An adjustable wave model for attention restoration.

Anxiety and depression are common psychiatric disorders that contribute significantly to serious physical and mental illnesses globally []. In 2022, depressive and anxiety disorders ranked among the top 25 causes of disease burden, accounting for approximately 14.3% of annual global deaths [, , , ]. People with anxiety or depression face heightened risks of hypertension [, ]. Hypertension alone claims about 10.8 million lives each year, with a high prevalence of anxiety and depression observed among people with hypertension, especially in South Asia []. In Bangladesh, a South Asian country, the point prevalence of anxiety and depression among adults aged 18 years and older is approximately 4.7% and 6.7%, respectively, while the prevalence of hypertension is 29% [, ]. Hypertension is one of the leading risk factors for cardiovascular diseases (CVDs) in Bangladesh, which ranks among the country's top 10 causes of mortality and disability‐adjusted life years (DALYs), alongside conditions such as depression [, ]. The co‐occurrence of anxiety and/or depression, and hypertension complicates treatment and heightens the risk of CVD and mortality, underscoring the need to understand risk factors for this comorbidity [, ]. In Bangladesh, risk factors for anxiety, depression, and hypertension are evident [, , , , ]. A similar pattern has been reported in other low‐ and middle‐income countries [, ]. However, limited attention is given to their comorbid condition, especially in rural areas where 68.5% of the country's total population resides []. In rural areas, limited access to healthcare and mental health services, compounded by unemployment, poverty, low health literacy, and pervasive stigma, significantly heighten the risk of adverse outcomes, including disability and premature death [, ]. This highlights the importance of addressing risk factors of comorbid psychiatric symptoms and hypertension and integrating management strategies to minimize these outcomes in rural areas. Furthermore, the application of advanced methods such as machine learning (ML) is limited in this area. In alignment with this, the current study applied advanced ML algorithms that have previously been used to predict anxiety, depression, and hypertension among various populations in Bangladesh [, , , , ]. ML methods can handle complex data patterns and often outperform traditional regression models in predictive accuracy [, , ]. Further, previous studies using traditional regression models to identify risk factors for anxiety, depression, and hypertension often lack to report model performance, weakening the models' applicability and the acceptability of findings [, , , ]. Therefore, the current study aims to identify factors associated with the comorbid psychiatric symptoms and hypertension among adults in rural Bangladesh using common ML algorithms.