Estimating Discontinuous Time-Varying Risk Factors and Treatment Benefits for COVID-19 with Interpretable ML
This provides a method for estimating discontinuous time-varying effects in medical data, which is incremental as it applies an existing ML approach to a new domain.
The study tackled the problem of changing risk factors and treatment benefits for COVID-19 over time by analyzing over 4000 hospitalized patients from March 2020 to August 2021, finding that biomarkers of thrombosis increasingly predicted mortality while the association between inflammation and thrombosis biomarkers weakened.
Treatment protocols, disease understanding, and viral characteristics changed over the course of the COVID-19 pandemic; as a result, the risks associated with patient comorbidities and biomarkers also changed. We add to the conversation regarding inflammation, hemostasis and vascular function in COVID-19 by performing a time-varying observational analysis of over 4000 patients hospitalized for COVID-19 in a New York City hospital system from March 2020 to August 2021. To perform this analysis, we apply tree-based generalized additive models with temporal interactions which recover discontinuous risk changes caused by discrete protocols changes. We find that the biomarkers of thrombosis increasingly predicted mortality from March 2020 to August 2021, while the association between biomarkers of inflammation and thrombosis weakened. Beyond COVID-19, this presents a straightforward methodology to estimate unknown and discontinuous time-varying effects.