A review of research on eligibility criteria for clinical trials

Practical Guide to Clinical Trial Accessibility: Making Trial Participation a Standard of Care

Despite being a cornerstone of cancer treatment advancement, clinical trials remain inaccessible for many patients because of structural, socioeconomic, and systemic barriers. In this multidisciplinary perspective piece, stakeholders from patient advocacy, community oncology, industry, and academic medicine offer a collaborative overview of key challenges and practical solutions to improve trial accessibility. Patient advocates highlight the need to address language barriers, financial toxicity, and underrepresentation through community engagement and patient-centered trial design. Community oncologists underscore infrastructure limitations, generalist practice burdens, and misaligned trial offerings, calling for eligibility reform and cooperative trial models. Industry partners examine how overly restrictive criteria and inconsistent protocol practices hinder diversity and propose portfolio-wide strategies, such as protocol watch lists, for inclusive design. Academic oncologists focus on trial complexity, investigator burden, and limited generalizability, advocating for pragmatic and decentralized trial paradigms. Together, these perspectives underscore the shared responsibility across sectors to modernize clinical trial design, reduce access barriers, and ensure that trial participation becomes a standard and equitable component of cancer care.

CPRS: a clinical protocol recommendation system based on LLMs

BACKGROUND

As fundamental documents in clinical trials, clinical trial protocols are intended to ensure that trials are conducted according to the objectives set by researchers. The advent of large models with superior semantic performance compared to traditional models provides fresh perspectives for research recommendations in clinical trial protocols.

METHOD

A clinical trial protocol recommendation system based on Large Language Models (LLMs) is proposed in this paper, combining GPT-4 and knowledge graph to assist in clinical trial protocol recommendations. Using knowledge graphs as an auxiliary tool, a finite set of clinical trial projects with similar features is identified. Subsequently, through the semantic capabilities of GPT-4, targeted recommendations are made to patients.

RESULTS

Experiments were conducted to compare GPT-4 and multiple models from the SBERT family that handle semantic similarity. The results indicate that GPT-4 is capable of better sorting clinical trial protocols based on similarity criteria and offering targeted recommendations to patients. Consequently, this capability meets the matching requirements between projects and patients and enhances the automation of clinical trial protocol recommendations. Additionally, in the future, personal factors of patients will be fully considered during the recommendation process to provide more accurate and personalized protocol recommendations.

CONCLUSION

By integrating knowledge graphs and LLMs, a better understanding and processing of clinical trial protocol information can be achieved, enabling the recommendation of appropriate protocols for patients and enhancing both matching efficiency and accuracy. Furthermore, the application of this system contributes to the automation of clinical trial protocol recommendations, playing a crucial role in medical research institutions such as clinical trial research institutes and public health management departments. Additionally, it significantly aids in advancing the development of clinical trials and the medical field at large.

Analysis of eligibility criteria clusters based on large language models for clinical trial design

OBJECTIVES

Clinical trials (CTs) are essential for improving patient care by evaluating new treatments' safety and efficacy. A key component in CT protocols is the study population defined by the eligibility criteria. This study aims to evaluate the effectiveness of large language models (LLMs) in encoding eligibility criterion information to support CT-protocol design.

MATERIALS AND METHODS

We extracted eligibility criterion sections, phases, conditions, and interventions from CT protocols available in the ClinicalTrials.gov registry. Eligibility sections were split into individual rules using a criterion tokenizer and embedded using LLMs. The obtained representations were clustered. The quality and relevance of the clusters for protocol design was evaluated through 3 experiments: intrinsic alignment with protocol information and human expert cluster coherence assessment, extrinsic evaluation through CT-level classification tasks, and eligibility section generation.

RESULTS

Sentence embeddings fine-tuned using biomedical corpora produce clusters with the highest alignment to CT-level information. Human expert evaluation confirms that clusters are well structured and coherent. Despite the high information compression, clusters retain significant CT information, up to 97% of the classification performance obtained with raw embeddings. Finally, eligibility sections automatically generated using clusters achieve 95% of the ROUGE scores obtained with a generative LLM prompted with CT-protocol details, suggesting that clusters encapsulate information useful to CT-protocol design.

