Oops, you're using an old version of your browser so some of the features on this page may not be displaying properly.

MINIMAL Requirements: Google Chrome 24+Mozilla Firefox 20+Internet Explorer 11Opera 15–18Apple Safari 7SeaMonkey 2.15-2.23

Poster Display session 3

5271 - A Pilot Study to Implement an Artificial Intelligence (AI) System for Gastrointestinal Cancer Clinical Trial Matching

Date

30 Sep 2019

Session

Poster Display session 3

Topics

Translational Research

Tumour Site

Presenters

Zhaohui Jin

Citation

Annals of Oncology (2019) 30 (suppl_5): v574-v584. 10.1093/annonc/mdz257

Authors

Z. Jin1, T. Haddad1, J. Hubbard1, M.L. Hartgers1, K. Leventakos1, K. Cornwell2, K. King2, B.A. Franke2, K. Pomerleau3, V. Bibeau4, S. Coverdill5, M. Rammage5, J. Helgeson3, A. Mahipal1

Author affiliations

  • 1 Medical Oncology, Mayo Clinic, 55905 - Rochester/US
  • 2 Medical Oncology Clinical Research, Mayo Clinic, 55905 - Rochester/US
  • 3 Research Administrative Services, Mayo Clinic, 55905 - Rochester/US
  • 4 Management Engineering & Internal Consulting, Mayo Clinic, 32224 - Jacksonville/US
  • 5 Ibm Watson Health, IBM, 02142 - Cambridge/US

Resources

Login to get immediate access to this content.

If you do not have an ESMO account, please create one for free.

Abstract 5271

Background

Clinical trials improve our knowledge of diseases and treatments while providing patients access to investigational agents. However, approximately 3% of newly diagnosed cancer patients are enrolled in clinical trials in the United States. Identifying an appropriate trial for a patient is time-consuming and cumbersome in the busy clinical practice. The Watson for Clinical Trial Matching (CTM) cognitive system uses AI to derive patient and cancer-related attributes from structured and unstructured text found in the electronic health record. These attributes are matched to complex eligibility criteria in clinical trial protocols.

Methods

In April 2019, a pilot study was launched to test the feasibility of implementing CTM in Gastrointestinal (GI) oncology at Mayo Clinic in Rochester, MN. Two clinical research coordinators (CRCs) screened patients for potential clinical trials prior to their clinic visits using both CTM and the traditional manual screening method. To avoid bias, each CRC screened a separate set of patients by both methods alternating which methodology was used first. The clinical trial match results were blinded to both CRCs. For each method, time to complete the screen and number of potential clinical trial matches were recorded.

Results

A total of 35 GI cancer patients with new diagnosis, recent resection or restaging scans were analyzed. Patients were evaluated against 50 GI-specific drug therapy and multi-disease phase I clinical trials. Clinical trial matching using CTM took an average of 10.1 minutes (Range: 4 to 20 min) per patient compared to an average of 30.5 minutes (Range: 5 to 75 min) per patient (p < 0.0001) using the manual method. CTM identified an average of 7.66 clinical trials (Range: 0-16) while the manual screening method identified an average of 1.97 clinical trials (Range: 0 to 6) per patient (p < 0.0001).

Conclusions

Implementation of Watson for CTM system with a CRC team may enable high volume patient screening for a large number of clinical trials in an efficient manner and promote awareness of clinical trial opportunities within the GI oncology practice. Further analysis to evaluate CTM accuracy and impact on enrollment is warranted and currently underway.

Clinical trial identification

Editorial acknowledgement

Legal entity responsible for the study

The authors.

Funding

Mayo Clinic.

Disclosure

T. Haddad: Advisory / Consultancy: TerSera Therapeautics; Research grant / Funding (self): Takeda. S. Coverdill: Full / Part-time employment: IBM Watson Health; Shareholder / Stockholder / Stock options: IBM. M. Rammage: Full / Part-time employment: IBM Watson Health; Licensing / Royalties: IBM. All other authors have declared no conflicts of interest.

This site uses cookies. Some of these cookies are essential, while others help us improve your experience by providing insights into how the site is being used.

For more detailed information on the cookies we use, please check our Privacy Policy.

Customise settings
  • Necessary cookies enable core functionality. The website cannot function properly without these cookies, and you can only disable them by changing your browser preferences.