{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T19:47:33Z","timestamp":1780084053039,"version":"3.54.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T00:00:00Z","timestamp":1736726400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T00:00:00Z","timestamp":1736726400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Holmusk Technologies, Inc"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>Background<\/jats:title>\n            <jats:p>Anhedonia and suicidal ideation are symptoms of major depressive disorder (MDD) that are not regularly captured in structured scales but may be captured in unstructured clinical notes. Natural language processing (NLP) techniques may be used to extract longitudinal data on suicidal behaviors and anhedonia within unstructured clinical notes. This study assessed the accuracy of using NLP techniques on electronic health records (EHRs) to identify these symptoms among patients with MDD.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods<\/jats:title>\n            <jats:p>EHR-derived, de-identified data were used from the NeuroBlu Database (version 23R1), a longitudinal behavioral health real-world database. Mental health clinicians annotated instances of anhedonia and suicidal symptoms in clinical notes creating a ground truth. Interrater reliability (IRR) was calculated using Krippendorff\u2019s alpha. A novel transformer architecture-based NLP model was trained on clinical notes to recognize linguistic patterns and contextual cues. Each sentence was categorized into one of four labels: (1) anhedonia; (2) suicidal ideation without intent or plan; (3) suicidal ideation with intent or plan; (4) absence of suicidal ideation or anhedonia. The model was assessed using positive predictive values (PPV), negative predictive values, sensitivity, specificity, F1-score, and AUROC.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>The model was trained, tested, and validated on 2,198, 1,247, and 1,016 distinct clinical notes, respectively. IRR was 0.80. For anhedonia, suicidal ideation with intent or plan, and suicidal ideation without intent or plan the model achieved a PPV of 0.98, 0.93, and 0.87, an F1-score of 0.98, 0.91, and 0.89 during training and a PPV of 0.99, 0.95, and 0.87 and F1-score of 0.99, 0.95, and 0.89 during validation.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusions<\/jats:title>\n            <jats:p>NLP techniques can leverage contextual information in EHRs to identify anhedonia and suicidal symptoms in patients with MDD. Integrating structured and unstructured data offers a comprehensive view of MDD\u2019s trajectory, helping healthcare providers deliver timely, effective interventions. Addressing current limitations will further enhance NLP models, enabling more accurate extraction of critical clinical features and supporting personalized, proactive mental health care.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1186\/s12911-025-02851-w","type":"journal-article","created":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T14:58:51Z","timestamp":1736780331000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Natural language processing to identify suicidal ideation and anhedonia in major depressive disorder"],"prefix":"10.1186","volume":"25","author":[{"given":"L. Alexander","family":"Vance","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leslie","family":"Way","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deepali","family":"Kulkarni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emily O. C.","family":"Palmer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhijit","family":"Ghosh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Melissa","family":"Unruh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kelly