How well do routinely collected demographic and clinical variables aid point-of-care lung ultrasound TB classification

2026-10-05

AI Summary

This study addresses the performance limitations of existing lung ultrasound-based automated tuberculosis screening systems, which fail to fully exploit multi-source information. To this end, we propose a multimodal classification framework that integrates clinical demographic data with ResNet-derived image features. Late fusion is implemented via output averaging, complemented by greedy feature selection to reduce input dimensionality. Experimental results demonstrate that a straightforward score-averaging strategy outperforms more complex early fusion approaches, while feature selection effectively mitigates input redundancy without compromising accuracy. The proposed model achieves an AUROC of 0.95, representing a 4% improvement over the baseline and validating the efficacy of incorporating routine clinical data fusion for intelligent tuberculosis screening.

Abstract

We consider the fusion of lung ultrasound images with routinely-collected clinical and demographic data for the purpose of automated tuberculosis (TB) screening using deep-learning. Such deep-learning based screening tools for TB could meaningfully support the health care system in Africa, where the burden of disease is severe and resources are constrained. Beginning with an established ResNet baseline for classification of lung ultrasound images, which achieves an area under the receiver operating characteristic (AUROC) curve of 0.91 [0.86,0.96] (95% CI), we consider the incorporation of the clinical and demographic data using three fusion approaches. We find that a simple average-based fusion of the output scores of separately-trained image and clinical data classifiers consistently matches or outperforms a more complex approach where the data is fused earlier and a combined classifier is trained. Fusing the image and the clinical classifiers in this way leads to a classifier with an overall AUROC of 0.95 [0.91,0.99] (specificity of 0.76 at sensitivity 0.93) which is an improvement of 4% absolute over the image-only baseline. We also find that greedy feature selection can be used to reduce the number of clinical and demographic inputs without sacrificing classification performance. Finally, when we differentiate between clinical and demographic data that are self-reported, that require some basic measurement or calculation, and that require a point-of-care (POC) test, we find the inclusion of the POC tests included in this study to be of minimal benefit to classification performance. We conclude that the incorporation of routinely-collected clinical and demographic data is a promising way to improve the performance of lung ultrasound based automatic classification.

Problem

• tuberculosis screening
• lung ultrasound
• deep learning
• data fusion
• clinical variables

Innovation

• Multimodal Fusion
• Lung Ultrasound
• Tuberculosis Screening
• Greedy Feature Selection
• Deep Learning