A predictive scoring instrument for tuberculosis lost to follow-up outcome

Abstract

BackgroundAdherence to tuberculosis (TB) treatment is troublesome, due to long therapy duration, quick therapeutic response which allows the patient to disregard about the rest of their treatment and the lack of motivation on behalf of the patient for improved. The objective of this study was to develop and validate a scoring system to predict the probability of lost to follow-up outcome in TB patients as a way to identify patients suitable for directly observed treatments (DOT) and other interventions to improve adherence.MethodsTwo prospective cohorts, were used to develop and validate a logistic regression model. A scoring system was constructed, based on the coefficients of factors associated with a lost to follow-up outcome. The probability of lost to follow-up outcome associated with each score was calculated. Predictions in both cohorts were tested using receiver operating characteristic curves (ROC).ResultsThe best model to predict lost to follow-up outcome included the following characteristics: immigration (1 point value), living alone (1 point) or in an institution (2 points), previous anti-TB treatment (2 points), poor patient understanding (2 points), intravenous drugs use (IDU) (4 points) or unknown IDU status (1 point). Scores of 0, 1, 2, 3, 4 and 5 points were associated with a lost to follow-up probability of 2,2% 5,4% 9,9%, 16,4%, 15%, and 28%, respectively. The ROC curve for the validation group demonstrated a good fit (AUC: 0,67 [95% CI; 0,65-0,70]).ConclusionThis model has a good capacity to predict a lost to follow-up outcome. Its use could help TB Programs to determine which patients are good candidates for DOT and other strategies to improve TB treatment adherence.

Early identification of individuals at risk for loss to follow-up of tuberculosis treatment: A generalised hierarchical analysis

“…We emphasise that at the national level, potential implementation of this clinical practice with the use of risk nomograms is an innovative and stimulating proposal for the development of the present study. Other researchers have also developed similar models to predict better TB treatment outcomes [21,23,35].…”

Feature selection and prediction of treatment failure in tuberculosis

“…The first to employ a logistic regression model for prediction were Kalhori et al in 2008, which, using clinical data, achieved an AUC of 0.70 [ 16 ]. Similarly, Rodrigo et al report a predictive scoring instrument for tuberculosis lost to follow-up with an AUC of 0.67 (95%CI 0.65–0.70) [ 17 ]. Recently, Cherkaoui et al conducted a prospective study employing questionnaires in rural Morocco.…”

Treatment Default amongst Patients with Tuberculosis in Urban Morocco: Predicting and Explaining Default and Post-Default Sputum Smear and Drug Susceptibility Results

“…Few studies have used formal modeling to develop a scoring system to predict the probability of treatment default [38] , [39] . By assigning points to independent predictors of default based on their logistic regression coefficients, we developed a scoring system that was 82.4% sensitive and 87.6% specific for TB treatment default in urban Morocco.…”