Predicting resistance to fluoroquinolones among patients with rifampicin-resistant tuberculosis using machine learning methods.
<h4>Background</h4>Limited access to drug-susceptibility tests (DSTs) and delays in receiving DST results are challenges for timely and appropriate treatment of multi-drug resistant tuberculosis (TB) in many low-resource settings. We investigated whether data collected as part of routine...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2022-01-01
|
| Series: | PLOS Digital Health |
| Online Access: | https://doi.org/10.1371/journal.pdig.0000059 |
| _version_ | 1797723379124404224 |
|---|---|
| author | Shiying You Melanie H Chitwood Kenneth S Gunasekera Valeriu Crudu Alexandru Codreanu Nelly Ciobanu Jennifer Furin Ted Cohen Joshua L Warren Reza Yaesoubi |
| author_facet | Shiying You Melanie H Chitwood Kenneth S Gunasekera Valeriu Crudu Alexandru Codreanu Nelly Ciobanu Jennifer Furin Ted Cohen Joshua L Warren Reza Yaesoubi |
| author_sort | Shiying You |
| collection | DOAJ |
| description | <h4>Background</h4>Limited access to drug-susceptibility tests (DSTs) and delays in receiving DST results are challenges for timely and appropriate treatment of multi-drug resistant tuberculosis (TB) in many low-resource settings. We investigated whether data collected as part of routine, national TB surveillance could be used to develop predictive models to identify additional resistance to fluoroquinolones (FLQs), a critical second-line class of anti-TB agents, at the time of diagnosis with rifampin-resistant TB.<h4>Methods and findings</h4>We assessed three machine learning-based models (logistic regression, neural network, and random forest) using information from 540 patients with rifampicin-resistant TB, diagnosed using Xpert MTB/RIF and notified in the Republic of Moldova between January 2018 and December 2019. The models were trained to predict the resistance to FLQs based on demographic and TB clinical information of patients and the estimated district-level prevalence of resistance to FLQs. We compared these models based on the optimism-corrected area under the receiver operating characteristic curve (OC-AUC-ROC). The OC-AUC-ROC of all models were statistically greater than 0.5. The neural network model, which utilizes twelve features, performed best and had an estimated OC-AUC-ROC of 0.87 (0.83,0.91), which suggests reasonable discriminatory power. A limitation of our study is that our models are based only on data from the Republic of Moldova and since not externally validated, the generalizability of these models to other populations remains unknown.<h4>Conclusions</h4>Models trained on data from phenotypic surveillance of drug-resistant TB can predict resistance to FLQs based on patient characteristics at the time of diagnosis with rifampin-resistant TB using Xpert MTB/RIF, and information about the local prevalence of resistance to FLQs. These models may be useful for informing the selection of antibiotics while awaiting results of DSTs. |
| first_indexed | 2024-03-12T10:02:03Z |
| format | Article |
| id | doaj.art-0deca208cb6846508edc6bbd736c75a7 |
| institution | Directory Open Access Journal |
| issn | 2767-3170 |
| language | English |
| last_indexed | 2024-03-12T10:02:03Z |
| publishDate | 2022-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLOS Digital Health |
| spelling | doaj.art-0deca208cb6846508edc6bbd736c75a72023-09-02T11:33:41ZengPublic Library of Science (PLoS)PLOS Digital Health2767-31702022-01-0116e000005910.1371/journal.pdig.0000059Predicting resistance to fluoroquinolones among patients with rifampicin-resistant tuberculosis using machine learning methods.Shiying YouMelanie H ChitwoodKenneth S GunasekeraValeriu CruduAlexandru CodreanuNelly CiobanuJennifer FurinTed CohenJoshua L WarrenReza Yaesoubi<h4>Background</h4>Limited access to drug-susceptibility tests (DSTs) and delays in receiving DST results are challenges for timely and appropriate treatment of multi-drug resistant tuberculosis (TB) in many low-resource settings. We investigated whether data collected as part of routine, national TB surveillance could be used to develop predictive models to identify additional resistance to fluoroquinolones (FLQs), a critical second-line class of anti-TB agents, at the time of diagnosis with rifampin-resistant TB.