TY - JOUR
T1 - Machine Learning Identifies Clinical and Genetic Factors Associated With Anthracycline Cardiotoxicity in Pediatric Cancer Survivors
AU - Chaix, Marie A.
AU - Parmar, Neha
AU - Kinnear, Caroline
AU - Lafreniere-Roula, Myriam
AU - Akinrinade, Oyediran
AU - Yao, Roderick
AU - Miron, Anastasia
AU - Lam, Emily
AU - Meng, Guoliang
AU - Christie, Anne
AU - Manickaraj, Ashok Kumar
AU - Marjerrison, Stacey
AU - Dillenburg, Rejane
AU - Bassal, Mylène
AU - Lougheed, Jane
AU - Zelcer, Shayna
AU - Rosenberg, Herschel
AU - Hodgson, David
AU - Sender, Leonard
AU - Kantor, Paul
AU - Manlhiot, Cedric
AU - Ellis, James
AU - Mertens, Luc
AU - Nathan, Paul C.
AU - Mital, Seema
N1 - Funding Information:
We thank Sangsoon Woo from Axio Research for statistical data analysis related to RF model development, the SickKids Centre for Applied Genomics for exome sequencing, and the SickKids Imaging Facility for technical support.
PY - 2020/12
Y1 - 2020/12
N2 - 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)
AB - 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)
KW - anthracycline
KW - cancer survivorship
KW - cardiomyopathy
KW - echocardiography
KW - genomics
KW - machine learning
KW - risk prediction
UR - http://www.scopus.com/inward/record.url?scp=85097372256&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097372256&partnerID=8YFLogxK
U2 - 10.1016/j.jaccao.2020.11.004
DO - 10.1016/j.jaccao.2020.11.004
M3 - Article
AN - SCOPUS:85097372256
VL - 2
SP - 690
EP - 706
JO - JACC: CardioOncology
JF - JACC: CardioOncology
SN - 2666-0873
IS - 5
ER -