Despite some previous examples of successful application to the field of pharmacogenomics, the utility of machine learning (ML) techniques for warfarin dose predictions in Caribbean Hispanic patients has yet to be fully evaluated. This study compares seven ML methods to predict warfarin dosing in Caribbean Hispanics. This is a secondary analysis of genetic and non-genetic clinical data from 190 cardiovascular Hispanic patients. Seven ML algorithms were applied to the data. Data was divided into 80 and 20% to be used as training and test sets. ML algorithms were trained with the training set to obtain the models. Model performance was determined by computing the corresponding mean absolute error (MAE) and % patients whose predicted optimal dose were within ±20% of the actual stabilization dose, and then compared between groups of patients with “normal” (i.e., > 21 but <49 mg/week), low (i.e., ≤21 mg/week, “sensitive”), and high (i.e., ≥49 mg/week, “resistant”) dose requirements. Random forest regression (RFR) significantly outperform all other methods, with a MAE of 4.73 mg/week and 80.56% of cases within ±20% of the actual stabilization dose. Among those with “normal” dose requirements, RFR performance is also better than the rest of models (MAE = 2.91 mg/week). In the “sensitive” group, support vector regression (SVR) shows superiority over the others with lower MAE of 4.79 mg/week. Finally, multivariate adaptive splines (MARS) shows the best performance in the resistant group (MAE = 7.22 mg/week) and 66.7% of predictions within ±20%. Models generated by using RFR, MARS, and SVR algorithms showed significantly better predictions of weekly warfarin dosing in the studied cohorts than other algorithms. Better performance of the ML models for patients with “normal,” “sensitive,” and “resistant” to warfarin were obtained when compared to other populations and previous statistical models.

Background: Acute lymphoblastic leukemia (ALL) is the most common cancer seen in children worldwide and in the Middle East. Although there have been major advances in treatment approaches for childhood ALL, serious toxicities do occur but with significant inter-individual variability. The aim of this study is to measure the frequency of polymorphisms in candidate genes involved in 6-Mercaptopurine (6-MP) disposition in a combined cohort of Middle Eastern Children with ALL, and evaluate whether these polymorphisms predict 6-MP intolerance and toxicity during ALL maintenance therapy.

Methods: The study includes children treated for ALL on two treatment protocols from two cohorts; one from Lebanon (N = 136) and another from Kurdistan province of Iran (N = 74). Genotyping for the following six candidate genetic polymorphisms: ITPA 94C > A (rs1127354) and IVS2+21A > C (rs7270101), TPMT*2 238G > C (rs1800462), TPMT*3B 460G > A (rs1800460) and *3C 719A > G (rs1142345), and NUDT15 415C > T (rs116855232) was performed and analyzed in association with 6-MP dose intensity and toxicity.

Results: As expected, TPMT and NUDT15 variants were uncommon. As for ITPA, both polymorphisms were more common in the Lebanese as compared to the Kurdish cohort with a minor allele frequency of 0.05 for 94C > A and 0.14 for IVS2+21A > C in the Lebanese only (N = 121), and of 0.01 for either ITPA polymorphism in Kurds. The most significant toxic effects were depicted with the NUDT15 polymorphism with a median 6-MP dose intensity of 33.33%, followed by 46.65% for TPMT*3A polymorphism, followed by 65.33% for two ITPA risk allele carriers and 74% for one ITPA risk allele carriers, in comparison to a median of 100% for the homozygous wild type in the combined cohort (P < 0.001). In addition, the onset of febrile neutropenia was significantly higher in variant allele carriers in the combined cohorts.

Conclusions: These data confirm the predictive role of TPMT, NUDT15, and ITPA in 6-MP intolerance in Middle Eastern children with ALL. Given the relatively high frequency of ITPA variants in our study and their significant association with 6-MP dose intensity, we recommend that physicians consider genotyping for ITPA variants in conjunction with TPMT and NUDT15 prior to 6-MP therapy in these children.