Machine learning and algorithmic fairness in public and population health

Mhasawade, Vishwali; Zhao, Yuan; Chunara, Rumi

doi:10.1038/s42256-021-00373-4

Cited by 103 publications

(51 citation statements)

References 88 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our study presents an opportunity to look at individualized risk assessment for stunting among children. Further, our study took into consideration key social, economic and environmental factors that may be key determinants of a child’s nutrition status compared to HAZ, which only takes into consideration the age, height and weight of children, which is one major strength of the ML algorithm in predicting health outcomes [ 37 ].…”

Section: Discussionmentioning

confidence: 99%

Performance of Machine Learning Classifiers in Classifying Stunting among Under-Five Children in Zambia

et al. 2022

View full text Add to dashboard Cite

Stunting is a global public health issue. We sought to train and evaluate machine learning (ML) classification algorithms on the Zambia Demographic Health Survey (ZDHS) dataset to predict stunting among children under the age of five in Zambia. We applied Logistic regression (LR), Random Forest (RF), SV classification (SVC), XG Boost (XgB) and Naïve Bayes (NB) algorithms to predict the probability of stunting among children under five years of age, on the 2018 ZDHS dataset. We calibrated predicted probabilities and plotted the calibration curves to compare model performance. We computed accuracy, recall, precision and F1 for each machine learning algorithm. About 2327 (34.2%) children were stunted. Thirteen of fifty-eight features were selected for inclusion in the model using random forest. Calibrating the predicted probabilities improved the performance of machine learning algorithms when evaluated using calibration curves. RF was the most accurate algorithm, with an accuracy score of 79% in the testing and 61.6% in the training data while Naïve Bayesian was the worst performing algorithm for predicting stunting among children under five in Zambia using the 2018 ZDHS dataset. ML models aids quick diagnosis of stunting and the timely development of interventions aimed at preventing stunting.

show abstract

Section: Discussionmentioning

confidence: 99%

Performance of Machine Learning Classifiers in Classifying Stunting among Under-Five Children in Zambia

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Creation of curated, open databases with deidentified or aggregate patient information is one excellent solution to combat racially imbalanced data [ 2 ]. However, this option might not always be feasible for data sharing in facial and skin images, geographically linked, or environmental exposure data due to privacy concerns [ 17 ]. Another option would be to pretrain models with large, non-specific datasets or with synthetic data generation to boost the model’s ability to recognize a diversity of cases prior to training with the original data (See Box 1 ) [ 15 ].…”

Section: Developmentmentioning

confidence: 99%

Advancing health equity with artificial intelligence

Thomasian

Eickhoff

Adashi

2021

J Public Health Pol

View full text Add to dashboard Cite

“…Secondly, system dynamics modeling approaches or agent-based models contributes to arrange and assess the weights of interventions at multiple levels ( 24 , 25 ). Thirdly, by incorporating more information and handling missing data, machine learning can be used for resource allocation and result prediction ( 26 ).…”

Section: Introductionmentioning

confidence: 99%

Study of the Economic, Environmental, and Social Factors Affecting Chinese Residents' Health Based on Machine Learning

Pan²,

Meng³

et al. 2022

Front. Public Health

View full text Add to dashboard Cite

The Healthy China Strategy puts realistic demands for residents' health levels, but the reality is that various factors can affect health. In order to clarify which factors have a great impact on residents' health, based on China's provincial panel data from 2011 to 2018, this paper selects 17 characteristic variables from the three levels of economy, environment, and society and uses the XG boost algorithm and Random forest algorithm based on recursive feature elimination to determine the influencing variables. The results show that at the economic level, the number of industrial enterprises above designated size, industrial added value, population density, and per capita GDP have a greater impact on the health of residents. At the environmental level, coal consumption, energy consumption, total wastewater discharge, and solid waste discharge have a greater impact on the health level of residents. Therefore, the Chinese government should formulate targeted measures at both economic and environmental levels, which is of great significance to realizing the Healthy China strategy.

show abstract

Machine learning and algorithmic fairness in public and population health

Cited by 103 publications

References 88 publications

Performance of Machine Learning Classifiers in Classifying Stunting among Under-Five Children in Zambia

Performance of Machine Learning Classifiers in Classifying Stunting among Under-Five Children in Zambia

Advancing health equity with artificial intelligence

Study of the Economic, Environmental, and Social Factors Affecting Chinese Residents' Health Based on Machine Learning

Contact Info

Product

Resources

About