scholarly journals Building a specialized lexicon for breast cancer clinical trial subject eligibility analysis

2021 ◽  
Vol 27 (1) ◽  
pp. 146045822198939
Author(s):  
Euisung Jung ◽  
Hemant Jain ◽  
Atish P Sinha ◽  
Carmelo Gaudioso
Keyword(s):  
Breast Cancer ◽  
Clinical Trial ◽  
Clinical Trials ◽  
Text Mining ◽  
Language Processing ◽  
Snomed Ct ◽  
Lexical Resources ◽  
Named Entities ◽  
Domain Experts ◽  
Trial Subject

A natural language processing (NLP) application requires sophisticated lexical resources to support its processing goals. Different solutions, such as dictionary lookup and MetaMap, have been proposed in the healthcare informatics literature to identify disease terms with more than one word (multi-gram disease named entities). Although a lot of work has been done in the identification of protein- and gene-named entities in the biomedical field, not much research has been done on the recognition and resolution of terminologies in the clinical trial subject eligibility analysis. In this study, we develop a specialized lexicon for improving NLP and text mining analysis in the breast cancer domain, and evaluate it by comparing it with the Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT). We use a hybrid methodology, which combines the knowledge of domain experts, terms from multiple online dictionaries, and the mining of text from sample clinical trials. Use of our methodology introduces 4243 unique lexicon items, which increase bigram entity match by 38.6% and trigram entity match by 41%. Our lexicon, which adds a significant number of new terms, is very useful for matching patients to clinical trials automatically based on eligibility matching. Beyond clinical trial matching, the specialized lexicon developed in this study could serve as a foundation for future healthcare text mining applications.

Artificial Intelligence Tool for Optimizing Eligibility Screening for Clinical Trials in a Large Community Cancer Center

2020 ◽  
pp. 50-59 ◽  
Author(s):  
J. Thaddeus Beck ◽  
Melissa Rammage ◽  
Gretchen P. Jackson ◽  
Anita M. Preininger ◽  
Irene Dankwa-Mullan ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Clinical Trial ◽  
Clinical Trials ◽  
Language Processing ◽  
Medical Records ◽  
Cancer Center ◽  
Patients With Cancer ◽  
Attribute Extraction ◽  
Time Required ◽  
Manual Review

PURPOSE Less than 5% of patients with cancer enroll in clinical trials, and 1 in 5 trials are stopped for poor accrual. We evaluated an automated clinical trial matching system that uses natural language processing to extract patient and trial characteristics from unstructured sources and machine learning to match patients to clinical trials. PATIENTS AND METHODS Medical records from 997 patients with breast cancer were assessed for trial eligibility at Highlands Oncology Group between May and August 2016. System and manual attribute extraction and eligibility determinations were compared using the percentage of agreement for 239 patients and 4 trials. Sensitivity and specificity of system-generated eligibility determinations were measured, and the time required for manual review and system-assisted eligibility determinations were compared. RESULTS Agreement between system and manual attribute extraction ranged from 64.3% to 94.0%. Agreement between system and manual eligibility determinations was 81%-96%. System eligibility determinations demonstrated specificities between 76% and 99%, with sensitivities between 91% and 95% for 3 trials and 46.7% for the 4th. Manual eligibility screening of 90 patients for 3 trials took 110 minutes; system-assisted eligibility determinations of the same patients for the same trials required 24 minutes. CONCLUSION In this study, the clinical trial matching system displayed a promising performance in screening patients with breast cancer for trial eligibility. System-assisted trial eligibility determinations were substantially faster than manual review, and the system reliably excluded ineligible patients for all trials and identified eligible patients for most trials.

