2022
Predicting resistance to fluoroquinolones among patients with rifampicin-resistant tuberculosis using machine learning methods
You S, Chitwood MH, Gunasekera KS, Crudu V, Codreanu A, Ciobanu N, Furin J, Cohen T, Warren JL, Yaesoubi R. Predicting resistance to fluoroquinolones among patients with rifampicin-resistant tuberculosis using machine learning methods. PLOS Digital Health 2022, 1: e0000059. PMID: 36177394, PMCID: PMC9518704, DOI: 10.1371/journal.pdig.0000059.Peer-Reviewed Original ResearchDrug susceptibility testXpert MTB/RIFMachine learning-based modelsLearning-based modelsMachine learning methodsRifampicin-resistant tuberculosisTime of diagnosisRifampin-resistant tuberculosisMTB/RIFNeural network modelLearning methodsNetwork modelMulti-drug resistant tuberculosisNational TB surveillanceDrug-resistant tuberculosisOptimism-corrected areaSelection of antibioticsAnti-TB agentsDistrict-level prevalenceLow-resource settingsPatient characteristicsResistant tuberculosisTB surveillanceAppropriate treatmentDST results
2019
Disparities in access to diagnosis and care in Blantyre, Malawi, identified through enhanced tuberculosis surveillance and spatial analysis
MacPherson P, Khundi M, Nliwasa M, Choko AT, Phiri VK, Webb EL, Dodd PJ, Cohen T, Harris R, Corbett EL. Disparities in access to diagnosis and care in Blantyre, Malawi, identified through enhanced tuberculosis surveillance and spatial analysis. BMC Medicine 2019, 17: 21. PMID: 30691470, PMCID: PMC6350280, DOI: 10.1186/s12916-019-1260-6.Peer-Reviewed Original ResearchConceptsTB case notification ratesCase notification ratesCommunity health workersNotification ratesTB casesLow case detectionSingle sputum sampleInverse care lawArea-level factorsTB registrationTB clinicTB patientsClinical characteristicsTB diagnosisTuberculosis casesResultsIn totalTB surveillanceCase detectionModifiable predictorsSputum samplesHealth workersTB officersTB microscopyAdjusted modelTuberculosis surveillance