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

by   Hojjat Salehinejad, et al.

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 of 98.8 validation, the model demonstrated an AUC of 95.4 specificity of 94.1 validation dataset that is temporally and geographically distinct from the training dataset indicates that ML generalizability is achievable in medical imaging applications.


page 3

page 4

page 10


Deep learning-based detection of intravenous contrast in computed tomography scans

Purpose: Identifying intravenous (IV) contrast use within CT scans is a ...

CT Data Curation for Liver Patients: Phase Recognition in Dynamic Contrast-Enhanced CT

As the demand for more descriptive machine learning models grows within ...

Operational Learning-based Boundary Estimation in Electromagnetic Medical Imaging

Incorporating boundaries of the imaging object as a priori information t...

Generalizability of Machine Learning Models: Quantitative Evaluation of Three Methodological Pitfalls

Despite the great potential of machine learning, the lack of generalizab...

Underspecification Presents Challenges for Credibility in Modern Machine Learning

ML models often exhibit unexpectedly poor behavior when they are deploye...

DeepRadiologyNet: Radiologist Level Pathology Detection in CT Head Images

We describe a system to automatically filter clinically significant find...

CT Image Harmonization for Enhancing Radiomics Studies

While remarkable advances have been made in Computed Tomography (CT), ca...