Genetic and Survey Data Improves Performance of Machine Learning Model for Long COVID

Abstract

Over 200 million SARS-CoV-2 patients have or will develop persistent symptoms (long COVID). Given this pressing research priority, the National COVID Cohort Collaborative (N3C) developed a machine learning model using only electronic health record data to identify potential patients with long COVID. We hypothesized that additional data from health surveys, mobile devices, and genotypes could improve prediction ability. In a cohort of SARS-CoV-2 infected individuals (n=17,755) in the All of Us program, we applied and expanded upon the N3C long COVID prediction model, testing machine learning infrastructures, assessing model performance, and identifying factors that contributed most to the prediction models. For the survey/mobile device information and genetic data, extreme gradient boosting and a convolutional neural network delivered the best performance for predicting long COVID, respectively. Combined survey, genetic, and mobile data increased specificity and the Area Under Curve the Receiver Operating Characteristic score versus the original N3C model.

Figure 1. Training, Testing, and Validation Set Parameters.

Flowchart describing how the AoU data was divided into sets based on data availability.

Figure 2. Model Output Sources and Predictive Method.

Flowchart showing how the predictive components of separate models are combined into a single predictive outcome.

Figure 3. Cohort Data Availability.

Venn diagram showing the data available for AoU participants.

Figure 4. Average ROC of Models.

Shows the Average ROC curve for each combination of models from cross validation results. Shaded area represents the standard deviation of the ROC curve, and color represents models used.

Figure 5. Top Twenty Predictive Features in the Combined Model.

The relative contribution of the 20 most powerful features in our predictive method. Color of each bar represents the data source of the feature.