{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T06:22:53Z","timestamp":1787638973147,"version":"build-2736575974"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"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. Digit. Health"],"abstract":"<jats:p>Artificial intelligence (AI) in healthcare is often framed as a problem of model performance. This view overlooks a prior representational problem: many clinical data are human-cognitive proxies built for communication, documentation, classification, or administration rather than high-fidelity computational access to clinical phenomena. In rehabilitation medicine, movement quality, compensatory strategy, sensorimotor integration, fatigue-related deterioration, and postural instability are frequently compressed into proxy measures such as TUG, BBS, FMA, ECOG performance status, diagnosis codes, or clinical notes. We propose Clinical Reality Translation-Construction (CRTC), a representational design framework that specifies how clinically meaningful phenomena can be constructed as AI-readable entities before model development. CRTC argues that the bottleneck in rehabilitation AI is often representational before it is algorithmic. Its central task is not merely to automate interpretation of existing human-readable proxies, but to construct pathway-based clinical representations: AI-readable entities that model how clinical problems emerge through bodily impairment, temporal adaptation, environmental coupling, habitual compensation, symptom perception, institutional classification, and lived disability. Drawing on digital phenotyping, digital biomarkers, ambient AI documentation, imaging AI, digital twins, wearable monitoring, and rehabilitation kinematics, this Perspective outlines CRTC and criteria for evaluating whether richer representations improve prediction, explanation, actionability, and equitable implementation. CRTC therefore shifts the primary design question from how AI should learn to what should become available for learning.<\/jats:p>","DOI":"10.3389\/fdgth.2026.1917999","type":"journal-article","created":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T05:35:00Z","timestamp":1787636100000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["The representational bottleneck in rehabilitation AI: from human-cognitive proxies to pathway-based clinical representations"],"prefix":"10.3389","volume":"8","author":[{"given":"Eun Joo","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Rehabilitation Medicine, Seoul National University Bundang Hospital","place":["Seongnam, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seung Hyun","family":"Chung","sequence":"additional","affiliation":[{"name":"Department of Physical Medicine and Rehabilitation, National Cancer Center","place":["Goyang, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,25]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"e49655","DOI":"10.2196\/49655","article-title":"Implementing AI in hospitals to achieve a learning health system: systematic review of current enablers and barriers","volume":"26","author":"Kamel Rahimi","year":"2024","journal-title":"J Med Internet Res"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1145\/3757924","article-title":"Inherent bias in electronic health records: a scoping review of sources of bias","author":"Perets","year":"2025","journal-title":"ACM Trans Intell Syst Technol"},{"key":"B3","doi-asserted-by":"publisher","first-page":"e0000651","DOI":"10.1371\/journal.pdig.0000651","article-title":"Bias in medical AI: implications for clinical decision-making","volume":"3","author":"Cross","year":"2024","journal-title":"PLOS Digit Health"},{"key":"B4","doi-asserted-by":"publisher","first-page":"3851","DOI":"10.3390\/jcm15103851","article-title":"Machine learning-based prediction of transition to functional upper limb recovery after intensive inpatient rehabilitation in early subacute stroke","volume":"15","author":"Park","year":"2026","journal-title":"J Clin Med"},{"key":"B5","doi-asserted-by":"publisher","first-page":"7609","DOI":"10.3390\/s25247609","article-title":"Compensation strategies in post-stroke individuals: insights from upper body kinematics analysis based on inertial sensors","volume":"25","author":"Thouant","year":"2025","journal-title":"Sensors"},{"key":"B6","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/s10549-026-07952-2","article-title":"Effects of a sensorimotor-based, movement quality-focused intervention on functional mobility in breast cancer survivors: a multicenter randomized controlled trial","volume":"216","author":"Yang","year":"2026","journal-title":"Breast Cancer Res Treat"},{"key":"B7","doi-asserted-by":"publisher","first-page":"6100","DOI":"10.3390\/s23136100","article-title":"Assessing upper limb function in breast cancer survivors using wearable sensors and machine learning in a free-living environment","volume":"23","author":"Vets","year":"2023","journal-title":"Sensors"},{"key":"B8","doi-asserted-by":"publisher","first-page":"3","DOI":"10.2458\/lymph.4649","article-title":"The diagnosis and treatment of peripheral lymphedema: 2020 consensus document of the international society of lymphology","volume":"53","year":"2020","journal-title":"Lymphology"},{"key":"B9","doi-asserted-by":"publisher","first-page":"989","DOI":"10.1245\/s10434-021-10645-3","article-title":"Diagnostic criteria for breast cancer-related lymphedema of the upper extremity: the need for universal agreement","volume":"29","author":"Kassamani","year":"2022","journal-title":"Ann Surg Oncol"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1616","DOI":"10.3390\/diagnostics14151616","article-title":"Localised objective characterisation assessment of lymphoedema (LOCAL): using high-frequency ultrasound, bioelectrical impedance spectroscopy and volume to evaluate superficial tissue composition","volume":"14","author":"Sanderson","year":"2024","journal-title":"Diagnostics"},{"key":"B11","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1089\/lrb.2022.0066","article-title":"Early detection of breast cancer-related lymphedema: accuracy of indocyanine green lymphography compared with bioimpedance spectroscopy and subclinical lymphedema