{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T13:50:51Z","timestamp":1791294651445,"version":"4.1.0"},"reference-count":52,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T00:00:00Z","timestamp":1791244800000},"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. Neurol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Early identification of stroke survivors who are unlikely to achieve clinically meaningful motor improvement after aquatic therapy may help optimize rehabilitation prescriptions and support precision rehabilitation. This study aimed to develop and validate machine-learning models based on pretreatment Fugl-Meyer Assessment (FMA) data to predict insufficient motor improvement after aquatic therapy, to examine whether actual aquatic-therapy exposure improves prediction, and to identify the most important predictors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We conducted a single-center retrospective study of patients with stroke who received the routine aquatic rehabilitation programme in the Department of Rehabilitation Medicine between January 2022 and December 2025. The primary outcome was insufficient improvement in total Fugl-Meyer motor function at day 56 \u00b1 7 days after the start of aquatic therapy, defined as \u0394 FMA &amp;lt;10 points; total FMA was recalculated as FMA upper-extremity plus lower-extremity scores. Temporal validation was used: cases from January 2022 to December 2024 formed the training set, and cases from January to December 2025 formed the temporal validation set. Two modeling strategies were developed. Model A included baseline clinical information and the initial rehabilitation and aquatic-therapy plans available after prescription and before the first aquatic session. Model B added actual treatment-execution parameters accumulated through day 14 (allowable landmark window, days 12\u201316). ExtraTrees, Random Forest, XGBoost, logistic regression and K-nearest neighbors were compared, and model performance was assessed with the area under the receiver operating characteristic curve (AUC), calibration, decision-curve analysis (DCA) and Shapley additive explanations (SHAP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 1,320 patients were included, of whom 409 had insufficient FMA improvement after aquatic therapy. The development set included 786 patients and 241 events, and the temporal validation set included 534 patients and 168 events. In the temporal validation set, Random Forest performed best for Model A, with an AUC of 0.818 [95% confidence interval (CI) 0.777\u20130.853] and Brier score of 0.172 (95% CI 0.160\u20130.186). At the frozen sensitivity-prioritized threshold of 0.408, Model A had an accuracy of 0.700, sensitivity of 0.857, specificity of 0.628, positive predictive value of 0.514, negative predictive value of 0.906 and F1 score of 0.643. Random Forest also performed best for Model B, with an AUC of 0.814 (95% CI 0.774\u20130.850) and Brier score of 0.174 (95% CI 0.163\u20130.186). The paired change in AUC was \u22120.004 (95% CI \u22120.022 to 0.014). Model A SHAP analysis highlighted planned aquatic-course duration, planned weekly aquatic frequency, baseline FMA-LE, baseline upper-extremity FMA and time from stroke onset to rehabilitation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The interpretable Model A used routine clinical data and initial rehabilitation prescriptions available before the first aquatic session and was evaluated in a later cohort from the same center. Model B analysis illustrates how risk could be updated at day 14 once genuine execution records become available. These analyses do not show that model-guided treatment adjustment improves motor recovery; external validation and prospective clinical-impact evaluation are required before clinical use.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2026.1871732","type":"journal-article","created":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T12:52:27Z","timestamp":1791291147000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development of an interpretable machine-learning model to predict insufficient functional improvement after aquatic therapy in stroke"],"prefix":"10.3389","volume":"17","author":[{"given":"Ying","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Rehabilitation, Beijing Rehabilitation Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Disabled Persons Rehabilitation Service Center","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuyan","family":"Qie","sequence":"additional","affiliation":[{"name":"Department of Rehabilitation, Beijing Rehabilitation Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,6]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"880","DOI":"10.1177\/23969873231191304","article-title":"Motor rehabilitation after stroke: European Stroke Organisation (ESO) consensus-based definition and guiding framework","volume":"8","author":"Kwakkel","year":"2023","journal-title":"European Stroke J."},{"key":"B2","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1016\/j.neuroscience.2025.03.017","article-title":"Artificial intelligence in stroke rehabilitation: from acute care to long-term recovery","volume":"572","author":"Kopalli","year":"2025","journal-title":"Neuroscience."},{"key":"B3","doi-asserted-by":"publisher","first-page":"6585","DOI":"10.3390\/s24206585","article-title":"AI Applications in adult stroke recovery and rehabilitation: a scoping review using AI","volume":"24","author":"Senadheera","year":"2024","journal-title":"Sensors (Basel, Switzerland)."},{"key":"B4","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/j.pmr.2023.06.003","article-title":"Biomarkers of motor outcomes after stroke","volume":"35","author":"Ackerley","year":"2024","journal-title":"Phys Med Rehabil Clin N Am."},{"key":"B5","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1111\/ane.13371","article-title":"Aquatic therapy in stroke rehabilitation: systematic review and meta-analysis","volume":"143","author":"Veldema","year":"2021","journal-title":"Acta Neurol Scand."},{"key":"B6","first-page":"429","article-title":"Effect of water exercise therapy on Lower Limb Function Rehabilitation in Hemiplegic Patients with the First Stroke","volume":"29","author":"Bei","year":"2023","journal-title":"Altern Ther Health Med."},{"key":"B7","doi-asserted-by":"publisher","first-page":"e27825","DOI":"10.1097\/MD.0000000000027825","article-title":"The efficacy of aquatic therapy in stroke rehabilitation: A protocol for systematic review and meta-analysis","volume":"100","author":"Li","year":"2021","journal-title":"Medicine."},{"key":"B8","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1186\/s12984-024-01523-6","article-title":"Predicting upper limb motor recovery in subacute stroke patients via fNIRS-measured cerebral functional responses induced by robotic training","volume":"21","author":"Zhou","year":"2024","journal-title":"J Neuroeng Rehabil."},{"key":"B9","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1186\/s12984-022-01032-4","article-title":"Machine learning methods for functional recovery prediction and prognosis in post-stroke rehabilitation: a systematic review","volume":"19","author":"Campagnini","year":"2022","journal-title":"J Neuroeng Rehabil."},{"key":"B10","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1186\/s12874-025-02516-2","article-title":"The reporting quality and methodological quality of dynamic prediction models for cancer prognosis","volume":"25","author":"Yan","year":"2025","journal-title":"BMC Med Res Methodol."},{"key":"B11","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s12874-021-01469-6","article-title":"Completeness of reporting of clinical prediction models developed using supervised machine learning: a systematic review","volume":"22","author":"Andaur Navarro","year":"2022","journal-title":"BMC Med Res Methodol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1016\/j.jocn.2021.08.009","article-title":"Effects of cognitive motor dual-task training on stroke patients: A RCT-based meta-analysis","volume":"92","author":"Zhou","year":"2021","journal-title":"J Clin Neurosci Offic J Neurosurg Soc Australasia."},{"key":"B13","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ."},{"key":"B14","doi-asserted-by":"publisher","first-page":"4812","DOI":"10.26355\/eurrev_202306_32598","article-title":"Artificial Intelligence machine learning and conventional physical therapy for upper limb outcome in patients with stroke: a systematic review and meta-analysis","volume":"27","author":"Mahmoud","year":"2023","journal-title":"Eur Rev Med Pharmacol Sci."},{"key":"B15","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv Neural Inf Process Syst."},{"key":"B16","doi-asserted-by":"publisher","first-page":"1417","DOI":"10.1109\/TBME.2020.3036095","article-title":"Evaluating Rehabilitation Progress Using Motion Features Identified by Machine Learning","volume":"68","author":"Lu","year":"2021","journal-title":"IEEE Trans Biomed Eng."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.1177\/23969873251338142","article-title":"European Stroke Organisation (ESO) guideline on motor rehabilitation","volume":"10","author":"Alt Murphy","year":"2025","journal-title":"European Stroke J."},{"key":"B18","doi-asserted-by":"publisher","first-page":"7705397010","DOI":"10.5014\/ajot.2023.077501","article-title":"Occupational Therapy Practice Guidelines for Adults With Stroke","volume":"77","author":"Hildebrand","year":"2023","journal-title":"Am J Occup Therapy Offic Public Am Occup Therapy Assoc."},{"key":"B19","doi-asserted-by":"publisher","first-page":"5728","DOI":"10.3390\/ijerph20095728","article-title":"Gait training with functional electrical stimulation improves mobility in people post-stroke","volume":"20","author":"Dantas","year":"2023","journal-title":"Int J Environ Res Public Health."},{"key":"B20","doi-asserted-by":"publisher","first-page":"CD006185","DOI":"10.1002\/14651858.CD006185.pub6","article-title":"Electromechanical-assisted training for walking after stroke","volume":"5","author":"Mehrholz","year":"2025","journal-title":"Cochr Database System Rev."