{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T18:04:27Z","timestamp":1793037867148,"version":"4.5.0"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Nutr."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Patients with dysphagia who are transitioning from clinical to domestic environments face significant life-threatening risks due to the \u201cnutrition\u2013texture disconnect\u201d\u2014the systemic gap between hospital-prescribed International Dysphagia Diet Standardisation Initiative (IDDSI) levels and actual home-prepared meals. Existing dietary monitoring tools effectively track caloric intake, yet they lack the rheological sensing capabilities required to prevent acute choking and liquid aspiration hazards. This preliminary feasibility study introduces a novel, smartphone-centric Internet of Things platform that operationalizes a multimodal large language model (MLLM) as an \u201cintelligent soft sensor\u201d to bridge this safety gap.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The system utilizes a three-stage cascaded pipeline\u2014incorporating chain-of-thought reasoning and bi-directional safety logic\u2014to perform automated dish recognition, localized nutritional retrieval, and pre-consumption IDDSI texture auditing from a single smartphone image. To evaluate performance, the platform was benchmarked against the newly established Clinical-Expert IDDSI Validation Benchmark, a curated dataset of 115 diverse meal images independently verified via physical rheological testing by certified clinical specialists. A comprehensive comparative evaluation was conducted across 14 commercial and open-source models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our Qwen-based pipeline achieved a total exact match accuracy of 61.74%. Crucially, the system demonstrated the highest safety profile among 14 tested commercial and open-source models, achieving the lowest total false negative rate (FNR) of 9.2%. While localized open-source models exhibited a critical failure mode regarding liquid aspiration hazards (100% FNR), our cloud-based system maintained a robust 7.14% FNR for liquids.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These empirical results indicate that the proposed platform serves as a superior, safety-first screening proxy tool for digital healthcare. By prioritizing a low hazard\u2013miss rate over raw conversational baseline accuracy, the system successfully bridges the safety gap between clinical prescriptions and daily home-based monitoring. The framework offers an ethical, non-invasive, and highly scalable soft-sensing solution for longitudinal, unsupervised dysphagia oversight in home-care settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnut.2026.1829703","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T05:38:44Z","timestamp":1782711524000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Multimodal LLM-driven IoT digital healthcare platform for intelligent dysphagia dietary monitoring"],"prefix":"10.3389","volume":"13","author":[{"given":"Zebang","family":"He","sequence":"first","affiliation":[{"name":"Research and Development Office, The Education University of Hong Kong","place":["New Territories, Hong Kong SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steve W. Y.","family":"Mung","sequence":"additional","affiliation":[{"name":"Research and Development Office, The Education University of Hong Kong","place":["New Territories, Hong Kong SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna Chi Shan","family":"Kam","sequence":"additional","affiliation":[{"name":"Department of Special Education and Counselling, The Education University of Hong Kong","place":["New Territories, Hong Kong SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chetwyn C. H.","family":"Chan","sequence":"additional","affiliation":[{"name":"Department of Psychology, The Education University of Hong Kong","place":["New Territories, Hong Kong SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,29]]},"reference":[{"key":"ref1","volume-title":"StatPearls","author":"Azer","year":"2026"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1159\/000339974","article-title":"Definition, prevalence and burden of oropharyngeal dysphagia: a serious problem among older adults worldwide and the impact on prognosis and hospital resources","volume":"72","author":"Cichero","year":"2012","journal-title":"Nestl\u00e9 Nutr Inst Workshop Ser"},{"key":"ref3","year":""},{"key":"ref4","doi-asserted-by":"publisher","first-page":"82","DOI":"10.3390\/geriatrics5040082","article-title":"Is iddsi an evidence-based framework? A relevant question for the frail older population","volume":"5","author":"C\u00f4t\u00e9","year":"2020","journal-title":"Geriatrics"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"e35858","DOI":"10.2196\/35858","article-title":"Mobile apps for dietary and food timing assessment: evaluation for use in clinical research","volume":"7","author":"Gioia","year":"2023","journal-title":"JMIR Form Res"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1109\/THMS.2015.2408615","article-title":"Dysphagia screening: contributions of cervical auscultation signals and modern signal-processing techniques","volume":"45","author":"Dudik","year":"2015","journal-title":"IEEE Trans Hum\u2013Mach Syst"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JTEHM.2015.2500562","article-title":"Smartphone-based real-time assessment of swallowing ability from the swallowing sound","volume":"3","author":"Jayatilake","year":"2015","journal-title":"IEEE J Transl Eng Health Med"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"2103","DOI":"10.1109\/TBME.2004.836504","article-title":"Classification of normal and dysphagic swallows by acoustical means","volume":"51","author":"Lazareck","year":"2004","journal-title":"IEEE Trans Biomed Eng"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1109\/10.52346","article-title":"Biomechanical measurements to characterize the oral phase of dysphagia","volume":"37","author":"Reddy","year":"2002","journal-title":"IEEE Trans Biomed Eng"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1090","DOI":"10.1109\/TBME.2008.2010504","article-title":"Segmentation of dual-axis swallowing accelerometry