symptoms","volume":"21","author":"Soran","year":"2023","journal-title":"Lymphat Res Biol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1038\/s41746-025-02226-5","article-title":"Distinct visual biases affect humans and artificial intelligence in medical imaging diagnoses","volume":"9","author":"McLeod","year":"2026","journal-title":"NPJ Digit Med"},{"key":"B13","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1038\/s41746-026-02554-0","article-title":"Barriers and opportunities of scaling ambient AI scribes for clinical documentation across diverse healthcare settings","volume":"9","author":"Ohde","year":"2026","journal-title":"npj Digit Med"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-026-02664-9","article-title":"Embeddings of clinical codes enable knowledge-grounded AI in medicine","author":"Johnson","year":"2026","journal-title":"NPJ Digit Med"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2604.01661","article-title":"Ontology-aware design patterns for clinical AI systems: translating reification theory into software architecture","author":"Stummer","year":"2026","journal-title":"arXiv"},{"key":"B16","doi-asserted-by":"publisher","first-page":"103","DOI":"10.5535\/arm.240029","article-title":"Outcome measurement in balance problems: berg balance scale","volume":"48","author":"Joa","year":"2024","journal-title":"Ann Rehabil Med"},{"key":"B17","doi-asserted-by":"crossref","DOI":"10.1007\/978-94-010-0846-4","volume-title":"Analyses Concerning Passive and Active Synthesis: Lectures on Transcendental Logic","author":"Husserl","year":"2001"},{"key":"B18","volume-title":"Home and Beyond: Generative Phenomenology After Husserl","author":"Steinbock","year":"1995"},{"key":"B19","doi-asserted-by":"publisher","first-page":"5558563","DOI":"10.1155\/ecc\/5558563","article-title":"Physical and psychological burdens among breast cancer survivors: evaluating post-treatment gait impairment, falls, and depression using real-world data","volume":"2025","author":"Namoos","year":"2025","journal-title":"Eur J Cancer Care"},{"key":"B20","doi-asserted-by":"publisher","first-page":"e0245987","DOI":"10.1371\/journal.pone.0245987","article-title":"Symptom perception and functioning in patients with advanced cancer","volume":"16","author":"Yang","year":"2021","journal-title":"PLoS One"},{"key":"B21","doi-asserted-by":"publisher","first-page":"100725","DOI":"10.1016\/j.lanhl.2025.100725","article-title":"Digital biomarkers of ageing for monitoring physiological systems in community-dwelling adults","volume":"6","author":"Lu","year":"2025","journal-title":"Lancet Healthy Longev"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1500811","DOI":"10.3389\/fdgth.2024.1500811","article-title":"A novel machine learning based framework for developing composite digital biomarkers of disease progression","volume":"6","author":"Zhai","year":"2025","journal-title":"Front Digit Health"},{"key":"B23","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1038\/s41746-025-01602-5","article-title":"The comprehensive clinical benefits of digital phenotyping: from broad adoption to full impact","volume":"8","author":"Zhang","year":"2025","journal-title":"npj Digit Med"},{"key":"B24","doi-asserted-by":"publisher","first-page":"e49096","DOI":"10.2196\/49096","article-title":"Digital phenotyping for monitoring and disease trajectory prediction of patients with cancer: protocol for a prospective observational cohort study","volume":"12","author":"Jenciute","year":"2023","journal-title":"JMIR Res Protoc"},{"key":"B25","doi-asserted-by":"publisher","first-page":"2065","DOI":"10.1038\/s41591-021-01558-5","article-title":"Digital twins for predictive oncology will be a paradigm shift for precision cancer care","volume":"27","author":"Hernandez-Boussard","year":"2021","journal-title":"Nat Med"},{"key":"B26","doi-asserted-by":"publisher","first-page":"503","DOI":"10.3390\/jpm15110503","article-title":"Digital twins in personalized medicine: bridging innovation and clinical reality","volume":"15","author":"Silva","year":"2025","journal-title":"J Pers Med"},{"key":"B27","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1038\/s44387-025-00044-4","article-title":"The AI revolution: how multimodal intelligence will reshape the oncology ecosystem","volume":"1","author":"Dellamonica","year":"2025","journal-title":"npj Artif Intell"},{"key":"B28","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","article-title":"Foundation models for generalist medical artificial intelligence","volume":"616","author":"Moor","year":"2023","journal-title":"Nature"},{"key":"B29","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1038\/s41746-025-01692-1","article-title":"A scoping review of self-supervised representation learning for clinical decision making using EHR categorical data","volume":"8","author":"Zheng","year":"2025","journal-title":"npj Digit Med"},{"key":"B30","doi-asserted-by":"publisher","first-page":"e54934","DOI":"10.2196\/54934","article-title":"The applications of artificial intelligence for assessing fall risk: systematic review","volume":"26","author":"Gonzalez-Castro","year":"2024","journal-title":"J Med Internet Res"},{"key":"B31","doi-asserted-by":"publisher","first-page":"e15429","DOI":"10.2196\/15429","article-title":"Innovative assisted living tools, remote monitoring technologies, artificial intelligence-driven solutions, and robotic systems for aging societies: systematic review","volume":"2","author":"Sapci","year":"2019","journal-title":"JMIR Aging"},{"key":"B32","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1038\/s41746-024-01047-2","article-title":"Why we should not mistake accuracy of medical AI for efficiency","volume":"7","author":"Jongsma","year":"2024","journal-title":"NPJ Digit Med"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1917999\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T05:35:02Z","timestamp":1787636102000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1917999\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,25]]},"references-count":32,"alternative-id":["10.3389\/fdgth.2026.1917999"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2026.1917999","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,25]]},"article-number":"1917999"}}