{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T12:32:40Z","timestamp":1775478760505,"version":"3.50.1"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T00:00:00Z","timestamp":1676246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T00:00:00Z","timestamp":1676246400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100002301","name":"Eesti Teadusagentuur","doi-asserted-by":"publisher","award":["PSG721"],"award-info":[{"award-number":["PSG721"]}],"id":[{"id":"10.13039\/501100002301","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Brain Inf."],"published-print":{"date-parts":[[2023,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Major Depressive Disorder (MDD) is one of the most common and comorbid mental disorders that impacts a person\u2019s day-to-day activity. In addition, MDD affects one\u2019s linguistic footprint, which is reflected by subtle changes in speech production. This allows us to use natural language processing (NLP) techniques to build a neural classifier to detect depression from speech transcripts. Typically, current NLP systems discriminate only between the depressed and non-depressed states. This approach, however, disregards the complexity of the clinical picture of depression, as different people with MDD can suffer from different sets of depression symptoms. Therefore, predicting individual symptoms can provide more fine-grained information about a person\u2019s condition. In this work, we look at the depression classification problem through the prism of the symptom network analysis approach, which shifts attention from a categorical analysis of depression towards a personalized analysis of symptom profiles. For that purpose, we trained a multi-target hierarchical regression model to predict individual depression symptoms from patient\u2013psychiatrist interview transcripts from the DAIC-WOZ corpus. Our model achieved results on par with state-of-the-art models on both binary diagnostic classification and depression severity prediction while at the same time providing a more fine-grained overview of individual symptoms for each person. The model achieved a mean absolute error (MAE) from 0.438 to 0.830 on eight depression symptoms and showed state-of-the-art results in binary depression estimation (73.9 macro-F1) and total depression score prediction (3.78 MAE). Moreover, the model produced a symptom correlation graph that is structurally identical to the real one. The proposed symptom-based approach provides more in-depth information about the depressive condition by focusing on the individual symptoms rather than a general binary diagnosis.<\/jats:p>","DOI":"10.1186\/s40708-023-00185-9","type":"journal-article","created":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T09:05:38Z","timestamp":1676279138000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Towards automatic text-based estimation of depression through symptom prediction"],"prefix":"10.1186","volume":"10","author":[{"given":"Kirill","family":"Milintsevich","sequence":"first","affiliation":[]},{"given":"Kairit","family":"Sirts","sequence":"additional","affiliation":[]},{"given":"Ga\u00ebl","family":"Dias","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,13]]},"reference":[{"key":"185_CR1","unstructured":"WHO  (2017) Depression and other common mental disorders: global health estimates. Technical report, World Health Organization"},{"key":"185_CR2","doi-asserted-by":"crossref","unstructured":"American Psychiatric Association (2013) Diagnostic and Statistical Manual of Mental Disorders, 5th edn. American Psychiatric Pub, Arlington","DOI":"10.1176\/appi.books.9780890425596"},{"key":"185_CR3","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.jad.2013.11.021","volume":"156","author":"S Rodgers","year":"2014","unstructured":"Rodgers S, Holtforth MG, M\u00fcller M, Hengartner MP, R\u00f6ssler W, Ajdacic-Gross V (2014) Symptom-based subtypes of depression