A Concept-based Interpretable Model for the Diagnosis of Choroid Neoplasias using Multimodal Data

TL;DR

This paper presents a concept-based interpretable machine learning model for diagnosing choroid neoplasias, utilizing multimodal data to achieve high accuracy and significantly improve junior doctors' diagnostic performance.

Contribution

The study introduces the largest dataset for choroid neoplasias and develops an interpretable model that rivals black-box methods and enhances clinician accuracy.

Findings

Achieved an F1 score of 0.91 with the model.

Boosted junior doctors' diagnostic accuracy by 42%.

Utilized multimodal data from 750 patients over 18 years.

Abstract

Diagnosing rare diseases presents a common challenge in clinical practice, necessitating the expertise of specialists for accurate identification. The advent of machine learning offers a promising solution, while the development of such technologies is hindered by the scarcity of data on rare conditions and the demand for models that are both interpretable and trustworthy in a clinical context. Interpretable AI, with its capacity for human-readable outputs, can facilitate validation by clinicians and contribute to medical education. In the current work, we focus on choroid neoplasias, the most prevalent form of eye cancer in adults, albeit rare with 5.1 per million. We built the so-far largest dataset consisting of 750 patients, incorporating three distinct imaging modalities collected from 2004 to 2022. Our work introduces a concept-based interpretable model that distinguishes between three types of choroidal tumors, integrating insights from domain experts via radiological reports. Remarkably, this model not only achieves an F1 score of 0.91, rivaling that of black-box models, but also boosts the diagnostic accuracy of junior doctors by 42%. This study highlights the significant potential of interpretable machine learning in improving the diagnosis of rare diseases, laying a groundwork for future breakthroughs in medical AI that could tackle a wider array of complex health scenarios.