signals in healthy subjects with analysis of anthropometric effects on duration of swallowing activities","volume":"56","author":"Sejdic","year":"2009","journal-title":"IEEE Trans Biomed Eng"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2025.3573282","article-title":"Deep learning for video fluoroscopic swallowing study analysis: a survey on classification, detection, and segmentation techniques","author":"Fakhry","year":"2025","journal-title":"IEEE Access"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1109\/JBHI.2020.3000057","article-title":"Upper esophageal sphincter opening segmentation with convolutional recurrent neural networks in high resolution cervical auscultation","volume":"25","author":"Khalifa","year":"2020","journal-title":"IEEE J Biomed Health Inform"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"956","DOI":"10.1109\/JBHI.2022.3224323","article-title":"Autonomous swallow segment extraction using deep learning in neck-sensor vibratory signals from patients with dysphagia","volume":"27","author":"Khalifa","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"e65551","DOI":"10.2196\/65551","article-title":"Current technological advances in dysphagia screening: systematic scoping review","volume":"27","author":"Wong","year":"2025","journal-title":"J Med Internet Res"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1038\/s41528-023-00286-9","article-title":"Wearable, epidermal devices for assessment of swallowing function","volume":"7","author":"Rafeedi","year":"2023","journal-title":"NPJ Flexible Electron"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1186\/s12984-024-01329-6","article-title":"Prediction of dysphagia aspiration through machine learning-based analysis of patients\u2019 postprandial voices","volume":"21","author":"Kim","year":"2024","journal-title":"J Neuroeng Rehabil"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1109\/JTEHM.2025.3571255","article-title":"Unstructured electronic health records of dysphagic patients analyzed by large language models","volume":"13","author":"Neubig","year":"2025","journal-title":"IEEE J Transl Eng Health Med"},{"key":"ref18","first-page":"99","article-title":"USDA Food and Nutrient Database for Dietary Studies (FNDDS), 5.0*","volume-title":"Procedia food science","author":"Montville","year":"2013"},{"key":"ref19","first-page":"8903","author":"Thames","year":"2021"},{"key":"ref20","first-page":"32","author":"Chen","year":"2016"},{"key":"ref21","first-page":"367","author":"Deng","year":"2019"},{"key":"ref22","first-page":"367","author":"Ege","year":"2017"},{"key":"ref23","first-page":"1233","article-title":"Im2Calories: Towards an Automated Mobile Vision Food Diary","author":"Meyers","year":"2015"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"12882","DOI":"10.1109\/JSEN.2020.3041023","article-title":"A systematic review of sensor-based methodologies for food portion size estimation","volume":"21","author":"Raju","year":"2020","journal-title":"IEEE Sens J"},{"key":"ref25","first-page":"3741","author":"Vinod","year":"2024"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"162835","DOI":"10.1109\/ACCESS.2021.3128995","article-title":"An open-source approach to solving the problem of accurate food-intake monitoring","volume":"9","author":"Biasizzo","year":"2021","journal-title":"IEEE Access"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1109\/tce.2021.3131687","article-title":"Ibuffet: an AIoT-based intelligent calorie management system for eating buffet meals with calorie intake control","volume":"67","author":"Chang","year":"2021","journal-title":"IEEE Trans Consum Electron"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1109\/tce.2018.2867802","article-title":"Smart-log: a deep-learning based automated nutrition monitoring system in the IoT","volume":"64","author":"Sundaravadivel","year":"2018","journal-title":"IEEE Trans Consum Electron"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1177\/1932296815582222","article-title":"\u201cSnap-n-eat\u201d food recognition and nutrition estimation on a smartphone","volume":"9","author":"Zhang","year":"2015","journal-title":"J Diabetes Sci Technol"},{"key":"ref30","first-page":"385","article-title":"Single-view food portion estimation based on geometric models","volume":"2015","author":"Fang","year":"2015","journal-title":"ISM"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"1180","DOI":"10.1017\/S136898001800054X","article-title":"Image-based food portion size estimation using a smartphone without a fiducial marker","volume":"22","author":"Yang","year":"2019","journal-title":"Public Health Nutr"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"24824","DOI":"10.52202\/068431-1800","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref33","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref34","first-page":"190","volume-title":"Understanding the impact of Negative Prompts: When and how do they take effect?, European Conference on Computer vision","author":"Ban","year":"2024"},{"key":"ref35","first-page":"1182","author":"O'Leary","year":"2010"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"5503204","DOI":"10.1109\/LSENS.2026.3688480","article-title":"Iot-based multiscale weighing system using centralized data aggregation for nutrition intake monitoring","volume":"10","author":"Lo","year":"2026","journal-title":"IEEE Sens Lett"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"44522","DOI":"10.1109\/JSEN.2025.3620093","article-title":"Smart food area\u2013weight system for dietary and nutritional monitoring","volume":"25","author":"Lai","year":"2025","journal-title":"IEEE Sens J"}],"container-title":["Frontiers in Nutrition"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnut.2026.1829703\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:42:08Z","timestamp":1783694528000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnut.2026.1829703\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,29]]},"references-count":37,"alternative-id":["10.3389\/fnut.2026.1829703"],"URL":"https:\/\/doi.org\/10.3389\/fnut.2026.1829703","relation":{},"ISSN":["2296-861X"],"issn-type":[{"value":"2296-861X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,29]]},"article-number":"1829703"}}