PLOS digital health最新文献

{"title":"Toward fully algorithmic care for type 1 diabetes: The case for AI autonomy, and a recalibrated role for the diabetologist in an ageing type 2 diabetes population.","authors":"Mounzer Maaz, Samar Maaz, Islam Maaz, Randa Dardari, Helene Dardari, Dured Dardari","doi":"10.1371/journal.pdig.0001734","DOIUrl":"10.1371/journal.pdig.0001734","url":null,"abstract":"<p><p>Artificial intelligence can already automate selected diabetes tasks, but the evidence is uneven. Automated insulin delivery is established in type 1 diabetes; in type 2 diabetes, validated screening and insulin-adjustment tools support a tiered, human-governed model rather than wholesale autonomy.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 9","pages":"e0001734"},"PeriodicalIF":7.7,"publicationDate":"2026-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13588365/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149003028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating large language models for lay summaries of radiology reports using tailored prompting strategies and mixed-method assessment.","authors":"Nanziba Tasneem, Christian B van der Pol, Ambreen Zahoor, Nitin Juggath, Kyle McGowan, Cynthia Lokker, Ashirbani Saha","doi":"10.1371/journal.pdig.0001672","DOIUrl":"10.1371/journal.pdig.0001672","url":null,"abstract":"<p><p>Radiology reports are often filled with medical jargon that limits patient understanding. Lay summaries can improve understanding but are time-consuming for healthcare providers to create. The objective of this study is to explore the use of tailored prompts for five Large Language Models (LLMs) in generating lay summaries from radiology reports. Using 100 reports from the publicly available \"BioNLP 2023 report summarization\" dataset, lay summaries were generated by each LLM, under select prompting styles [Few-Shot (GPT-4), Generated Knowledge (GPT-4o mini, Gemini 1.5 - Pro, Gemini 1.5 - Flash), and Zero-Shot (Llama 3.1)] informed by a pilot work. The summaries were evaluated using a mixed-method framework: subjective assessment (Likert statements) by blinded experts (n = 2 radiology fellows) and Large Reasoning Models (LRMs) [(Gemini 2.5 - Pro (LRM 1); GPT-oss-120b (LRM 2)], and readability metrics (Flesch-Kincaid Grade Level and Flesch Reading Ease). Using percentage agreement of Likert statements, the LLM-prompt combinations' performances were ranked, and Friedman and post-hoc Nemenyi tests were conducted. Gemini 1.5 - Flash and - Pro (generated knowledge) were rated highest by human experts and LRMs for generating actionable lay summaries that require minimal supervision [P < 4.97 × 10-2 (Rater 1); P < 9.03 × 10-21 (Rater 2), P < 6.90 × 10-15 (LRM 1), P < 2.760 × 10-5 (LRM 2). GPT-4 (few-shot) achieved the highest human-rated accuracy (98%), while Gemini 1.5 - Flash (LRM 1-rated: 95%) and Gemini 1.5 - Pro (LRM 2-rated: 91%) ranked first in LRM-rated accuracy. Gemini 1.5 - Pro produced the most accessible summaries (Flesch-Kincaid Grade Level: 7.55 ± 1.38, Flesch Reading Ease: 67.84 ± 7.78). Strong agreement was observed between experts and LRMs [0.96% (LRM 1) and 3.4% (LRM 2) complete disagreement]. Overall, this study highlights Gemini-models with generated knowledge prompts and the potential of LRM evaluators in assessing LLM-generated lay summaries.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 9","pages":"e0001672"},"PeriodicalIF":7.7,"publicationDate":"2026-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13585270/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148993023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A medically grounded LLM agent-based tool to detect patient safety events in medical records.","authors":"Diego Trujillo, Dulin Wang, Nathan Bahr, Tina Yi-Jin Hsieh, Byeongyeon Cho, Garth Meckler, Matthew Hansen, Carl Eriksson, Kyu Seo Kim, Steven Bedrick, Xiaoqian Jiang, Jeanne-Marie Guise","doi":"10.1371/journal.pdig.0001174","DOIUrl":"10.1371/journal.pdig.0001174","url":null,"abstract":"<p><p>Large language models (LLMs) have shown incredible promise in medicine. While LLMs may be particularly useful in areas requiring extensive review of clinical records, their use remains limited due to their tendency to hallucinate and fabricate information. Hallucination issues, as well as their consequences, are exacerbated in low-probability, high-stakes scenarios such as rare adverse safety events or medical errors. We present SAFE-AI (Structured and Automated Framework for Explainable AI), a novel method for clinical decision making that combines the strengths of clinical expert knowledge with LLMs in an ontology-driven model that minimizes hallucinations using strict rules. We test this