Deep learning on longitudinal CT scans: automated prediction of treatment outcomes in hospitalized tuberculosis patients

Mayidili Nijiati; Lin Guo; Abudouresuli Tuersun; Maihemitijiang Damola; Abudoukeyoumujiang Abulizi; Jiake Dong; Li Xia; Kunlei Hong; Xiaoguang Zou

doi:10.1016/j.isci.2023.108326

Deep learning on longitudinal CT scans: automated prediction of treatment outcomes in hospitalized tuberculosis patients

iScience. 2023 Oct 23;26(11):108326. doi: 10.1016/j.isci.2023.108326. eCollection 2023 Nov 17.

Authors

Mayidili Nijiati¹, Lin Guo², Abudouresuli Tuersun¹, Maihemitijiang Damola¹, Abudoukeyoumujiang Abulizi¹, Jiake Dong¹, Li Xia², Kunlei Hong², Xiaoguang Zou³

Affiliations

¹ Department of Radiology, The First People's Hospital of Kashi Prefecture, Kashi, China.
² Shenzhen Zhiying Medical Imaging, Shenzhen, China.
³ Clinical Medical Research Center, The First People's Hospital of Kashi Prefecture, Kashi, China.

Abstract

Three deep learning (DL)-based prediction models (PMs) using longitudinal CT images were developed to predict tuberculosis (TB) treatment outcomes. The internal dataset consists of 493 bacteriologically confirmed TB patients who completed the anti-tuberculosis treatment with three-time CT scans, including a pretreatment CT scan and two follow-up CT scans. PM1 was trained using only pretreatment CT scans, and PM2 and PM3 were developed by adding follow-up scans. An independent testing was performed on external dataset comprising 86 TB patients. The area under the curve for classifying success and drug-resistant (DR)-TB was improved on both internal (0.609 vs. 0.625 vs. 0.815) and external (0.627 vs. 0.705 vs. 0.735) dataset by adding follow-up scans. The accuracy and F1-score also showed an increasing tendency in the external test. Regular follow-up CT scans can aid in the treatment prediction, and special attention should be given to early intensive phase of treatment to identify high-risk DR-TB patients.

Keywords: Bioinformatics; Machine learning; Respiratory medicine.