A software application for mining and presenting relevant cancer clinical trials per cancer Mutation

Lisa M. Gandy, Jordan Gumm, Amanda L. Blackford, Elana Fertig, Luis A. Diaz

Research output: Contribution to journalArticle

Abstract

ClinicalTrials.org is a popular portal which physicians use to find clinical trials for their patients. However, the current setup of ClinicalTrials.org makes it difficult for oncologists to locate clinical trials for patients based on mutational status. We present CTMine, a system that mines ClinicalTrials.org for clinical trials per cancer mutation and displays the trials in a user-friendly Web application. The system currently lists clinical trials for 6 common genes (ALK, BRAF, ERBB2, EGFR, KIT, and KRAS). The current machine learning model used to identify relevant clinical trials focusing on the above gene mutations had an average 88% precision/recall. As part of this analysis, we compared human versus machine and found that oncologists were unable to reach a consensus on whether a clinical trial mined by CTMine was “relevant” per gene mutation, a finding that highlights an important topic which deems future exploration.

Original languageEnglish (US)
JournalCancer Informatics
Volume16
DOIs
StatePublished - Jan 1 2017

Fingerprint

Software
Clinical Trials
Mutation
Neoplasms
Genes
Physicians
Oncologists

Keywords

  • Clinicaltrials.gov
  • Gene-specific therapies
  • Information retrieval
  • Machine learning
  • Natural language processing

ASJC Scopus subject areas

  • Oncology
  • Cancer Research

Cite this

A software application for mining and presenting relevant cancer clinical trials per cancer Mutation. / Gandy, Lisa M.; Gumm, Jordan; Blackford, Amanda L.; Fertig, Elana; Diaz, Luis A.

In: Cancer Informatics, Vol. 16, 01.01.2017.

Research output: Contribution to journalArticle

Gandy, Lisa M. ; Gumm, Jordan ; Blackford, Amanda L. ; Fertig, Elana ; Diaz, Luis A. / A software application for mining and presenting relevant cancer clinical trials per cancer Mutation. In: Cancer Informatics. 2017 ; Vol. 16.
@article{3775ea5110444717b4b2c48c4db86700,
title = "A software application for mining and presenting relevant cancer clinical trials per cancer Mutation",
abstract = "ClinicalTrials.org is a popular portal which physicians use to find clinical trials for their patients. However, the current setup of ClinicalTrials.org makes it difficult for oncologists to locate clinical trials for patients based on mutational status. We present CTMine, a system that mines ClinicalTrials.org for clinical trials per cancer mutation and displays the trials in a user-friendly Web application. The system currently lists clinical trials for 6 common genes (ALK, BRAF, ERBB2, EGFR, KIT, and KRAS). The current machine learning model used to identify relevant clinical trials focusing on the above gene mutations had an average 88{\%} precision/recall. As part of this analysis, we compared human versus machine and found that oncologists were unable to reach a consensus on whether a clinical trial mined by CTMine was “relevant” per gene mutation, a finding that highlights an important topic which deems future exploration.",
keywords = "Clinicaltrials.gov, Gene-specific therapies, Information retrieval, Machine learning, Natural language processing",
author = "Gandy, {Lisa M.} and Jordan Gumm and Blackford, {Amanda L.} and Elana Fertig and Diaz, {Luis A.}",
year = "2017",
month = "1",
day = "1",
doi = "10.1177/1176935117711940",
language = "English (US)",
volume = "16",
journal = "Cancer Informatics",
issn = "1176-9351",
publisher = "Libertas Academica Ltd.",

}

TY - JOUR

T1 - A software application for mining and presenting relevant cancer clinical trials per cancer Mutation

AU - Gandy, Lisa M.

AU - Gumm, Jordan

AU - Blackford, Amanda L.

AU - Fertig, Elana

AU - Diaz, Luis A.

PY - 2017/1/1

Y1 - 2017/1/1

N2 - ClinicalTrials.org is a popular portal which physicians use to find clinical trials for their patients. However, the current setup of ClinicalTrials.org makes it difficult for oncologists to locate clinical trials for patients based on mutational status. We present CTMine, a system that mines ClinicalTrials.org for clinical trials per cancer mutation and displays the trials in a user-friendly Web application. The system currently lists clinical trials for 6 common genes (ALK, BRAF, ERBB2, EGFR, KIT, and KRAS). The current machine learning model used to identify relevant clinical trials focusing on the above gene mutations had an average 88% precision/recall. As part of this analysis, we compared human versus machine and found that oncologists were unable to reach a consensus on whether a clinical trial mined by CTMine was “relevant” per gene mutation, a finding that highlights an important topic which deems future exploration.

AB - ClinicalTrials.org is a popular portal which physicians use to find clinical trials for their patients. However, the current setup of ClinicalTrials.org makes it difficult for oncologists to locate clinical trials for patients based on mutational status. We present CTMine, a system that mines ClinicalTrials.org for clinical trials per cancer mutation and displays the trials in a user-friendly Web application. The system currently lists clinical trials for 6 common genes (ALK, BRAF, ERBB2, EGFR, KIT, and KRAS). The current machine learning model used to identify relevant clinical trials focusing on the above gene mutations had an average 88% precision/recall. As part of this analysis, we compared human versus machine and found that oncologists were unable to reach a consensus on whether a clinical trial mined by CTMine was “relevant” per gene mutation, a finding that highlights an important topic which deems future exploration.

KW - Clinicaltrials.gov

KW - Gene-specific therapies

KW - Information retrieval

KW - Machine learning

KW - Natural language processing

UR - http://www.scopus.com/inward/record.url?scp=85045004125&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045004125&partnerID=8YFLogxK

U2 - 10.1177/1176935117711940

DO - 10.1177/1176935117711940

M3 - Article

VL - 16

JO - Cancer Informatics

JF - Cancer Informatics

SN - 1176-9351

ER -