Journal of Medical Systems最新文献

{"title":"Before Reaching for an LLM: Matching Clinical NLP Complexity to the Task.","authors":"Shinji Kobayashi","doi":"10.1007/s10916-026-02479-x","DOIUrl":"https://doi.org/10.1007/s10916-026-02479-x","url":null,"abstract":"","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149228004","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":"A Web-Based Registry Framework Linking Transfusion Practice to Long-Term Patient Outcomes: Design and Single-Center Feasibility Study.","authors":"Elina Nürenberg-Goloub, Benjamin Friedrichson, Michael Nordine, Holger Storf, Kai Zacharowski, Jan Andreas Kloka","doi":"10.1007/s10916-026-02474-2","DOIUrl":"https://doi.org/10.1007/s10916-026-02474-2","url":null,"abstract":"<p><p>Blood transfusions are among the most common medical interventions performed worldwide. Several comprehensive databases link transfusions to routinely collected health data but do not include the indication and the decision-making basis for a particular administration, nor patient-reported long-term outcomes. We developed a web-based registry for the standardized assessment of transfusion practice and patient outcomes, designed for an observation period of up to 30 years. The framework combines clinical data captured at the point of care with patient-reported outcome measures collected through automated digital follow-up, ensures privacy by design through physical separation of identifying and medical data, and codes diagnoses and procedures in SNOMED CT. We evaluated feasibility in a single-center pilot at Goethe University Hospital Frankfurt (11 September 2024-15 January 2026), with patient-reported follow-up collected through 13 August 2026. A total of 408 patients were enrolled, yielding 1,298 administrations across nine treatment categories in a predominantly cardiac surgical cohort. The pilot demonstrated that the registry integrates into routine clinical workflows, captures the parameters required for guideline-adherence monitoring, and supports sex-disaggregated, descriptive analyses of transfusion practice. Follow-up was completed by 12.5% of patients at 3 months and 15.2% of patients at 1 year; paired baseline-follow-up assessments of physical capacity and frailty demonstrate the data structure for capturing functional recovery. Risk-adjusted benchmarking, network-wide analyses, and donor outcomes are designed capabilities of the framework that were not evaluated in this pilot. The platform is available in 16 languages and participation is open to further institutions.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149227989","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":"Development and Exploratory Evaluation of a Large Language Model-Supported Scoping Review Workflow.","authors":"Frederick H Kuo, Jamie L Fierstein, Madeline de la Concha, Yasmin Saeed, Ryan Shargo, Dina Ashour, Ernest Amankwah, Ellis Crabtree, Mohamed A Rehman, Peter Najjar, Khyzer Aziz, Brant H Tudor, Luis M Ahumada","doi":"10.1007/s10916-026-02477-z","DOIUrl":"https://doi.org/10.1007/s10916-026-02477-z","url":null,"abstract":"<p><p>Large language models (LLMs) have demonstrated human-level performance in literature review screening phases and have been evaluated in systematic-review workflows. However, LLM performance in scoping reviews, which are broader and more heterogeneous, remains understudied. We developed a modular LLM-supported framework for scoping-review workflows and compared the performance of two general-purpose LLMs against human reviewers on a reference scoping review. The reference review's keyword search results (n = 1336) and prompt sets mirroring workflow stages were provided to GPT-5 and gpt-oss-20b (OpenAI, August 2025). Outputs were benchmarked against human decisions for agreement; disagreements were adjudicated. For title-abstract screening and final-inclusion concordance, unanimous and adjudicated decisions were combined into a composite reference standard. In title-abstract screening, GPT-5 and gpt-oss-20b workflows showed substantial interrater agreement with human consensus (AC1: 0.769; 0.722); reference concordance was 90.9% (p = 0.08) and 92.4% (p = 0.004) versus humans' 89.0%. For final inclusion status, interrater agreement was almost-perfect (AC1: 0.948; 0.853); reference concordance was 95.4% (p = 0.23) and 92.4% (p < 0.001) versus humans' 96.1%. Across data categorization/synthesis, interrater agreement was fair to almost-perfect (AC1: 0.493-0.949; 0.342-0.929); total variation distances (representing distribution divergence) were 1.55%-28.0%. All sources found comparably low definition-adherent use rates of the term \"human digital twin\" (humans 12.1%; GPT-5 13.0%; gpt-oss-20b 18.0%). Both LLM-supported workflows achieved