Metraipolis › archive › dc_ef8b0fdd8252
Cross-cohort TB classification using clinical data gathered in Uganda and South Africa — arXiv:2610.03256
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.03256
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T23:10:12.347Z
- SHA-256 of the archived text
a8b9a6bba1eba494d93c6b1ca7e517529b39fd94f499cbb5e97218c9ddfdc681- Stable URL of this page
https://metraipolis.com/documento/dc_ef8b0fdd8252
How to cite
Cross-cohort TB classification using clinical data gathered in Uganda and South Africa — arXiv:2610.03256 — arXiv, https://arxiv.org/abs/2610.03256 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ef8b0fdd8252 (Metraipolis archive dc_ef8b0fdd8252, sha256 a8b9a6bba1eba494d93c6b1ca7e517529b39fd94f499cbb5e97218c9ddfdc681)
BibTeX
@misc{dcef8b0fdd8252,
title = {Cross-cohort TB classification using clinical data gathered in Uganda and South Africa — arXiv:2610.03256},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.03256},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ef8b0fdd8252; sha256 a8b9a6bba1eba494d93c6b1ca7e517529b39fd94f499cbb5e97218c9ddfdc681},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03256. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.03256 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-05T23:01:38.680Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).