Feature selection and prediction of treatment failure in tuberculosis

Autor: David Sasson, Ned McCague, Ben Min-Woo Illigens, Christopher Martin Sauer, Iván Sánchez Fernández, Kenneth E. Paik, Leo Anthony Celi
Jazyk: angličtina
Rok vydání: 2018
Předmět:
0301 basic medicine
Bacterial Diseases
Male
Support Vector Machine
Extensively Drug-Resistant Tuberculosis
Antitubercular Agents
lcsh:Medicine
Drug resistance
Diagnostic Radiology
Machine Learning
0302 clinical medicine
Mathematical and Statistical Techniques
Risk Factors
Medicine and Health Sciences
030212 general & internal medicine
Treatment Failure
lcsh:Science
Microscopy
Multidisciplinary
Pharmaceutics
Radiology and Imaging
Statistics
Middle Aged
Pulmonary Imaging
Infectious Diseases
Physical Sciences
Female
Research Article
Adult
medicine.medical_specialty
Computer and Information Sciences
Tuberculosis
Imaging Techniques
MEDLINE
Developing country
Research and Analysis Methods
Microbiology
03 medical and health sciences
Pharmacotherapy
Drug Therapy
Artificial Intelligence
Diagnostic Medicine
Internal medicine
Support Vector Machines
Microbial Control
medicine
Humans
Statistical Methods
Pharmacology
business.industry
lcsh:R
Extensively drug-resistant tuberculosis
Biology and Life Sciences
Stepwise regression
medicine.disease
Missing data
Tropical Diseases
030104 developmental biology
lcsh:Q
Antimicrobial Resistance
business
Mathematics
Forecasting
Zdroj: PLoS ONE, Vol 13, Iss 11, p e0207491 (2018)
PLoS ONE
ISSN: 1932-6203
Popis: Background Tuberculosis is a major cause of morbidity and mortality in the developing world. Drug resistance, which is predicted to rise in many countries worldwide, threatens tuberculosis treatment and control. Objective To identify features associated with treatment failure and to predict which patients are at highest risk of treatment failure. Methods On a multi-country dataset managed by the National Institute of Allergy and Infectious Diseases we applied various machine learning techniques to identify factors statistically associated with treatment failure and to predict treatment failure based on baseline demographic and clinical characteristics alone. Results The complete-case analysis database consisted of 587 patients (68% males) with a median (p25-p75) age of 40 (30–51) years. Treatment failure occurred in approximately one fourth of the patients. The features most associated with treatment failure were patterns of drug sensitivity, imaging findings, findings in the microscopy Ziehl-Nielsen stain, education status, and employment status. The most predictive model was forward stepwise selection (AUC: 0.74), although most models performed at or above AUC 0.7. A sensitivity analysis using the 643 original patients filling the missing values with multiple imputation showed similar predictive features and generally increased predictive performance. Conclusion Machine learning can help to identify patients at higher risk of treatment failure. Closer monitoring of these patients may decrease treatment failure rates and prevent emergence of antibiotic resistance. The use of inexpensive basic demographic and clinical features makes this approach attractive in low and middle-income countries.
Databáze: OpenAIRE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje