Prediction of Thiopurine Metabolite Levels Based on Haematological and Biochemical Parameters

0512143 - ÚEB 2020 RIV US eng J - Journal Article
Hradsky, O. - Potuznikova, K. - Široká, Jitka - Lerchova, T. - Urbánek, Lubor - Mihál, V. - Spenerova, M. - Velganova-Veghova, M. - Karaskova, E. - Bronsky, J.
Prediction of Thiopurine Metabolite Levels Based on Haematological and Biochemical Parameters.
Journal of Pediatric Gastroenterology and Nutrition. Roč. 69, č. 4 (2019), e105-e110. ISSN 0277-2116. E-ISSN 1536-4801
Institutional support: RVO:61389030
Keywords : 6-mercaptopurine * 6-thioguanine * azathioprine * Crohn disease
OECD category: Technologies involving the manipulation of cells, tissues, organs or the whole organism (assisted reproduction)
Impact factor: 2.937, year: 2019
Method of publishing: Open access
http://dx.doi.org/10.1097/MPG.0000000000002436

Objectives: Therapeutic drug monitoring of thiopurine erythrocyte levels is not available in all centers and it usually requires quite a long time to obtain the results. The aims of this study were to build a model predicting low levels of 6-thioguanine and 6-methylmercaptopurine in pediatric inflammatory bowel disease (IBD) patients and to build a model to predict nonadherence in patients treated with azathioprine (AZA). Methods: The study consisted of 332 observations in 88 pediatric IBD patients. Low AZA dosing was defined as 6-thioguanine levels <125 pmol/8 × 108 erythrocytes and 6-methylmercaptopurine levels <5700 pmol/8 × 108 erythrocytes. Nonadherence was defined as undetectable levels of 6-thioguanine and 6-methylmercaptopurine <240 pmol/8 × 108 erythrocytes. Data were divided into training and testing part. To construct the model predicting low 6-thioguanine levels, nonadherence, and the level of 6-thioguanine, the modification of random forest method with cross-validation and resampling was used. Results: The final models predicting low 6-thioguanine levels and nonadherence had area under the curve, 0.87 and 0.94, sensitivity, 0.81 and 0.82, specificity, 0.80 and 86, and distance, 0.31 and 0.21, respectively, when applied on the testing part of the dataset. When the final model for prediction of 6-thioguanine values was applied on testing dataset, a root-mean-square error of 110 was obtained. Conclusions: Using easily obtained laboratory parameters, we constructed a model with sufficient accuracy to predict patients with low 6-thioguanine levels and a model for prediction of AZA treatment nonadherence (web applications: https://hradskyo.shinyapps.io/6TG-prediction/ and https://hradskyo.shinyapps.io/Non-adherence/).
Permanent Link: http://hdl.handle.net/11104/0302353