method to identify medication errors in medical charts. We collected a sample of 18,402 lines of clinical information from 300 EMS clinical charts that were independently dually reviewed by two expert physicians for epinephrine adverse safety events (ASEs), with 96% inter-rater agreement. We tested SAFE-AI against these labels, achieving similar performance to human experts in detecting epinephrine overdoses with 97.9% accuracy, and 91.6% accuracy in identifying delays in epinephrine administration, greatly outperforming baseline LLMs models. Notably, some disagreements between clinicians and the model were found to be justifiable differences in judgment rather than errors. SAFE-AI presents a novel approach for clinical AI applications that addresses two key limitations of current machine learning methods: 1) over-reliance on probabilistic pattern recognition instead of established medical knowledge, and 2) perpetuation of biases present in training data. This framework is easily adaptable to a range of clinical applications, paving the way for provable and trustworthy AI in medicine.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 9","pages":"e0001174"},"PeriodicalIF":7.7,"publicationDate":"2026-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13585220/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148993007","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assisting patients with reliable information gathering: A guide to building efficient QA systems for medical use.","authors":"Zhipeng Yin, Zichong Wang, Min Chen, Ian Stockwell, Xin Ning, Jun Liu, Wenbin Zhang","doi":"10.1371/journal.pdig.0001634","DOIUrl":"10.1371/journal.pdig.0001634","url":null,"abstract":"<p><p>The application of question-answering (QA) systems in the medical domain has rapidly advanced, significantly improving patients' access to reliable health-related information. However, current approaches face notable challenges, including the difficulty in obtaining large-scale and unbiased medical datasets, significant privacy concerns, and inefficiencies due to manual dataset annotation. To address these issues, This study introduce a novel methodology leveraging publicly accessible online health forums to systematically build an unbiased, privacy-conscious QA dataset, and it employs Topic-guided Semantic Modeling (TGSM) for automated topic identification, enabling efficient and targeted annotation of relevant patient-generated content. Subsequently, this study propose a two-stage QA pipeline based on a Retriever-Reader architecture, which is further enhanced through fine-tuning state-of-the-art transformer-based models on the constructed domain-specific QA dataset. Experimental results demonstrate that our fine-tuned BioBERT significantly outperforms existing benchmarks, offering accurate patient-derived insights and providing a replicable framework for building efficient medical QA systems.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 9","pages":"e0001634"},"PeriodicalIF":7.7,"publicationDate":"2026-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13585261/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148993041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Inflammation is associated with altered functional connectivity of the cingulate cortex in individuals with subthreshold depression.","authors":"Zhangzhang Qi, Pan Chen, Guanmao Chen, Zhenye Luo, Shu Zhang, Lijun Jiang, Guixian Tang, Li Huang, Qian Tao, Ying Wang","doi":"10.1371/journal.pdig.0001665","DOIUrl":"10.1371/journal.pdig.0001665","url":null,"abstract":"<p><p>Subthreshold depression (StD) represents a critical prodromal phase that often precedes clinical depression. Identifying biological indicators during this stage is essential for the prophylaxis of major depressive disorder. The present study investigated the interplay between serum pro-inflammatory cytokines, functional connectivity (FC) within subregions of the cingulate cortex (CC), and psychometric profiles in an StD cohort. The study included 126 participants with StD and 104 healthy controls. Resting-state functional magnetic resonance imaging data, psychological assessments [Center for Epidemiologic Studies Depression Scale (CES-D), 24-item Hamilton Depression Rating Scale (HAMD-24), Hamilton Anxiety Scale (HAMA), Ruminative Responses Scale (RRS)], and serum pro-inflammatory cytokine levels [tumor necrosis factor-alpha (TNF-α), interleukin-1 beta (IL-1β), IL-6, and IL-17] were collected. The StD group exhibited increased FC in three specific circuits: The left middle CC (MCC) to the bilateral caudate nucleus (CN); the left supracallosal anterior CC (supACC) to the bilateral anterior cerebellar lobe; the right supACC to the right