Abstract
The global surge in COVID-19 cases underscores the need for fast, scalable, and reliable testing. Current COVID-19 diagnostic tests are limited by turnaround time, limited availability, or occasional false findings. Here, we developed a machine learning-based framework for predicting individual COVID-19 positive diagnosis relying only on readily-available baseline data, including patient demographics, comorbidities, and common lab values. Leveraging a cohort of 31,739 adults within an academic health system, we trained and tested multiple types of machine learning models, achieving an area under the curve of 0.75. Feature importance analyses highlighted serum calcium levels, temperature, age, lymphocyte count, smoking, hemoglobin levels, aspartate aminotransferase levels, and oxygen saturation as key predictors. Additionally, we developed a single decision tree model that provided an operable method for stratifying sub-populations. Overall, this study provides a proof-of-concept that COVID-19 diagnosis prediction models can be developed using only baseline data. The resulting prediction can complement existing tests to enhance screening and pandemic containment workflows.
Highlights
The global surge in COVID-19 cases underscores the need for fast, scalable, and reliable testing
The predictive models could prioritize sub-populations for COVID-19 diagnosis in situations where testing capacity may be limited, or they could be used in conjunction with clinical judgment or other predictive models to verify RT-PCR test results
Our predictive models identified key clinical features that correlate with a positive diagnosis, providing insights on efficient patient stratification and population screening
Summary
The global surge in COVID-19 cases underscores the need for fast, scalable, and reliable testing. Based on the Bayes’ theorem, medical tests that are not perfectly sensitive and specific can yield undesired ratios of true to false findings, especially when widespread testing of the general population is performed[11]. In such circumstances, combining tests with other prioritization metrics can improve accuracy and help allocate testing for high-risk individuals. Establishing a machine learning-based tool that relies only on baseline data will help in prioritizing sub-populations for COVID-19 testing, and is urgently needed to relieve the burden of large-scale screening when testing capacity may be limited
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
