Translating statistical models into useful clinical tools by learning from real-world, heterogeneous patient data.
Electronic health records (EHRs) are generated through the interaction of patients, clinicians, biological systems, and healthcare infrastructure. These data contain signals — and artifacts — that reflect both disease biology and the complex realities of medical care.
We collaborate directly with health systems to:
Build interpretable AI tools that clinicians can trust and use,
Discover heterogeneous patterns in population data for personalized medicine,
Translate modeling insights into practical clinical interventions.
Our approach blends robust statistical methods with domain expertise, enabling tools that are scientifically sound and operationally feasible in real-world care settings.
This work spans partnerships with UW Health, the Emergency Care Systems Lab (ECSL), and national data providers, and is grounded in our commitment to interpretable, patient-centered modeling.
References
2022
Automated interpretable discovery of heterogeneous treatment effectiveness: A COVID-19 case study
Testing multiple treatments for heterogeneous (varying) effectiveness with respect to many underlying risk factors requires many pairwise tests; we would like to instead automatically discover and visualize patient archetypes and predictors of treatment effectiveness using multitask machine learning. In this paper, we present a method to estimate these heterogeneous treatment effects with an interpretable hierarchical framework that uses additive models to visualize expected treatment benefits as a function of patient factors (identifying personalized treatment benefits) and concurrent treatments (identifying combinatorial treatment benefits). This method achieves state-of-the-art predictive power for COVID-19 in-hospital mortality and interpretable identification of heterogeneous treatment benefits. We first validate this method on the large public MIMIC-IV dataset of ICU patients to test recovery of heterogeneous treatment effects. Next we apply this method to a proprietary dataset of over 3000 patients hospitalized for COVID-19, and find evidence of heterogeneous treatment effectiveness predicted largely by indicators of inflammation and thrombosis risk: patients with few indicators of thrombosis risk benefit most from treatments against inflammation, while patients with few indicators of inflammation risk benefit most from treatments against thrombosis. This approach provides an automated methodology to discover heterogeneous and individualized effectiveness of treatments.
2021
Data-Driven Patterns in Protective Effects of Ibuprofen and Ketorolac on Hospitalized Covid-19 Patients
Rich Caruana, Benjamin Lengerich, and Yin Aphinyanaphongs
The impact of nonsteroidal anti-inflammatory drugs (NSAIDs) on patients with Covid-19 has been unclear. A major reason for this uncertainty is the confounding between treatments, patient comorbidities, and illness severity. Here, we perform an observational analysis of over 3000 patients hospitalized for Covid-19 in a New York hospital system to identify the relationship between in-patient treatment with Ibuprofen or Ketorolac and mortality. Our analysis finds evidence consitent with a protective effect for Ibuprofen and Ketorolac, with evidence stronger for a protective effect of Ketorolac than for a protective effect of Ibuprofen.
@inproceedings{caruana2021data,title={Data-Driven Patterns in Protective Effects of Ibuprofen and Ketorolac on Hospitalized Covid-19 Patients},author={Caruana, Rich and Lengerich, Benjamin and Aphinyanaphongs, Yin},journal={American Medical Informatics Association (AMIA) Annual Symposium},year={2021},keywords={Healthcare, Covid-19},}