superior frontal gyrus (SFG). Furthermore, serum concentrations of TNF-α, IL-1β, and IL-17 were significantly increased. FC between the left MCC and bilateral CN was associated with CES-D and RRS scores, whereas FC between the right supACC and right SFG was associated with HAMA scores. Interaction between IL-1β and FC in the right supACC-SFG circuit was independently associated with HAMA scores, whereas interaction between IL-17 and FC in the same circuit independently predicted RRS scores. The statistical interaction between IL-1β and IL-17 levels and right supACC-SFG FC is associated with anxiety and rumination symptoms in StD, which may indicate an increased risk of progression to major depression. These findings underscore the significance of neuroimmune associations in subthreshold depression.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 9","pages":"e0001665"},"PeriodicalIF":7.7,"publicationDate":"2026-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13585250/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148993060","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"M3: Conversational LLMs simplify secure clinical data access, understanding, and analysis.","authors":"Rafi Al Attrach, Pedro Moreira, Rajna Fani, Renato Umeton, Amelia Fiske, Leo Anthony Celi","doi":"10.1371/journal.pdig.0001671","DOIUrl":"10.1371/journal.pdig.0001671","url":null,"abstract":"<p><p>Large-scale clinical databases offer opportunities for medical research, but their complexity creates barriers to effective use. The Medical Information Mart for Intensive Care (MIMIC-IV), one of the world's largest open-source electronic health record databases, traditionally requires both SQL proficiency and clinical domain expertise. We introduce M3, a system that enables natural language querying of MIMIC-IV data through the Model Context Protocol. With a single command, M3 retrieves MIMIC-IV from PhysioNet, launches a local SQLite instance or connects to hosted BigQuery, and allows researchers to pose clinical questions in plain English. We evaluated M3 using samples from the EHRSQL 2024 benchmark with two language models. On one hundred answerable questions, the proprietary Claude Sonnet 4 achieved 94% accuracy and the open-weights gpt-oss-20B (deployable locally on consumer hardware) achieved 93%; on a matched sample of one hundred unanswerable questions, where correct behavior is to abstain rather than produce SQL, gpt-oss-20B correctly abstained on 69%. Both models translate natural language into SQL, execute queries against MIMIC-IV, and return structured results alongside the underlying query for verification. Error analysis revealed that most failures stemmed from complex temporal reasoning or ambiguous question phrasing rather than fundamental architectural limitations. The comparable performance of a smaller open-weights model demonstrates that privacy-preserving local deployment is viable for sensitive clinical data analysis. M3 lowers technical barriers to critical care data analysis and is designed with security measures including OAuth2 authentication, query validation, and audit logging.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 9","pages":"e0001671"},"PeriodicalIF":7.7,"publicationDate":"2026-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13585222/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148993034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Utilization of a HIPAA-compliant large language model chatbot in an academic pediatric medical center.","authors":"Benjamin Rader, Dinesh K Rai, Melissa L Stewart, Sarah Lejfer, Sampath Chennuri, James Hartwell, Victor Moyano, Max H Witwer, Peter C Laussen, Heather L Nelson, John S Brownstein","doi":"10.1371/journal.pdig.0001684","DOIUrl":"10.1371/journal.pdig.0001684","url":null,"abstract":"<p><p>Despite growing interest in LLM chatbots, little evidence exists on usage patterns in hospital systems. This paper presents a mixed-methods case study of \"InternalGPT,\" a HIPAA-compliant LLM chatbot made available to employees of the institution. Survey responses and 14 months of system utilization data were analyzed across diverse professional roles in the institution. Of approximately 15,800 hospital employees, 2,149 (13.6%) requested InternalGPT access. Motivations for sign-up aligned with professional roles: operations professionals prioritized administrative automation, clinicians focused on clinical augmentation, and scientists on research and coding. Among InternalGPT users, 52.8% recorded at least one token use; 33.6% never logged-in, and 13.7% logged-in but never used the tool. The top 20% of users consumed 69.4% of tokens. Key barriers to engagement among non-users included limited time for exploration (51.4%) and difficulty using (21.8%), integrating (15.5%), or accessing (9.2%) InternalGPT. Among a small group of employees with sustained InternalGPT use (n = 461), a subset who responded to a self-report survey (n = 92) indicated a mean productivity gain of 30%, corresponding to an exploratory perceived productivity value of $6.3M to $18.9M under varying extrapolation assumptions. Although most hospital employees never used the HIPAA-compliant LLM chatbot, a small minority who utilized it regularly reported substantial productivity improvements, highlighting both the value proposition of LLMs in healthcare and potential for increased engagement. Implementation and knowledge challenges were more frequently cited than AI-feature and performance concerns as key barriers to adoption. These findings underscore that successful LLM implementation in healthcare hinges not only on advanced AI technology, but also on robust system capacity building including investments in user education and technical integration.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 9","pages":"e0001684"},"PeriodicalIF":7.7,"publicationDate":"2026-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13585266/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148993047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DEPP: A diabetes exercise prescription protocol knowledge base.","authors":"Ting Bao, Xingyun Liu, Shumin Ren, Ke Zhang, Jiale Du, Danting Li, Bingqing Liu, Jinhua Feng, Rongrong Wu, Erman Wu, Chaoying Zhan, Min Jiang, Li Shen, Cheng Bi, Yingbo Zhang, Sheyu Li, Juan M Ruso, Bairong Shen","doi":"10.1371/journal.pdig.0001728","DOIUrl":"10.1371/journal.pdig.0001728","url":null,"abstract":"<p><p>Exercise plays a critical role in diabetes management by improving glycemic control and reducing cardiovascular risk. However, personalizing exercise prescriptions to individual characteristics and preferences is challenging, especially given the global shortage of exercise professionals, and current approaches often rely on general guidelines that lack support for individualized, evidence-based planning. To address this gap, we developed the Diabetes Exercise Prescription Protocol (DEPP) knowledge base, a structured evidence resource to assist healthcare experts in formulating personalized exercise prescriptions. DEPP was constructed by manually extracting and annotating data from 529 English-language studies retrieved from PubMed, resulting in a curated set of 766 exercise prescription protocols. The system uses a browser/server architecture implemented with Flask, SQLite, and Waitress. The knowledge base enables personalized retrieval and comparison of evidence-based protocols using a novel \"FITT-VP-WC\" framework, which extends the established FITT-VP principles by explicitly integrating warnings and contraindications as core safety components. Usability and clinical utility were evaluated with 12 sports physicians and 16 students (SUS/NPS) and in a vignette-based comparison with 20 clinicians (DEPP vs. no tool). The overall SUS score was 80.18 (physicians: 83.13, students: 77.97, p > 0.05) and NPS was 28.6% (physicians: 50.0%, students: 12.5%, p > 0.05), indicating good acceptance. In the comparative study, DEPP-assisted prescriptions significantly outperformed those without the tool across three standardized patient cases (all p < 0.001), confirming its practical benefit. The knowledge base is freely accessible at http://depp.sysbio.org.cn. This resource offers a new tool for evidence-based, personalized exercise prescription in diabetes care with positive user feedback.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 9","pages":"e0001728"},"PeriodicalIF":7.7,"publicationDate":"2026-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13581003/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148984284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A systematic review of prolonged posture monitoring with accelerometer-based wearable sensors.","authors":"Meixing Liao, Kai Huang, Eva Libeert, Bart Vanrumste, Simon Brumagne, Zhe Chen, Jean-Marie Aerts","doi":"10.1371/journal.pdig.0001538","DOIUrl":"10.1371/journal.pdig.0001538","url":null,"abstract":"<p><p>Prolonged sitting and standing are associated with health risks. Unlike generic sedentary behaviour monitoring based on energy expenditure, prolonged posture monitoring requires posture-specific detection and uninterrupted bout segmentation, yet current accelerometer-based approaches remain heterogeneous. This systematic review synthesises current practices and identifies research gaps across the sensing-to-feedback pipeline, including data collection, preparation, analysis, and user feedback. Ten