Modeling Dual-Task Performance: Identifying Key Predictors Using Artificial Neural Networks

Abstract

Dual-task paradigms that combine cognitive and motor tasks offer a valuable lens for detecting subtle impairments in cognitive and physical functioning, especially in older adults. This study used artificial neural network (ANN) modeling to predict clinical, cognitive, and psychosocial outcomes from integrated gait, speech-linguistic, demographic, physiological, and psychological data collected during single- and dual-task conditions. Forty healthy adults (ages 20-84) completed physical, cognitive, and psychosocial assessments and a dual-task walking task involving cell phone use. ANN models were optimized using hyperparameter tuning and k-fold cross-validation to predict outcomes such as the Montreal Cognitive Assessment (MOCA), Trail Making Tests (TMT A and B), Activities-Specific Balance Confidence (ABC) Scale, Geriatric Depression Scale (GDS), and measures of memory, affect, and social support. The models achieved high accuracy for MOCA (100%), ABC (80%), memory function (80%), and social support satisfaction (75%). Feature importance analyses revealed key predictors such as speech-linguistic markers and sensory impairments. First-person plural pronoun used and authenticity of internal thoughts during dual-task emerged as strong predictors of MOCA and memory. Models were less accurate for complex executive tasks like TMT A and B. These findings support the potential of ANN models for the early detection of cognitive and psychosocial changes.

Keywords: artificial neural network (ANN); cognitive assessment; cognitive-motor integration; dual-task performance; gait analysis; machine learning in healthcare; psychosocial predictors; speech-linguistic features; timing.

Figure 1

Schematic representation of the artificial neural network (ANN) architecture used for outcome prediction. The model includes an input layer composed of multi-domain features (e.g., gait, speech-linguistic, psychological, sensory, and demographic inputs), a single hidden layer with an optimized number of neurons determined via hyperparameter tuning, and an output layer corresponding to a single clinical or psychosocial outcome. The ANN was trained using the Levenberg–Marquardt backpropagation algorithm with 5-fold cross-validation. Model performance was assessed using root mean squared error (RMSE) and R-squared values (R²), and interpretability was enhanced with feature importance scores and partial dependence plots (PDPs). The blue lines represent weighted connections between neurons across layers, indicating information flow during network training and prediction.

Figure 2

This figure provides an overall view of the relationship between each outcome and the corresponding features (the top ten important features). It serves as a comprehensive summary illustrating how various features impact the outcomes. Each plot within the figure represents a probability density function (PDF), offering insight into the strength and distribution of feature importance across the outcomes. This visualization emphasizes the key contributions of specific features in predicting each outcome, highlighting the interdependence between features and their respective outcomes in a concise overview. The complete names of features and outputs are described in Table S1.

Figure 3

Mean Squared Error (MSE) performance plot of the ANN model across 19 training epochs. The blue, green, and red curves represent training, validation, and test errors. The best validation performance was achieved at epoch 13 with an MSE of 103.32, demonstrating convergence and stability across dataset partitions. The green circle indicates the point of best validation performance, achieved at epoch 13, where the MSE was minimized for the validation dataset.

Figure 4

Comparison of the desired (black line) and ANN-estimated (red dotted line) outputs across total observations. The close alignment between the predicted and actual values demonstrates strong agreement and highlights the model’s prediction accuracy.