Machine Learning-Based Risk Assessment for Cancer Therapy-Related Cardiac Dysfunction in 4300 Longitudinal Oncology Patients.
anthracycline therapy
cancer therapy–related cardiac dysfunction
cardiotoxicity
cardio‐oncology
echocardiography
machine learning
Journal
Journal of the American Heart Association
ISSN: 2047-9980
Titre abrégé: J Am Heart Assoc
Pays: England
ID NLM: 101580524
Informations de publication
Date de publication:
12 2020
12 2020
Historique:
pubmed:
27
11
2020
medline:
27
3
2021
entrez:
26
11
2020
Statut:
ppublish
Résumé
Background The growing awareness of cardiovascular toxicity from cancer therapies has led to the emerging field of cardio-oncology, which centers on preventing, detecting, and treating patients with cardiac dysfunction before, during, or after cancer treatment. Early detection and prevention of cancer therapy-related cardiac dysfunction (CTRCD) play important roles in precision cardio-oncology. Methods and Results This retrospective study included 4309 cancer patients between 1997 and 2018 whose laboratory tests and cardiovascular echocardiographic variables were collected from the Cleveland Clinic institutional electronic medical record database (Epic Systems). Among these patients, 1560 (36%) were diagnosed with at least 1 type of CTRCD, and 838 (19%) developed CTRCD after cancer therapy (de novo). We posited that machine learning algorithms can be implemented to predict CTRCDs in cancer patients according to clinically relevant variables. Classification models were trained and evaluated for 6 types of cardiovascular outcomes, including coronary artery disease (area under the receiver operating characteristic curve [AUROC], 0.821; 95% CI, 0.815-0.826), atrial fibrillation (AUROC, 0.787; 95% CI, 0.782-0.792), heart failure (AUROC, 0.882; 95% CI, 0.878-0.887), stroke (AUROC, 0.660; 95% CI, 0.650-0.670), myocardial infarction (AUROC, 0.807; 95% CI, 0.799-0.816), and de novo CTRCD (AUROC, 0.802; 95% CI, 0.797-0.807). Model generalizability was further confirmed using time-split data. Model inspection revealed several clinically relevant variables significantly associated with CTRCDs, including age, hypertension, glucose levels, left ventricular ejection fraction, creatinine, and aspartate aminotransferase levels. Conclusions This study suggests that machine learning approaches offer powerful tools for cardiac risk stratification in oncology patients by utilizing large-scale, longitudinal patient data from healthcare systems.
Identifiants
pubmed: 33241727
doi: 10.1161/JAHA.120.019628
pmc: PMC7763760
doi:
Substances chimiques
Antineoplastic Agents
0
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Langues
eng
Sous-ensembles de citation
IM
Pagination
e019628Subventions
Organisme : NHLBI NIH HHS
ID : K99 HL138272
Pays : United States
Organisme : NHLBI NIH HHS
ID : R00 HL138272
Pays : United States
Références
J Chem Inf Model. 2018 May 29;58(5):943-956
pubmed: 29712429
JAMA Netw Open. 2019 Jul 3;2(7):e197314
pubmed: 31314120
Cancer. 2020 Jan 1;126(1):181-188
pubmed: 31454422
CA Cancer J Clin. 2019 Sep;69(5):363-385
pubmed: 31184787
Clin Chem. 1992 Oct;38(10):1933-53
pubmed: 1394976
Pharmacol Res. 2018 Mar;129:95-99
pubmed: 29127059
Circulation. 2018 Oct 16;138(16):1623-1635
pubmed: 30354459
Fundam Clin Pharmacol. 2010 Dec;24(6):675-85
pubmed: 20199585
Circ Cardiovasc Imaging. 2017 Oct;10(10):
pubmed: 28956772
Prog Cardiovasc Dis. 2020 May - Jun;63(3):367-376
pubmed: 32201286
BMJ. 2016 Aug 09;354:i4098
pubmed: 27511067
JAMA. 1991 Sep 25;266(12):1672-7
pubmed: 1886191
Nat Rev Clin Oncol. 2015 Dec;12(12):718-31
pubmed: 26462128
J Chemother. 2013 Dec;25(6):369-75
pubmed: 24392943
N Engl J Med. 2019 Apr 4;380(14):1347-1358
pubmed: 30943338
Med Clin North Am. 2012 Jan;96(1):87-91
pubmed: 22391253
Cancer. 1967 Mar;20(3):333-53
pubmed: 4290058
Circ J. 2012;76(3):563-71
pubmed: 22293452
Natl Vital Stat Rep. 2019 May;68(5):1-9
pubmed: 32501204
JAMA. 1993 Oct 27;270(16):1949-55
pubmed: 8411552
Heart. 2010 Nov;96(21):1744-9
pubmed: 20956490
Medicine (Baltimore). 2015 Nov;94(47):e2160
pubmed: 26632749
Diab Vasc Dis Res. 2008 Nov;5(4):269-75
pubmed: 18958836
J Clin Oncol. 2017 Mar 10;35(8):870-877
pubmed: 27893331
J Am Heart Assoc. 2014 Apr 22;3(2):e000665
pubmed: 24755151
Ann Intern Med. 1976 Oct;85(4):447-52
pubmed: 970770
N Engl J Med. 1995 Jun 29;332(26):1758-66
pubmed: 7760894
CA Cancer J Clin. 2019 Jan;69(1):7-34
pubmed: 30620402
JAMA Netw Open. 2018 Aug 3;1(4):e181079
pubmed: 30646102
Circulation. 1996 Feb 1;93(3):450-6
pubmed: 8565161
Am J Med. 1984 Feb 27;76(2A):4-12
pubmed: 6702862
Nat Methods. 2020 Mar;17(3):261-272
pubmed: 32015543
J Thorac Dis. 2017 May;9(5):E503-E506
pubmed: 28616322
JACC CardioOncol. 2019 Dec;1(2):208-217
pubmed: 32905430
Int J Cardiol. 2016 Apr 15;209:284-90
pubmed: 26913370
NPJ Digit Med. 2018 Aug 28;1:40
pubmed: 31304321
Circ Arrhythm Electrophysiol. 2019 Jul;12(7):e007316
pubmed: 31216884
J Am Heart Assoc. 2020 Dec;9(23):e019628
pubmed: 33241727
J Card Fail. 2003 Feb;9(1):13-25
pubmed: 12612868
Eur Heart J. 2019 Dec 21;40(48):3913-3920
pubmed: 31318428
J Chem Inf Model. 2019 Mar 25;59(3):1073-1084
pubmed: 30715873