},{"key":"B21","doi-asserted-by":"publisher","first-page":"101674","DOI":"10.1016\/j.rehab.2022.101674","article-title":"Effect of wearable exoskeleton on post-stroke gait: a systematic review and meta-analysis","volume":"66","author":"Hsu","year":"2023","journal-title":"Ann Phys Rehabil Med."},{"key":"B22","doi-asserted-by":"publisher","first-page":"7802180070","DOI":"10.5014\/ajot.2024.050391","article-title":"Effectiveness of activity-based task-oriented training on upper extremity recovery for adults with atroke: a systematic review","volume":"78","author":"Lee","year":"2024","journal-title":"Am J Occup Therapy Offic Public Am Occup Therapy Assoc."},{"key":"B23","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1186\/s12916-023-03029-9","article-title":"Vestibular rehabilitation therapy on balance and gait in patients after stroke: a systematic review and meta-analysis","volume":"21","author":"Meng","year":"2023","journal-title":"BMC Med."},{"key":"B24","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1080\/10749357.2021.1899700","article-title":"Reliability and validity of Japanese version of Fugl-Meyer assessment for the lower extremities","volume":"29","author":"Nakazono","year":"2022","journal-title":"Top Stroke Rehabil."},{"key":"B25","doi-asserted-by":"publisher","first-page":"83","DOI":"10.5535\/arm.20225","article-title":"The Korean version of the Fugl-Meyer assessment: reliability and validity evaluation","volume":"45","author":"Kim","year":"2021","journal-title":"Ann Rehabil Med."},{"key":"B26","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1186\/s12984-024-01372-3","article-title":"Effect of task-oriented training assisted by force feedback hand rehabilitation robot on finger grasping function in stroke patients with hemiplegia: a randomised controlled trial","volume":"21","author":"Li","year":"2024","journal-title":"J Neuroeng Rehabil."},{"key":"B27","doi-asserted-by":"publisher","first-page":"391","DOI":"10.23736\/S1973-9087.24.08307-2","article-title":"Can cerebellar theta-burst stimulation improve balance function and gait in stroke patients? A randomized controlled trial","volume":"60","author":"Zhu","year":"2024","journal-title":"European J Phys Rehabil Med."},{"key":"B28","doi-asserted-by":"publisher","first-page":"2100711","DOI":"10.1109\/JTEHM.2022.3208585","article-title":"Wearable sensors improve prediction of post-stroke walking function following inpatient rehabilitation","volume":"10","author":"O'Brien","year":"2022","journal-title":"IEEE J Transl Eng Health Med."},{"key":"B29","doi-asserted-by":"publisher","first-page":"1265","DOI":"10.1080\/07853890.2022.2059557","article-title":"Pre-stroke socioeconomic status predicts upper limb motor recovery after inpatient neurorehabilitation","volume":"54","author":"Wolf","year":"2022","journal-title":"Ann Med."},{"key":"B30","doi-asserted-by":"publisher","first-page":"1619","DOI":"10.1002\/acn3.70077","article-title":"Precision-optimised post-stroke prognoses","volume":"12","author":"Hope","year":"2025","journal-title":"Ann Clin Transl Neurol."},{"key":"B31","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1136\/jnnp-2023-331996","article-title":"The relationship between corticospinal excitability and structural integrity in stroke patients","volume":"96","author":"Daghsen","year":"2024","journal-title":"J Neurol Neurosurg Psychiatry."},{"key":"B32","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1177\/15459683251351879","article-title":"Prediction of motor recovery after subacute cerebral infarction: role of corticocerebellar pathway integrity","volume":"39","author":"Liu","year":"2025","journal-title":"Neurorehabil Neural Repair."},{"key":"B33","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1177\/15459683241281299","article-title":"Altered corticospinal and intracortical excitability after stroke: a systematic review with meta-analysis","volume":"38","author":"Washabaugh","year":"2024","journal-title":"Neurorehabil Neural Repair."},{"key":"B34","doi-asserted-by":"publisher","first-page":"e14471","DOI":"10.1111\/cns.14471","article-title":"Neurophysiological characterization of stroke recovery: a longitudinal TMS and EEG study","volume":"30","author":"Ding","year":"2024","journal-title":"CNS Neurosci Therap."},{"key":"B35","doi-asserted-by":"publisher","first-page":"e082505","DOI":"10.1136\/bmj-2024-082505","article-title":"PROBAST+AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods","volume":"388","author":"Moons","year":"2025","journal-title":"BMJ"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1626","DOI":"10.1080\/09593985.2022.2049939","article-title":"Aquatic strength training improves postural stability and walking function in stroke patients","volume":"39","author":"Gu","year":"2023","journal-title":"Physiother Theory Pract."},{"key":"B37","doi-asserted-by":"publisher","first-page":"5636","DOI":"10.1002\/hbm.25643","article-title":"Coherent neural oscillations inform early stroke motor recovery","volume":"42","author":"Cassidy","year":"2021","journal-title":"Hum Brain Mapp."