Improving Predictive Models With Causal Methods – Study Protocol

Background

In a previous study, Kowadlo et al. [1] developed algorithms (POP – Patient OPtimizer) to predict outcomes for surgical patients at Austin Health. The POP algorithms predict postoperative complications, kidney failure, and hospital length-of-stay. The findings highlight the potential of risk prediction to improve health outcomes and justify further work to improve performance and generalisability.

Objectives

The objectives are to:

• Establish and validate a causal graph of elective surgery in a hospital setting

• Test whether causal inference can be used in algorithm development to improve generalisation of predictive models to different patient cohorts

• Implement and test the concept of ‘preventable risk’, risk stratification that combines risk prediction with causal effect; to assist in decision making

Method

In order to achieve the objectives, we will:

• Apply causal discovery methods to the INSPIRE dataset (Lim et al. [2]), to create a causal graph

• Validate the graph by combining clinical input with data analysis, to identify relevant confounding and collider variables

• Methodically control for confounders and colliders, while training and evaluating predictive models for length-of-stay, mortality, readmission or complications

• Measure the generalisation of predictive models across patient populations, when controlling for identified confounders and colliders

• Implement Conditional Average Treatment Estimate (CATE) and combine it with risk prediction to calculate preventable risk