Machine learning model to predict the adherence of tuberculosis patients experiencing increased levels of liver enzymes in Indonesia.
Indonesia is still the second-highest tuberculosis burden country in the world. The antituberculosis adverse drug reaction and adherence may influence the success of treatment. The objective of this study is to define the model for predicting the adherence in tuberculosis patients, based on the incr...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0315912 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540220764979200 |
|---|---|
| author | Dyah Aryani Perwitasari Imaniar Noor Faridah Haafizah Dania Didik Setiawan Triantoro Safaria |
| author_facet | Dyah Aryani Perwitasari Imaniar Noor Faridah Haafizah Dania Didik Setiawan Triantoro Safaria |
| author_sort | Dyah Aryani Perwitasari |
| collection | DOAJ |
| description | Indonesia is still the second-highest tuberculosis burden country in the world. The antituberculosis adverse drug reaction and adherence may influence the success of treatment. The objective of this study is to define the model for predicting the adherence in tuberculosis patients, based on the increased level of liver enzymes. The longitudinal study using adult tuberculosis patients treated with the first line of antituberculosis was conducted prospectively. The pregnant women and patients with complications such as gout, diabetes mellitus, liver disorder and HIV were excluded. We measured the total bilirubin, aspartate aminotransferase (AST), and alanine aminotransferase (ALT) and adherence over the 2nd, 4th, and 6th months of the treatment. We used the ORANGE Data mining as the machine learning to predict the adherence. We recruited 201 patients, whereas the male participants and less than 61 years old as the dominant participants. Around 33%, 35% and 35% tuberculosis patients experienced the increase level of bilirubine, ALT and AST, respectively. There were significant differences in ALT and AST between good and poor adherence groups, especially in the female patients. The Neural Network and Random Forests were the most suitable models to predict tuberculosis patients' adherence with good Area Under The Curve (AUC). |
| format | Article |
| id | doaj-art-efe968b3d8914a938cb02e40e5174e30 |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-efe968b3d8914a938cb02e40e5174e302025-02-05T05:32:12ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01201e031591210.1371/journal.pone.0315912Machine learning model to predict the adherence of tuberculosis patients experiencing increased levels of liver enzymes in Indonesia.Dyah Aryani PerwitasariImaniar Noor FaridahHaafizah DaniaDidik SetiawanTriantoro SafariaIndonesia is still the second-highest tuberculosis burden country in the world. The antituberculosis adverse drug reaction and adherence may influence the success of treatment. The objective of this study is to define the model for predicting the adherence in tuberculosis patients, based on the increased level of liver enzymes. The longitudinal study using adult tuberculosis patients treated with the first line of antituberculosis was conducted prospectively. The pregnant women and patients with complications such as gout, diabetes mellitus, liver disorder and HIV were excluded. We measured the total bilirubin, aspartate aminotransferase (AST), and alanine aminotransferase (ALT) and adherence over the 2nd, 4th, and 6th months of the treatment. We used the ORANGE Data mining as the machine learning to predict the adherence. We recruited 201 patients, whereas the male participants and less than 61 years old as the dominant participants. Around 33%, 35% and 35% tuberculosis patients experienced the increase level of bilirubine, ALT and AST, respectively. There were significant differences in ALT and AST between good and poor adherence groups, especially in the female patients. The Neural Network and Random Forests were the most suitable models to predict tuberculosis patients' adherence with good Area Under The Curve (AUC).https://doi.org/10.1371/journal.pone.0315912 |
| spellingShingle | Dyah Aryani Perwitasari Imaniar Noor Faridah Haafizah Dania Didik Setiawan Triantoro Safaria Machine learning model to predict the adherence of tuberculosis patients experiencing increased levels of liver enzymes in Indonesia. PLoS ONE |
| title | Machine learning model to predict the adherence of tuberculosis patients experiencing increased levels of liver enzymes in Indonesia. |
| title_full | Machine learning model to predict the adherence of tuberculosis patients experiencing increased levels of liver enzymes in Indonesia. |
| title_fullStr | Machine learning model to predict the adherence of tuberculosis patients experiencing increased levels of liver enzymes in Indonesia. |
| title_full_unstemmed | Machine learning model to predict the adherence of tuberculosis patients experiencing increased levels of liver enzymes in Indonesia. |
| title_short | Machine learning model to predict the adherence of tuberculosis patients experiencing increased levels of liver enzymes in Indonesia. |
| title_sort | machine learning model to predict the adherence of tuberculosis patients experiencing increased levels of liver enzymes in indonesia |
| url | https://doi.org/10.1371/journal.pone.0315912 |
| work_keys_str_mv | AT dyaharyaniperwitasari machinelearningmodeltopredicttheadherenceoftuberculosispatientsexperiencingincreasedlevelsofliverenzymesinindonesia AT imaniarnoorfaridah machinelearningmodeltopredicttheadherenceoftuberculosispatientsexperiencingincreasedlevelsofliverenzymesinindonesia AT haafizahdania machinelearningmodeltopredicttheadherenceoftuberculosispatientsexperiencingincreasedlevelsofliverenzymesinindonesia AT didiksetiawan machinelearningmodeltopredicttheadherenceoftuberculosispatientsexperiencingincreasedlevelsofliverenzymesinindonesia AT triantorosafaria machinelearningmodeltopredicttheadherenceoftuberculosispatientsexperiencingincreasedlevelsofliverenzymesinindonesia |