M. Y.","family":"Chan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amey","family":"Girdhari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joydeep","family":"Sarkar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,13]]},"reference":[{"key":"2851_CR1","unstructured":"World Health Organization. Preventing suicide: a global imperative [Internet] Geneva 2014 [Available from: http:\/\/www.who.int\/mental_health\/suicide-prevention\/world_report_2014\/en\/"},{"key":"2851_CR2","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.jad.2021.05.115","volume":"293","author":"H Cai","year":"2021","unstructured":"Cai H, Jin Y, Liu S, Zhang Q, Zhang L, Cheung T, et al. Prevalence of suicidal ideation and planning in patients with major depressive disorder: a meta-analysis of observation studies. J Affect Disord. 2021;293:148\u201358.","journal-title":"J Affect Disord"},{"issue":"2","key":"2851_CR3","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1176\/appi.ajp.2016.16010077","volume":"174","author":"Y Barak-Corren","year":"2017","unstructured":"Barak-Corren Y, Castro VM, Javitt S, Hoffnagle AG, Dai Y, Perlis RH, et al. Predicting suicidal behavior from Longitudinal Electronic Health Records. Am J Psychiatry. 2017;174(2):154\u201362.","journal-title":"Am J Psychiatry"},{"issue":"3","key":"2851_CR4","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1007\/s40471-022-00293-w","volume":"9","author":"JM Boggs","year":"2022","unstructured":"Boggs JM, Kafka JM. A critical review of text mining applications for suicide research. Curr Epidemiol Rep. 2022;9(3):126\u201334.","journal-title":"Curr Epidemiol Rep"},{"issue":"1","key":"2851_CR5","doi-asserted-by":"publisher","first-page":"7426","DOI":"10.1038\/s41598-018-25773-2","volume":"8","author":"AC Fernandes","year":"2018","unstructured":"Fernandes AC, Dutta R, Velupillai S, Sanyal J, Stewart R, Chandran D. Identifying suicide ideation and suicidal attempts in a Psychiatric Clinical Research database using Natural Language Processing. Sci Rep. 2018;8(1):7426.","journal-title":"Sci Rep"},{"key":"2851_CR6","doi-asserted-by":"crossref","unstructured":"American Psychiatric Association. The Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition. 5th ed: American Psychiatric Publishing. 2013 May 27, 2013. 991 p.","DOI":"10.1176\/appi.books.9780890425596"},{"key":"2851_CR7","doi-asserted-by":"publisher","first-page":"103507","DOI":"10.1016\/j.brat.2019.103507","volume":"125","author":"GK Khazanov","year":"2020","unstructured":"Khazanov GK, Xu C, Dunn BD, Cohen ZD, DeRubeis RJ, Hollon SD. Distress and anhedonia as predictors of depression treatment outcome: a secondary analysis of a randomized clinical trial. Behav Res Ther. 2020;125:103507.","journal-title":"Behav Res Ther"},{"key":"2851_CR8","doi-asserted-by":"crossref","unstructured":"Whitton AE, Pizzagalli DA. Anhedonia in depression and bipolar disorder. Anhedonia: preclinical, translational, and clinical integration. Springer; 2022. pp. 111\u201327.","DOI":"10.1007\/7854_2022_323"},{"issue":"3","key":"2851_CR9","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1002\/wps.21110","volume":"22","author":"M Berk","year":"2023","unstructured":"Berk M, K\u00f6hler-Forsberg O, Turner M, Penninx B, Wrobel A, Firth J, et al. Comorbidity between major depressive disorder and physical diseases: a comprehensive review of epidemiology, mechanisms and management. World Psychiatry. 2023;22(3):366\u201387.","journal-title":"World Psychiatry"},{"key":"2851_CR10","unstructured":"Kshatriya BSA, Nunez NA, Resendez MG, Ryu E, Coombes BJ, Fu S et al. Neural language models with distant supervision to identify major depressive disorder from clinical notes. arXiv Preprint arXiv:210409644. 2021."},{"issue":"1","key":"2851_CR11","first-page":"21","volume":"23","author":"N Vaci","year":"2020","unstructured":"Vaci N, Liu Q, Kormilitzin A, De Crescenzo F, Kurtulmus A, Harvey J, et al. Natural language processing for structuring clinical text data on depression using UK-CRIS. BMJ Ment Health. 2020;23(1):21\u20136.","journal-title":"BMJ Ment Health"},{"issue":"4","key":"2851_CR12","doi-asserted-by":"publisher","first-page":"816","DOI":"10.3758\/s13415-020-00804-6","volume":"20","author":"A Borsini","year":"2020","unstructured":"Borsini A, Wallis ASJ, Zunszain P, Pariante CM, Kempton MJ. Characterizing anhedonia: a systematic review of neuroimaging across the subtypes of reward processing deficits in depression. Cogn Affect Behav Neurosci. 2020;20(4):816\u201341.","journal-title":"Cogn Affect Behav Neurosci"},{"issue":"5","key":"2851_CR13","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1016\/S2215-0366(15)00579-9","volume":"3","author":"LM Williams","year":"2016","unstructured":"Williams LM. Precision psychiatry: a neural circuit taxonomy for depression and anxiety. Lancet Psychiatry. 2016;3(5):472\u201380.","journal-title":"Lancet Psychiatry"},{"key":"2851_CR14","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.pnpbp.2019.01.002","volume":"92","author":"B Cao","year":"2019","unstructured":"Cao B, Zhu J, Zuckerman H, Rosenblat JD, Brietzke E, Pan Z, et al. Pharmacological interventions targeting anhedonia in patients with major depressive disorder: a systematic review. Prog Neuropsychopharmacol Biol Psychiatry. 2019;92:109\u201317.","journal-title":"Prog Neuropsychopharmacol Biol Psychiatry"},{"issue":"1","key":"2851_CR15","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1038\/s41398-021-01522-4","volume":"11","author":"X Zhu","year":"2021","unstructured":"Zhu X, Ward J, Cullen B, Lyall DM, Strawbridge RJ, Lyall LM, et al. Phenotypic and genetic associations between anhedonia and brain structure in UK Biobank. Translational Psychiatry. 2021;11(1):395.","journal-title":"Translational Psychiatry"},{"issue":"16","key":"2851_CR16","doi-asserted-by":"publisher","first-page":"2790","DOI":"10.1017\/S0033291719002940","volume":"50","author":"M Ironside","year":"2020","unstructured":"Ironside M, Admon R, Maddox SA, Mehta M, Douglas S, Olson DP, et al. Inflammation and depressive phenotypes: evidence from medical records from over 12 000 patients and brain morphology. Psychol Med. 2020;50(16):2790\u20138.","journal-title":"Psychol Med"},{"issue":"Suppl 1","key":"2851_CR17","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1002\/pds.2335","volume":"21","author":"JT Walkup","year":"2012","unstructured":"Walkup JT, Townsend L, Crystal S, Olfson M. A systematic review of validated methods for identifying suicide or suicidal ideation using administrative or claims data. Pharmacoepidemiol Drug Saf. 2012;21(Suppl 1):174\u201382.","journal-title":"Pharmacoepidemiol Drug Saf"},{"issue":"7","key":"2851_CR18","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1002\/pds.3421","volume":"22","author":"ST Callahan","year":"2013","unstructured":"Callahan ST, Fuchs DC, Shelton RC, Balmer LS, Dudley JA, Gideon PS, et al. Identifying suicidal behavior among adolescents using administrative claims data. Pharmacoepidemiol Drug Saf. 2013;22(7):769\u201375.","journal-title":"Pharmacoepidemiol Drug Saf"},{"issue":"1","key":"2851_CR19","doi-asserted-by":"publisher","first-page":"65","DOI":"10.3122\/jabfm.2015.01.140181","volume":"28","author":"HD Anderson","year":"2015","unstructured":"Anderson HD, Pace WD, Brandt E, Nielsen RD, Allen RR, Libby AM, et al. Monitoring suicidal patients in primary care using electronic health records. J Am Board Fam Med. 2015;28(1):65\u201371.","journal-title":"J Am Board Fam Med"},{"issue":"4","key":"2851_CR20","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1016\/j.clinthera.2017.12.015","volume":"40","author":"A Liede","year":"2018","unstructured":"Liede A, Wade S, Lethen J, Hernandez RK, Warner D, Abernethy AP, et al. An observational study of concomitant use of emerging therapies and denosumab or zoledronic acid in prostate cancer. Clin Ther. 2018;40(4):536\u201349. e3.","journal-title":"Clin