},{"key":"B38","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1177\/15459683211054178","article-title":"Machine learning for predicting motor improvement after acute subcortical infarction using baseline whole brain volumes","volume":"36","author":"Liu","year":"2022","journal-title":"Neurorehabil Neural Repair."},{"key":"B39","doi-asserted-by":"publisher","first-page":"1211","DOI":"10.1093\/brain\/awab469","article-title":"Functional connectivity drives stroke recovery: shifting the paradigm from correlation to causation","volume":"145","author":"Cassidy","year":"2022","journal-title":"Brain J Neurol."},{"key":"B40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TBME.2026.3698000","article-title":"EEG ensemble learning framework for prognostic prediction of post-rTMS motor recovery in stroke","author":"Jia","year":"2026","journal-title":"IEEE Trans Biomed Eng."},{"key":"B41","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1097\/NPT.0000000000000347","article-title":"A clinical practice guideline for the use of ankle-foot orthoses and functional electrical stimulation post-stroke","volume":"45","author":"Johnston","year":"2021","journal-title":"J Neurol Phys Therapy: JNPT."},{"key":"B42","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.gaitpost.2021.08.016","article-title":"Treatment of knee hyperextension in post-stroke gait","volume":"91","author":"Geerars","year":"2022","journal-title":"System Rev Gait Posture."},{"key":"B43","doi-asserted-by":"publisher","first-page":"12229","DOI":"10.3390\/ijerph182212229","article-title":"The effects of sit-to-stand training combined with real-time visual feedback on strength, balance, gait ability, and quality of life in patients with stroke: a randomized controlled trial","volume":"18","author":"Hyun","year":"2021","journal-title":"Int J Environ Res Public Health."},{"key":"B44","doi-asserted-by":"publisher","first-page":"1098","DOI":"10.3390\/medicina57101098","article-title":"Effects of task-specific training after cognitive sensorimotor exercise on proprioception, spasticity, and gait speed in stroke patients: a randomized controlled study","volume":"57","author":"Kim","year":"2021","journal-title":"Medicina (Kaunas, Lithuania)"},{"key":"B45","doi-asserted-by":"publisher","first-page":"1148","DOI":"10.1097\/PHM.0000000000002016","article-title":"Effect of dual-task training on gait and balance in stroke patients: an updated meta-analysis","volume":"101","author":"Shu","year":"2022","journal-title":"Am J Phys Med Rehabil."},{"key":"B46","doi-asserted-by":"publisher","first-page":"1186","DOI":"10.1177\/02692155221097033","article-title":"Effects of dual-task training on gait and balance in stroke patients: a meta-analysis","volume":"36","author":"Zhang","year":"2022","journal-title":"Clin Rehabil."},{"key":"B47","doi-asserted-by":"publisher","first-page":"349","DOI":"10.3233\/NRE-220275","article-title":"Effectiveness of physical therapy interventions on post-stroke spasticity: an umbrella review","volume":"52","author":"Brusola","year":"2023","journal-title":"NeuroRehabilitation."},{"key":"B48","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1186\/s12984-024-01493-9","article-title":"Effectiveness of unilateral lower-limb exoskeleton robot on balance and gait recovery and neuroplasticity in patients with subacute stroke: a randomized controlled trial","volume":"21","author":"Huo","year":"2024","journal-title":"J Neuroeng Rehabil."},{"key":"B49","doi-asserted-by":"publisher","first-page":"521","DOI":"10.21037\/apm-21-3710","article-title":"Effects of physical therapy-based rehabilitation on recovery of upper limb motor function after stroke in adults: a systematic review and meta-analysis of randomized controlled trials","volume":"11","author":"Huang","year":"2022","journal-title":"Ann Palliat Med."},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2026.3724147","article-title":"Patient-specific non-invasive epileptogenic zone localization via high-resolution time-frequency representations and CNN deep learning","author":"Wang","year":"2026","journal-title":"IEEE Transac Biomed Eng."},{"key":"B51","doi-asserted-by":"publisher","first-page":"1712","DOI":"10.1002\/jmri.29617","article-title":"Diagnosis of major depressive disorder based on individualized brain functional and structural connectivity","volume":"61","author":"Guo","year":"2025","journal-title":"J Magn Reson Imaging."},{"key":"B52","doi-asserted-by":"publisher","first-page":"106996","DOI":"10.1016\/j.bspc.2024.106996","article-title":"MTNet: Multimodal transformer network for mild depression detection through fusion of EEG and eye tracking","volume":"100","author":"Zhu","year":"2025","journal-title":"Biomed Signal Process Control."}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1871732\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T12:52:29Z","timestamp":1791291149000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1871732\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,6]]},"references-count":52,"alternative-id":["10.3389\/fneur.2026.1871732"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2026.1871732","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,6]]},"article-number":"1871732"}}