databases, including Web of Science, Scopus, ProQuest Central, PubMed/MEDLINE, EMBASE, CINAHL, SPORTDiscus, IEEE Xplore, ACM Digital Library, and Engineering Village, were searched. Eligible studies monitored uninterrupted sitting or standing bouts of at least ten minutes during wake time using body-worn accelerometer-based sensors, provided sufficient methodological detail, and were published as peer-reviewed journal articles or full conference proceedings in English. From 27,334 records, fourteen studies were included. Risk of bias was assessed using design-specific tools: JBI checklists for randomised and cross-sectional studies, and WEAR-BOT for wearable-sensor validation or algorithm-development studies. Prolonged sitting was the primary target, while prolonged standing was not assessed as a dedicated bout-level outcome. Thigh-worn activPAL devices were most frequently used for posture measurement or as reference criteria. Bout duration thresholds and interruption rules varied substantially. Deep learning models reported the strongest performance for sitting recognition and transition detection. Four studies included feedback components, but none used real-time posture monitoring outcomes to trigger feedback. Substantial heterogeneity precluded quantitative synthesis, and the evidence base was concentrated in Western, office-based populations. Overall, accelerometer-based wearable sensors provide a feasible basis for monitoring prolonged sitting. Key gaps include inconsistent definitions, limited specific detection, heterogeneous data preparation and validation reporting, and a lack of translation from monitoring to actionable feedback. Future research should prioritise transparent bout definitions, reproducible pipelines, inclusive external validation, and interpretable feedback systems. PROSPERO registration: CRD42025637387.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 9","pages":"e0001538"},"PeriodicalIF":7.7,"publicationDate":"2026-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13577576/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148978999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Medicine Quality Monitoring Globe: A public health intelligence system for collecting and curating reports of substandard and falsified medical products from publicly available Internet news media.","authors":"Clark C Freifeld, Kerlijn Van Assche, Alberto Olliaro, Martial Battain, Inthapavanh Kitignavong, Vayouly Vidhamaly, Phonepasith Boupha, Kem Boutsamay, Ngan Thi Do, Konnie Bellingham, Viengsavanh Pimxayvong, Thitthiphone Olinh, Ana Rosado Olmo, Jingying Xu, Shan Jiang, Andrea Soult, Southida Insal, Philippe J Guérin, Paul N Newton, Céline Caillet","doi":"10.1371/journal.pdig.0001648","DOIUrl":"10.1371/journal.pdig.0001648","url":null,"abstract":"<p><p>The circulation of substandard and falsified (SF) medical products, including medicines, vaccines, and medical devices, continues to impact health of populations worldwide. Meanwhile, surveillance of SF products and data sharing are limited in most of the world, and incidents are rarely published in accessible databases. We describe here the Medicine Quality Monitoring Globe system (MQM Globe) for capturing, curating, characterising, and disseminating online media reports relating to SF products. The system consists of the curation environment and the Web application. Online reports are acquired from search engines, direct feeds, and targeted extraction, in five languages. They then pass a series of automated content characterisation steps to filter and label them by relevance, location, and product. Reports are then reviewed by a trained curator staff, before being made available through a visualisation Web application. Over the study period from July 2018 through December 2024, we identified 11,000 relevant distinct SF incidents, across a broad range of geography, products, and categories. The automated relevance classifier exhibited precision of 37%, recall 90%, and F1-score 52%, for English-language content. The information captured by the MQM Globe is publicly available and can help inform public health authorities as situations emerge. It is the only publicly available repository of open source intelligence specifically on SF medical products. It can be used as an informational tool to trigger intelligence-led activities across law enforcement, customs and Medicine Regulatory Authorities.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 9","pages":"e0001648"},"PeriodicalIF":7.7,"publicationDate":"2026-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13577332/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148978944","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}