Boosting the interpretability of clinical risk scores with intervention predictions

TL;DR

This paper introduces a joint modeling approach that combines clinical risk scores with intervention predictions to improve interpretability of machine learning forecasts in ICU settings.

Contribution

It presents a novel joint model of intervention policy and adverse event risk, explicitly communicating assumptions about future interventions to clinicians.

Findings

Combining risk scores with intervention probabilities enhances interpretability.

The model applied to MIMIC-III demonstrates practical utility.

Explicit intervention modeling clarifies prediction assumptions.

Abstract

Machine learning systems show significant promise for forecasting patient adverse events via risk scores. However, these risk scores implicitly encode assumptions about future interventions that the patient is likely to receive, based on the intervention policy present in the training data. Without this important context, predictions from such systems are less interpretable for clinicians. We propose a joint model of intervention policy and adverse event risk as a means to explicitly communicate the model's assumptions about future interventions. We develop such an intervention policy model on MIMIC-III, a real world de-identified ICU dataset, and discuss some use cases that highlight the utility of this approach. We show how combining typical risk scores, such as the likelihood of mortality, with future intervention probability scores leads to more interpretable clinical predictions.