and their psychosocial correlates: a person-centered approach focusing on the influence of sex. Journal of Affective Disorders 156:92\u2013103","journal-title":"Journal of Affective Disorders"},{"key":"185_CR4","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1016\/j.jad.2015.10.040","volume":"190","author":"M Ten Have","year":"2016","unstructured":"Ten Have M, Lamers F, Wardenaar K, Beekman A, de Jonge P, van Dorsselaer S, Tuithof M, Kleinjan M, de Graaf R (2016) The identification of symptom-based subtypes of depression: A nationally representative cohort study. J Affect Disord 190:395\u2013406","journal-title":"J Affect Disord"},{"issue":"5","key":"185_CR5","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1017\/S1351324916000383","volume":"23","author":"RA Calvo","year":"2017","unstructured":"Calvo RA, Milne DN, Hussain MS, Christensen H (2017) Natural language processing in mental health applications using non-clinical texts. Natural Language Engineering 23(5):649\u2013685","journal-title":"Natural Language Engineering"},{"issue":"1","key":"185_CR6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41746-019-0211-0","volume":"3","author":"S Chancellor","year":"2020","unstructured":"Chancellor S, De Choudhury M (2020) Methods in predictive techniques for mental health status on social media: a critical review. NPJ Digital Med 3(1):1\u201311","journal-title":"NPJ Dgital Med"},{"key":"185_CR7","doi-asserted-by":"crossref","unstructured":"Mallol-Ragolta A, Zhao Z, Stappen L, Cummins N, Schuller B (2019) A hierarchical attention network-based approach for depression detection from transcribed clinical interviews","DOI":"10.21437\/Interspeech.2019-2036"},{"key":"185_CR8","doi-asserted-by":"crossref","unstructured":"Xezonaki D, Paraskevopoulos G, Potamianos A, Narayanan S (2020) Affective conditioning on hierarchical attention networks applied to depression detection from transcribed clinical interviews. In: Interspeech (INTERSPEECH), pp. 4556\u20134560","DOI":"10.21437\/Interspeech.2020-2819"},{"key":"185_CR9","doi-asserted-by":"publisher","first-page":"1040","DOI":"10.1016\/j.jad.2021.09.001","volume":"295","author":"Z Dai","year":"2021","unstructured":"Dai Z, Zhou H, Ba Q, Zhou Y, Wang L, Li G (2021) Improving depression prediction using a novel feature selection algorithm coupled with context-aware analysis. J Affect Disord 295:1040\u20131048","journal-title":"J Affect Disord"},{"key":"185_CR10","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1146\/annurev-clinpsy-050212-185608","volume":"9","author":"D Borsboom","year":"2013","unstructured":"Borsboom D, Cramer AO (2013) Network analysis: an integrative approach to the structure of psychopathology. Ann Rev Clin Psychol 9:91\u2013121","journal-title":"Ann Rev Clin Psychol"},{"key":"185_CR11","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.brat.2016.06.006","volume":"86","author":"RJ McNally","year":"2016","unstructured":"McNally RJ (2016) Can network analysis transform psychopathology? Behav Res Ther 86:95\u2013104","journal-title":"Behav Res Ther"},{"issue":"3","key":"185_CR12","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1002\/da.23136","volume":"38","author":"T Kaiser","year":"2021","unstructured":"Kaiser T, Herzog P, Voderholzer U, Brakemeier E-L (2021) Unraveling the comorbidity of depression and anxiety in a large inpatient sample: Network analysis to examine bridge symptoms. Depression and anxiety 38(3):307\u2013317","journal-title":"Depression and anxiety"},{"key":"185_CR13","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.jpsychires.2018.11.016","volume":"109","author":"M Price","year":"2019","unstructured":"Price M, Legrand AC, Brier ZM, H\u00e9bert-Dufresne L (2019) The symptoms at the center: examining the comorbidity of posttraumatic stress disorder, generalized anxiety disorder, and depression with network analysis. J Psychiatr Res 109:52\u201358","journal-title":"jJ Psychiatr