Key result
A random forest machine learning model outperformed US and UK risk scores in predicting short-term risk of diabetes (AUC 0.910 vs 0.671) and hypertension (AUC 0.792 vs 0.698).
Why the study?
Scaling up noncommunicable disease screening in resource-limited settings requires accurate risk stratification algorithms tailored for community-based screening programs to identify high-risk patients efficiently.
Do machine learning-based risk stratification algorithms improve the prediction accuracy for short-term risk of diabetes and hypertension compared to established US and UK risk scores in resource-limited settings?
Observational (n=2,278)
Do machine learning-based risk stratification algorithms improve the prediction accuracy for short-term risk of diabetes and hypertension compared to established US and UK risk scores in resource-limited settings?
Absolute Event Rate: 0.91% vs 0.671%
Machine learning models significantly improve the accuracy of risk stratification for diabetes and hypertension in resource-limited settings compared to standard US and UK risk scores, potentially reducing screening costs.
May support ML for risk prediction; leaves open outcome benefits and requires prospective validation in resource-limited settings.
BACKGROUND The impending scale up of noncommunicable disease screening programs in low- and middle-income countries coupled with limited health resources require that such programs be as accurate as possible at identifying patients at high risk. OBJECTIVE The aim of this study was to develop machine learning–based risk stratification algorithms for diabetes and hypertension that are tailored for the at-risk population served by community-based screening programs in low-resource settings. METHODS We trained and tested our models by using data from 2278 patients collected by community health workers through door-to-door and camp-based screenings in the urban slums of Hyderabad, India between July 14, 2015 and April 21, 2018. We determined the best models for predicting short-term (2-month) risk of diabetes and hypertension (a model for diabetes and a model for hypertension) and compared these models to previously developed risk scores from the United States and the United Kingdom by using prediction accuracy as characterized by the area under the receiver operating characteristic curve (AUC) and the number of false negatives. RESULTS We found that models based on random forest had the highest prediction accuracy for both diseases and were able to outperform the US and UK risk scores in terms of AUC by 35.5% for diabetes (improvement of 0.239 from 0.671 to 0.910) and 13.5% for hypertension (improvement of 0.094 from 0.698 to 0.792). For a fixed screening specificity of 0.9, the random forest model was able to reduce the expected number of false negatives by 620 patients per 1000 screenings for diabetes and 220 patients per 1000 screenings for hypertension. This improvement reduces the cost of incorrect risk stratification by US $1.99 (or 35%) per screening for diabetes and US $1.60 (or 21%) per screening for hypertension. CONCLUSIONS In the next decade, health systems in many countries are planning to spend significant resources on noncommunicable disease screening programs and our study demonstrates that machine learning models can be leveraged by these programs to effectively utilize limited resources by improving risk stratification.
No takes yet. Share an insight, caveat, or question.
Boutilier et al. (2020) conducted an observational in Diabetes and hypertension (n=2,278). Random forest machine learning model vs. US and UK risk scores was evaluated on Prediction accuracy (AUC) for short-term risk of diabetes. A random forest machine learning model outperformed US and UK risk scores in predicting short-term risk of diabetes (AUC 0.910 vs 0.671) and hypertension (AUC 0.792 vs 0.698).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: