A multilevel scenario based predictive analytics framework to model the community mental health and built environment nexus

Abstract

The built environment affects mental health outcomes, but this relationship is less studied and understood. This article proposes a novel multi-level scenario-based predictive analytics framework (MSPAF) to explore the complex relationships between community mental health outcomes and the built environment conditions. The MSPAF combines rigorously validated interpretable machine learning algorithms and scenario-based sensitivity analysis to test various hypotheses on how the built environment impacts community mental health outcomes across the largest metropolitan areas in the US. Among other findings, our results suggest that declining socio-economic conditions of the built environment (e.g., poverty, low income, unemployment, decreased access to public health insurance) are significantly associated with increased reported mental health disorders. Similarly, physical conditions of the built environment (e.g., increased housing vacancies and increased travel costs) are significantly associated with increased reported mental health disorders. However, this positive relationship between the physical conditions of the built environment and mental health outcomes does not hold across all the metropolitan areas, suggesting a mixed effect of the built environment’s physical conditions on community mental health. We conclude by highlighting future opportunities of incorporating other variables and datasets into the MSPAF framework to test additional hypotheses on how the built environment impacts community mental health.

A simulation‐based generalized framework to model vulnerability of interdependent critical infrastructure systems under incomplete information

“…Ganguly et al. described such a sensitivity analysis framework in detail for sensitivity analysis of model parameters applied to crime analysis (Ganguly & Mukherjee, 2021) and mental health prediction (Mukherjee et al., 2021). Such a framework has also been used in the scientific domain of infrastructure risk assessment using data‐driven techniques (Masoudvaziri et al., 2020; Mukherjee & Nateghi, 2019).…”

Effect of Motivational Enhancement Therapy on Patterns of Substance Abuse in Postpartum Women: A Randomized Clinical Trial

“…Change in pattern of substance use is not a one-dimensional phenomenon, but a multifaceted phenomenon, consisting of social, cultural, family, and economic dimensions. The counseling method used in this study has been specifically developed as one of the three interventions tested in the 1993 Multilevel Approach toward Community Health plan and includes a comprehensive clinical study of drug abuse and alcohol dependence [27,28].…”

Impact assessment of emergency care units on hospitalizations for respiratory system diseases in Brazil

“…As demonstrated by Kapelner and Bleich 25 , models composed by sums of regression trees have a greater capacity compared to single tree models to capture interactions and nonlinearities, generating counterfactual groups more similar to the treated group. Thus, the BART method has been used for a variety of healthcare applications such as covid incidence 24 , community mental health outcomes 26 and predictability of pressure ulcers 27 . The application of the model was performed using the statistical software R using a package with the same name as the method.…”