DISCUSSION

Clusters derived from sentence-level LLM embeddings effectively summarize complex eligibility criterion data while retaining relevant CT-protocol details. Clustering-based approaches provide a scalable enhancement in CT design that balances information compression with accuracy.

CONCLUSIONS

Clustering eligibility criteria using LLM embeddings provides a practical and efficient method to summarize critical protocol information. We provide an interactive visualization of the pipeline here.

Effects of Dietary Fiber Interventions on Glycemic Control and Weight Management in Diabetes: A Systematic Review of Randomized Controlled Trials

This systematic review explores the impact of dietary fiber interventions on glycemic control and weight management in individuals with diabetes or at risk for diabetes. A comprehensive search was conducted across PubMed, Embase, and Cochrane Library following the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines, identifying randomized controlled trials published in the last five years. Ten studies met the inclusion criteria, evaluating various types of dietary fiber, including soluble, insoluble, viscous fiber, and resistant starch. The findings demonstrated significant improvements in key glycemic markers such as fasting plasma glucose, glycated hemoglobin (HbA1c), and postprandial glucose levels, as well as weight management outcomes such as reductions in body weight and waist circumference. Secondary benefits included improvements in lipid profiles, insulin sensitivity, and gut microbiota composition. The quality assessment revealed a low risk of bias in most studies, ensuring robust evidence. Despite these promising results, gaps in long-term effects and variations in intervention efficacy warrant further research. These findings emphasize the potential of dietary fiber as a practical and accessible intervention in diabetes management and prevention.

Role of Statins in Reducing Cardiovascular Mortality: A Systematic Review of Long-Term Outcomes

Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, highlighting the critical need for effective preventive therapies. Statins, or HMG-CoA reductase inhibitors, are widely prescribed for their ability to lower low-density lipoprotein (LDL) cholesterol and reduce CV risk. This systematic review evaluates the long-term impact of statins on CV and all-cause mortality across diverse populations, including those with chronic kidney disease, chronic heart failure, and other comorbid conditions. A comprehensive search of major databases identified randomized controlled trials and large observational cohort studies with follow-up periods exceeding one year. Findings demonstrated significant reductions in CV mortality (hazard ratio (HR) range: 0.38-0.76) and all-cause mortality (HR range: 0.55-0.80) with statin therapy, particularly among high-risk groups, such as individuals with elevated LDL-C and moderate chronic kidney disease. Additional benefits were observed in preventing major adverse cardiovascular events (MACEs). Subgroup analyses revealed variations in efficacy based on age, sex, comorbidities, and statin type or dosage, with some populations, such as those with chronic heart failure and chronic obstructive pulmonary disease, showing limited benefit. Geographic and ethnic diversity were underrepresented in the included studies, and data on long-term effects in populations with advanced renal impairment or inflammatory conditions remain insufficient. These gaps underscore the need for methodologically robust studies and tailored approaches to statin therapy that account for individual patient profiles, including comorbidities and demographic factors. Practical steps include integrating statins with newer lipid-lowering agents and developing personalized treatment protocols to maximize their benefits and minimize risks. This review reinforces the critical role of statins in reducing the global burden of CVDs while emphasizing areas for future research.

"The Truth Is, We Must Miss Some": A Qualitative Study of the Patient Eligibility Screening Process, and Automation Perspectives, for Cancer Clinical Trials

BACKGROUND

Recruitment of cancer patients into clinical trials (CTs) is a challenge. We aimed to explore how patient eligibility assessment is conducted in practice, what factors support or hinder this process, and to assess the potential usefulness of Clinical Trial Recruitment Support Systems (CTRSS) for patient-to-trial matching.

