Aligning Subjective Ratings in Clinical Decision Making

TL;DR

This paper presents a method to align subjective expert evaluations with objective clinical indicators using pairwise ranking, resulting in a combined score that improves disease detection and severity assessment.

Contribution

It introduces a novel approach to integrate subjective and objective clinical data through pairwise ranking, enhancing diagnostic accuracy and interpretability.

Findings

Improved classification accuracy for disease detection.

Generated a sparse, nuanced severity score.

Demonstrated effectiveness in Psoriatic Arthritis case study.

Abstract

In addition to objective indicators (e.g. laboratory values), clinical data often contain subjective evaluations by experts (e.g. disease severity assessments). While objective indicators are more transparent and robust, the subjective evaluation contains a wealth of expert knowledge and intuition. In this work, we demonstrate the potential of pairwise ranking methods to align the subjective evaluation with objective indicators, creating a new score that combines their advantages and facilitates diagnosis. In a case study on patients at risk for developing Psoriatic Arthritis, we illustrate that the resulting score (1) increases classification accuracy when detecting disease presence/absence, (2) is sparse and (3) provides a nuanced assessment of severity for subsequent analysis.