This paper introduces HuLP, a Human-in-the-Loop for Prog-
nosis model designed to enhance the reliability and interpretability of
prognostic models in clinical contexts, especially when faced with the
complexities of missing covariates and outcomes. HuLP offers an inno-
vative approach that enables human expert intervention, empowering
clinicians to interact with and correct models’ predictions, thus foster-
ing collaboration between humans and AI models to produce more ac-
curate prognosis. Additionally, HuLP addresses the challenges of miss-
ing data by utilizing neural networks and providing a tailored method-
ology that effectively handles missing data. Traditional methods often
struggle to capture the nuanced variations within patient populations,
leading to compromised prognostic predictions. HuLP imputes missing
covariates based on imaging features, aligning more closely with clini-
cian workflows and enhancing reliability. We conduct our experiments
on two real-world, publicly available medical datasets to demonstrate
the superiority and competitiveness of HuLP.
Paper Link: https://arxiv.org/pdf/2403.13078