Identification of Cancer Care and Protocol Characteristics Associated With Recruitment in Breast Cancer Clinical Trials

2008 ◽  
Vol 26 (27) ◽  
pp. 4458-4465 ◽  
Author(s):  
Julie Lemieux ◽  
Pamela J. Goodwin ◽  
Kathleen I. Pritchard ◽  
Karen A. Gelmon ◽  
Louise J. Bordeleau ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Clinical Trial ◽  
Clinical Trials ◽  
Cancer Care ◽  
Primary Objective ◽  
Cancer Clinical Trials ◽  
Cooperative Groups ◽  
Number Of Patients ◽  
Trial Protocols ◽  
Few Data

Purpose It is estimated that only 5% of patients with cancer participate in a clinical trial. Barriers to participation may relate to available protocols, physicians, and patients, but few data exist on barriers related to cancer care environments and protocol characteristics. Methods The primary objective was to identify characteristics of cancer care environments and clinical trial protocols associated with a low recruitment into breast cancer clinical trials. Secondary objectives were to determine yearly recruitment fraction onto clinical trials from 1997 to 2002 in Ontario, Canada, and to compare recruitment fraction among years. Questionnaires were sent to hospitals requesting characteristics of cancer care environments and to cooperative groups/pharmaceutical companies for information on protocols and the number of patients recruited per hospital/year. Poisson regression was used to estimate the recruitment fraction. Results Questionnaire completion rate varied between 69% and 100%. Recruitment fraction varied between 5.4% and 8.5% according to year. More than 30% of patients were diagnosed in hospitals with no available trials. In multivariate analysis, the following characteristics were associated with recruitment: use of placebo versus not (relative risk [RR] = 0.80; P = .05), nonmetastatic versus metastatic trial (RR = 2.80; P < .01), and for nonmetastatic trials, protocol allowing an interval of 12 weeks or longer versus less than 12 weeks (from diagnosis, surgery, or end of therapy) before enrollment (RR = 1.36; P < .01). Conclusion Allowable interval of 12 weeks or longer to randomly assign patients in clinical trials could help recruitment. In our study, absence of an available clinical trial represented the largest barrier to recruitment.

Barriers to participation in breast cancer trials

2007 ◽  
Vol 25 (18_suppl) ◽  
pp. 6593-6593
Author(s):  
O. Herasme ◽  
J. Goldberg ◽  
R. Sandoval ◽  
C. Harris ◽  
Y. Ortiz-Pride ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Clinical Trial ◽  
Clinical Trials ◽  
Child Care ◽  
Cancer Patients ◽  
Controlled Trial ◽  
Demographic Factors ◽  
Trial Participation ◽  
Barriers To Participation ◽  
Cancer Trials

6593 Background: Clinical cancer trials allow investigators to test the effectiveness and safety of new cancer drugs and treatments. Historically, fewer that 5% of cancer patients have participated in clinical trials. The purpose of this study was to assess attitudes, beliefs, and practical barriers to clinical trial recruitment. Methods: Women were recruited in the Herbert Irving Comprehensive Cancer Center while waiting for routine breast screening or for oncology care in connection with a diagnosis of breast cancer. The 29-item survey questionnaire covered demographic factors, prior cancer diagnosis or risk factors, past experience with clinical trials if any, willingness to participate in different types of trials, and attitudinal and practical barriers to participation. Results: Of 329 respondents, 48.9% were non- Hispanic white, 10.9% non-Hispanic black, 34.9% Hispanic, and 5.30% other/unknown. The mean age of participants was 52.5 (SD=12.1). Of 131 (39.8%) participants reporting that they had been asked to participate in clinical trial, 82 were white, 17 black and 32 Hispanic. Of those who enrolled, 64 were white, 14 were black, and 19 Hispanic. Of those asked to participate 56/63 breast cancer patients (88.9%) and 44/68 others (64.7%) enrolled (P=0.002). Of 48 who reported that they had child care responsibilities, 33 enrolled (68.8) compared to 67/83 (80.7%) of those without such responsibilities (P=0.07). Of the total sample, 88/220 (40.0%) of those without childcare responsibilities but only 32/109 (29.4) said they would be willing to participate in a placebo-controlled trial. Respondents were twice as likely to say they would participate in a trial comparing two active agents as a placebo-controlled trial. Conclusion: Our findings suggest that being asked to participate in a clinical trial may be associated with demographic factors, and that specific circumstances, such as child care responsibilities, may also affect trial participation. Awareness of these barriers may help investigators to develop effective strategies for overcoming them and for improving trial participation overall. No significant financial relationships to disclose.

