Do it Like the Doctor: How We Can Design a Model That Uses Domain Knowledge to Diagnose Pneumothorax

TL;DR

This paper explores integrating expert domain knowledge into AI models to improve the diagnosis of Pneumothorax from lung ultrasound images, addressing data scarcity and rare condition challenges.

Contribution

It introduces a method to incorporate domain expertise into AI model design for Pneumothorax diagnosis, enhancing performance with limited data.

Findings

Expert knowledge was successfully extracted from doctors.

Recommendations for AI model design were developed based on domain knowledge.

The approach aims to improve diagnostic accuracy in data-scarce scenarios.

Abstract

Computer-aided diagnosis for medical imaging is a well-studied field that aims to provide real-time decision support systems for physicians. These systems attempt to detect and diagnose a plethora of medical conditions across a variety of image diagnostic technologies including ultrasound, x-ray, MRI, and CT. When designing AI models for these systems, we are often limited by little training data, and for rare medical conditions, positive examples are difficult to obtain. These issues often cause models to perform poorly, so we needed a way to design an AI model in light of these limitations. Thus, our approach was to incorporate expert domain knowledge into the design of an AI model. We conducted two qualitative think-aloud studies with doctors trained in the interpretation of lung ultrasound diagnosis to extract relevant domain knowledge for the condition Pneumothorax. We extracted knowledge of key features and procedures used to make a diagnosis. With this knowledge, we employed knowledge engineering concepts to make recommendations for an AI model design to automatically diagnose Pneumothorax.