Res"},{"issue":"12","key":"185_CR14","doi-asserted-by":"publisher","first-page":"1219","DOI":"10.1001\/jamapsychiatry.2015.2079","volume":"72","author":"C van Borkulo","year":"2015","unstructured":"van Borkulo C, Boschloo L, Borsboom D, Penninx BW, Waldorp LJ, Schoevers RA (2015) Association of symptom network structure with the course of depression. JAMA Psychiatry 72(12):1219\u20131226","journal-title":"JAMA Psychiatry"},{"key":"185_CR15","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1016\/j.jad.2015.09.005","volume":"189","author":"EI Fried","year":"2016","unstructured":"Fried EI, Epskamp S, Nesse RM, Tuerlinckx F, Borsboom D (2016) What are\u2019good\u2019depression symptoms? comparing the centrality of dsm and non-dsm symptoms of depression in a network analysis. J Affect Disord 189:314\u2013320","journal-title":"J Affect Disord"},{"key":"185_CR16","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.jad.2020.03.078","volume":"271","author":"S-C Park","year":"2020","unstructured":"Park S-C, Kim D (2020) The centrality of depression and anxiety symptoms in major depressive disorder determined using a network analysis. J Affect Disord 271:19\u201326","journal-title":"J Affect Disord"},{"issue":"1","key":"185_CR17","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1186\/s12916-015-0325-4","volume":"13","author":"EI Fried","year":"2015","unstructured":"Fried EI, Nesse RM (2015) Depression sum-scores don\u2019t add up: why analyzing specific depression symptoms is essential. BMC Med 13(1):72. https:\/\/doi.org\/10.1186\/s12916-015-0325-4","journal-title":"BMC Med"},{"key":"185_CR18","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.cobeha.2017.07.005","volume":"18","author":"SC Guntuku","year":"2017","unstructured":"Guntuku SC, Yaden DB, Kern ML, Ungar LH, Eichstaedt JC (2017) Detecting depression and mental illness on social media: an integrative review. Curr Opin Behav Sci 18:43\u201349","journal-title":"Curr Opin Behav Sci"},{"issue":"1","key":"185_CR19","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/0272-7358(88)90050-5","volume":"8","author":"AT Beck","year":"1988","unstructured":"Beck AT, Steer RA, Carbin MG (1988) Psychometric properties of the Beck Depression Inventory: Twenty-five years of evaluation. Clinical Psychology Review 8(1):77\u2013100. https:\/\/doi.org\/10.1016\/0272-7358(88)90050-5","journal-title":"Clinical Psychol Rev"},{"key":"185_CR20","doi-asserted-by":"crossref","unstructured":"Hamilton M (1986) The hamilton rating scale for depression. In: Assessment of Depression, pp. 143\u2013152. Springer, Berlin","DOI":"10.1007\/978-3-642-70486-4_14"},{"key":"185_CR21","doi-asserted-by":"publisher","unstructured":"Kroenke K, Strine TW, Spitzer RL, Williams JBW, Berry JT, Mokdad AH (2009) The PHQ-8 as a measure of current depression in the general population. Journal of Affective Disorders 114(1\u20133):163\u2013173. https:\/\/doi.org\/10.1016\/j.jad.2008.06.026. Accessed 2021-06-03","DOI":"10.1016\/j.jad.2008.06.026"},{"key":"185_CR22","unstructured":"Gratch J, Artstein R, Lucas G, Stratou G, Scherer S, Nazarian A, Wood R, Boberg J, DeVault D, Marsella S, et\u00a0al. (2014) The distress analysis interview corpus of human and computer interviews. In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC\u201914), pp. 3123\u20133128"},{"key":"185_CR23","doi-asserted-by":"crossref","unstructured":"Niu M, Chen K, Chen Q, Yang L (2021) Hcag: A hierarchical context-aware graph attention model for depression detection. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4235\u20134239","DOI":"10.1109\/ICASSP39728.2021.9413486"},{"issue":"5","key":"185_CR24","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1109\/MIS.2019.2925204","volume":"34","author":"SA Qureshi","year":"2019","unstructured":"Qureshi SA, Saha S, Hasanuzzaman M, Dias G (2019) Multitask representation learning for multimodal estimation of depression level. IEEE Intelli Systems 34(5):45\u201352. https:\/\/doi.org\/10.1109\/MIS.2019.2925204","journal-title":"IEEE Intell Syst"},{"issue":"3","key":"185_CR25","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1109\/MCI.2020.2998234","volume":"15","author":"SA Qureshi","year":"2020","unstructured":"Qureshi SA, Dias G, Hasanuzzaman M, Saha S (2020) Improving depression level estimation by concurrently learning emotion intensity. IEEE Comput Intell Mag 15(3):47\u201359","journal-title":"IEEE Comput Intell Mag"},{"key":"185_CR26","doi-asserted-by":"crossref","unstructured":"Qureshi SA, Dias G, Saha S, Hasanuzzaman M (2021) Gender-aware estimation of depression severity level in a multimodal setting. In: International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138","DOI":"10.1109\/IJCNN52387.2021.9534330"},{"key":"185_CR27","unstructured":"Hong S, Cohn A, Hogg DC (2022) Using graph representation learning with schema encoders to measure the severity of depressive symptoms. In: International Conference on Learning Representations (ICLR)"},{"key":"185_CR28","doi-asserted-by":"publisher","unstructured":"Mao K, Zhang W, Wang DB, Li A, Jiao R, Zhu Y, Wu B, Zheng T, Qian L, Lyu W, Ye M, Chen J (2022) Prediction of depression severity based on the prosodic and semantic features with bidirectional lstm and time distributed cnn. IEEE Transactions on Affective Computing. https:\/\/doi.org\/10.1109\/TAFFC.2022.3154332","DOI":"10.1109\/TAFFC.2022.3154332"},{"issue":"2","key":"185_CR29","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1109\/JBHI.2015.2503985","volume":"21","author":"G Gaut","year":"2015","unstructured":"Gaut G, Steyvers M, Imel ZE, Atkins DC, Smyth P (2015) Content coding of psychotherapy transcripts using labeled topic models. IEEE journal of biomedical and health informatics 21(2):476\u2013487","journal-title":"IEEE journal of biomedical and health informatics"},{"key":"185_CR30","doi-asserted-by":"crossref","unstructured":"Delahunty F, Johansson R, Arcan M (2019) Passive diagnosis incorporating the phq-4 for depression and anxiety. In: Proceedings of the Fourth Social Media Mining for Health Applications (# SMM4H) Workshop & Shared Task, pp. 40\u201346","DOI":"10.18653\/v1\/W19-3205"},{"key":"185_CR31","doi-asserted-by":"crossref","unstructured":"Yadav S, Chauhan J, Sain JP, Thirunarayan K, Sheth A, Schumm J (2020) Identifying depressive symptoms from tweets: Figurative language enabled multitask learning framework. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 696\u2013709","DOI":"10.18653\/v1\/2020.coling-main.61"},{"key":"185_CR32","doi-asserted-by":"crossref","unstructured":"Yazdavar AH, Al-Olimat HS, Ebrahimi M, Bajaj G, Banerjee T, Thirunarayan K, Pathak J, Sheth A (2017) Semi-supervised approach to monitoring clinical depressive symptoms in social media. In: Proceedings of the 2017 IEEE\/ACM International Conference on Advances in Social Networks Analysis and Mining 2017, pp. 1191\u20131198","DOI":"10.1145\/3110025.3123028"},{"key":"185_CR33","doi-asserted-by":"crossref","unstructured":"Nguyen T, Yates A, Zirikly A, Desmet B, Cohan A (2022) Improving the generalizability of depression detection by leveraging clinical questionnaires. arXiv preprint arXiv:2204.10432","DOI":"10.18653\/v1\/2022.acl-long.578"},{"key":"185_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2021.106734","volume":"120","author":"X Yao","year":"2021","unstructured":"Yao X, Yu G, Tang J, Zhang J (2021) Extracting depressive symptoms and their associations from an online depression community. Computers in human behavior 120:106734","journal-title":"Computers in human behavior"},{"issue":"1","key":"185_CR35","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.cmpb.2015.03.008","volume":"120","author":"C Karmen","year":"2015","unstructured":"Karmen C, Hsiung RC, Wetter T (2015) Screening internet forum participants for depression symptoms by assembling and enhancing multiple nlp methods. Computer Methods Programs Biomed 120(1):27\u201336","journal-title":"Computer Methods Programs Biomed"},{"key":"185_CR36","unstructured":"Davcheva E (2019) Classifying mental health conditions via symptom identification: A novel deep learning approach. In: International Conference of Information Systems, 2019"},{"key":"185_CR37","doi-asserted-by":"publisher","unstructured":"Yang Z, Yang D, Dyer C, He X, Smola A, Hovy E (2016) Hierarchical Attention Networks for Document Classification. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1480\u20131489. Association for Computational Linguistics, San Diego, California . https:\/\/doi.org\/10.18653\/v1\/N16-1174. http:\/\/aclweb.org\/anthology\/N16-1174 Accessed 2021-06-03","DOI":"10.18653\/v1\/N16-1174"},{"key":"185_CR38","unstructured":"Ba JL, Kiros JR, Hinton GE (2016) Layer normalization. arXiv preprint arXiv:1607.06450"},{"key":"185_CR39","doi-asserted-by":"crossref","unstructured":"Reimers N, Gurevych I (2019) Sentence-bert: Sentence embeddings using siamese bert-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. http:\/\/arxiv.org\/abs\/1908.10084","DOI":"10.18653\/v1\/D19-1410"},{"key":"185_CR40","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692"},{"key":"185_CR41","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"key":"185_CR42","unstructured":"Sanh V, Debut L, Chaumond J, Wolf T (2019) Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108"},{"key":"185_CR43","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast R-CNN. arXiv:1504.08083","DOI":"10.1109\/ICCV.2015.169"},{"key":"185_CR44","unstructured":"Dodge J, Ilharco G, Schwartz R, Farhadi A, Hajishirzi H, Smith NA (2020) Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping. CoRR abs\/2002.06305"},{"issue":"5","key":"185_CR45","first-page":"216","volume":"5","author":"H Borchani","year":"2015","unstructured":"Borchani H, Varando G, Bielza C, Larranaga P (2015) A survey on multi-output regression. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 5(5):216\u2013233","journal-title":"Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery"},{"key":"185_CR46","doi-asserted-by":"crossref","unstructured":"Van\u00a0Borkulo CD, van Bork R, Boschloo L, Kossakowski JJ, Tio P, Schoevers RA, Borsboom D, Waldorp LJ (2022) Comparing network structures on three aspects: A permutation test. Psychological methods","DOI":"10.1037\/met0000476"},{"key":"185_CR47","doi-asserted-by":"crossref","unstructured":"Li J, Chen X, Hovy E, Jurafsky D (2015) Visualizing and understanding neural models in nlp. arXiv preprint arXiv:1506.01066","DOI":"10.18653\/v1\/N16-1082"},{"key":"185_CR48","unstructured":"Sundararajan M, Taly A, Yan Q (2017) Axiomatic attribution for deep networks. In: International Conference on Machine Learning, pp. 3319\u20133328. PMLR"}],"container-title":["Brain Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40708-023-00185-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40708-023-00185-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40708-023-00185-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T09:07:47Z","timestamp":1676279267000},"score":1,"resource":{"primary":{"URL":"https:\/\/braininformatics.springeropen.com\/articles\/10.1186\/s40708-023-00185-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,13]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["185"],"URL":"https:\/\/doi.org\/10.1186\/s40708-023-00185-9","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-2096670\/v1","asserted-by":"object"}]},"ISSN":["2198-4018","2198-4026"],"issn-type":[{"value":"2198-4018","type":"print"},{"value":"2198-4026","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,13]]},"assertion":[{"value":"23 September 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 February 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All authors have seen and approved the current version of the paper.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"4"}}