aiqbench analysis
This study evaluates machine learning models, including logistic regression and neural networks, for tuberculosis screening using clinical data from Uganda and South Africa. The research highlights that while feature selection improves performance across architectures, simpler models like logistic regression often match or exceed the consistency of deeper networks on held-out international cohorts. These findings offer practical insights into deploying accessible ML tools for global health diagnostics where expensive molecular testing is limited.
Cross-cohort TB classification using clinical data gathered in Uganda and South Africa
arXiv:2610.03256v1 Announce Type: new Abstract: We present a first evaluation of machine learning applied to patient clinical and demographic data gathered in two different countries for the purpose of tuberculosis (TB) screening to identify people who would benefit from expensive molecular testing. Experiments are based on the recently-compiled CAGE-TB dataset, which includes sub-cohorts of people with presumptive TB presenting at community health care centres in South Africa and Uganda. Three neural network architectures (logistic regression (LR), multilayer perceptrons (MLP) and convolutional neural networks (CNN)) are considered in conjunction with greedy feature selection. For the convolutional neural network, a strategy that jointly optimises feature selection and feature ordering is proposed and shown to lead to consistent development and test set improvements. For all three models, development set area under the receiver operating characteristic (AUROC) curve is improved by 2-7% using feature selection. LR after feature selection achieves an AUROC of 0.8 [0.75,0.86] (95% CI) and 0.84 [0.78,0.9] when testing on the held-out Ugandan and South African data respectively. Although outperforming LR on the development cohort, the deeper networks (MLP, CNN) show inconsistent trends on the held-out cohorts, while LR achieves performance within 1-2% of the best achieved in terms of AUROC. LR narrowly misses the WHO minimum requirements by 4-9% in sensitivity even though the network is being evaluated on a completely held-out cohort. The development of neural-network based classifiers for TB screening therefore appears viable.
Authors:Joshua M. Jansen van Vüren, Devendra S. Parihar, Daphne Naidoo, Marisa Klopper, Frank Cobelens, Lutz Kolbe, Kimsey Zajac, Willy Ssengooba, Moses Joloba, Grant Theron, Thomas R. Niesler
Abstract:We present a first evaluation of machine learning applied to patient clinical and demographic data gathered in two different countries for the purpose of tuberculosis (TB) screening to identify people who would benefit from expensive molecular testing. Experiments are based on the recently-compiled CAGE-TB dataset, which includes sub-cohorts of people with presumptive TB presenting at community health care centres in South Africa and Uganda. Three neural network architectures (logistic regression (LR), multilayer perceptrons (MLP) and convolutional neural networks (CNN)) are considered in conjunction with greedy feature selection. For the convolutional neural network, a strategy that jointly optimises feature selection and feature ordering is proposed and shown to lead to consistent development and test set improvements. For all three models, development set area under the receiver operating characteristic (AUROC) curve is improved by 2-7% using feature selection. LR after feature selection achieves an AUROC of 0.8 [0.75,0.86] (95% CI) and 0.84 [0.78,0.9] when testing on the held-out Ugandan and South African data respectively. Although outperforming LR on the development cohort, the deeper networks (MLP, CNN) show inconsistent trends on the held-out cohorts, while LR achieves performance within 1-2% of the best achieved in terms of AUROC. LR narrowly misses the WHO minimum requirements by 4-9% in sensitivity even though the network is being evaluated on a completely held-out cohort. The development of neural-network based classifiers for TB screening therefore appears viable.
Machine Learning (cs.LG)
I.2.6; I.5.1; I.5.2; J.3
arXiv:2610.03256 [cs.LG]
(or arXiv:2610.03256v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.03256 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 279 words
Related coverage
Seeing beyond BMI: Estimating cardiometabolic risk with smartphone imagery
Google Research · Aug 17, 2026
Biomedical Imaging's Real Bottleneck Is the Data, Not the Model
Databricks · Oct 8, 2026
Introducing CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement
Microsoft Research · Aug 11, 2026
Cross-Modal Contrastive Learning from Histopathology and CT for Automated Renal Cell Carcinoma Grading
arXiv · Sep 24, 2026