Search

BackgroundPatients with cancer are at risk for poor COVID-19 outcomes. We aimed to identify cancer-related risk factors for poor COVID-19 outcomes.Patients and MethodsWe conducted a retrospective cohort study using the University of California Health COVID Research Data Set. This database includes prospectively-collected, electronic health data of patients who underwent testing for SARS-CoV-2 at seventeen California medical centers. We identified adult patients tested for SARS-CoV-2 between February 1, 2020 and December 31, 2020, and selected a cohort of patients with cancer using diagnostic codes. We obtained demographic, comorbidity, laboratory, cancer type, and antineoplastic therapy data. The primary outcome was hospitalization within 30 days after first positive SARS-CoV-2 test. Secondary outcomes were SARS-CoV-2 positivity and composite endpoint for severe COVID-19 (intensive care, mechanical ventilation, or death within 30 days after first positive test). We used multivariable logistic regression to identify cancer-related factors associated with outcomes.ResultsWe identified 409,462 patients undergoing SARS-CoV-2 testing. Of 49,918 patients with cancer, 1,781 (3.6%) tested positive. Patients with cancer were less likely to test positive (OR 0.69, 95%CI 0.66-0.73, PP=0.007); venetoclax (OR 3.63, 95%CI 1.02-12.92, P=0.046); methotrexate (OR 3.65, 95%CI 1.17-11.37, P=0.026); Asian race (OR 1.92, 95%CI 1.23-2.98, P=0.004); and Hispanic/Latino ethnicity (OR 1.96, 95%CI 1.41-2.73, PConclusionsIn this large, diverse cohort of Californians, cancer was not a risk factor for SARS-CoV-2 positivity. Patients with BCR/ABL-negative myeloproliferative neoplasm and patients receiving methotrexate or venetoclax may be at an increased risk of hospitalization following SARS-CoV-2 infection. Further mechanistic and comparative studies are needed to explain and confirm our findings.

The application of data science in cancer research has been boosted by major advances in three primary areas: (1) Data: diversity, amount, and availability of biomedical data; (2) Advances in Artificial Intelligence (AI) and Machine Learning (ML) algorithms that enable learning from complex, large-scale data; and (3) Advances in computer architectures allowing unprecedented acceleration of simulation and machine learning algorithms. These advances help build in silico ML models that can provide transformative insights from data including: molecular dynamics simulations, next-generation sequencing, omics, imaging, and unstructured clinical text documents. Unique challenges persist, however, in building ML models related to cancer, including: (1) access, sharing, labeling, and integration of multimodal and multi-institutional data across different cancer types; (2) developing AI models for cancer research capable of scaling on next generation high performance computers; and (3) assessing robustness and reliability in the AI models. In this paper, we review the National Cancer Institute (NCI) -Department of Energy (DOE) collaboration, Joint Design of Advanced Computing Solutions for Cancer (JDACS4C), a multi-institution collaborative effort focused on advancing computing and data technologies to accelerate cancer research on three levels: molecular, cellular, and population. This collaboration integrates various types of generated data, pre-exascale compute resources, and advances in ML models to increase understanding of basic cancer biology, identify promising new treatment options, predict outcomes, and eventually prescribe specialized treatments for patients with cancer.