TY - JOUR
T1 - Causal Phenotyping for Susceptibility to Cardiotoxicity from Antineoplastic Breast Cancer Medications
AU - Sun, Deyu
AU - Simon, Gyorgy J
AU - Skube, Steven
AU - Blaes, Anne H
AU - Melton-Meaux, Genevieve B
AU - Zhang, Rui
N1 - Copyright:
This record is sourced from MEDLINE/PubMed, a database of the U.S. National Library of Medicine
PY - 2017
Y1 - 2017
N2 - Cardiotoxicity is a relatively common and particularly important adverse event caused by chemotherapy for breast cancer patients. Typical associative phenotypes, such as risk factors associated with diabetes, can often be detected solely based on the data elements existing in electronic health records; however, causal phenotypes, such as risk factors causing cardiotoxicity, require establishing causation between chemotherapy and determining new heart disease, and cannot be directly observedfrom EHR. We propose three phenotyping algorithms to assess breast cancer patients' susceptibility to cardiotoxicity caused by five first-line antineoplastic drugs: (1) causal phenotype model to predict the patients' risk of cardiotoxicity as the difference between the heart disease risks with exposure and nonexposure to the drugs; (2) regular predictive model; (3) combined predictive model of the above two models. Concordances for three methods were 0.60, 0.62, and 0.68. When considering all exposed patients, concordances were 0.66, 0.58 and 0.65 at 280 days after treatment. The study demonstrates the potential utility of causal phenotyping.
AB - Cardiotoxicity is a relatively common and particularly important adverse event caused by chemotherapy for breast cancer patients. Typical associative phenotypes, such as risk factors associated with diabetes, can often be detected solely based on the data elements existing in electronic health records; however, causal phenotypes, such as risk factors causing cardiotoxicity, require establishing causation between chemotherapy and determining new heart disease, and cannot be directly observedfrom EHR. We propose three phenotyping algorithms to assess breast cancer patients' susceptibility to cardiotoxicity caused by five first-line antineoplastic drugs: (1) causal phenotype model to predict the patients' risk of cardiotoxicity as the difference between the heart disease risks with exposure and nonexposure to the drugs; (2) regular predictive model; (3) combined predictive model of the above two models. Concordances for three methods were 0.60, 0.62, and 0.68. When considering all exposed patients, concordances were 0.66, 0.58 and 0.65 at 280 days after treatment. The study demonstrates the potential utility of causal phenotyping.
UR - http://www.scopus.com/inward/record.url?scp=85054319463&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85054319463&partnerID=8YFLogxK
M3 - Article
C2 - 29854236
AN - SCOPUS:85054319463
SN - 1559-4076
VL - 2017
SP - 1655
EP - 1664
JO - AMIA ... Annual Symposium proceedings. AMIA Symposium
JF - AMIA ... Annual Symposium proceedings. AMIA Symposium
ER -