Machine learning based digital assessment of mild cognitive impairment using mouse trajectories during the trail making test

Résumé fourni par la source

One of the objectives of digital neuropsychology is to apply computational methods to improve the accuracy of traditional assessments. The Trail Making Test (TMT) is one of the most popular neuropsychological tests for executive functions assessment. Participants have to connect a sequence of items in order without lifting the pencil. In Part A (TMT-A) the items are identified with Arabic numerals. In Part B (TMT-B) they are identified with numbers and capital letters, and participants have to connect them in alternate order (1-A-2-B-…). We implemented a computerized TMT (cTMT) that preserves its original structure and records high-resolution mouse trajectories. Seventy-four older adults (41 with mild cognitive impairment and 33 healthy controls) completed the cTMT and a standard diagnostic battery. We also developed NeuroTask, a Python library that extracts features from cursor time series, including reaction times, speed and acceleration metrics, trajectory deviations, and state-based measures. We compared demographic, digital, and non-digital models using nested cross-validation and non-parametric permutation tests. Demographic models provided only modest discrimination (AUC = 0.56). Digital mouse features improved performance (AUC = 0.67), and combining them with demographics reached an AUC of 0.70, which approached the performance of the neuropsychological battery used to define the diagnosis (AUC = 0.76). In complementary regression analyses with digital plus demographic features, we obtained significant predictions for four out of seven target scores: MMSE, Digit Symbol, TMT-A and TMT-B. These results indicate that fine-grained mouse-movement features from the cTMT provide useful information for classifying mild cognitive impairment and for predicting multiple neuropsychological scores.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.