Multi-Task Classification for Improved Health Outcome Prediction Based on Environmental Indicators
This paper aims to address the challenges associated with evaluating the impact of neighborhood environments on health outcomes. Google street view (GSV) images provide a valuable tool for assessing neighborhood environments on a large scale. By annotating the GSV images with labels indicating the p...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10183986/ |
_version_ | 1797773343183601664 |
---|---|
author | Mitra Alirezaei Quynh C. Nguyen Ross Whitaker Tolga Tasdizen |
author_facet | Mitra Alirezaei Quynh C. Nguyen Ross Whitaker Tolga Tasdizen |
author_sort | Mitra Alirezaei |
collection | DOAJ |
description | This paper aims to address the challenges associated with evaluating the impact of neighborhood environments on health outcomes. Google street view (GSV) images provide a valuable tool for assessing neighborhood environments on a large scale. By annotating the GSV images with labels indicating the presence or absence of specific neighborhood features, we can develop classifiers capable of automatically analyzing and evaluating the environment. However, the process of labeling GSV images to analyze and evaluate the environment is a time-consuming and labor-intensive task. To overcome these challenges, we propose using a multi-task classifier to enhance the training of classifiers with limited supervised GSV data. Our multi-task classifier utilizes readily available, inexpensive online images collected from Flickr as a related classification task. The hypothesis is that a classifier trained on multiple related tasks is less likely to overfit to small amounts of training data and generalizes better to unseen data. We leverage the power of multiple related tasks to improve the classifier’s overall performance and generalization capability. Here we show that, with the proposed learning paradigm, predicted labels for GSV test images are more accurate. Across different environment indicators, the accuracy, <inline-formula> <tex-math notation="LaTeX">$F_{1}$ </tex-math></inline-formula> score and balanced accuracy increase up to 6% in the multi-task learning framework compared to its single-task learning counterpart. The enhanced accuracy of the predicted labels obtained through the multi-task classifier contributes to a more reliable and precise regression analysis determining the correlation between predicted built environment indicators and health outcomes. The <inline-formula> <tex-math notation="LaTeX">$R^{2}$ </tex-math></inline-formula> values calculated for different health outcomes improve by up to 4% using multi-task learning detected indicators. |
first_indexed | 2024-03-12T22:04:10Z |
format | Article |
id | doaj.art-67810a1397bc4d408403d61e558bf675 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-03-12T22:04:10Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-67810a1397bc4d408403d61e558bf6752023-07-24T23:00:33ZengIEEEIEEE Access2169-35362023-01-0111733307333910.1109/ACCESS.2023.329577710183986Multi-Task Classification for Improved Health Outcome Prediction Based on Environmental IndicatorsMitra Alirezaei0https://orcid.org/0000-0003-2417-1659Quynh C. Nguyen1https://orcid.org/0000-0003-4745-6681Ross Whitaker2Tolga Tasdizen3https://orcid.org/0000-0001-6574-0366Department of Electrical and Computer Engineering, University of Utah, Salt Lake City, UT, USADepartment of Epidemiology and Biostatistics, University of Maryland School of Public Health, College Park, MD, USASchool of Computing, University of Utah, Salt Lake City, UT, USADepartment of Electrical and Computer Engineering, University of Utah, Salt Lake City, UT, USAThis paper aims to address the challenges associated with evaluating the impact of neighborhood environments on health outcomes. Google street view (GSV) images provide a valuable tool for assessing neighborhood environments on a large scale. By annotating the GSV images with labels indicating the presence or absence of specific neighborhood features, we can develop classifiers capable of automatically analyzing and evaluating the environment. However, the process of labeling GSV images to analyze and evaluate the environment is a time-consuming and labor-intensive task. To overcome these challenges, we propose using a multi-task classifier to enhance the training of classifiers with limited supervised GSV data. Our multi-task classifier utilizes readily available, inexpensive online images collected from Flickr as a related classification task. The hypothesis is that a classifier trained on multiple related tasks is less likely to overfit to small amounts of training data and generalizes better to unseen data. We leverage the power of multiple related tasks to improve the classifier’s overall performance and generalization capability. Here we show that, with the proposed learning paradigm, predicted labels for GSV test images are more accurate. Across different environment indicators, the accuracy, <inline-formula> <tex-math notation="LaTeX">$F_{1}$ </tex-math></inline-formula> score and balanced accuracy increase up to 6% in the multi-task learning framework compared to its single-task learning counterpart. The enhanced accuracy of the predicted labels obtained through the multi-task classifier contributes to a more reliable and precise regression analysis determining the correlation between predicted built environment indicators and health outcomes. The <inline-formula> <tex-math notation="LaTeX">$R^{2}$ </tex-math></inline-formula> values calculated for different health outcomes improve by up to 4% using multi-task learning detected indicators.https://ieeexplore.ieee.org/document/10183986/Built environmentdeep neural networksGoogle street viewhealth outcomesmulti-task model |
spellingShingle | Mitra Alirezaei Quynh C. Nguyen Ross Whitaker Tolga Tasdizen Multi-Task Classification for Improved Health Outcome Prediction Based on Environmental Indicators IEEE Access Built environment deep neural networks Google street view health outcomes multi-task model |
title | Multi-Task Classification for Improved Health Outcome Prediction Based on Environmental Indicators |
title_full | Multi-Task Classification for Improved Health Outcome Prediction Based on Environmental Indicators |
title_fullStr | Multi-Task Classification for Improved Health Outcome Prediction Based on Environmental Indicators |
title_full_unstemmed | Multi-Task Classification for Improved Health Outcome Prediction Based on Environmental Indicators |
title_short | Multi-Task Classification for Improved Health Outcome Prediction Based on Environmental Indicators |
title_sort | multi task classification for improved health outcome prediction based on environmental indicators |
topic | Built environment deep neural networks Google street view health outcomes multi-task model |
url | https://ieeexplore.ieee.org/document/10183986/ |
work_keys_str_mv | AT mitraalirezaei multitaskclassificationforimprovedhealthoutcomepredictionbasedonenvironmentalindicators AT quynhcnguyen multitaskclassificationforimprovedhealthoutcomepredictionbasedonenvironmentalindicators AT rosswhitaker multitaskclassificationforimprovedhealthoutcomepredictionbasedonenvironmentalindicators AT tolgatasdizen multitaskclassificationforimprovedhealthoutcomepredictionbasedonenvironmentalindicators |