Mobeena Jamshed

Early detection of Mild Cognitive Impairment (MCI), a prodromal stage of dementia, plays a pivotal role in enabling timely clinical intervention and slowing cognitive decline. This paper presents a multi-sensor balance assessment framework designed to identify MCI-related postural instabilities using a wearable inertial measurement unit (IMU) network. The proposed system employs five synchronized IMUs placed at the waist, thighs, and shanks to capture balance dynamics across four static balance tasks: Eyes-Open, Eyes-Closed, Right-Leg Lift, and Left-Leg Lift. A three-stage feature selection strategy, comprising variance and correlation pruning, univariate filtering, and embedded model selection, is implemented within a Leave-One-Subject-Out (LOSO) cross-validation scheme to extract discriminative sway features. Classification using Support Vector Machines and tree-based ensemble models consistently yields superior results, achieving accuracies between 71.7% and 79.2%, with the highest performance observed in the Eyes-Open condition. A compact 10-feature subset demonstrates stable and robust discriminative power across all tasks. Compared to a single-sensor baseline, the multi-sensor configuration provides improved classification performance, underscoring the feasibility of compact, balance-driven, non-invasive MCI screening through wearable sensor systems.

Mild Cognitive Impairment (MCI) represents an early stage of dementia where subtle motor deficits often accompany cognitive changes. The proposed study systematically evaluates sensor placements and static balance conditions to define a practical minimal-sensor wearable framework for effective MCI screening. Sixty older adults (30 MCI, 30 cognitively normal) completed four stance tasks: eyes-open, eyes-closed, and single-leg stands, while wearing inertial measurement units (IMUs) on the waist, bilateral thighs and bilateral shanks. From the acceleration and gyroscope signals of the sensors, 76 time-domain and frequency-domain features were extracted, from each sensor, to quantify postural sway. A multi-step feature selection pipeline identified a compact subset of the most discriminatory features. Several machine learning classifiers were evaluated in a leave-one-subject-out (LOSO) crossvalidation. The results show that a single IMU on the waist or shank yields the highest individual accuracy of 76.7%, and a dual-sensor fusion (waist+shank) further improves performance to 79.2% in eyes-open condition. Overall, the proposed system consistently distinguished MCI from healthy controls across all evaluated tasks. The results underscore the feasibility of a simple wearable system as an effective, non-invasive tool for early MCI detection.

Early detection of Mild Cognitive Impairment (MCI), a prodromal stage of dementia, plays a pivotal role in enabling timely clinical intervention and slowing cognitive decline. This paper presents a multi-sensor balance assessment framework designed to identify MCI-related postural instabilities using a wearable inertial measurement unit (IMU) network. The proposed system employs five synchronized IMUs placed at the waist, thighs, and shanks to capture balance dynamics across four static balance tasks: Eyes-Open, Eyes-Closed, Right-Leg Lift, and Left-Leg Lift. A three-stage feature selection strategy, comprising variance and correlation pruning, univariate filtering, and embedded model selection, is implemented within a Leave-One-Subject-Out (LOSO) cross-validation scheme to extract discriminative sway features. Classification using Support Vector Machines and tree-based ensemble models consistently yields superior results, achieving accuracies between 71.7% and 79.2%, with the highest performance observed in the Eyes-Open condition. A compact 10-feature subset demonstrates stable and robust discriminative power across all tasks. Compared to a single-sensor baseline, the multi-sensor configuration provides improved classification performance, underscoring the feasibility of compact, balance-driven, non-invasive MCI screening through wearable sensor systems.