Reinforcement Learning–Based Digital Therapeutic Intervention for Postprostatectomy Incontinence: Development and Pilot Feasibility Study
Reinforcement-Learning-basierte digitale therapeutische Intervention bei postprostatektischer Inkontinenz: Entwicklung und Pilot-Feasibility-Studie
JMIR Cancer · 2026-02-06 · 12 · e83375
DOI: 10.2196/83375 ↗Auf einen Blick
Eine RL-gestützte Intervention für PPI wurde entwickelt und in einer 3-monatigen Pilotstudie mit 16 Patient:innen auf Durchführbarkeit geprüft. Es zeigten sich günstige, explorative Veränderungen mehrerer Symptome.
Fragestellung
Entwicklung und erste Prüfung eines RL-gestützten klinischen Verhaltensinterventions-Systems für adaptive, personalisierte Rehabilitation bei PPI.
Methode
Zweistufige Studie: Entwicklung eines CBIS mit prospektiver Kohorte und 3-Tage-Blasentagebüchern; danach einarmige Pre-Post-Pilotstudie über 3 Monate mit 16 Patient:innen.
Ergebnisse
Feasibility günstig, mittlere Nutzungsfrequenz 5,2 (SD 1,1) pro Tag. Tagesharnfrequenz 5,74 auf 4,69/Tag, Nachtfrequenz 1,8 auf 1,0/Nacht, Inkontinenzepisoden 7,0 auf 4,0/Tag.
Einschränkungen
Einarmiges Design, kleine Stichprobe und keine Kontrollgruppe; Ergebnisse explorativ und hypothesengenerierend.
Schlussfolgerung der Autor:innen
Das CBIS ist das erste RL-gestützte digitale Therapiesystem für PPI und ermöglicht adaptive, evidenzbasierte Verhaltensoptimierung; weitere multizentrische Studien sind nötig.
Kernaussagen
- Hohe Systemnutzung während der 3 Monate
- Mehrere Symptome verbesserten sich in der Pre-Post-Analyse
- Keine Kontrollgruppe; klinische Wirksamkeit nicht bestätigt
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
At a glance
Journal article in JMIR Cancer, published online on 2026-02-06. Written by Fan Fan and 9 co-authors. Institution: Department of Urology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China. Major MEDLINE topics: Prostatectomy, Urinary Incontinence, Postoperative Complications. Cited 1 times so far (Crossref); 39 references. The full text is freely available in PubMed Central.
Topics: Inkontinenz
Abstract (original language)
Background
Postprostatectomy incontinence (PPI) is a common complication after robot-assisted radical prostatectomy and significantly impairs patients’ quality of life. Although behavioral interventions such as pelvic floor muscle training and bladder diaries are evidence-based, their effectiveness is often limited by poor adherence and lack of personalization.
Objective
This study aimed to develop and evaluate a reinforcement learning (RL)–driven clinical behavioral intervention-supporting system (CBISs) for adaptive, personalized rehabilitation in patients with PPI.
Methods
The study comprised 2 sequential stages. First, the CBISs was developed through (1) construction of a medical record database from a prospective cohort of PPI patients using standardized 3-day bladder diaries, (2) design of functional modules and user interfaces based on clinical rehabilitation needs, and (3) development of an RL model using XGBoost (extreme gradient boosting) and Bayesian optimization to generate individualized training plans. Second, a separate cohort of 16 patients participated in a single-arm, pre-post pilot study to evaluate feasibility and preliminary outcome trends over a 3-month intervention period, with assessments based on bladder diary parameters and system usage metrics.
Results
The CBISs successfully implemented an adaptive, closed-loop behavioral rehabilitation framework that dynamically tailored training recommendations according to individual voiding patterns, fluid intake behaviors, and adherence signals. Feasibility outcomes were favorable, with high system engagement observed throughout the intervention (mean usage frequency 5.2, SD 1.1 times per day). In exploratory pre-post analyses (n=16), consistent directional improvements were observed across multiple outcomes. Mean daytime urinary frequency decreased from 5.74 (SD 1.21) episodes per day to 4.69 (SD 1.08) episodes per day, while median nighttime urinary frequency declined from 1.8 (IQR 1.6-2.2) episodes per night to 1.0 (IQR 1.0-1.6) episodes per night. Median incontinence episodes were reduced from 7.0 (IQR 6.0-11.0) episodes per day to 4.0 (IQR 2.0-6.0) episodes per day. Objective urine leakage measured by the 1-hour pad test decreased from a median of 8.5 (IQR 4.0-19.0) g to 3.5 (IQR 2.0-9.0) g. Patient-reported symptom burden, assessed using the International Consultation on Incontinence Questionnaire–Short Form (ICIQ-UI SF), showed a median reduction from 14.0 (IQR 12.0-20.0) points to 9.0 (IQR 6.0-16.0) points. Although several within-participant changes were statistically detectable, effect magnitudes varied across individuals. Given the single-arm design, small sample size, and lack of a control group, findings are presented as exploratory and hypothesis-generating rather than confirmatory of clinical efficacy.
Conclusions
The CBISs represents the first RL-powered digital therapeutic system for PPI, enabling adaptive, evidence-based behavioral optimization. By addressing limitations of static rehabilitation protocols and declining adherence, it offers a scalable approach for personalized PPI management. Future multicenter trials are needed to confirm its clinical effectiveness.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Urology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China.
- The Nethersole School of Nursing, Faculty of Medicine, Chinese University of Hong Kong, Hong Kong, China (Hong Kong).
- Department of Nursing, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China.
ORCID profiles: Fan Fan, Hao Huang, Jingwen Yan, Chao-Yue Xu, Xiuhua Wu, Chunmei Zhou, Dandan Wen, Hai Huang, Ho Cheung Li, Yihong Qiu
Cite
APA
Fan, F., Huang, H., Yan, J., Xu, C. Y., Wu, X., Zhou, C., Wen, D., Huang, H., Li, H. C., & Qiu, Y. (2026). Reinforcement Learning–Based Digital Therapeutic Intervention for Postprostatectomy Incontinence: Development and Pilot Feasibility Study. JMIR Cancer, 12, e83375. https://doi.org/10.2196/83375
Vancouver
Fan F, Huang H, Yan J, Xu CY, Wu X, Zhou C, et al. Reinforcement Learning–Based Digital Therapeutic Intervention for Postprostatectomy Incontinence: Development and Pilot Feasibility Study. JMIR Cancer. 2026;12:e83375. doi:10.2196/83375
BibTeX
@article{Fan2026,
author = {Fan, Fan and Huang, Hao and Yan, Jingwen and Xu, Chao-Yue and Wu, Xiuhua and Zhou, Chunmei and Wen, Dandan and Huang, Hai and Li, Ho Cheung and Qiu, Yihong},
title = {Reinforcement Learning–Based Digital Therapeutic Intervention for Postprostatectomy Incontinence: Development and Pilot Feasibility Study},
journal = {JMIR Cancer},
year = {2026},
volume = {12},
pages = {e83375},
doi = {10.2196/83375}
}
EUVIMED