1
|
Kehl KL, Mazor T, Trukhanov P, Lindsay J, Galvin MR, Farhat KS, McClure E, Giordano A, Gandhi L, Schrag D, Hassett MJ, Cerami E. Identifying Oncology Clinical Trial Candidates Using Artificial Intelligence Predictions of Treatment Change: A Pilot Implementation Study. JCO Precis Oncol 2024; 8:e2300507. [PMID: 38513166 DOI: 10.1200/po.23.00507] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/09/2023] [Revised: 11/25/2023] [Accepted: 01/23/2024] [Indexed: 03/23/2024] Open
Abstract
PURPOSE Precision oncology clinical trials often struggle to accrue, partly because it is difficult to find potentially eligible patients at moments when they need new treatment. We piloted deployment of artificial intelligence tools to identify such patients at a large academic cancer center. PATIENTS AND METHODS Neural networks that process radiology reports to identify patients likely to start new systemic therapy were applied prospectively for patients with solid tumors that had undergone next-generation sequencing at our center. Model output was linked to the MatchMiner tool, which matches patients to trials using tumor genomics. Reports listing genomically matched patients, sorted by probability of treatment change, were provided weekly to an oncology nurse navigator (ONN) coordinating recruitment to nine early-phase trials. The ONN contacted treating oncologists when patients likely to change treatment appeared potentially trial-eligible. RESULTS Within weekly reports to the ONN, 60,199 patient-trial matches were generated for 2,150 patients on the basis of genomics alone. Of these, 3,168 patient-trial matches (5%) corresponding to 525 patients were flagged for ONN review by our model, representing a 95% reduction in review compared with manual review of all patient-trial matches weekly. After ONN review for potential eligibility, treating oncologists for 74 patients were contacted. Common reasons for not contacting treating oncologists included cases where patients had already decided to continue current treatment (21%); the trial had no slots (14%); or the patient was ineligible on ONN review (12%). Of 74 patients whose oncologists were contacted, 10 (14%) had a consult regarding a trial and five (7%) enrolled. CONCLUSION This approach facilitated identification of potential patients for clinical trials in real time, but further work to improve accrual must address the many other barriers to trial enrollment in precision oncology research.
Collapse
Affiliation(s)
| | - Tali Mazor
- Dana-Farber Cancer Institute, Boston, MA
| | | | | | | | | | | | | | | | | | | | | |
Collapse
|
2
|
Keller RB, Mazor T, Sholl L, Aguirre AJ, Singh H, Sethi N, Bass A, Nagaraja AK, Brais LK, Hill E, Hennessey C, Cusick M, Del Vecchio Fitz C, Zwiesler Z, Siegel E, Ovalle A, Trukhanov P, Hansel J, Shapiro GI, Abrams TA, Biller LH, Chan JA, Cleary JM, Corsello SM, Enzinger AC, Enzinger PC, Mayer RJ, McCleary NJ, Meyerhardt JA, Ng K, Patel AK, Perez KJ, Rahma OE, Rubinson DA, Wisch JS, Yurgelun MB, Hassett MJ, MacConaill L, Schrag D, Cerami E, Wolpin BM, Nowak JA, Giannakis M. Programmatic Precision Oncology Decision Support for Patients With Gastrointestinal Cancer. JCO Precis Oncol 2023; 7:e2200342. [PMID: 36634297 PMCID: PMC9929103 DOI: 10.1200/po.22.00342] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/13/2023] Open
Abstract
PURPOSE With the growing number of available targeted therapeutics and molecular biomarkers, the optimal care of patients with cancer now depends on a comprehensive understanding of the rapidly evolving landscape of precision oncology, which can be challenging for oncologists to navigate alone. METHODS We developed and implemented a precision oncology decision support system, GI TARGET, (Gastrointestinal Treatment Assistance Regarding Genomic Evaluation of Tumors) within the Gastrointestinal Cancer Center at the Dana-Farber Cancer Institute. With a multidisciplinary team, we systematically reviewed tumor molecular profiling for GI tumors and provided molecularly informed clinical recommendations, which included identifying appropriate clinical trials aided by the computational matching platform MatchMiner, suggesting targeted therapy options on or off the US Food and Drug Administration-approved label, and consideration of additional or orthogonal molecular testing. RESULTS We reviewed genomic data and provided clinical recommendations for 506 patients with GI cancer who underwent tumor molecular profiling between January and June 2019 and determined follow-up using the electronic health record. Summary reports were provided to 19 medical oncologists for patients with colorectal (n = 198, 39%), pancreatic (n = 124, 24%), esophagogastric (n = 67, 13%), biliary (n = 40, 8%), and other GI cancers. We recommended ≥ 1 precision medicine clinical trial for 80% (406 of 506) of patients, leading to 24 enrollments. We recommended on-label and off-label targeted therapies for 6% (28 of 506) and 25% (125 of 506) of patients, respectively. Recommendations for additional or orthogonal testing were made for 42% (211 of 506) of patients. CONCLUSION The integration of precision medicine in routine cancer care through a dedicated multidisciplinary molecular tumor board is scalable and sustainable, and implementation of precision oncology recommendations has clinical utility for patients with cancer.
Collapse
Affiliation(s)
- Rachel B. Keller
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Tali Mazor
- Department of Data Science, Dana-Farber Cancer Institute, Boston, MA
| | - Lynette Sholl
- Center for Advanced Molecular Diagnostics, Brigham & Women's Hospital & Harvard Medical School, Boston, MA
| | - Andrew J. Aguirre
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA,Broad Institute of Harvard and MIT, Cambridge, MA
| | - Harshabad Singh
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Nilay Sethi
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Adam Bass
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Ankur K. Nagaraja
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Lauren K. Brais
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Emma Hill
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Connor Hennessey
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Margaret Cusick
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | | | - Zachary Zwiesler
- Department of Data Science, Dana-Farber Cancer Institute, Boston, MA
| | - Ethan Siegel
- Department of Data Science, Dana-Farber Cancer Institute, Boston, MA
| | - Andrea Ovalle
- Department of Data Science, Dana-Farber Cancer Institute, Boston, MA
| | - Pavel Trukhanov
- Department of Data Science, Dana-Farber Cancer Institute, Boston, MA
| | - Jason Hansel
- Department of Data Science, Dana-Farber Cancer Institute, Boston, MA
| | - Geoffrey I. Shapiro
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Thomas A. Abrams
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Leah H. Biller
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Jennifer A. Chan
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - James M. Cleary
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Steven M. Corsello
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Andrea C. Enzinger
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Peter C. Enzinger
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Robert J. Mayer
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Nadine J. McCleary
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Jeffrey A. Meyerhardt
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Kimmie Ng
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Anuj K. Patel
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Kimberley J. Perez
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Osama E. Rahma
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Douglas A. Rubinson
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Jeffrey S. Wisch
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Matthew B. Yurgelun
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Michael J. Hassett
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Laura MacConaill
- Center for Advanced Molecular Diagnostics, Brigham & Women's Hospital & Harvard Medical School, Boston, MA
| | - Deborah Schrag
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Ethan Cerami
- Department of Data Science, Dana-Farber Cancer Institute, Boston, MA
| | - Brian M. Wolpin
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA
| | - Jonathan A. Nowak
- Center for Advanced Molecular Diagnostics, Brigham & Women's Hospital & Harvard Medical School, Boston, MA
| | - Marios Giannakis
- Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, Boston, MA,Broad Institute of Harvard and MIT, Cambridge, MA,Marios Giannakis, Department of Medical Oncology, Dana-Farber Cancer Institute & Harvard Medical School, 450 Brookline Ave., Boston, MA 02215; e-mail:
| |
Collapse
|
3
|
Klein H, Mazor T, Siegel E, Trukhanov P, Ovalle A, Vecchio Fitz CD, Zwiesler Z, Kumari P, Van Der Veen B, Marriott E, Hansel J, Yu J, Albayrak A, Barry S, Keller RB, MacConaill LE, Lindeman N, Johnson BE, Rollins BJ, Do KT, Beardslee B, Shapiro G, Hector-Barry S, Methot J, Sholl L, Lindsay J, Hassett MJ, Cerami E. MatchMiner: an open-source platform for cancer precision medicine. NPJ Precis Oncol 2022; 6:69. [PMID: 36202909 PMCID: PMC9537311 DOI: 10.1038/s41698-022-00312-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2022] [Accepted: 09/15/2022] [Indexed: 11/17/2022] Open
Abstract
Widespread, comprehensive sequencing of patient tumors has facilitated the usage of precision medicine (PM) drugs to target specific genomic alterations. Therapeutic clinical trials are necessary to test new PM drugs to advance precision medicine, however, the abundance of patient sequencing data coupled with complex clinical trial eligibility has made it challenging to match patients to PM trials. To facilitate enrollment onto PM trials, we developed MatchMiner, an open-source platform to computationally match genomically profiled cancer patients to PM trials. Here, we describe MatchMiner’s capabilities, outline its deployment at Dana-Farber Cancer Institute (DFCI), and characterize its impact on PM trial enrollment. MatchMiner’s primary goals are to facilitate PM trial options for all patients and accelerate trial enrollment onto PM trials. MatchMiner can help clinicians find trial options for an individual patient or provide trial teams with candidate patients matching their trial’s eligibility criteria. From March 2016 through March 2021, we curated 354 PM trials containing a broad range of genomic and clinical eligibility criteria and MatchMiner facilitated 166 trial consents (MatchMiner consents, MMC) for 159 patients. To quantify MatchMiner’s impact on trial consent, we measured time from genomic sequencing report date to trial consent date for the 166 MMC compared to trial consents not facilitated by MatchMiner (non-MMC). We found MMC consented to trials 55 days (22%) earlier than non-MMC. MatchMiner has enabled our clinicians to match patients to PM trials and accelerated the trial enrollment process.
Collapse
Affiliation(s)
- Harry Klein
- Department of Data Science, Dana-Farber Cancer Institute (DFCI), Boston, MA, USA.
| | - Tali Mazor
- Department of Data Science, Dana-Farber Cancer Institute (DFCI), Boston, MA, USA.
| | - Ethan Siegel
- Department of Data Science, Dana-Farber Cancer Institute (DFCI), Boston, MA, USA
| | - Pavel Trukhanov
- Department of Data Science, Dana-Farber Cancer Institute (DFCI), Boston, MA, USA
| | - Andrea Ovalle
- Department of Data Science, Dana-Farber Cancer Institute (DFCI), Boston, MA, USA
| | | | - Zachary Zwiesler
- Department of Data Science, Dana-Farber Cancer Institute (DFCI), Boston, MA, USA
| | - Priti Kumari
- Department of Data Science, Dana-Farber Cancer Institute (DFCI), Boston, MA, USA
| | | | - Eric Marriott
- Department of Data Science, Dana-Farber Cancer Institute (DFCI), Boston, MA, USA
| | - Jason Hansel
- Department of Data Science, Dana-Farber Cancer Institute (DFCI), Boston, MA, USA
| | - Joyce Yu
- Department of Data Science, Dana-Farber Cancer Institute (DFCI), Boston, MA, USA
| | - Adem Albayrak
- Informatics and Analytics, Dana-Farber Cancer Institute, Boston, MA, USA
| | - Susan Barry
- Dana-Farber Cancer Institute, Boston, MA, USA
| | - Rachel B Keller
- Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, USA
| | | | - Neal Lindeman
- Department of Pathology, Brigham and Women's Hospital, Boston, MA, USA
| | - Bruce E Johnson
- Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, USA
| | - Barrett J Rollins
- Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, USA.,Department of Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, USA
| | - Khanh T Do
- Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, USA.,Department of Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, USA
| | - Brian Beardslee
- Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, USA
| | - Geoffrey Shapiro
- Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, USA.,Department of Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, USA
| | | | - John Methot
- Informatics and Analytics, Dana-Farber Cancer Institute, Boston, MA, USA
| | - Lynette Sholl
- Department of Pathology, Brigham and Women's Hospital, Boston, MA, USA
| | - James Lindsay
- Department of Data Science, Dana-Farber Cancer Institute (DFCI), Boston, MA, USA
| | - Michael J Hassett
- Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, USA
| | - Ethan Cerami
- Department of Data Science, Dana-Farber Cancer Institute (DFCI), Boston, MA, USA
| |
Collapse
|
4
|
Klein H, Mazor T, Kumari P, Ovalle A, Trukhanov P, Hansel J, Yu J, Lindsay J, Hassett M, Cerami E. Abstract 4091: Design and adoption of MatchMiner at Dana-Farber Cancer Institute. Cancer Res 2022. [DOI: 10.1158/1538-7445.am2022-4091] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Abstract
Precision medicine (PM) drugs targeting alterations such as EGFR mutations and BCR-ABL fusions have provided great clinical benefit to patients. However, with an abundance of tumor sequencing data and trial eligibility criteria available, it can be challenging for clinicians to identify PM trial options for patients. To address this challenge at Dana-Farber Cancer Institute (DFCI), we developed MatchMiner, an open-source platform for computationally matching patients to PM trials. MatchMiner has three modes of use: (1) patient-centric, where clinicians can view all available trial matches for a patient, (2) trial-centric, where clinical trial teams identify patients for their trials based on genomic and clinical criteria, and (3) trial search, where clinicians search for available trials based on clinical and genomic eligibility. Trial matching is performed via the MatchEngine, which computes trial matches based on patient genomic and clinical data and PM trial eligibility criteria. To encode trial eligibility criteria, we developed a structured format called clinical trial markup language (CTML), which uses Boolean logic to encode inclusion and exclusion criteria. Here, we describe our implementation of MatchMiner at DFCI including strategies that were successful and MatchMiner’s impact on trial consent. Since MatchMiner first went live in March 2017, a number of strategies have helped facilitate utilization of MatchMiner. The biggest impact has come from targeted departmental collaborations (Gastrointestinal, Breast, and Center for Cancer Therapeutic Innovation or CCTI), where the MatchMiner team worked directly with key departmental stakeholders to develop customized workflows. To facilitate access to MatchMiner among individual clinicians, we integrated the patient-centric and trial search modes into the Epic electronic health record. Other implementation strategies were piloted, such as weekly emails to clinicians alerting them to potential trial matches, but were less impactful. Overall, departmental collaborations have resulted in several ongoing MatchMiner initiatives. Thus far at DFCI, we have curated 354 PM trials into MatchMiner and facilitated 220 patient consents. For PM trials, 222 genes, 7 mutational signatures and nearly all cancer types were represented, demonstrating that there is a wide range of PM trial options available to patients. We also examined the distribution of trial phases and disease centers running each trial. The majority were Phase I and Phase II trials run out of the CCTI, consistent with the frequency with which novel drugs do not progress to later phase trials. Lastly, we have identified 220 trial consents that benefitted from MatchMiner. Retrospective analysis of a subset of these trial consents (n=166) revealed a significant 22% decrease in time to consent relative to other consents to the same trials, demonstrating the clinical impact of MatchMiner.
Citation Format: Harry Klein, Tali Mazor, Priti Kumari, Andrea Ovalle, Pavel Trukhanov, Jason Hansel, Joyce Yu, James Lindsay, Michael Hassett, Ethan Cerami. Design and adoption of MatchMiner at Dana-Farber Cancer Institute [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 4091.
Collapse
Affiliation(s)
| | - Tali Mazor
- 1Dana-Farber Cancer Institute, Boston, MA
| | | | | | | | | | - Joyce Yu
- 1Dana-Farber Cancer Institute, Boston, MA
| | | | | | | |
Collapse
|
5
|
Klein H, Mazor T, Kumari P, Lindsay J, Ovalle A, Trukhanov P, Yu J, Hassett M, Cerami E. Abstract P160: MatchMiner: An open-source platform for cancer precision medicine. Mol Cancer Ther 2021. [DOI: 10.1158/1535-7163.targ-21-p160] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Abstract
With the advent of next generation sequencing in cancer care, patients’ tumors can be genomically profiled and specific genetic alterations can be targeted with precision medicine drugs. However, the abundance of patient sequencing data coupled with complex clinical trial eligibility has made it challenging to match patients to precision medicine trials. To facilitate interpretation of complex tumor sequencing data and clinical trial genomic eligibility criteria, we developed MatchMiner, an open-source platform to computationally match cancer patients to precision medicine clinical trials. MatchMiner has several modes of clinical use: (1) patient-centric, where clinicians look up trial matches for their patient, (2) trial-centric, where clinical trial investigators identify patients for their clinical trials, and (3) trial search, where clinicians identify available trials based on any criteria, including external genomic reports. To support users in all three modes, MatchMiner also displays full genomic reports for patients and detailed trial information in user-friendly formats. MatchMiner trial matching is performed via the MatchEngine, an algorithm that computes matches based on patient genomic and clinical data and trial eligibility criteria. The MatchEngine accepts many different data inputs for patient-trial matching, and is easily customized to work with data available at any institution. At Dana-Farber Cancer Institute (DFCI), MatchMiner supports the following data: 1) patient-specific genomic sequencing data, including mutations, copy number alterations, structural variants, tumor mutational burden and mutational signatures including mismatch repair deficiency or microsatellite instability, 2) patient-specific clinical data, including primary cancer type, gender, age, and vital status, and 3) trial eligibility criteria including genomic targets, cancer type, and age. Unique to MatchMiner, each trial’s eligibility criteria is encoded in clinical trial markup language (CTML), a structured format that encodes detailed information about a trial and utilizes boolean logic to encode inclusion and exclusion criteria. Although MatchMiner has been operational at DFCI since early 2017, its impact on patient care has not yet been extensively studied. Thus far, MatchMiner has facilitated 181 precision medicine trial consents (MatchMiner consents, MMC) for 159 patients. To quantify MatchMiner’s impact on trial consent, we retrospectively measured time from genomic sequencing report date to trial consent date for a subset of the 181 MMC (166 MMC). We compared time to trial consent date for the 166 MMC to a group of 353 consents for the same trials not facilitated by MatchMiner (non-MatchMiner consents, non-MMC). MMC consented to trials 22% faster (P=0.004, median=195 days, IQR=85-34) than non-MMC (median=250 days; IQR=99-491). Thus, clinical use of MatchMiner decreased time to enroll in a precision medicine study, and suggests that use of precision medicine trial matching tools such as MatchMiner are important for the future of patient care.
Citation Format: Harry Klein, Tali Mazor, Priti Kumari, James Lindsay, Andrea Ovalle, Pavel Trukhanov, Joyce Yu, Michael Hassett, Ethan Cerami. MatchMiner: An open-source platform for cancer precision medicine [abstract]. In: Proceedings of the AACR-NCI-EORTC Virtual International Conference on Molecular Targets and Cancer Therapeutics; 2021 Oct 7-10. Philadelphia (PA): AACR; Mol Cancer Ther 2021;20(12 Suppl):Abstract nr P160.
Collapse
Affiliation(s)
| | - Tali Mazor
- Dana-Farber Cancer Institute, Boston, MA
| | | | | | | | | | - Joyce Yu
- Dana-Farber Cancer Institute, Boston, MA
| | | | | |
Collapse
|
6
|
Klein H, Mazor T, Kumari P, Lindsay J, Ovalle A, Siegel E, Trukhanov P, Yu J, Hassett M, Cerami E. Abstract 1198: MatchMiner: An open-source computational platform that accelerates patient enrollment on to precision medicine trials. Cancer Res 2021. [DOI: 10.1158/1538-7445.am2021-1198] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Abstract
With the advent of next generation sequencing in cancer care, patients' tumors can be genomically profiled and specific genetic alterations can be targeted with precision medicine drugs. However, the abundance of patient sequencing data coupled with complex clinical trial eligibility has made it challenging to match patients to precision medicine trials. To facilitate interpretation of complex tumor sequencing data and clinical trial genomic eligibility criteria, we developed MatchMiner, an open-source platform to computationally match cancer patients to precision medicine clinical trials. MatchMiner supports two distinct workflows: (1) patient-centric mode, in which an oncologist can find clinical trial matches for a specific patient, and (2) trial-centric mode, in which a clinical trial investigator can identify and recruit patients for a specific trial. In MatchMiner at DFCI, there are currently 330+ precision medicine trials and genomic and genomic and clinical data from 39,000+ patients. Although MatchMiner has been operational at Dana-Farber Cancer Institute since early 2017, its impact on patient care has not yet been extensively studied.
In this study, we analyzed temporal trends of 170 MatchMiner-driven trial enrollments. We compared these 170 MatchMiner-driven trial enrollments to non-MatchMiner-driven trial enrollments to determine how MatchMiner has impacted patient enrollments. To compare MatchMiner-driven trial enrollments to non-MatchMiner-driven enrollments, we limited the non-MatchMiner group by choosing patients who enrolled on the same trials. We also ensured that all patients in both enrollment groups had a genomic report present in MatchMiner before their consent date. We then analyzed temporal trends between genomic report dates, patient consent and on-study dates, and patient views in MatchMiner. MatchMiner-driven enrollments had a significant decrease in time from genomic report date to consent date compared to non-MatchMiner-driven enrollments. Thus, clinical use of MatchMiner decreased time to enroll in a precision medicine study, and suggests that use of precision medicine trial matching tools such as MatchMiner are important for the future of patient care.
The MatchMiner open-source software package is available through GitHub (https://github.com/dfci/matchminer). We are committed to supporting MatchMiner as an open-source software; to our knowledge, at least five cancer centers are implementing MatchMiner.
Citation Format: Harry Klein, Tali Mazor, Priti Kumari, James Lindsay, Andrea Ovalle, Ethan Siegel, Pavel Trukhanov, Joyce Yu, Michael Hassett, Ethan Cerami. MatchMiner: An open-source computational platform that accelerates patient enrollment on to precision medicine trials [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 1198.
Collapse
Affiliation(s)
| | - Tali Mazor
- Dana-Farber Cancer Institute, Boston, MA
| | | | | | | | | | | | - Joyce Yu
- Dana-Farber Cancer Institute, Boston, MA
| | | | | |
Collapse
|