Sleep is a fundamental physiological process that supports cognitive functioning, emotional stability, and overall physical health. However, the prevalence of insomnia has increased substantially in recent years, largely influenced by evolving lifestyle patterns such as prolonged digital engagement, irregular work schedules, psychological stress, sedentary behavior, and unhealthy dietary habits. This review paper presents a comprehensive examination of the relationship between modern lifestyle factors and the growing incidence of insomnia, with particular emphasis on the potential of data-driven approaches for early detection and risk forecasting. The study synthesizes findings from existing literature covering clinical sleep research, behavioral studies, wearable sensing technologies, and machine learning-based predictive models. A comparative analysis of previous studies is conducted by evaluating commonly used datasets, feature sets, learning algorithms, predictive performance, and reported limitations. The review reveals that while several machine learning techniques—including Support Vector Machines, Random Forest models, and deep learning architectures—have demonstrated promising results in identifying sleep-related abnormalities, many studies rely on limited datasets, single-modality inputs, or short-term observational data. Furthermore, current research often lacks integrated frameworks capable of combining behavioral, physiological, and contextual lifestyle information for reliable insomnia forecasting. To address these limitations, the paper proposes a conceptual predictive framework that integrates lifestyle monitoring with machine learning-driven risk assessment. The framework outlines multiple stages including lifestyle data acquisition from wearable devices, smartphone sensors, and self-reported surveys, followed by data preprocessing, feature extraction, and predictive modeling. By analyzing behavioral indicators such as sleep duration patterns, activity levels, stress indicators, and physiological signals, the system aims to classify individuals into different insomnia risk categories including low, moderate, and high risk. The proposed framework highlights the potential of multimodal data integration for improving prediction accuracy and enabling proactive sleep health management. Additionally, the paper discusses key challenges associated with data privacy, dataset availability, and model interpretability, while emphasizing the need for explainable artificial intelligence in healthcare applications. The findings suggest that combining continuous lifestyle monitoring with intelligent analytics can facilitate early identification of insomnia risks and support personalized preventive interventions. The study concludes that future advancements in digital health technologies, wearable sensing, and artificial intelligence can pave the way for scalable and personalized insomnia monitoring systems capable of enhancing preventive healthcare and improving long-term sleep health outcomes.

Keywords: Insomnia Prediction, Sleep Disorders, Lifestyle Analytics, Machine Learning in Healthcare, Digital Health Monitoring, Wearable Sleep Sensors, Behavioral Sleep Analysis, Artificial Intelligence for Healthcare, Sleep Quality Assessment, Predictive Health Analytics