Ther"},{"issue":"6","key":"2851_CR21","doi-asserted-by":"publisher","first-page":"e044353","DOI":"10.1136\/bmjopen-2020-044353","volume":"11","author":"SM Manemann","year":"2021","unstructured":"Manemann SM, St Sauver JL, Liu H, Larson NB, Moon S, Takahashi PY, et al. Longitudinal cohorts for harnessing the electronic health record for disease prediction in a US population. BMJ open. 2021;11(6):e044353.","journal-title":"BMJ open"},{"issue":"4","key":"2851_CR22","doi-asserted-by":"publisher","first-page":"e057227","DOI":"10.1136\/bmjopen-2021-057227","volume":"12","author":"R Patel","year":"2022","unstructured":"Patel R, Wee SN, Ramaswamy R, Thadani S, Tandi J, Garg R, et al. NeuroBlu, an electronic health record (EHR) trusted research environment (TRE) to support mental healthcare analytics with real-world data. BMJ Open. 2022;12(4):e057227.","journal-title":"BMJ Open"},{"key":"2851_CR23","doi-asserted-by":"publisher","first-page":"946387","DOI":"10.3389\/fpsyt.2022.946387","volume":"13","author":"C Crema","year":"2022","unstructured":"Crema C, Attardi G, Sartiano D, Redolfi A. Natural language processing in clinical neuroscience and psychiatry: a review. Front Psychiatry. 2022;13:946387.","journal-title":"Front Psychiatry"},{"issue":"5","key":"2851_CR24","doi-asserted-by":"publisher","first-page":"e15708","DOI":"10.2196\/15708","volume":"23","author":"A Le Glaz","year":"2021","unstructured":"Le Glaz A, Haralambous Y, Kim-Dufor DH, Lenca P, Billot R, Ryan TC, et al. Machine Learning and Natural Language Processing in Mental Health: systematic review. J Med Internet Res. 2021;23(5):e15708.","journal-title":"J Med Internet Res"},{"issue":"1","key":"2851_CR25","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1038\/s41398-023-02592-2","volume":"13","author":"M Malgaroli","year":"2023","unstructured":"Malgaroli M, Hull TD, Zech JM, Althoff T. Natural language processing for mental health interventions: a systematic review and research framework. Transl Psychiatry. 2023;13(1):309.","journal-title":"Transl Psychiatry"},{"issue":"1","key":"2851_CR26","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1038\/s44184-024-00056-z","volume":"3","author":"EC Stade","year":"2024","unstructured":"Stade EC, Stirman SW, Ungar LH, Boland CL, Schwartz HA, Yaden DB, et al. Large language models could change the future of behavioral healthcare: a proposal for responsible development and evaluation. Npj Ment Health Res. 2024;3(1):12.","journal-title":"Npj Ment Health Res"},{"issue":"1","key":"2851_CR27","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1038\/s41746-023-00951-3","volume":"6","author":"A Swaminathan","year":"2023","unstructured":"Swaminathan A, Lopez I, Mar RAG, Heist T, McClintock T, Caoili K, et al. Natural language processing system for rapid detection and intervention of mental health crisis chat messages. NPJ Digit Med. 2023;6(1):213.","journal-title":"NPJ Digit Med"},{"key":"2851_CR28","doi-asserted-by":"publisher","first-page":"617","DOI":"10.1016\/j.jad.2019.09.044","volume":"260","author":"CS Wu","year":"2020","unstructured":"Wu CS, Kuo CJ, Su CH, Wang SH, Dai HJ. Using text mining to extract depressive symptoms and to validate the diagnosis of major depressive disorder from electronic health records. J Affect Disord. 2020;260:617\u201323.","journal-title":"J Affect Disord"},{"issue":"3","key":"2851_CR29","doi-asserted-by":"publisher","first-page":"e17984","DOI":"10.2196\/17984","volume":"8","author":"I Spasic","year":"2020","unstructured":"Spasic I, Nenadic G. Clinical text data in machine learning: systematic review. JMIR Med Inf. 2020;8(3):e17984.","journal-title":"JMIR Med Inf"},{"key":"2851_CR30","doi-asserted-by":"publisher","first-page":"100045","DOI":"10.1016\/j.nlp.2023.100045","volume":"6","author":"D Kulkarni","year":"2024","unstructured":"Kulkarni D, Ghosh A, Girdhari A, Liu S, Vance LA, Unruh M, et al. Enhancing pre-trained