<h4>Methods and findings</h4>We assessed three machine learning-based models (logistic regression, neural network, and random forest) using information from 540 patients with rifampicin-resistant TB, diagnosed using Xpert MTB/RIF and notified in the Republic of Moldova between January 2018 and December 2019. The models were trained to predict the resistance to FLQs based on demographic and TB clinical information of patients and the estimated district-level prevalence of resistance to FLQs. We compared these models based on the optimism-corrected area under the receiver operating characteristic curve (OC-AUC-ROC). The OC-AUC-ROC of all models were statistically greater than 0.5. The neural network model, which utilizes twelve features, performed best and had an estimated OC-AUC-ROC of 0.87 (0.83,0.91), which suggests reasonable discriminatory power. A limitation of our study is that our models are based only on data from the Republic of Moldova and since not externally validated, the generalizability of these models to other populations remains unknown.<h4>Conclusions</h4>Models trained on data from phenotypic surveillance of drug-resistant TB can predict resistance to FLQs based on patient characteristics at the time of diagnosis with rifampin-resistant TB using Xpert MTB/RIF, and information about the local prevalence of resistance to FLQs. These models may be useful for informing the selection of antibiotics while awaiting results of DSTs.https://doi.org/10.1371/journal.pdig.0000059 |
| spellingShingle | Shiying You Melanie H Chitwood Kenneth S Gunasekera Valeriu Crudu Alexandru Codreanu Nelly Ciobanu Jennifer Furin Ted Cohen Joshua L Warren Reza Yaesoubi Predicting resistance to fluoroquinolones among patients with rifampicin-resistant tuberculosis using machine learning methods. PLOS Digital Health |
| title | Predicting resistance to fluoroquinolones among patients with rifampicin-resistant tuberculosis using machine learning methods. |
| title_full | Predicting resistance to fluoroquinolones among patients with rifampicin-resistant tuberculosis using machine learning methods. |
| title_fullStr | Predicting resistance to fluoroquinolones among patients with rifampicin-resistant tuberculosis using machine learning methods. |
| title_full_unstemmed | Predicting resistance to fluoroquinolones among patients with rifampicin-resistant tuberculosis using machine learning methods. |
| title_short | Predicting resistance to fluoroquinolones among patients with rifampicin-resistant tuberculosis using machine learning methods. |
| title_sort | predicting resistance to fluoroquinolones among patients with rifampicin resistant tuberculosis using machine learning methods |
| url | https://doi.org/10.1371/journal.pdig.0000059 |
| work_keys_str_mv | AT shiyingyou predictingresistancetofluoroquinolonesamongpatientswithrifampicinresistanttuberculosisusingmachinelearningmethods AT melaniehchitwood predictingresistancetofluoroquinolonesamongpatientswithrifampicinresistanttuberculosisusingmachinelearningmethods AT kennethsgunasekera predictingresistancetofluoroquinolonesamongpatientswithrifampicinresistanttuberculosisusingmachinelearningmethods AT valeriucrudu predictingresistancetofluoroquinolonesamongpatientswithrifampicinresistanttuberculosisusingmachinelearningmethods AT alexandrucodreanu predictingresistancetofluoroquinolonesamongpatientswithrifampicinresistanttuberculosisusingmachinelearningmethods AT nellyciobanu predictingresistancetofluoroquinolonesamongpatientswithrifampicinresistanttuberculosisusingmachinelearningmethods AT jenniferfurin predictingresistancetofluoroquinolonesamongpatientswithrifampicinresistanttuberculosisusingmachinelearningmethods AT tedcohen predictingresistancetofluoroquinolonesamongpatientswithrifampicinresistanttuberculosisusingmachinelearningmethods AT joshualwarren predictingresistancetofluoroquinolonesamongpatientswithrifampicinresistanttuberculosisusingmachinelearningmethods AT rezayaesoubi predictingresistancetofluoroquinolonesamongpatientswithrifampicinresistanttuberculosisusingmachinelearningmethods |