that of Prof. Valmed (35 ± 4) and OpenEvidence (9 ± 1). ChatGPT-5 Thinking achieved significantly higher ratings across all evaluation categories, with no significant differences between the two medically specialized systems. Treatment plans generated by ChatGPT-5 Thinking were ranked as the top choice in 96.4% of rater-case combinations, compared with 3.6% for OpenEvidence, while Prof. Valmed was never ranked first. In this blinded, multicenter evaluation, a general-purpose LLM outperformed two medically specialized, retrieval-augmented systems in generating breast cancer treatment plans across all assessed categories. These results indicate that while regulatory clearance and domain specialization address key requirements for AI-enabled clinical decision support systems, these factors alone do not translate into superior performance in breast cancer care. At present, medically specialized systems may be best used as supportive tools under expert oversight, while further optimization and real-world validation are needed.Clinical trial number: Not applicable.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13332881/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148387250","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":"Starmate: A Lightweight AI Assistant for Autism Caregivers Developed and Evaluated Through a User-Centered Mixed-Methods Framework.","authors":"Zhifan Li, Xiaoxia Liu, Tianhao Chen, Yuting Yang, Xiaoyan Liu, Yuanyuan Lv, Zixuan Zhao, Xueying Li, Xiaoqing Yin, Zhongwen Feng, Yue Lan, Yanjie Zhao, Wei Ke, Yong Lin, Kefeng Li","doi":"10.1007/s10916-026-02433-x","DOIUrl":"https://doi.org/10.1007/s10916-026-02433-x","url":null,"abstract":"<p><p>Autism spectrum disorder (ASD) affects tens of millions of families worldwide, yet parents confront abundant but unreliable online advice and limited access to timely, empathetic guidance. To address this critical gap, we developed Starmate ( http://kefeng.mpu.edu.mo/starmate ), a 1.5B-parameter, domain-tuned AI assistant for ASD caregivers, using a rigorous user-centered mixed-methods framework. Informed by in-depth interviews ([Formula: see text]) and a Kano survey ([Formula: see text]) that identified \"Hands-on guidance\" as a must-have caregiver requirement, we engineered a novel modular architecture that integrates sentiment analysis, expert-vetted knowledge-graph-augmented retrieval (LightRAG), and a domain-fine-tuned Qwen2.5-1.5B model. In a blinded, side-by-side comparison against leading commercial LLMs, Starmate demonstrated improved performance across key metrics within this evaluation framework (86.76 vs 78.43-83.84; [Formula: see text]) and showed specific advantages in Empathy, Hands-on guidance, and Logical clarity (all [Formula: see text]). Automated benchmarking corroborated these results, with top scores for Professional accuracy (86.18), Empathy (86.79), and Hands-on guidance (82.58). These findings demonstrate the technical feasibility of a lightweight, privacy-conscious, domain-specific LLM to generate accurate, empathetic, and actionable responses in benchmarked scenarios, laying the groundwork for future real-world usability and clinical testing.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148368751","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":"Predicting the Predictor: Unresolved Validity Threats in LLM-Based ASA Classification.","authors":"Kaijian Yang","doi":"10.1007/s10916-026-02431-z","DOIUrl":"10.1007/s10916-026-02431-z","url":null,"abstract":"","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148361092","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}