“Background: Adherence 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 Trichostatin A 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.\n\nMethods: Two 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).\n\nResults: The best model to predict lost to follow-up outcome included the following characteristics: immigration BI 2536 (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]).\n\nConclusion: This 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.”
“Motivation: Metabolite identification from tandem mass spectra is an important problem in metabolomics, underpinning subsequent metabolic modelling and network analysis. Yet, currently this task requires matching the observed spectrum against a database of reference spectra originating from similar equipment and closely matching operating parameters, a condition that is rarely satisfied in public repositories.
PR-171 Furthermore, the computational support for identification of molecules not present in reference databases is lacking. Recent efforts in assembling large public mass spectral databases such as MassBank have opened the door for the development of a new genre of metabolite identification methods.\n\nResults: We introduce a novel framework for prediction of molecular characteristics and identification of metabolites from tandem mass spectra using machine learning with the support vector machine. Our approach is to first predict a large set of molecular properties of the unknown metabolite from salient tandem mass spectral signals, and in the second step to use the predicted properties for matching against large molecule databases, such as PubChem.