fair to almost-perfect agreement and high screening/final-inclusion reference concordance. The main synthesis finding was directionally consistent across workflows, with all sources identifying infrequent correct use of \"human digital twin\"; total variation distance may be useful in assessing distribution-level concordance. Limitations include a single domain/vendor, fixed prompts, and predefined taxonomies; broader evaluations are warranted. In this single-domain benchmark, LLM-supported scoping-review workflows showed feasibility for supporting and potentially streamlining selected review stages, with broadly comparable performance on evaluated endpoints and conclusion-level concordance. Generalizability, reproducibility, and operational efficiency beyond this benchmark remain to be established.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149194624","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":"Semantic Governance Stops at the Model: What Laboratory-Aware AI Checklists Leave to Post-Deployment Oversight.","authors":"Koichiro Yuji, Wakako Yuji","doi":"10.1007/s10916-026-02478-y","DOIUrl":"https://doi.org/10.1007/s10916-026-02478-y","url":null,"abstract":"","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149194663","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":"Leveraging High-Frequency Postoperative ICU Arterial Blood Pressure Data from Electronic Health Records for Research: A Brief Report.","authors":"Gen Li, Robert E Freundlich, Benjamin French, David R McIlroy","doi":"10.1007/s10916-026-02472-4","DOIUrl":"10.1007/s10916-026-02472-4","url":null,"abstract":"<p><p>Postoperative blood pressure fluctuations after cardiac surgery are highly clinically relevant, yet analyzing high-frequency arterial pressure data remains challenging. In this study, we introduce a novel methodology for processing minute-by-minute postoperative intensive care unit (ICU) arterial pressure data. The pipeline implements a series of systematic data-cleaning steps to resolve artifacts and ensure physiological plausibility, and deploys a multi-stage imputation framework to address missing intervals. Our approach constructs longitudinal blood pressure profiles that quantify the time spent within predefined blood pressure ranges, minimizing assumptions and enhancing data utility for research. We detail a rigorous and reusable workflow for data extraction, cleaning, and imputation, which may address limitations of previous methods and offer a framework to build a robust exposure metric for future research utilizing postoperative arterial pressure data.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13668971/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149182618","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":"When Human Oversight Cannot Keep Pace: A Task-level Oversight-margin Framework for Cardiovascular Artificial Intelligence.","authors":"Aykan Çelik","doi":"10.1007/s10916-026-02476-0","DOIUrl":"https://doi.org/10.1007/s10916-026-02476-0","url":null,"abstract":"","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149182693","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":"Evaluating Case Selection for Human Oversight in Clinical AI.","authors":"Yu-Jung Cha","doi":"10.1007/s10916-026-02475-1","DOIUrl":"https://doi.org/10.1007/s10916-026-02475-1","url":null,"abstract":"","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149182702","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":"Decision-Use Qualification of Digital Therapeutic Alliance for Version Selection in Generative Mental-Health AI.","authors":"Mohammad Mahdi Akbarzadeh","doi":"10.1007/s10916-026-02473-3","DOIUrl":"10.1007/s10916-026-02473-3","url":null,"abstract":"","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149166984","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":"A Controlled Single-Speaker Evaluation of Ambient Voice Technologies' Speech-to-Text Function Using Narrated Surgical Case-Reports.","authors":"Ruairi O'Kane, Daniel Stonehouse-Smith, Melody Shirazi, Rachel Hutchinson, Morgan Gregg, Riya Patel, Jadbinder Seehra, Spyridon N Papageorgiou, Martyn T Cobourne","doi":"10.1007/s10916-026-02471-5","DOIUrl":"10.1007/s10916-026-02471-5","url":null,"abstract":"<p><p>Ambient voice technologies (AVT) utilise automatic speech recognition (ASR) and generative artificial intelligence for speech-to-text conversion, and are advocated as efficient, accurate tools for clinical documentation. We investigated (n = 8) AVT systems using surgical case-reports as narratives in a controlled single-speaker evaluation prioritising safety outcomes: specifically 3 commercial transcription-systems (Dragon-Medical-One, Heidi-Health, Tortus); 4 ASR speech-to-text Application Programming Interfaces (Speechmatics-Enhanced, Amazon-Medical-Transcribe, Whisper, GPT4oTranscribe); and an experimental two-stage ASR-Large Language Model (LLM) pipeline incorporating GPT4oTranscribe with GPT-5-LLM generative error correction (GPT4oTranscribe-Corrected-5). Reference-transcripts (n = 100; 32,897 words, range = 44-449, mean = 329/per-transcript) derived from surgical case-reports were recorded and input into AVT systems as audio-recordings for transcription-output generation. Primary outcome was proportion of transcription-outputs containing at least one clinically significant Class 3 error graded for potential harm. Secondary outcomes included transcription accuracy: Domain-Word-Error-Rate (DWER) against SNOMED-CT, lexical-accuracy (ROUGE score) and semantic similarity (BERT, BART scores). To investigate impact of the experimental pipeline on clinically significant errors, raw ASR and LLM-processed transcription-outputs were compared and errors classified as resolved, remaining or newly introduced. Across (n = 800) transcript-outputs, 30-68% (GPT4oTranscribe-Corrected-5; Amazon-Medical-Transcribe and Dragon-Medical-One, respectively) contained at least one clinically significant Class 3 error. LLM-processing reduced the proportion of transcript-outputs affected (53% to 30%), amongst 89 clinically significant errors in ASR-output, 51 were resolved, 38 remained significant and 4 were newly introduced. Reference-transcript length significantly increased odds of Class 3 errors for 4 systems (GPT4oTranscribe, Tortus, Amazon-Medical-Transcribe, Dragon-Medical-One; odds ratio 2.65-3.34/additional 100 reference-words). Errors with potential to cause severe harm or death (NHS England Level 3-4) totalled (n = 53) across systems, concentrated in the domains of medication-type/dose (39.6%), and investigations/laboratory results (30.2%). Performance varied across systems for transcription metrics (P < 0.001). GPT4oTranscribe-Corrected-5 (DWER = 3.60%) and Heidi-Health (DWER = 5.67%) performed best for medical terminology; Amazon-Medical-Transcribe worst (DWER = 24.03%). For lexical and semantic similarity GPT4oTranscribe-Corrected-5 performed best, followed by Heidi-Health. The ASR-LLM pipeline reduced clinically significant errors but did introduce new ones in 3% of transcript-outputs. The safety and effectiveness of these systems in clinical practice requires further evaluation.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13652911/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149149744","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":"Real-World Deployment and Operational Evaluation of an On-Premise Thermal IoMT System in an Intensive Care Unit.","authors":"Eva Avilés, Jose-Luis Lafuente, Samuel González, Juan-Jose Beunza","doi":"10.1007/s10916-026-02455-5","DOIUrl":"10.1007/s10916-026-02455-5","url":null,"abstract":"<p><p>Thermal imaging provides a non-contact approach for continuous environmental monitoring in intensive care units, although most existing studies remain limited to controlled or experimental settings with limited real-world validation. This study aimed to design, deploy, and operationally evaluate a scalable, low-cost, on-premise thermal Internet of Medical Things system in a real intensive care unit. A distributed network of seven thermal acquisition nodes, scalable to thirteen beds, was implemented using embedded devices and radiometric infrared cameras. Thermal images were transmitted through the hospital Wi-Fi network to a local server for storage, indexing, and near real-time visualization. System performance was evaluated using operational metrics including end-to-end latency, throughput, availability, and connectivity incidents. During a 10-day structured evaluation, the system generated 5,763,312 thermal images (approximately 1.47 TB), achieving an aggregate acquisition rate of 6.67 images per second. After architectural optimization, mean latency decreased from 26,344 ms to 126 ms (99.52% reduction), with a median of 117 ms and a 95th percentile of 207 ms. Effective system availability reached 95.29%, with most incidents associated with transient wireless connectivity interruptions. These results demonstrate the feasibility of deploying a distributed thermal IoMT system in a real intensive care unit under hospital information technology governance, offering a preliminary reference model for on-premise, nonintrusive thermal sensing infrastructures in critical care, pending validation across additional institutional and hardware settings.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"50 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13645914/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149127703","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}