1
|
Yang Y, Jayaraj S, Ludmir E, Roberts K. Text Classification of Cancer Clinical Trial Eligibility Criteria. AMIA ... ANNUAL SYMPOSIUM PROCEEDINGS. AMIA SYMPOSIUM 2024; 2023:1304-1313. [PMID: 38222417 PMCID: PMC10785908] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Subscribe] [Scholar Register] [Indexed: 01/16/2024]
Abstract
Automatic identification of clinical trials for which a patient is eligible is complicated by the fact that trial eligibility are stated in natural language. A potential solution to this problem is to employ text classification methods for common types of eligibility criteria. In this study, we focus on seven common exclusion criteria in cancer trials: prior malignancy, human immunodeficiency virus, hepatitis B, hepatitis C, psychiatric illness, drug/substance abuse, and autoimmune illness. Our dataset consists of 764 phase III cancer trials with these exclusions annotated at the trial level. We experiment with common transformer models as well as a new pre-trained clinical trial BERT model. Our results demonstrate the feasibility of automatically classifying common exclusion criteria. Additionally, we demonstrate the value of a pre-trained language model specifically for clinical trials, which yield the highest average performance across all criteria.
Collapse
Affiliation(s)
- Yumeng Yang
- School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, USA
| | - Soumya Jayaraj
- School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, USA
| | - Ethan Ludmir
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Kirk Roberts
- School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, USA
| |
Collapse
|
2
|
Sherry AD, Corrigan KL, Kouzy R, Jaoude JA, Yang Y, Patel RR, Totten DJ, Newman NB, Das P, Taniguchi C, Minsky B, Snyder RA, Fuller CD, Ludmir E. Prevalence, trends, and characteristics of trials investigating local therapy in contemporary phase 3 clinical cancer research. Cancer 2023; 129:3430-3438. [PMID: 37382235 DOI: 10.1002/cncr.34929] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2023] [Revised: 04/11/2023] [Accepted: 05/05/2023] [Indexed: 06/30/2023]
Abstract
BACKGROUND Although most patients with cancer are treated with local therapy (LT), the proportion of late-phase clinical trials investigating local therapeutic interventions is unknown. The purpose of this study was to determine the proportion, characteristics, and trends of phase 3 cancer clinical trials assessing the therapeutic value of LT over time. METHODS This was a cross-sectional analysis of interventional randomized controlled trials in oncology published from 2002 through 2020 and registered on ClinicalTrials.gov. Trends and characteristics of LT trials were compared to all other trials. RESULTS Of 1877 trials screened, 794 trials enrolling 584,347 patients met inclusion criteria. A total of 27 trials (3%) included a primary randomization assessing LT compared with 767 trials (97%) investigating systemic therapy or supportive care. Annual increase in the number of LT trials (slope [m] = 0.28; 95% confidence interval [CI], 0.15-0.39; p < .001) was outpaced by the increase of trials testing systemic therapy or supportive care (m = 7.57; 95% CI, 6.03-9.11; p < .001). LT trials were more often sponsored by cooperative groups (22 of 27 [81%] vs. 211 of 767 [28%]; p < .001) and less often sponsored by industry (5 of 27 [19%] vs. 609 of 767 [79%]; p < .001). LT trials were more likely to use overall survival as primary end point compared to other trials (13 of 27 [48%] vs. 199 of 767 [26%]; p = .01). CONCLUSIONS In contemporary late-phase oncology research, LT trials are increasingly under-represented, under-funded, and evaluate more challenging end points compared to other modalities. These findings strongly argue for greater resource allocation and funding mechanisms for LT clinical trials. PLAIN LANGUAGE SUMMARY Most people who have cancer receive treatments directed at the site of their cancer, such as surgery or radiation. We do not know, however, how many trials test surgery or radiation compared to drug treatments (that go all over the body). We reviewed trials testing the most researched strategies (phase 3) completed between 2002 and 2020. Only 27 trials tested local treatments like surgery or radiation compared to 767 trials testing other treatments. Our study has important implications for funding research and understanding cancer research priorities.
Collapse
Affiliation(s)
- Alexander D Sherry
- Division of Radiation Oncology, Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Kelsey L Corrigan
- Division of Radiation Oncology, Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Ramez Kouzy
- Division of Radiation Oncology, Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Joseph Abi Jaoude
- Division of Radiation Oncology, Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Yumeng Yang
- Department of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, Texas, USA
| | - Roshal R Patel
- Division of Radiation Oncology, Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
- Department of Radiation Oncology, Memorial Sloan-Kettering Cancer Center, New York, New York, USA
| | - Douglas J Totten
- Department of Otolaryngology-Head and Neck Surgery, Indiana University School of Medicine, Indianapolis, Indiana, USA
| | - Neil B Newman
- Department of Radiation Oncology, University of Texas Health Science Center at San Antonio, San Antonio, Texas, USA
| | - Prajnan Das
- Division of Radiation Oncology, Department of Gastrointestinal Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Cullen Taniguchi
- Division of Radiation Oncology, Department of Gastrointestinal Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
- Division of Radiation Oncology, Department of Experimental Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Bruce Minsky
- Division of Radiation Oncology, Department of Gastrointestinal Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Rebecca A Snyder
- Division of Surgery, Department of Surgical Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
- Department of Health Services Research, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - C David Fuller
- Division of Radiation Oncology, Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Ethan Ludmir
- Division of Radiation Oncology, Department of Gastrointestinal Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| |
Collapse
|
3
|
Das A, Lin TA, Lin C, Meirson T, McCaw ZR, Tian L, Ludmir EB. Assessment of Median and Mean Survival Time in Cancer Clinical Trials. JAMA Netw Open 2023; 6:e236498. [PMID: 37010873 PMCID: PMC10071342 DOI: 10.1001/jamanetworkopen.2023.6498] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/12/2023] [Accepted: 02/16/2023] [Indexed: 04/04/2023] Open
Abstract
This cohort study assesses the relative stability of median and mean survival time estimates reported in cancer clinical trials.
Collapse
Affiliation(s)
- Ananya Das
- The University of Texas MD Anderson Cancer Center, Houston
| | - Timothy A. Lin
- Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Christine Lin
- The University of Texas MD Anderson Cancer Center, Houston
| | - Tomer Meirson
- Azrieli Faculty of Medicine, Bar-Ilan University, Ramat Gan, Israel
| | | | - Lu Tian
- Department of Health Research and Policy, Stanford University, Stanford, California
| | | |
Collapse
|