Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Medical Informatics

Date Submitted: Mar 30, 2021
Date Accepted: May 16, 2021

The final, peer-reviewed published version of this preprint can be found here:

Predicting Antituberculosis Drug–Induced Liver Injury Using an Interpretable Machine Learning Method: Model Development and Validation Study

Zhong T, Zhuang Z, Dong X, Wong KH, Wong WT, Wang J, He D, Liu S

Predicting Antituberculosis Drug–Induced Liver Injury Using an Interpretable Machine Learning Method: Model Development and Validation Study

JMIR Med Inform 2021;9(7):e29226

DOI: 10.2196/29226

PMID: 34283036

PMCID: 8335604

Predicting Antituberculosis Drug-Induced Liver Injury Using Interpretable Machine Learning Method: Model Development and Validation Study

  • Tao Zhong; 
  • Zian Zhuang; 
  • Xiaoli Dong; 
  • Ka Hing Wong; 
  • Wing Tak Wong; 
  • Jian Wang; 
  • Daihai He; 
  • Shengyuan Liu

ABSTRACT

Background:

Tuberculosis is a global pandemic, being one of the top ten causes of death and the main cause of death from a single source of infection. Drug-induced liver injury (DILI) is the most common and serious side effect during the treatment of tuberculosis patients.

Objective:

We aim to predict the status of liver injury in patients with TB at clinical treatment stage.

Methods:

We designed an interpretable prediction model based on XGBoost algorithm and identified the most robust and meaningful predictors to predict the risk of TB-DILI.

Results:

We found that the patients’ most recent ALT test value, average change rate of patients’ last two ALT test values, cumulative dose of PZA and cumulative dose of EMB to be the best predictors for assessing the DILI risk. In the validation dataset, the model has a precision of 90%, a recall of 74%, a classification accuracy of 76% and a balanced error rate of 77% in predicting the TB-DILI cases. In addition, the model provided high risk warnings for patients in advance of the drug-induced liver injury onset for a median of 29 days (IQR, (15, 45.75)).

Conclusions:

The model shows the high accuracy and interpretability in predicting the TB-DILI cases, which can provide useful information to Clinicians to adjust the medication regimen and avoid more serious liver injury in patients.


 Citation

Please cite as:

Zhong T, Zhuang Z, Dong X, Wong KH, Wong WT, Wang J, He D, Liu S

Predicting Antituberculosis Drug–Induced Liver Injury Using an Interpretable Machine Learning Method: Model Development and Validation Study

JMIR Med Inform 2021;9(7):e29226

DOI: 10.2196/29226

PMID: 34283036

PMCID: 8335604

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.