Stress Estimation in Elderly Oncology Patients Using Visual Wearable Representations and Multi-Instance Learning

TL;DR

This study develops a wearable-based, multi-instance learning approach to estimate perceived stress in elderly breast cancer patients, enabling continuous stress monitoring beyond traditional patient-reported measures.

Contribution

Introduces a novel multimodal wearable data representation and a lightweight MIL model for stress estimation in elderly oncology patients.

Findings

Moderate correlation between predicted and questionnaire stress scores (R^2 up to 0.28)

Achieved RMSE around 6.1-6.6 and MAE around 5.5-6.1 at 3 and 6 months

Demonstrates feasibility of continuous stress assessment using wearable sensors and weak supervision

Abstract

Psychological stress is clinically relevant in cardio-oncology, yet it is typically assessed only through patient-reported outcome measures (PROMs) and is rarely integrated into continuous cardiotoxicity surveillance. We estimate perceived stress in an elderly, multicenter breast cancer cohort (CARDIOCARE) using multimodal wearable data from a smartwatch (physical activity and sleep) and a chest-worn ECG sensor. Wearable streams are transformed into heterogeneous visual representations, yielding a weakly supervised setting in which a single Perceived Stress Scale (PSS) score corresponds to many unlabeled windows. A lightweight pretrained mixture-of-experts backbone (Tiny-BioMoE) embeds each representation into 192-dimensional vectors, which are aggregated via attention-based multiple instance learning (MIL) to predict PSS at month 3 (M3) and month 6 (M6). Under leave-one-subject-out (LOSO) evaluation, predictions showed moderate agreement with questionnaire scores (M3: R^2=0.24, Pearson r=0.42, Spearman rho=0.48; M6: R^2=0.28, Pearson r=0.49, Spearman rho=0.52), with global RMSE/MAE of 6.62/6.07 at M3 and 6.13/5.54 at M6.