Risk score prediction for bacteriologically confirmed tuberculosis among HIV-infected adults on antiretroviral therapy in Ethiopia: prognostic model development.

Abstract

This study was aimed at developing a risk score prediction model for bacteriologically confirmed TB among HIV-infected adults receiving antiretroviral therapy in Ethiopia. An institutional-based retrospective follow-up study was conducted among 569 HIV-infected adults on ART. We used demographic and clinical prognostic factors to develop a risk prediction model. Model performance was evaluated by discrimination and calibration using the area under the receiver operating characteristic (AUROC) curve and calibration plot. Bootstrapping was used for internal validation. A decision curve analysis was used to evaluate the clinical utility. Opportunistic infection, functional status, anemia, isoniazid preventive therapy, and WHO clinical stages were used to develop risk prediction. The AUROC curve of the original model was 87.53% (95% CI: 83.88-91.25) and the calibration plot (p-value = 0.51). After internal validation, the AUROC curve of 86.61% (95% CI: 82.92-90.29%) was comparable with the original model, with an optimism coefficient of 0.0096 and good calibration (p-value = 0.10). Our model revealed excellent sensitivity (92.65%) and negative predictive value (NPV) (98.60%) with very good specificity (70.06%) and accuracy (72.76%). After validation, accuracy (74.85%) and specificity (76.27%) were improved, but sensitivity (86.76%) and NPV (97.66%) were relatively reduced. The risk prediction model had a net benefit up to 7.5 threshold probabilities. This prognostic model had very good performance. Moreover, it had very good sensitivity and excellent NPV. The model could help clinicians use risk estimation and stratification for early diagnosis and treatment to improve patient outcomes and quality of life.