This research centres on the identification of patients experiencing depression. To identify the condition, this paper suggests three machine learning methodologies: Artificial Neural Network (ANN), Support Vector Machine (SVM), and Multi Linear Regression (MLR) models. The primary aim was pinpointing the most efficient model for accurately recognising depression. Following a thorough evaluation, the ANN model displayed superior performance among the trio, achieving 100% accuracy in depression identification. The ANN model’s architecture, comprising one input, hidden, and output layer, proved to be a better fit for the data, resulting in fewer errors than the SVM and MLR models. The study utilised accuracy and loss graphs from training and validation datasets and a confusion matrix to evaluate model efficacy. The results confirm that the ANN model surpasses the others, particularly regarding cross-entropy loss. These findings highlight the ANN model’s potential usefulness in sending timely text messages or alerts to healthcare professionals based on the patient’s condition and treatment needs.
Sodhi et al. (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: