{"doi":"10.1101/2024.09.18.24313828","title":"Leveraging large language models for systematic reviewing: A case study using HIV medication adherence research","abstract":"Background The rapidly accumulating scientific literature in HIV presents a significant challenge in accurately and efficiently assessing the relevant literature. This study explores the potential capabilities of using large language models (LLMs), such as ChatGPT, for selecting relevant studies for a systematic review. Method Scientific papers were initially obtained from bibliographic database searches using a Boolean search strategy with pre-defined keywords. From 15,839 unique records, three reviewers manually identified 39 relevant papers based on pre-specified inclusion and exclusion criteria. In the ChatGPT experiment, over 10% of records were randomly chosen as the experimental dataset, including the 39 manually identified manuscripts. These unique records (n=1,680) underwent screening via ChatGPT-4 using the same prespecified criteria. Four strategies were employed including standard prompting, i.e., input-output (IO), chain of thought with zero-shot learning (0-CoT), CoT with few-shot learning (FS-CoT), and Majority Voting (which integrates all three promoting strategies). Performance of the models were assessed using recall, F-score, and precision measures. Results Recall scores (% of true abstracts successfully identified and retrieved by the model from all input data/records) for different ChatGPT configurations were 0.82 (IO), 0.97 (0-CoT), and both the FS-CoT and the Majority Voting prompts achieved a recall score of 1.0. F-scores were 0.34 (IO), 0.29 (0-CoT), 0.39 (FS-CoT), and 0.46 (majority voting). Precision measures were 0.22(IO), 0.17(0-CoT), 0.24(FS-CoT), and 0.30 (Majority Voting). Computational time varied with 2.32, 4.55, 6.44, and 13.30 hours for IO, 0-CoT, FS-CoT, and majority voting,respectively. Processing costs for the 1,680 unique records were approximately $63, $73, $186, and $325, respectively. Conclusion LLMs, like ChatGPT, are viable for systematic reviews, efficiently identifying studies meeting pre-specified criteria. Greater efficacy was observed when a more sophisticated prompt design was employed, integrating IO, 0-CoT and FS-CoT prompt techniques (i.e., majority voting). LLMs can expedite the study selection process in systematic reviews compared to manual methods, with minimal cost implications.","journal":"medRxiv","year":2024,"id":503453,"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":0,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.7239,"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":295081,"name":"Zhenlong Li","orcid":"0000-0002-8938-5466","position":1,"is_corresponding":false},{"id":453363,"name":"Shan Qiao","orcid":"0000-0001-9685-0277","position":2,"is_corresponding":false},{"id":376172,"name":"Huan Ning","orcid":"0000-0003-3698-3240","position":3,"is_corresponding":false},{"id":906802,"name":"Abhishek Aggarwal","orcid":"0000-0002-9808-8084","position":4,"is_corresponding":false},{"id":1247613,"name":"Guangzhe Frank Yuan","orcid":null,"position":5,"is_corresponding":false},{"id":1353758,"name":"Atena Pasha","orcid":null,"position":6,"is_corresponding":false},{"id":689443,"name":"Michael J. Stirratt","orcid":"0000-0001-5243-9312","position":7,"is_corresponding":false},{"id":350480,"name":"Lori A. J. Scott‐Sheldon","orcid":"0000-0003-1524-3374","position":8,"is_corresponding":false},{"id":1026906,"name":"M. Naser Lessani","orcid":"0000-0001-8657-3798","position":0,"is_corresponding":true}],"reference_count":20,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-19T02:10:31.826282Z","pmid":null,"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":[]}