contextual embeddings with triplet loss as an effective fine-tuning method for extracting clinical features from electronic health record derived mental health clinical notes. Nat Lang Process J. 2024;6:100045.","journal-title":"Nat Lang Process J"},{"issue":"3","key":"2851_CR31","first-page":"411","volume":"30","author":"K Krippendorff","year":"2004","unstructured":"Krippendorff K. Reliability in Content Analysis. Hum Commun Res. 2004;30(3):411\u201333.","journal-title":"Hum Commun Res"},{"key":"2851_CR32","doi-asserted-by":"crossref","unstructured":"Chinchor N, Sundheim BM, editors. MUC-5 evaluation metrics. Fifth Message Understanding Conference (MUC-5): Proceedings of a Conference Held in Baltimore, Maryland, August 25\u201327, 1993; 1993.","DOI":"10.3115\/1072017.1072023"},{"issue":"9","key":"2851_CR33","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1097\/JTO.0b013e3181ec173d","volume":"5","author":"JN Mandrekar","year":"2010","unstructured":"Mandrekar JN. Receiver operating characteristic curve in diagnostic test assessment. J Thorac Oncol. 2010;5(9):1315\u20136.","journal-title":"J Thorac Oncol"},{"issue":"1\u20133","key":"2851_CR34","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.jad.2006.08.020","volume":"99","author":"IH Franken","year":"2007","unstructured":"Franken IH, Rassin E, Muris P. The assessment of anhedonia in clinical and non-clinical populations: further validation of the Snaith\u2013Hamilton pleasure scale (SHAPS). J Affect Disord. 2007;99(1\u20133):83\u20139.","journal-title":"J Affect Disord"},{"issue":"3","key":"2851_CR35","first-page":"83","volume":"20","author":"J Geraci","year":"2017","unstructured":"Geraci J, Wilansky P, de Luca V, Roy A, Kennedy JL, Strauss J. Applying deep neural networks to unstructured text notes in electronic medical records for phenotyping youth depression. BMJ Ment Health. 2017;20(3):83\u20137.","journal-title":"BMJ Ment Health"},{"issue":"9","key":"2851_CR36","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1046\/j.1525-1497.2001.016009606.x","volume":"16","author":"K Kroenke","year":"2001","unstructured":"Kroenke K, Spitzer RL, Williams JB. The PHQ-9: validity of a brief depression severity measure. J Gen Intern Med. 2001;16(9):606\u201313.","journal-title":"J Gen Intern Med"}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-025-02851-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-025-02851-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-025-02851-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T14:58:56Z","timestamp":1736780336000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-025-02851-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,13]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["2851"],"URL":"https:\/\/doi.org\/10.1186\/s12911-025-02851-w","relation":{},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,13]]},"assertion":[{"value":"26 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Institutional review board approval of the study protocol, including a waiver of Health Insurance Portability and Accountability Act authorization, was obtained from WCG IRB (reference # 1-1470336-1) prior to study conduct, and covers data originating from all sites represented. WCG IRB reviewed the protocol against the Common Rule and determined that it was exempt from ongoing IRB oversight and review and from obtaining informed consent as per exemptions outlined in 45 CFR \u00a7\u00a046.104(d)(4).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare the following financial interests\/personal relationships which may be considered as potential competing interests: AV, EOCP, LW, DK and AGirdhari report current employment with and equity ownership in Holmusk Technologies, Inc. AGhosh, MU, KMYC and JS report previous employment with and equity ownership in Holmusk Technologies, Inc.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"20"}}