Artificial intelligence-aided clinical annotation of a large multi-cancer genomic dataset

• Published in: Nature communications Vol. 12; no. 1; pp. 7304 - 9
• Main Authors: Kehl, Kenneth L., Xu, Wenxin, Gusev, Alexander, Bakouny, Ziad, Choueiri, Toni K., Riaz, Irbaz Bin, Elmarakeby, Haitham, Van Allen, Eliezer M., Schrag, Deborah
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 15.12.2021; Nature Publishing Group; Nature Portfolio
• Subjects: 45; 692/4017; 692/4028/67; Annotations; Artificial Intelligence; Biomarkers; Cancer; Cancer research; Correlation; Databases, Genetic; Datasets; Electronic health records; Electronic medical records; Genomics; Humanities and Social Sciences; Humans; Immune checkpoint; Language; Medical research; Metastases; Molecular Sequence Annotation; multidisciplinary; Mutation; Natural Language Processing; Neoplasms - genetics; Oncology; Patients; Precision medicine; Science; Science (multidisciplinary); Solid tumors; Survival; Tumors
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-021-27358-6

To accelerate cancer research that correlates biomarkers with clinical endpoints, methods are needed to ascertain outcomes from electronic health records at scale. Here, we train deep natural language processing (NLP) models to extract outcomes for participants with any of 7 solid tumors in a precision oncology study. Outcomes are extracted from 305,151 imaging reports for 13,130 patients and 233,517 oncologist notes for 13,511 patients, including patients with 6 additional cancer types. NLP models recapitulate outcome annotation from these documents, including the presence of cancer, progression/worsening, response/improvement, and metastases, with excellent discrimination (AUROC > 0.90). Models generalize to cancers excluded from training and yield outcomes correlated with survival. Among patients receiving checkpoint inhibitors, we confirm that high tumor mutation burden is associated with superior progression-free survival ascertained using NLP. Here, we show that deep NLP can accelerate annotation of molecular cancer datasets with clinically meaningful endpoints to facilitate discovery. To accelerate cancer research that correlates biomarkers with clinical endpoints, methods are needed to ascertain outcomes from electronic health records at scale. Here, the authors train natural language processing to extract outcomes for participants in a precision oncology study.