Remote Monitoring of Chemotherapy-Induced Peripheral Neuropathy via NeuroDetect iOS App (Preprint)

Abstract

Chemotherapy-induced peripheral neuropathy (CIPN) is a common and debilitating adverse effect of neurotoxic chemotherapy characterized by symptoms such as numbness, tingling, and weakness. Effective monitoring and detection of CIPN are crucial for avoiding progression to irreversible symptoms. Due to the inconvenience of clinic-based objective assessment, CIPN detection relies primarily on patients’ reporting of subjective symptoms, and patient-reported outcomes (PROs) are used to facilitate CIPN detection. Our prior study found evidence that objective functional assessments completed via a smartphone app may differentiate patients with and without CIPN after treatment.

This longitudinal study aims to evaluate app-based remote monitoring of CIPN in patients with cancer undergoing neurotoxic chemotherapeutic treatment and to compare app-based CIPN detection with PRO.

The NeuroDetect app includes subjective EORTC QLQ-CIPN20 (CIPN20) and six objective functional assessments that use smartphone sensors to mimic neurological examinations, such as walking, standing, and manual dexterity tests. The functional assessment data were collected from patients with cancer undergoing neurotoxic chemotherapy, and a neurological examination was conducted at the end of treatment to diagnose CIPN in the feet (CIPN-f) or hands (CIPN-h). Various classification models including NeuroDetect features and/or CIPN20 items were trained and evaluated for accuracy in predicting CIPN probability.

Of the 45 patients who completed functional assessments and neurological examinations, 24 had CIPN-f, and 29 had CIPN-h. The NeuroDetect model could discriminate between patients with and without CIPN-f (AUC = 83.8%) but not CIPN-h (AUC = 67.9%). The rolling rotation features from the eyes-closed phase of the Romberg Stance assessment showed the greatest contribution to CIPN-f. NeuroDetect-only models had numerically superior performance to CIPN20-only models in both CIPN-f and CIPN-h, and the combination of NeuroDetect and CIPN20 numerically outperformed either assessment strategy individually.

Our findings suggest that remote smartphone based functional CIPN assessment may improve CIPN detection during treatment. Integration of subjective and objective assessment provides a comprehensive approach to monitoring CIPN. Future work should refine the functional assessments and models to enhance clinical feasibility and usability.