A Real-World Demonstration of Machine Learning Generalizability: Intracranial Hemorrhage Detection on Head CT

TL;DR

This study demonstrates that machine learning models for intracranial hemorrhage detection on head CT scans can achieve high accuracy and generalize well to real-world clinical settings, beyond laboratory conditions.

Contribution

The paper provides evidence that ML models trained on public datasets can perform reliably in diverse, real-world clinical environments for medical imaging tasks.

Findings

Achieved 95.4% AUC on external validation dataset.

Demonstrated high sensitivity and specificity in real-world setting.

Proved ML model generalizability in clinical practice.

Abstract

Machine learning (ML) holds great promise in transforming healthcare. While published studies have shown the utility of ML models in interpreting medical imaging examinations, these are often evaluated under laboratory settings. The importance of real world evaluation is best illustrated by case studies that have documented successes and failures in the translation of these models into clinical environments. A key prerequisite for the clinical adoption of these technologies is demonstrating generalizable ML model performance under real world circumstances. The purpose of this study was to demonstrate that ML model generalizability is achievable in medical imaging with the detection of intracranial hemorrhage (ICH) on non-contrast computed tomography (CT) scans serving as the use case. An ML model was trained using 21,784 scans from the RSNA Intracranial Hemorrhage CT dataset while generalizability was evaluated using an external validation dataset obtained from our busy trauma and neurosurgical center. This real world external validation dataset consisted of every unenhanced head CT scan (n = 5,965) performed in our emergency department in 2019 without exclusion. The model demonstrated an AUC of 98.4%, sensitivity of 98.8%, and specificity of 98.0%, on the test dataset. On external validation, the model demonstrated an AUC of 95.4%, sensitivity of 91.3%, and specificity of 94.1%. Evaluating the ML model using a real world external validation dataset that is temporally and geographically distinct from the training dataset indicates that ML generalizability is achievable in medical imaging applications.