Jay G Ronquillo1,2, William T Lester3,4. 1. Center for Biomedical Informatics and Information Technology, National Cancer Institute, Rockville, MD. 2. Office of Data Science Strategy, National Institutes of Health, Bethesda, MD. 3. Laboratory of Computer Science, Massachusetts General Hospital, Boston, MA. 4. Harvard Medical School, Boston, MA.
Abstract
PURPOSE: Cloud computing has led to dramatic growth in the volume, variety, and velocity of cancer data. However, cloud platforms and services present new challenges for cancer research, particularly in understanding the practical tradeoffs between cloud performance, cost, and complexity. The goal of this study was to describe the practical challenges when using a cloud-based service to improve the cancer clinical trial matching process. METHODS: We collected information for all interventional cancer clinical trials from ClinicalTrials.gov and used the Google Cloud Healthcare Natural Language Application Programming Interface (API) to analyze clinical trial Title and Eligibility Criteria text. An informatics pipeline leveraging interoperability standards summarized the distribution of cancer clinical trials, genes, laboratory tests, and medications extracted from cloud-based entity analysis. RESULTS: There were a total of 38,851 cancer-related clinical trials found in this study, with the distribution of cancer categories extracted from Title text significantly different than in ClinicalTrials.gov (P < .001). Cloud-based entity analysis of clinical trial criteria identified a total of 949 genes, 1,782 laboratory tests, 2,086 medications, and 4,902 National Cancer Institute Thesaurus terms, with estimated detection accuracies ranging from 12.8% to 89.9%. A total of 77,702 API calls processed an estimated 167,179 text records, which took a total of 1,979 processing-minutes (33.0 processing-hours), or approximately 1.5 seconds per API call. CONCLUSION: Current general-purpose cloud health care tools-like the Google service in this study-should not be used for automated clinical trial matching unless they can perform effective extraction and classification of the clinical, genetic, and medication concepts central to precision oncology research. A strong understanding of the practical aspects of cloud computing will help researchers effectively navigate the vast data ecosystems in cancer research.
PURPOSE: Cloud computing has led to dramatic growth in the volume, variety, and velocity of cancer data. However, cloud platforms and services present new challenges for cancer research, particularly in understanding the practical tradeoffs between cloud performance, cost, and complexity. The goal of this study was to describe the practical challenges when using a cloud-based service to improve the cancer clinical trial matching process. METHODS: We collected information for all interventional cancer clinical trials from ClinicalTrials.gov and used the Google Cloud Healthcare Natural Language Application Programming Interface (API) to analyze clinical trial Title and Eligibility Criteria text. An informatics pipeline leveraging interoperability standards summarized the distribution of cancer clinical trials, genes, laboratory tests, and medications extracted from cloud-based entity analysis. RESULTS: There were a total of 38,851 cancer-related clinical trials found in this study, with the distribution of cancer categories extracted from Title text significantly different than in ClinicalTrials.gov (P < .001). Cloud-based entity analysis of clinical trial criteria identified a total of 949 genes, 1,782 laboratory tests, 2,086 medications, and 4,902 National Cancer Institute Thesaurus terms, with estimated detection accuracies ranging from 12.8% to 89.9%. A total of 77,702 API calls processed an estimated 167,179 text records, which took a total of 1,979 processing-minutes (33.0 processing-hours), or approximately 1.5 seconds per API call. CONCLUSION: Current general-purpose cloud health care tools-like the Google service in this study-should not be used for automated clinical trial matching unless they can perform effective extraction and classification of the clinical, genetic, and medication concepts central to precision oncology research. A strong understanding of the practical aspects of cloud computing will help researchers effectively navigate the vast data ecosystems in cancer research.
Authors: Samson W Tu; Mor Peleg; Simona Carini; Michael Bobak; Jessica Ross; Daniel Rubin; Ida Sim Journal: J Biomed Inform Date: 2010-09-17 Impact factor: 6.317
Authors: Danny T Y Wu; David A Hanauer; Qiaozhu Mei; Patricia M Clark; Lawrence C An; Joshua Proulx; Qing T Zeng; V G Vinod Vydiswaran; Kevyn Collins-Thompson; Kai Zheng Journal: J Am Med Inform Assoc Date: 2015-08-11 Impact factor: 4.497
Authors: Yizhao Ni; Jordan Wright; John Perentesis; Todd Lingren; Louise Deleger; Megan Kaiser; Isaac Kohane; Imre Solti Journal: BMC Med Inform Decis Mak Date: 2015-04-14 Impact factor: 2.796
Authors: Hilary Pinnock; Melanie Barwick; Christopher R Carpenter; Sandra Eldridge; Gonzalo Grandes; Chris J Griffiths; Jo Rycroft-Malone; Paul Meissner; Elizabeth Murray; Anita Patel; Aziz Sheikh; Stephanie J C Taylor Journal: BMJ Date: 2017-03-06