{"doi":"10.48550/arxiv.2409.18878","title":"Suicide Phenotyping from Clinical Notes in Safety-Net Psychiatric Hospital Using Multi-Label Classification with Pre-Trained Language Models","abstract":"Accurate identification and categorization of suicidal events can yield better suicide precautions, reducing operational burden, and improving care quality in high-acuity psychiatric settings. Pre-trained language models offer promise for identifying suicidality from unstructured clinical narratives. We evaluated the performance of four BERT-based models using two fine-tuning strategies (multiple single-label and single multi-label) for detecting coexisting suicidal events from 500 annotated psychiatric evaluation notes. The notes were labeled for suicidal ideation (SI), suicide attempts (SA), exposure to suicide (ES), and non-suicidal self-injury (NSSI). RoBERTa outperformed other models using binary relevance (acc=0.86, F1=0.78). MentalBERT (F1=0.74) also exceeded BioClinicalBERT (F1=0.72). RoBERTa fine-tuned with a single multi-label classifier further improved performance (acc=0.88, F1=0.81), highlighting that models pre-trained on domain-relevant data and the single multi-label classification strategy enhance efficiency and performance.","journal":"PubMed","year":2024,"id":487456,"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":0.954,"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":1199064,"name":"Yan Hu","orcid":"0009-0008-2413-5918","position":1,"is_corresponding":false},{"id":537773,"name":"Scott D. Lane","orcid":"0000-0002-3447-6539","position":2,"is_corresponding":false},{"id":914525,"name":"Salih Selek","orcid":"0000-0001-5197-5682","position":3,"is_corresponding":false},{"id":783684,"name":"Lokesh Shahani","orcid":"0000-0002-6731-6275","position":4,"is_corresponding":false},{"id":1332173,"name":"Rodrigo Machado-Vieira","orcid":null,"position":5,"is_corresponding":false},{"id":235057,"name":"Jair C. Soares","orcid":"0000-0002-5466-5628","position":6,"is_corresponding":false},{"id":12534,"name":"Hua Xu","orcid":"0000-0002-5274-4672","position":7,"is_corresponding":false},{"id":49903,"name":"Hongfang Liu","orcid":"0000-0003-2570-3741","position":8,"is_corresponding":false},{"id":444275,"name":"Ming Huang","orcid":"0000-0001-7367-3626","position":9,"is_corresponding":false},{"id":367322,"name":"Zehan Li","orcid":"0000-0002-2955-6809","position":0,"is_corresponding":true}],"reference_count":18,"raw_metadata":null,"created_at":"2026-07-19T02:08:10.215754Z","pmid":"40502237","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":[]}