Cross-Domain Text Mining to Predict Adverse Events from Tyrosine Kinase Inhibitors for Chronic Myeloid Leukemia

• Type of Material: Article
• Authors: Nidhi Mehra, Emory University; Armon Varmeziar, Emory University; Xinyu Chen, Emory University; Olivia Kronick, Emory University; Rachel Fisher, Emory University; Vamsi Kota, Emory University; Cassie Mitchell, Emory University
• Language: English
• Date: 2022-10-01
• Publisher: MDPI
• Publication Version: Final Published Version
• Copyright Statement: © 2022 by the authors.
• License: Creative Commons Attribution 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.3390/cancers14194686
• Title of Journal or Parent Work: CANCERS
• Volume: 14
• Issue: 19
• Grant/Funding Information: This research was funded by Georgia Institute of Technology President’s Undergraduate 467 Research Award to N.M.; research funding from Incyte pharmaceuticals to V.K.; NIH grant R21CA232249, Children’s Hospital of Atlanta Aflac pilot grant, and National Science Foundation CAREER award 1944247 to C.S.M.
• Keywords: Oncology; chronic myeloid leukemia; side effect; BCR ABL; REMISSION; RESISTANCE; tyrosine kinase inhibitor; MALIGNANCIES; Science & Technology; NILOTINIB; adverse event; FRONTLINE; EFFICACY; IMATINIB THERAPY; Life Sciences & Biomedicine; heterogeneous information network; natural language processing; DASATINIB; machine learning; toxicity; CHRONIC MYELOGENOUS LEUKEMIA; CML PATIENTS
• Research Categories: Health Sciences, Pathology; Health Sciences, Oncology

Abstract

Tyrosine kinase inhibitors (TKIs) are prescribed for chronic myeloid leukemia (CML) and some other cancers. The objective was to predict and rank TKI-related adverse events (AEs), including under-reported or preclinical AEs, using novel text mining. First, k-means clustering of 2575 clinical CML TKI abstracts separated TKIs by significant (p < 0.05) AE type: gastrointestinal (bosutinib); edema (imatinib); pulmonary (dasatinib); diabetes (nilotinib); cardiovascular (ponatinib). Next, we propose a novel cross-domain text mining method utilizing a knowledge graph, link prediction, and hub node network analysis to predict new relationships. Cross-domain text mining of 30+ million articles via SemNet predicted and ranked known and novel TKI AEs. Three physiology-based tiers were formed using unsupervised rank aggregation feature importance. Tier 1 ranked in the top 1%: hematology (anemia, neutropenia, thrombocytopenia, hypocellular marrow); glucose (diabetes, insulin resistance, metabolic syndrome); iron (deficiency, overload, metabolism), cardiovascular (hypertension, heart failure, vascular dilation); thyroid (hypothyroidism, hyperthyroidism, parathyroid). Tier 2 ranked in the top 5%: inflammation (chronic inflammatory disorder, autoimmune, periodontitis); kidney (glomerulonephritis, glomerulopathy, toxic nephropathy). Tier 3 ranked in the top 10%: gastrointestinal (bowel regulation, hepatitis, pancreatitis); neuromuscular (autonomia, neuropathy, muscle pain); others (secondary cancers, vitamin deficiency, edema). Results suggest proactive TKI patient AE surveillance levels: regular surveillance for tier 1, infrequent surveillance for tier 2, and symptom-based surveillance for tier 3.