JMIR Publications

ABSTRACT

Background:

Detecting peripheral neuropathy (PNP) is crucial in preventing complications such as foot ulceration. Clinical examinations for PNP are infrequently provided to high-risk patients due to restrictions on facilities, care providers, or time. A gamified health assessment approach combining wearable sensors holds the potential to address these challenges and provide individuals with instantaneous feedback on their health status.

Objective:

We aimed to develop and evaluate an application that assesses PNP through video games controlled by pressure sensor-equipped insoles.

Methods:

In the proof-of-concept exploratory cohort study, a complete game-based framework that allowed the study participant to play four video games solely by modulating plantar pressure values was established. Foot plantar pressures were measured by the insole and transferred via Bluetooth to an Android tablet for game control in real time. Game results and sensor data were delivered to the study server for visualization and analysis. 299 patients with diabetes mellitus and 30 with metabolic syndrome were tested utilizing the game application. Patients’ game performance was assessed by extracting features from gaming data set and further compared with nerve conduction studies (NCS) findings, neuropathy symptoms and disability scores. Predictive models for PNP were trained with 70% of acquired data and validated on a held-out testing data set.

Results:

Overall, clinically evident PNP was present in 247 participants (75.1%), with 88 (26.7%) showing asymmetric affection. In a Subcohort (n=37) undergoing NCS as gold standard nerve conduction velocities and nerve amplitudes significantly correlated with 79 independent game features (|R|>0.4, highest R-value +0.65, p<0.001; adjusted R2=0.36). Within another Subcohort (n=173) with normal cognitive abilities and matched co-variates (age, gender, BMI, etc.), hypothesis-driven key capabilities and specific game features were significantly correlated with the presence of PNP. Predictive models using selected game features achieved 76.1% (left) and 81.7% (right foot) accuracy for PNP detection. Multi-class models yielded AUC of 0.76 (left) and 0.72 (right foot) for assessing nerve damage patterns (small, large, or mixed nerve fiber damage).

Conclusions:

The game-based application presents a promising avenue for methodological PNP screening, potentially facilitating evaluation of peripheral nerve status. Evaluation in expanded cohorts may iteratively optimize AI model efficacy. Clinical Trial: Not applicable.