Presentation Title (IN ALL CAPS)

USING RANDOM FOREST ALGORITHM TO EXPLORE FACTORS ASSOCIATED WITH CHANGE IN QUALITY OF LIFE AMONG PERMANENT SUPPORTIVE HOUSING RESIDENTS

Departmental Affiliation and City, State, Zip for All Authors

School of Public Health, Fort Worth, Texas, 76107

Classification

SPH Student (For Competition)

Research Presentation Category

Community Health and Prevention

Layperson Narrative or Summary (3-5 sentences)

Quality of Life (QOL) is a multifaceted concept that encompasses various constructs ranging across physical health, psychological state of mind, social circumstances, environmental factors, etc. This study identified predictors of change in the QOL at 6-months, compared to baseline, among permanent supportive housing residents with a history of chronic homelessness and mental illness. Having a heart disease or breathing disorder is found responsible for a reduction in QOL, whereas reduction in depression, improvement in leisure time activities, quality of relationships, a positive/no change in the satisfaction with living arrangements, a positive/no change in perceptions of being troubled by social problems, and a reduction in the number of legal encounters helped to improve QOL.

Scientific Abstract

Purpose: Purpose of this study was to identify predictors of change in the overall quality of life (QOL) at 6-months, compared to baseline, among permanent supportive housing residents with a history of chronic homelessness and mental illness. Methods: Data were collected at baseline and 6-months using 18 questionnaires, encompassing over 100 variables on 457 adults. The short version of the Quality of Life Enjoyment and Satisfaction Questionnaire was used to measure QOL. We used random forest (RF), a machine learning technique, for dimension reduction and a multiple linear regression with the reduced set of variables obtained from RF to propose a final predictive model. Results: The mean improvement in QOL score at 6-months was 4.24 (SD=13.52, effect size=0.31). Significant predictors of the change in QOL were one’s baseline QOL (p<0.0001), presence of a heart disease or breathing disorder (p=0.01 and p=0.0002), reduction in depression (p=0.0001), improvement in leisure time activities (p=0.001), quality of relationships (p=0.02), a positive/no change in the satisfaction with living arrangements (p=0.03), a positive/no change in perceptions of being troubled by social problems (p< 0.001), and a reduction in the number of legal encounters (p=0.02). Conclusion: QOL is a multifaceted concept that encompasses various constructs ranging across physical health, psychological state of mind, social circumstances, environmental factors, etc. We hope that future interventions addressing QOL in this vulnerable population will benefit from our findings. Methodologically, we illustrate the benefit of using machine learning techniques in behavioral/social experiments to leverage “big data” and conduct comprehensive analyses.

This document is currently not available here.

Share

COinS
 

USING RANDOM FOREST ALGORITHM TO EXPLORE FACTORS ASSOCIATED WITH CHANGE IN QUALITY OF LIFE AMONG PERMANENT SUPPORTIVE HOUSING RESIDENTS

Purpose: Purpose of this study was to identify predictors of change in the overall quality of life (QOL) at 6-months, compared to baseline, among permanent supportive housing residents with a history of chronic homelessness and mental illness. Methods: Data were collected at baseline and 6-months using 18 questionnaires, encompassing over 100 variables on 457 adults. The short version of the Quality of Life Enjoyment and Satisfaction Questionnaire was used to measure QOL. We used random forest (RF), a machine learning technique, for dimension reduction and a multiple linear regression with the reduced set of variables obtained from RF to propose a final predictive model. Results: The mean improvement in QOL score at 6-months was 4.24 (SD=13.52, effect size=0.31). Significant predictors of the change in QOL were one’s baseline QOL (p<0.0001), presence of a heart disease or breathing disorder (p=0.01 and p=0.0002), reduction in depression (p=0.0001), improvement in leisure time activities (p=0.001), quality of relationships (p=0.02), a positive/no change in the satisfaction with living arrangements (p=0.03), a positive/no change in perceptions of being troubled by social problems (p< 0.001), and a reduction in the number of legal encounters (p=0.02). Conclusion: QOL is a multifaceted concept that encompasses various constructs ranging across physical health, psychological state of mind, social circumstances, environmental factors, etc. We hope that future interventions addressing QOL in this vulnerable population will benefit from our findings. Methodologically, we illustrate the benefit of using machine learning techniques in behavioral/social experiments to leverage “big data” and conduct comprehensive analyses.