METHODS

We conducted semi-structured interviews in France with healthcare professionals involved in cancer CTs and experts on trial recruitment. We focused on the stages in-between trial feasibility, and patient information and consent. Interviews were recorded, and the transcripts were analyzed thematically. We used the Systems Engineering Initiative for Patient Safety (SEIPS) 2.0 framework to organize our results.

RESULTS

We interviewed 25 participants. We identified common steps for cancer patient eligibility assessment: prescreening under medical supervision, followed by the validation of patient-trial matching based on manual chart review. This process built on rich interactions between clinicians, other professionals (clinical research assistants, data scientists, medical coding experts), and patients. Technological factors, mainly related to data infrastructure (both for patient data and trial data), and organizational factors (research culture, incentives, formal and informal research networks) mediated the performance of the recruitment process. Participants had mixed feelings towards CTRSSs; they welcomed automated pre-screening but insisted on manual verification. Given the necessary collaborative nature of multisite trials, coordinated efforts to support a common data infrastructure could be helpful.

CONCLUSIONS

Material, organizational, and human factors affect cancer patient eligibility assessment for CTs. Patient-to-trial matching tools bear potential, but good understanding of the ecosystem, including stakeholders' motivations, is a prerequisite.

Machine learning and natural language processing in clinical trial eligibility criteria parsing: a scoping review

Automatic eligibility criteria parsing in clinical trials is crucial for cohort recruitment leading to data validity and trial completion. Recent years have witnessed an explosion of powerful machine learning (ML) and natural language processing (NLP) models that can streamline the patient accrual process. In this PRISMA-based scoping review, we comprehensively evaluate existing literature on the application of ML/NLP models for parsing clinical trial eligibility criteria. The review covers 9160 papers published between 2000 and 2024, with 88 publications subjected to data charting along 17 dimensions. Our review indicates insufficient use of state-of-the-art artificial intelligence (AI) models in the analysis of clinical protocols.

Optimizing Clinical Trial Eligibility Design Using Natural Language Processing Models and Real-World Data: Algorithm Development and Validation

BACKGROUND

Clinical trials are vital for developing new therapies but can also delay drug development. Efficient trial data management, optimized trial protocol, and accurate patient identification are critical for reducing trial timelines. Natural language processing (NLP) has the potential to achieve these objectives.

OBJECTIVE

This study aims to assess the feasibility of using data-driven approaches to optimize clinical trial protocol design and identify eligible patients. This involves creating a comprehensive eligibility criteria knowledge base integrated within electronic health records using deep learning-based NLP techniques.

METHODS

We obtained data of 3281 industry-sponsored phase 2 or 3 interventional clinical trials recruiting patients with non-small cell lung cancer, prostate cancer, breast cancer, multiple myeloma, ulcerative colitis, and Crohn disease from ClinicalTrials.gov, spanning the period between 2013 and 2020. A customized bidirectional long short-term memory- and conditional random field-based NLP pipeline was used to extract all eligibility criteria attributes and convert hypernym concepts into computable hyponyms along with their corresponding values. To illustrate the simulation of clinical trial design for optimization purposes, we selected a subset of patients with non-small cell lung cancer (n=2775), curated from the Mount Sinai Health System, as a pilot study.

RESULTS

We manually annotated the clinical trial eligibility corpus (485/3281, 14.78% trials) and constructed an eligibility criteria-specific ontology. Our customized NLP pipeline, developed based on the eligibility criteria-specific ontology that we created through manual annotation, achieved high precision (0.91, range 0.67-1.00) and recall (0.79, range 0.50-1) scores, as well as a high F1-score (0.83, range 0.67-1), enabling the efficient extraction of granular criteria entities and relevant attributes from 3281 clinical trials. A standardized eligibility criteria knowledge base, compatible with electronic health records, was developed by transforming hypernym concepts into machine-interpretable hyponyms along with their corresponding values. In addition, an interface prototype demonstrated the practicality of leveraging real-world data for optimizing clinical trial protocols and identifying eligible patients.

