Risk prediction for delayed clearance of high-dose methotrexate in pediatric hematological malignancies by machine learning

Zhan, Min; Chen, Zebin; Ding, Chang-Cai; Qu, Qiang; Wang, Guoqiang; Liu, Sixi; Wen, Feiqiu

doi:10.1007/s12185-021-03184-w

Cited by 7 publications

(7 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reduced expression of RFC1 has been associated with decreased MTX‐PG accumulation in leukemia cells, and various SNPs have been associated with plasma MTX levels and gastrointestinal, hepatic, and bone marrow toxicities 41–43 . The AA genotype was associated with delayed MTX clearance, decreased event‐free survival, and increased risk of minimal residual disease in Chinese pediatric ALL patients 7,44 . Notably, this SNP was the only locus that was likely or very clearly associated with both outcomes in our study.…”

Section: Discussionmentioning

confidence: 51%

“…[41][42][43] The AA genotype was associated with delayed MTX clearance, decreased event-free survival, and increased risk of minimal residual disease in Chinese pediatric ALL patients. 7,44 Notably, this SNP was the only locus that was likely or very clearly associated with both outcomes in our study. This evidence suggests an active role of this locus in producing clinically relevant aberrations in MTX disposition.…”

Section: Discussionmentioning

confidence: 55%

See 1 more Smart Citation

Novel and replicated clinical and genetic risk factors for toxicity from high‐dose methotrexate in pediatric acute lymphoblastic leukemia

et al. 2023

View full text Add to dashboard Cite

Methotrexate (MTX) is a key component of treatment for pediatric acute lymphoblastic leukemia (ALL). Many effective ALL regimens include multiple administrations of MTX in doses that may cause life-threatening adverse effects such as gastrointestinal inflammation, hepatitis, kidney injury, and myelosuppression. These toxic side effects may increase the risk of infections, organ dysfunction, treatment delays, and poor treatment outcomes. MTX doses ≥1000 mg/m 2 are commonly given in the hospital with aggressive supportive care and therapeutic drug monitoring to decrease these risks. Many patients do not clear the drug as expected, which results in prolonged hospitalizations and increased health care costs.

show abstract

Section: Discussionmentioning

confidence: 51%

Section: Discussionmentioning

confidence: 55%

Novel and replicated clinical and genetic risk factors for toxicity from high‐dose methotrexate in pediatric acute lymphoblastic leukemia

et al. 2023

View full text Add to dashboard Cite

show abstract

“…MTX is primarily renally excreted. The concurrent use of some medications has been shown to significantly alter serum and urine pH, causing impaired MTX clearance due to crystal formation, or acute kidney injury ( 3 , 10 ). Our findings suggest a more subtle relationship between IV medication administration and DC.…”

Section: Discussionmentioning

confidence: 99%

“…Hence, while specific genetic polymorphisms can modulate MTX metabolism, their clinical impact appears to be less than that of renal function and hydration status. Multiple Machine Learning (ML) algorithms designed to predict MTX clearance have incorporated specific genetic polymorphisms into their risk prediction models, with only modest improvement in the accuracy of these models ( 10 ). The better performing and freely available model aimed at predicting serum MTX levels and the need for glucarpidase used a large patient cohort and achieved high accuracy by incorporating variables such as MTX dose, serum levels, BSA, weight, age, and creatinine, without genetic polymorphisms ( 19 ); suggesting that even though genetic polymorphisms play a role in HDMTX clearance, for most patients, other variables such as dose, weight, creatinine clearance and subsequently GFR play a greater role in MTX pharmacokinetics and clearance; thus, these factors would benefit from further optimization.…”

Section: Discussionmentioning

confidence: 99%

Factors influencing delayed clearance of high dose methotrexate (HDMTX) in pediatric, adolescent, and young adult oncology patients

Mosleh,

Snyder,

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

PurposeTo identify modifiable risk factors associated with prolonged clearance of methotrexate in pediatric, adolescent, and young adult (AYA) oncology patients receiving high dose methotrexate (HDMTX).Design/MethodA single institution, retrospective chart review of patients receiving HDMTX between 2010-2017. Patients had a diagnosis of either leukemia or osteosarcoma. Data included demographics, concurrent intravenous (IV) medications, IV fluids (IVF) administered, urine output (UO), and rises in serum creatinine (RSC) reflective of renal toxicity (RT). Outcome measures included 1) delayed targeted MTX clearance (DC), 2) actual time to clearance (TTC) and 3) length of stay (LOS).ResultsData from 447 HDMTX administrations were analyzed. The sample consisted of 241 (54%) osteosarcoma encounters, and 206 (46%) leukemia encounters, with an average patient age of 12.7 years. Multivariate analysis showed that DC was associated with the diagnosis of leukemia (OR 7.64, p <.0001), and less UO on day 1 (OR 0.76, p=0.005). Increased TTC was associated with increasing age (RR 1.02, p<0.0001), higher 24-hour MTX levels (RR 1.001, p=0.012) and 48-hour MTX levels (RR 1.02, p<0.0001), RT (RR 1.004, p<0.0001), use of IV lorazepam (RR 1.08, p=0.001) and IV metoclopramide (RR 1.08, p<0.001) both on day 3. Like TTC, LOS was affected by MTX levels at 24 (RR 1.001, p=0.025) and 48 hours (RR 1.03, p<0.0001), RT (RR 1.006, p<0.0001), total IV medications on day 3 (RR 1.042, p<0.0001), and the use of leucovorin on day 2 (RR 0.93, p=0.002).ConclusionMultiple modifiable risk factors were identified which can be leveraged to improve HDMTX clearance. Subsequent efforts will assess whether acting on such risk factors can improve MTX clearance and shorten LOS.

show abstract

“…Therefore, it is necessary to apply ML to predict the metabolic delay of methotrexate. Researchers, such as Wang Yang [ 13 ], Yang Fan [ 14 ], and Min Zhang [ 7 ], have begun using ML to develop prediction models for delayed MTX elimination. However, previous studies have encountered various issues such as small sample sizes, inadequate representation, limited model construction methods, and insufficient comparability.…”

Section: Introductionmentioning

confidence: 99%

Predicting delayed methotrexate elimination in pediatric acute lymphoblastic leukemia patients: an innovative web-based machine learning tool developed through a multicenter, retrospective analysis

Jian

Chen

Wang

et al. 2023

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background High-dose methotrexate (HD-MTX) is a potent chemotherapeutic agent used to treat pediatric acute lymphoblastic leukemia (ALL). HD-MTX is known for cause delayed elimination and drug-related adverse events. Therefore, close monitoring of delayed MTX elimination in ALL patients is essential. Objective This study aimed to identify the risk factors associated with delayed MTX elimination and to develop a predictive tool for its occurrence. Methods Patients who received MTX chemotherapy during hospitalization were selected for inclusion in our study. Univariate and least absolute shrinkage and selection operator (LASSO) methods were used to screen for relevant features. Then four machine learning (ML) algorithms were used to construct prediction model in different sampling method. Furthermore, the performance of the model was evaluated using several indicators. Finally, the optimal model was deployed on a web page to create a visual prediction tool. Results The study included 329 patients with delayed MTX elimination and 1400 patients without delayed MTX elimination who met the inclusion criteria. Univariate and LASSO regression analysis identified eleven predictors, including age, weight, creatinine, uric acid, total bilirubin, albumin, white blood cell count, hemoglobin, prothrombin time, immunological classification, and co-medication with omeprazole. The XGBoost algorithm with SMOTE exhibited AUROC of 0.897, AUPR of 0.729, sensitivity of 0.808, specificity of 0.847, outperforming the other models. And had AUROC of 0.788 in external validation. Conclusion The XGBoost algorithm provides superior performance in predicting the delayed elimination of MTX. We have created a prediction tool to assist medical professionals in predicting MTX metabolic delay.

show abstract

Risk prediction for delayed clearance of high-dose methotrexate in pediatric hematological malignancies by machine learning

Cited by 7 publications

References 44 publications

Novel and replicated clinical and genetic risk factors for toxicity from high‐dose methotrexate in pediatric acute lymphoblastic leukemia

Novel and replicated clinical and genetic risk factors for toxicity from high‐dose methotrexate in pediatric acute lymphoblastic leukemia

Factors influencing delayed clearance of high dose methotrexate (HDMTX) in pediatric, adolescent, and young adult oncology patients

Predicting delayed methotrexate elimination in pediatric acute lymphoblastic leukemia patients: an innovative web-based machine learning tool developed through a multicenter, retrospective analysis

Contact Info

Product

Resources

About