Enhancing Anxiety Prediction: Leveraging Machine Learning with Functional Design Metrics

Fear, nervousness, and social phobia all contribute to anxiety episodes reaching their peak in seconds. Using data collected from patient questionnaires, this study seeks to anticipate and diagnose anxiety disorders effectively and precisely using machine learning approaches. However, current research offers standardized metrics for assessing machine learning approaches throughout the design process. This work presents a systematic method for efficiently extracting literature from digital sources and emphasizes the need for data engineers to evaluate the efficiency of machine learning approaches to assure forecast quality. The International Organization for Standardization (ISO) 9126 standard is used to assess machine learning approaches for anxiety prediction to address this gap. This evaluation considers parameters such as functionality, accuracy, resilience, throughput, explainability, privacy, and correctness. These defined characteristics serve as the benchmark to measure the efficacy of machine learning approaches in predicting anxiety disorders.