Effects of an Art-Based Curriculum on Clinical Trials Attitudes and Breast Cancer Prevention Knowledge

2006 ◽  
Vol 33 (5) ◽  
pp. 664-676 ◽  
Author(s):  
Patricia M. Herman ◽  
Linda K. Larkey
Keyword(s):  
Breast Cancer ◽  
Clinical Trial ◽  
Clinical Trials ◽  
Education Program ◽  
Cancer Education ◽  
Controlled Study ◽  
Breast Health ◽  
Breast Cancer Education ◽  
The Difference ◽  
The U.S

Although Latinos now comprise the largest minority in the U.S. population, they continue to be seriously underrepresented in clinical trials. A nonrandomized controlled study of an innovative community-developed clinical trial and breast cancer education program targeting Latinas tested whether use of an art-based curriculum could increase willingness to enroll in six clinical trial scenarios and increase breast health and clinical trial knowledge. The art-based curriculum resulted in a larger increase in stated willingness to enroll across all clinical trial scenarios, and the difference was statistically significant ( p < .05) in three. Breast health and clinical trials knowledge increased similarly and significantly for both groups. The results of this study show promise for the use of a community-developed art-based curriculum in the Latina population to increase willingness to enroll in clinical trials.

Increasing participation in breast cancer research: (INSPIRE-BrC).

2014 ◽  
Vol 32 (26_suppl) ◽  
pp. 53-53
Author(s):  
Brandi Robinson ◽  
Sandra M. Swain
Keyword(s):  
Breast Cancer ◽  
Clinical Trial ◽  
Clinical Trials ◽  
Primary Outcome Measure ◽  
Test Method ◽  
Trial Participation ◽  
Lower Survival Rate ◽  
Black Patients ◽  
Clinical Trial Enrollment ◽  
The Impact

53 Background: Increasing black patients’ participation in cancer clinical trials is particularly important because of the population’s lower survival rate. Accrual to clinical trials remains low among the general population (1 to 3%), with recruitment of blacks the lowest of all groups at 0.5 to 1.5%. Clinical trials are key to developing new methods to prevent, detect, and treat cancer. INSPIRE-BrC aims to increase trial participation rates among black patients with breast cancer and examine the relationship between the intervention and attitudes/beliefs on the decision to participate. Methods: A sample size of 123 black patients with breast cancer at five MedStar sites will view a 15 minute, culturally tailored video about clinical trials, which targets six cultural and attitudinal barriers to participation. A pre-test/post-test method is used to determine the impact of the video on three variables — likely participation in therapeutic clinical trials; attitudes toward therapeutic clinical trials (assessed based on the 6 barriers); and actual trial enrollment. Expected Findings: We hypothesize that the intervention will increase clinical trial enrollment compared to our 2012 clinical trial enrollment baseline rate of 6% (22/384) for black patients with breast cancer in five MedStar hospitals. The primary outcome measure is the proportion of black patients with breast cancer who agree to participate in a therapeutic clinical trial among those who sign consent to INSPIRE-BrC. Study findings have the potential to increase patient recruitment as a promising tool for rapid dissemination of a theory-driven, evidence-based model to enhance clinical trial accrual among black patients with cancer. [Table: see text]

A natural language processing tool for automatic identification of new disease and disease progression: Parsing text in multi-institutional radiology reports to facilitate clinical trial eligibility screening.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 1555-1555
Author(s):  
Eric J. Clayton ◽  
Imon Banerjee ◽  
Patrick J. Ward ◽  
Maggie D Howell ◽  
Beth Lohmueller ◽  
...  
Keyword(s):  
Clinical Trial ◽  
Clinical Trials ◽  
Natural Language Processing ◽  
Natural Language ◽  
Disease Progression ◽  
Language Processing ◽  
Free Text ◽  
New Disease ◽  
Radiology Reports ◽  
Precision And Accuracy

