{"doi":"10.1101/2024.06.28.24309677","title":"Matching Patients to Clinical Trials using LLaMA 2 Embeddings and Siamese Neural Network","abstract":"Patient recruitment is a key desideratum for the success of a clinical trial that entails identifying eligible patients that match the selection criteria for the trial. However, the complexity of criteria information and heterogeneity of patient data render manual analysis a burdensome and time-consuming task. In an attempt to automate patient recruitment, this work proposes a Siamese Neural Network-based model, namely Siamese-PTM. Siamese-PTM employs the pretrained LLaMA 2 model to derive contextual representations of the EHR and criteria inputs and jointly encodes them using two weight-sharing identical subnetworks. We evaluate Siamese-PTM on structured and unstructured EHR to analyze their predictive informativeness as standalone and collective feature sets. We explore a variety of deep models for Siamese-PTM's encoders and compare their performance against the Single-encoder counterparts. We develop a baseline rule-based classifier, compared to which Siamese-PTM improved performance by 40%. Furthermore, visualization of Siamese-PTM's learned embedding space reinforces its predictive robustness.","journal":"medRxiv","year":2024,"id":487149,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":3,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9555,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2024-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":950958,"name":"Sivaraman Rajaganapathy","orcid":"0000-0003-4582-7274","position":1,"is_corresponding":false},{"id":388965,"name":"Yue Yu","orcid":"0000-0002-0860-6643","position":2,"is_corresponding":false},{"id":23317,"name":"Cui Tao","orcid":"0000-0002-4267-1924","position":3,"is_corresponding":false},{"id":461079,"name":"Maria Vassilaki","orcid":"0000-0001-8328-136X","position":4,"is_corresponding":false},{"id":18261,"name":"Nansu Zong","orcid":"0000-0003-0066-9524","position":5,"is_corresponding":false},{"id":1193192,"name":"Shaika Chowdhury","orcid":"0000-0001-6775-8623","position":0,"is_corresponding":true}],"reference_count":28,"raw_metadata":null,"created_at":"2026-07-19T02:08:06.013846Z","pmid":"38978646","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}