Using wearable device monitoring and artificial intelligence to develop predictive moels for predicting survival after radical cystectomy for bladder cancer-a secondary outcome analysis of the iROC trial.

Khetrapal P.; Liu Y.; Vasdev N.; Ahmed I.; Charlesworth P.; Shamim Khan M.; Hanchanale V.; Kotwal S.; Rowe E.; McGrath J.

Using wearable device monitoring and artificial intelligence to develop predictive moels for predicting survival after radical cystectomy for bladder cancer-a secondary outcome analysis of the iROC trial.

All Authors

Khetrapal P.

Liu Y.

Vasdev N.

Ahmed I.

Charlesworth P.

Shamim Khan M.

Hanchanale V.

Kotwal S.

Rowe E.

McGrath J.

LTHT Author

Kotwal, Sanjeev

LTHT Department

Abdominal Medicine & Surgery
Urology

Publication Date

2024

Item Type

Conference Abstract

Subject

CYSTECTOMY , ARTIFICIAL INTELLIGENCE , BIOMEDICAL RESEARCH , SURVIVAL RATE , URINARY BLADDER NEOPLASMS , MONITORING, AMBULATORY , MOTOR ACTIVITY

Abstract

Introduction: Associations between survival rates after undergoing radical cystectomy (RC) for bladder cancer and activity levels have not been reported. Material(s) and Method(s): The iROC randomized trial (NCT03049410) compared recovery following intracorporeal robot-Assisted RC (iRARC) vs open RC (ORC) for bladder cancer. Physical activity levels were collected as steps per over a 7-day period using a wrist-worn device at baseline and 12 weeks post-operatively. Stamina was measured using the 30-second chair-To-stand assessment at similar timepoints. Clinicopathological data was collected, and cross-sectional imaging was used to determine recurrence-free survival (RFS), and overall survival (OS). Result(s): Among 338 patients in the iROC trial, 319 patients received RC. Overall survival following RC was 87% (319-41/319) patients and RFS was 82% (319-57/319) over a median follow-up of 33 months. Wearable device data was available for 165 patients for analysis. Using clinicopathological features including age, gender, BMI, pathological T-stage and surgical margin, we demonstrated an AUC of 74% to predict RFS which improved slightly to 76% on adding activity and stamina data. For prediction of OS, using clinicopathological features demonstrated an AUC of 71%, which improved to 81% with the addition of activity and stamina data. Kaplan Meier analysis with patients divided into low and high risk groups by the final model showed an increased PFS (99% vs 59%) and OS (98% vs 53%) in 33 months after surgery. Conclusion(s): Wearable device and stamina data may offer additional prognostic information which could supplement traditional clinicopathological features.