Leveraging Large Language Models for Clinical Trial Eligibility Criteria Classification
The advent of transformer technology and large language models (LLMs) has further broadened the already extensive application field of artificial intelligence (AI). A large portion of medical records is stored in text format, such as clinical trial texts. Part of these texts is information regarding...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Digital |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-6470/5/2/12 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839654268853813248 |
|---|---|
| author | Sujan Ray Arpita Nath Sarker Neelakshi Chatterjee Kowshik Bhowmik Sayantan Dey |
| author_facet | Sujan Ray Arpita Nath Sarker Neelakshi Chatterjee Kowshik Bhowmik Sayantan Dey |
| author_sort | Sujan Ray |
| collection | DOAJ |
| description | The advent of transformer technology and large language models (LLMs) has further broadened the already extensive application field of artificial intelligence (AI). A large portion of medical records is stored in text format, such as clinical trial texts. Part of these texts is information regarding eligibility criteria. We aimed to harness the immense capabilities of an LLM by fine-tuning an open-source LLM (Llama-2) to develop a classifier from the clinical trial data. We were interested in investigating whether a fine-tuned LLM could better decide the eligibility criteria from the clinical trial text and compare the results with a more traditional method. Such an investigation can help us determine the extent to which we can rely on text-based applications developed from large language models and possibly open new avenues of application in the medical domain. Our results are comparable to the best-performing methods for this task. Since we used state-of-the-art technology, this research has the potential to open new avenues in the field of LLM application in the healthcare sector. |
| format | Article |
| id | doaj-art-dbc0224bd8c44c3a9c0f7b9dd8535288 |
| institution | Matheson Library |
| issn | 2673-6470 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Digital |
| spelling | doaj-art-dbc0224bd8c44c3a9c0f7b9dd85352882025-06-25T13:42:38ZengMDPI AGDigital2673-64702025-04-01521210.3390/digital5020012Leveraging Large Language Models for Clinical Trial Eligibility Criteria ClassificationSujan Ray0Arpita Nath Sarker1Neelakshi Chatterjee2Kowshik Bhowmik3Sayantan Dey4Computer Science and Engineering (EECS), University of Cincinnati, Cincinnati, OH 45221, USADepartment of Biology, University of West Georgia, Carrollton, GA 30118, USADepartment of Biostatistics, Health Informatics and Data Science, University of Cincinnati, Cincinnati, OH 45221, USAComputer Science and Engineering (EECS), University of Cincinnati, Cincinnati, OH 45221, USAComputer Science and Engineering (EECS), University of Cincinnati, Cincinnati, OH 45221, USAThe advent of transformer technology and large language models (LLMs) has further broadened the already extensive application field of artificial intelligence (AI). A large portion of medical records is stored in text format, such as clinical trial texts. Part of these texts is information regarding eligibility criteria. We aimed to harness the immense capabilities of an LLM by fine-tuning an open-source LLM (Llama-2) to develop a classifier from the clinical trial data. We were interested in investigating whether a fine-tuned LLM could better decide the eligibility criteria from the clinical trial text and compare the results with a more traditional method. Such an investigation can help us determine the extent to which we can rely on text-based applications developed from large language models and possibly open new avenues of application in the medical domain. Our results are comparable to the best-performing methods for this task. Since we used state-of-the-art technology, this research has the potential to open new avenues in the field of LLM application in the healthcare sector.https://www.mdpi.com/2673-6470/5/2/12artificial intelligenceclinical trialdeep neural networksfine-tuninglarge language modelsmachine learning |
| spellingShingle | Sujan Ray Arpita Nath Sarker Neelakshi Chatterjee Kowshik Bhowmik Sayantan Dey Leveraging Large Language Models for Clinical Trial Eligibility Criteria Classification Digital artificial intelligence clinical trial deep neural networks fine-tuning large language models machine learning |
| title | Leveraging Large Language Models for Clinical Trial Eligibility Criteria Classification |
| title_full | Leveraging Large Language Models for Clinical Trial Eligibility Criteria Classification |
| title_fullStr | Leveraging Large Language Models for Clinical Trial Eligibility Criteria Classification |
| title_full_unstemmed | Leveraging Large Language Models for Clinical Trial Eligibility Criteria Classification |
| title_short | Leveraging Large Language Models for Clinical Trial Eligibility Criteria Classification |
| title_sort | leveraging large language models for clinical trial eligibility criteria classification |
| topic | artificial intelligence clinical trial deep neural networks fine-tuning large language models machine learning |
| url | https://www.mdpi.com/2673-6470/5/2/12 |
| work_keys_str_mv | AT sujanray leveraginglargelanguagemodelsforclinicaltrialeligibilitycriteriaclassification AT arpitanathsarker leveraginglargelanguagemodelsforclinicaltrialeligibilitycriteriaclassification AT neelakshichatterjee leveraginglargelanguagemodelsforclinicaltrialeligibilitycriteriaclassification AT kowshikbhowmik leveraginglargelanguagemodelsforclinicaltrialeligibilitycriteriaclassification AT sayantandey leveraginglargelanguagemodelsforclinicaltrialeligibilitycriteriaclassification |