1555 Background: Screening every patient for clinical trials is time-consuming, costly and inefficient. Developing an automated method for identifying patients who have potential disease progression, at the point where the practice first receives their radiology reports, but prior to the patient’s office visit, would greatly increase the efficiency of clinical trial operations and likely result in more patients being offered trial opportunities. Methods: Using Natural Language Processing (NLP) methodology, we developed a text parsing algorithm to automatically extract information about potential new disease or disease progression from multi-institutional, free-text radiology reports (CT, PET, bone scan, MRI or x-ray). We combined semantic dictionary mapping and machine learning techniques to normalize the linguistic and formatting variations in the text, training the XGBoost model particularly to achieve a high precision and accuracy to satisfy clinical trial screening requirements. In order to be comprehensive, we enhanced the model vocabulary using a multi-institutional dataset which includes reports from two academic institutions. Results: A dataset of 732 de-identified radiology reports were curated (two MDs agreed on potential new disease/dz progression vs stable) and the model was repeatedly re-trained for each fold where the folds were randomly selected. The final model achieved consistent precision (>0.87 precision) and accuracy (>0.87 accuracy). See the table for a summary of the results, by radiology report type. We are continuing work on the model to validate accuracy and precision using a new and unique set of reports. Conclusions: NLP systems can be used to identify patients who potentially have suffered new disease or disease progression and reduce the human effort in screening or clinical trials. Efforts are ongoing to integrate the NLP process into existing EHR reporting. New imaging reports sent via interface to the EHR will be extracted daily using a database query and will be provided via secure electronic transport to the NLP system. Patients with higher likelihood of disease progression will be automatically identified, and their reports routed to the clinical trials office for clinical trial screening parallel to physician EHR mailbox reporting. The over-arching goal of the project is to increase clinical trial enrollment. 5-fold cross-validation performance of the NLP model in terms of accuracy, precision and recall averaged across all the folds.[Table: see text]

Racial distribution of clinical trial participants in the United States.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e18516-e18516
Author(s):  
Monaliben Patel ◽  
Lisa M. Hess ◽  
Eric Wen Su ◽  
Xiaohong Li ◽  
Debora S. Bruno
Keyword(s):  
Breast Cancer ◽  
Clinical Trial ◽  
Clinical Trials ◽  
Phase 2 ◽  
Phase 3 ◽  
Black Patients ◽  
The Us ◽  
Oncology Clinical Trials ◽  
Seer Data ◽  
Trial Participants

e18516 Background: Lack of diverse representation in clinical trials negatively impacts the cancer survival of patients and populations unaccounted for in clinical research. Efforts such as the 1993 NIH Revitalization Act have focused on improving the diversity of trial participants in the US. This retrospective study evaluated the racial distribution of oncology clinical trial participants using data published in clinicaltrials.gov from Jan 2010 through Dec 2020. Methods: I2E of Linguamatics (IQVIA, Inc), a natural language processing software, was used to identify participant race in oncology trials. Data extracted included trial identifier, year of completion, sponsor, cancer type, and race. Studies were limited to academic, cooperative group and government studies headquartered in the US. Clinical trial results were compared to the racial distribution of SEER 2010 data using z-test. Results: Data from 35,686 patients (14,220 enrolled to 236 phase 2 and 21,471 enrolled to 47 phase 3 trials) were available for analysis. A summary by race is provided in the Table, excluding unknown, which represented 8.5% of phase 2 and 3.5% of phase 3 trials. The proportions of white/black patients enrolled to phase 2 and phase 3 trials beginning in 2010-12 were 84.4%/11% and 83.1%/9.9%, respectively (total enrollment 84.9%/9.6%). For trials beginning in 2015-17, white/black enrollment represented 88.5%/8.1% of patients enrolled to phase 2 and 86.4%/10.1% of patients in phase 3 trials. Black patients represented 9.6% of all trial participants, in contrast with the SEER data where 12% of all patients were black (p < 0.001). For lung cancer trials, black participants represented only 7.9% of all trial participants whereas in breast cancer trials, 10.2% of participants were black, versus the SEER data specific to these tumor types (black patients represent 10.9%/11.5% of lung/breast cancer diagnoses between 2013 to 2017, both p < 0.01). Conclusions: This study suggests that over the past decade most races (other than white) have been significantly underrepresented in US oncology clinical trials, and is even more pronounced for black patients with lung cancer. Based on this analysis, there is no evidence that trial enrollment distribution, particularly of white versus black participants, has changed since 2010. Data are limited to the relative lack of studies reporting results that began enrollment after 2017. These findings suggest that the development of new strategies to improve the recruitment of racial minorities to oncology clinical trials are warranted.[Table: see text]

Sign in / Sign up

Export Citation Format

Share Document