CONCLUSIONS

Our customized NLP pipeline successfully generated a standardized eligibility criteria knowledge base by transforming hypernym criteria into machine-readable hyponyms along with their corresponding values. A prototype interface integrating real-world patient information allows us to assess the impact of each eligibility criterion on the number of patients eligible for the trial. Leveraging NLP and real-world data in a data-driven approach holds promise for streamlining the overall clinical trial process, optimizing processes, and improving efficiency in patient identification.

The usage of population and disease registries as pre-screening tools for clinical trials, a systematic review

OBJECTIVE

This systematic review aims to outline the use of population and disease registries for clinical trial pre-screening.

MATERIALS AND METHODS

The search was conducted in the time period of January 2014 to December 2022 in three databases: MEDLINE, Embase, and Web of Science Core Collection. References were screened using the Rayyan software, firstly based on titles and abstracts only, and secondly through full text review. Quality of the included studies was assessed using the List of Included Studies and quality Assurance in Review tool, enabling inclusion of publications of only moderate to high quality.

RESULTS

The search originally identified 1430 citations, but only 24 studies were included, reporting the use of population and/or disease registries for trial pre-screening. Nine disease domains were represented, with 54% of studies using registries based in the USA, and 62.5% of the studies using national registries. Half of the studies reported usage for drug trials, and over 478,679 patients were identified through registries in this review. Main advantages of the pre-screening methodology were reduced financial burden and time reduction.

DISCUSSION AND CONCLUSION

The use of registries for trial pre-screening increases reproducibility of the pre-screening process across trials and sites, allowing for implementation and improvement of a quality assurance process. Pre-screening strategies seem under-reported, and we encourage more trials to use and describe their pre-screening processes, as there is a need for standardized methodological guidelines.

Evaluation of Eligibility Criteria Relevance for the Purpose of IT-Supported Trial Recruitment: Descriptive Quantitative Analysis

BACKGROUND

Clinical trials (CTs) are crucial for medical research; however, they frequently fall short of the requisite number of participants who meet all eligibility criteria (EC). A clinical trial recruitment support system (CTRSS) is developed to help identify potential participants by performing a search on a specific data pool. The accuracy of the search results is directly related to the quality of the data used for comparison. Data accessibility can present challenges, making it crucial to identify the necessary data for a CTRSS to query. Prior research has examined the data elements frequently used in CT EC but has not evaluated which criteria are actually used to search for participants. Although all EC must be met to enroll a person in a CT, not all criteria have the same importance when searching for potential participants in an existing data pool, such as an electronic health record, because some of the criteria are only relevant at the time of enrollment.

OBJECTIVE

In this study, we investigated which groups of data elements are relevant in practice for finding suitable participants and whether there are typical elements that are not relevant and can therefore be omitted.

METHODS

We asked trial experts and CTRSS developers to first categorize the EC of their CTs according to data element groups and then to classify them into 1 of 3 categories: necessary, complementary, and irrelevant. In addition, the experts assessed whether a criterion was documented (on paper or digitally) or whether it was information known only to the treating physicians or patients.

RESULTS

We reviewed 82 CTs with 1132 unique EC. Of these 1132 EC, 350 (30.9%) were considered necessary, 224 (19.8%) complementary, and 341 (30.1%) total irrelevant. To identify the most relevant data elements, we introduced the data element relevance index (DERI). This describes the percentage of studies in which the corresponding data element occurs and is also classified as necessary or supplementary. We found that the query of "diagnosis" was relevant for finding participants in 79 (96.3%) of the CTs. This group was followed by "date of birth/age" with a DERI of 85.4% (n=70) and "procedure" with a DERI of 35.4% (n=29).

CONCLUSIONS

The distribution of data element groups in CTs has been heterogeneously described in previous works. Therefore, we recommend identifying the percentage of CTs in which data element groups can be found as a more reliable way to determine the relevance of EC. Only necessary and complementary criteria should be included in this DERI.