Dataset Information

Machine Learning Identifies Clinical and Genetic Factors Associated With Anthracycline Cardiotoxicity in Pediatric Cancer Survivors.

ABSTRACT:

Background

Despite known clinical risk factors, predicting anthracycline cardiotoxicity remains challenging.

Objectives

This study sought to develop a clinical and genetic risk prediction model for anthracycline cardiotoxicity in childhood cancer survivors.

Methods

We performed exome sequencing in 289 childhood cancer survivors at least 3 years from anthracycline exposure. In a nested case-control design, 183 case patients with reduced left ventricular ejection fraction despite low-dose doxorubicin (≤250 mg/m²), and 106 control patients with preserved left ventricular ejection fraction despite doxorubicin >250 mg/m² were selected as extreme phenotypes. Rare/low-frequency variants were collapsed to identify genes differentially enriched for variants between case patients and control patients. The expression levels of 5 top-ranked genes were evaluated in human induced pluripotent stem cell-derived cardiomyocytes, and variant enrichment was confirmed in a replication cohort. Using random forest, a risk prediction model that included genetic and clinical predictors was developed.

Results

Thirty-one genes were differentially enriched for variants between case patients and control patients (p < 0.001). Only 42.6% case patients harbored a variant in these genes compared to 89.6% control patients (odds ratio: 0.09; 95% confidence interval: 0.04 to 0.17; p = 3.98 × 10^-15). A risk prediction model for cardiotoxicity that included clinical and genetic factors had a higher prediction accuracy and lower misclassification rate compared to the clinical-only model. In vitro inhibition of gene-associated pathways (PI3KR2, ZNF827) provided protection from cardiotoxicity in cardiomyocytes.

Conclusions

Our study identified variants in cardiac injury pathway genes that protect against cardiotoxicity and informed the development of a prediction model for delayed anthracycline cardiotoxicity, and it also provided new targets in autophagy genes for the development of cardio-protective drugs. (Preventing Cardiac Sequelae in Pediatric Cancer Survivors [PCS2]; NCT01805778).

SUBMITTER: Chaix MA

PROVIDER: S-EPMC8352204 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background:Cardiotoxic effects of anthracycline therapy are a major cause of morbidity for childhood cancer survivors. The aim of this retrospective evaluation is to assess the efficacy of Tissue Doppler Imaging in the early detection of myocardial alterations in these patients. Methods:A population of 50 childhood cancer survivors (32 males and 18 females) who have been treated with anthracyclines was evaluated by standard and TDI echocardiographic examination of the basal and median region of the interventricular septum (IVSb, IVSm), of the left ventricular posterior wall (LVPWb, LVPWm), and of the mitral annulus; the results were compared with those obtained from a population of 50 healthy age-matched and sex-matched controls by using the Student test. The clinical and echocardiographic data of the two groups were compared also with the independent samples t-test. All data were expressed as mean?±?standard deviation. A two-tailed P-value <?0.05 was considered statistically significant. Statistical analysis was performed using STATA 7.0. Results:The case-control analysis showed statistically significant differences (p?<?0,05) between the patients and the controls values. The systolic performance of the patients was normal (LVEF (p?=?0,0029) and LVFS (p?=?0,0002)). Statistically significant differences between patients and controls were found for diastolic function measurements obtained with PW Doppler such as IVRT (p?=?0,0000), DT (p?=?0,0041), E (p?=?0,0000), A (p?=?0,0458), even if E/A ratio was not altered. TDI analysis also show significant differences between patients and controls in both LVPW and IVS (basal and middle segments); E/E' ratio and E'/A' ratio did not vary significantly. Linear Regression and multivariate analysis showed that Hematopoietic Stem Cell Transplantation had the highest impact on our measurements. Conclusions:The results showed a myocardial diastolic impairment with preserved ejection fraction. Since the median follow-up time of our cohort was 2 years, further evaluation is needed to better define the diastolic alterations. TDI analysis showed high sensitivity for the detection of mild myocardial dysfunction; the implementation of this novel method as standard practice in the follow-up of selected childhood cancer survivors might help to achieve a better management of long-term complications of cardiotoxic chemotherapy.