| Unique ID issued by UMIN | UMIN000061599 |
|---|---|
| Receipt number | R000070479 |
| Scientific Title | Development of an FIM Prediction Model for Stroke Patients in Convalescent Rehabilitation Wards Considering the Impact of Aging |
| Date of disclosure of the study information | 2026/05/31 |
| Last modified on | 2026/05/17 06:11:25 |
Development of an AI Model to Predict Functional Recovery after Stroke Rehabilitation
stroke AI-based Rehabilitation prognosis prediction with Advanced Interpretability
Development of an FIM Prediction Model for Stroke Patients in Convalescent Rehabilitation Wards Considering the Impact of Aging
Aging-aware Gradient Estimation of FIM in stroke rehabilitation
| Japan |
stroke
| Rehabilitation medicine |
Others
NO
To develop a Random Forest model predicting discharge FIM scores in stroke patients in convalescent rehabilitation wards, incorporating aging-related variables, and to evaluate its predictive accuracy and clinical interpretability using SHAP analysis.
Efficacy
Discharge motor FIM total score
- Discharge total FIM score - Discharge cognitive FIM total score- Individual FIM sub-item scores- Model performance - Variable contribution via SHAP values- Age-stratified model performance
Observational
| Not applicable |
| Not applicable |
Male and Female
Patients admitted to the convalescent rehabilitation ward at Shin-Sapporo Neurosurgical Hospital between January 2018 and March 2020
Patients with a primary diagnosis of cerebral infarction or intracerebral hemorrhage
Patients with a length of stay in the convalescent rehabilitation ward of at least one month
Patients with a history of neurological diseases (e.g., Parkinson's disease, multiple sclerosis)
Patients with a history of psychiatric disorders (e.g., schizophrenia, bipolar disorder)
Patients with a history or complication of brain tumor
Patients who experienced clinical deterioration during hospitalization (e.g., stroke recurrence, pneumonia, exacerbation of heart failure)
Patients with blindness
Patients who developed stroke during hospitalization at another medical facility
Patients with missing data
300
| 1st name | ryo |
| Middle name | |
| Last name | matsuda |
Hokkaido University of Science
department of Physical Therapy Faculty of Health Sciences
0068585
4-1, 15-chome, Maeda 7-jo, Teine-ku, Sapporo, Hokkaido 006-8585, Japan
0116887197
matsuda-r@hus.ac.jp
| 1st name | ryo |
| Middle name | |
| Last name | matsuda |
Hokkaido University of Science
department of Physical Therapy Faculty of Health Sciences
0068585
4-1, 15-chome, Maeda 7-jo, Teine-ku, Sapporo, Hokkaido 006-8585, Japan
0116887197
matsuda-r@hus.ac.jp
Hokkaido University of Science
Ryo Matsuda
Hokkaido University of Science
Other
Department of Rehabilitation, Neuroscience Research Center Shin Sapporo Neurosurgical Hospital
2-10, 6-chome, Atsubetsu-chuo 1-jo, Atsubetsu-ku, Sapporo, Hokkaido 004-0051, Japan
0118912500
pt@snh.or.jp
NO
| 2026 | Year | 05 | Month | 31 | Day |
Unpublished
304
No longer recruiting
| 2022 | Year | 03 | Month | 07 | Day |
| 2022 | Year | 03 | Month | 07 | Day |
| 2022 | Year | 03 | Month | 07 | Day |
| 2026 | Year | 04 | Month | 30 | Day |
This study was approved by the Ethics Committee of the Graduate School of Health Sciences, Hirosaki University (approval number: 2025-008, approval date: August 18 , 2025) and the Institutional Review Board of Shin-Sapporo Neurosurgical Hospital (approval date: March 7, 2022) as a retrospective observational study using existing clinical data. Individual informed consent was waived, and study information is disclosed on the hospital's notice board and website (opt-out approach). All data will be anonymized prior to analysis.
| 2026 | Year | 05 | Month | 17 | Day |
| 2026 | Year | 05 | Month | 17 | Day |
Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000070479