Abstract 501P
Background
Patients with cancer are at higher risk of dying of COVID-19. Known risk factors for 30-day all-cause mortality (ACM-30) in patients with cancer are older age, sex, smoking status, performance status, obesity, and co-morbidities. We hypothesized that common clinical and laboratory parameters would be predictive of a higher risk of 30-day ACM, and that a machine learning approach (random forest) could produce high accuracy.
Methods
In this multi-institutional COVID-19 and Cancer Consortium (CCC19) registry study, 12,661 patients enrolled between March 17, 2020 and December 31, 2021 were utilized to develop and validate a model of ACM-30. ACM-30 was defined as death from any cause within 30 days of COVID-19 diagnosis. Pre-specified variables were: age, sex, race, smoking status, ECOG performance status (PS), timing of cancer treatment relative to COVID19 diagnosis, severity of COVID19, type of cancer, and other laboratory measurements. Missing variables were imputed using random forest proximity. Random forest was utilized to model ACM-30. The area under the curve (AUC) was computed as a measure of predictive accuracy with out-of-bag prediction. One hundred bootstrapped samples were used to obtain the standard error of the AUC.
Results
The median age at COVID-19 diagnosis was 65 years, 53% were female, 18% were Hispanic, and 16.7% were Black. Over half were never smokers and the median body mass index was 28.2. Random forest with under sampling selected 20 factors prognostic of ACM-30. The AUC was 88.9 (95% CI 88.5-89.2). Highly informative parameters included: COVID-19 severity at presentation, cancer status, age, troponin level, ECOG PS and body mass index.
Conclusions
This prognostic model based on readily available clinical and laboratory values can be used to estimate individual survival probability within 30-days for COVID-19. In addition, this model can be used to select or classify patients with cancer and COVID-19 into risk groups based on validated cut points, for treatment selection, prophylaxis prioritization, and/or enrollment in clinical trials. Future work includes external validation using other large datasets of patients with COVID-19 and cancer.
Clinical trial identification
NCT04354701.
Editorial acknowledgement
Legal entity responsible for the study
Vanderbilt University Medical Center.
Funding
National Cancer Institute grant number P30 CA068485 to Vanderbilt University Medical Center; Vanderbilt Institute for Clinical and Translational Research grant support (UL1 TR000445 from NCATS / NIH) and the Duke Clinical Research Institute.
Disclosure
S. Halabi: Financial Interests, Personal, Other, DMC: Sanofi, Aveo Oncology; Non-Financial Interests, Personal, Other, Past President: Society for Clinical Trials; Financial Interests, Institutional, Other, Statistician on ASCO TAPUR Trial: ASCO TAPUR; Financial Interests, Institutional, Funding, For analysis: EPIC SCIENCES. C. Hwang: Financial Interests, Personal, Invited Speaker: OncLive; Financial Interests, Personal, Other, Consulting Fees: TEMPUS, Genzyme, EMD Sorono; Financial Interests, Institutional, Other, Clinical Trials: Merck, Bayer, Genentech; Financial Interests, Institutional, Invited Speaker, Clinical Trials: AstraZeneca, Bausch Health; Financial Interests, Personal and Institutional, Leadership Role: Wayne County Medical SocietyFoundation Board, Wayne County Medical Society of Southeast Michigan Board. C. Labaki: Financial Interests, Institutional, Research Grant: Genentech/imCORE. E. Ruiz: Financial Interests, Personal, Advisory Board: Roche, Amgen, BMS, Bayer; Financial Interests, Personal, Invited Speaker: Roche, Merck. C. Rangel-Escareño: Non-Financial Interests, Principal Investigator, I lead a team of young scientist in using and developing tools for complex data analysis in the field of genomic medicine: National Institute of Genomic Medicine; Non-Financial Interests, Other, Teaching courses at undergraduate and graduate level in the field of computational biology, bioinformatics and statistics: Tecnologico de Monterrey. E.A. Griffiths: Financial Interests, Personal and Institutional, Research Grant, Honoraria: Alexion Pharmaceutical, Astex, Genentech, AbbVie, Celgene/BMS; Financial Interests, Personal, Advisory Board, Honoraria: Novartis; Financial Interests, Personal, Advisory Board: Taiho Oncology, Takeda Oncology, CTI Biopharma, Apellis; Financial Interests, Institutional, Research Grant: Celldex Therapeutics, Blueprint Medicines; Non-Financial Interests, Personal, Member: Physician Educational Resource; Non-Financial Interests, Personal, Invited Speaker: ASH speaker, MD Education speaker. M. Accordino: Financial Interests, Personal, Other, Will serve as a medical consultant for a Disney TV show in the upcoming future: Disney TV. C. Friese: Financial Interests, Personal and Institutional, Principal Investigator, Unrelated to abstract: Merck Foundation; Financial Interests, Personal and Institutional, Project Lead, Unrelated to this abstract: NCCN/Pfizer; Financial Interests, Personal, Other, Member: United States National Cancer Advisory Board; Financial Interests, Personal, Other, Compensated but unrelated to abstract: oard of Governors. P. Yu: Financial Interests, Personal, Stocks/Shares: Danaher, Contrafect; Financial Interests, Personal, Leadership Role: ASCO PAC. S. Mishra: Financial Interests, Personal, Invited Speaker, Writing on COVID-19 related Popular Science: National Geographic; Financial Interests, Personal, Invited Speaker, Writing on patient advocacy and popular science: SurvivorNet; Financial Interests, Institutional, Full or part-time Employment: Vanderbilt University Medical Center. J. Warner: Financial Interests, Personal, Advisory Role: IBM Watson Health, Flatiron Health, Roche; Financial Interests, Personal, Other, Consulting (not for profit): Westat; Financial Interests, Personal, Other, Consulting Fees: Melac Tech; Financial Interests, Personal, Other, Partial ownership: HemOnc.org LLC; Financial Interests, Personal, Other, Member: ASCO Evidence Based Medicine Committee. All other authors have declared no conflicts of interest.