{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T10:57:48Z","timestamp":1788865068609,"version":"build-2803163510"},"reference-count":49,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Advanced Analytics Grant from IBM and Canadian Institute for Military and Veteran Health Research"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Health Informatics J"],"published-print":{"date-parts":[[2021,10]]},"abstract":"<jats:p>This study proposes a predictive model that uses structured data and unstructured narrative notes from Electronic Medical Records to accurately identify patients diagnosed with Post-Traumatic Stress Disorder (PTSD). We utilize data from primary care clinicians participating in the Manitoba Primary Care Research Network (MaPCReN) representing 154,118 patients. A reference sample of 195 patients that had their PTSD diagnosis confirmed using a manual chart review of structured data and narrative notes, and PTSD negative patients is used as the gold standard data for model training, validation and testing. We assess structured and unstructured data from eight tables in the MaPCReN namely, patient demographics, disease case, examinations, medication, billing records, health condition, risk factors, and encounter notes. Feature engineering is applied to convert data into proper representation for predictive modeling. We explore serial and parallel mixed data models that are trained on both structured and unstructured data to identify PTSD. Model performances were calculated based on a highly skewed hold-out test dataset. The serial model that uses both structured and text data as input, yielded the highest values in sensitivity (0.77), F-measure (0.76), and AUC (0.88) and the parallel model that uses both structured and text data as the input obtained the highest positive predicted value (PPV) (0.75). Diseases such as PTSD are difficult to diagnose. Information recorded in the chart note over multiple visits of the patients with the primary care physicians has higher predictive power than structured data and combining these two data types can increase the predictive capabilities of machine learning models in diagnosing PTSD. While the deep-learning model outperformed the traditional ensemble model in processing text data, the ensemble classifier obtained better results in ingesting a combination of features obtained from both data types in the serial mixed model. The study demonstrated that unstructured encounter notes enhance a model\u2019s ability to identify patients diagnosed with PTSD. These findings can enhance quality improvement, research, and disease surveillance related to PTSD in primary care populations.<\/jats:p>","DOI":"10.1177\/14604582211053259","type":"journal-article","created":{"date-parts":[[2021,11,25]],"date-time":"2021-11-25T01:23:16Z","timestamp":1637803396000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":25,"title":["Diagnosing post-traumatic stress disorder using electronic medical record data"],"prefix":"10.1177","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8602-3240","authenticated-orcid":false,"given":"Hasan","family":"Zafari","sequence":"first","affiliation":[{"name":"Queen\u2019s University, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8401-7878","authenticated-orcid":false,"given":"Leanne","family":"Kosowan","sequence":"additional","affiliation":[{"name":"University of Manitoba, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3326-0875","authenticated-orcid":false,"given":"Farhana","family":"Zulkernine","sequence":"additional","affiliation":[{"name":"Queen\u2019s University, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5436-8394","authenticated-orcid":false,"given":"Alexander","family":"Signer","sequence":"additional","affiliation":[{"name":"University of Manitoba, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2021,11,24]]},"reference":[{"key":"bibr1-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1186\/s12888-015-0399-8"},{"key":"bibr2-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpsychires.2014.08.017"},{"key":"bibr3-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1016\/j.genhosppsych.2013.04.016"},{"key":"bibr4-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1002\/jts.22399"},{"key":"bibr5-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1111\/jep.13587"},{"key":"bibr6-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1080\/09638237.2018.1521946"},{"key":"bibr7-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1177\/1073191115602551"},{"issue":"2","key":"bibr8-14604582211053259","first-page":"185","volume":"48","author":"Marini\u0107 I","year":"2007","journal-title":"Croat Medical Journal"},{"key":"bibr9-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpsychires.2017.09.010"},{"key":"bibr10-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1002\/wps.20150"},{"key":"bibr11-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1016\/j.janxdis.2018.10.004"},{"key":"bibr12-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1186\/s12888-017-1384-1"},{"key":"bibr13-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2015.05.057"},{"key":"bibr14-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1002\/hup.2691"},{"key":"bibr15-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1080\/24725579.2019.1583703"},{"key":"bibr16-14604582211053259","first-page":"837","volume-title":"AMIA Annual Symposium Proceedings","author":"Ma S","year":"2016"},{"key":"bibr17-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-016-0477-6"},{"key":"bibr18-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1370\/afm.1644"},{"key":"bibr19-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1097\/PSY.0b013e31803146d8"},{"key":"bibr20-14604582211053259","first-page":"2825","volume":"12","author":"Pedregosa F","year":"2011","journal-title":"The J Machine Learn Research"},{"key":"bibr21-14604582211053259","unstructured":"Sklearn. \u201csklearn.ensemble.RandomForestClassifier\u201d. scikit-learn developers. https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.ensemble.RandomForestClassifier.html (accessed on 15 June 2021)"},{"key":"bibr22-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-010-0001-0"},{"key":"bibr23-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4992"},{"key":"bibr24-14604582211053259","doi-asserted-by":"crossref","unstructured":"Y Kim. Convolutional neural networks for sentence classification. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1746\u20131751, Doha, Qatar, October 2014. Association for Computational Linguistics.","DOI":"10.3115\/v1\/D14-1181"},{"key":"bibr25-14604582211053259","author":"Brownlee J","year":"2017","journal-title":"Machine Learn Mastery"},{"key":"bibr26-14604582211053259","volume-title":"The functional API","author":"Keras"},{"key":"bibr27-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/6817627"},{"key":"bibr28-14604582211053259","volume-title":"Classification and regression trees","author":"Breiman L","year":"1984"},{"key":"bibr29-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-8-25"},{"key":"bibr30-14604582211053259","volume-title":"Stats.pearsonr","author":"Scipy"},{"key":"bibr31-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1037\/a0036347"},{"key":"bibr32-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2017.2767063"},{"key":"bibr33-14604582211053259","doi-asserted-by":"publisher","DOI":"10.2196\/19739"},{"key":"bibr34-14604582211053259","volume-title":"Deep EHR: Chronic disease prediction using medical notes","author":"Liu J","year":"2018"},{"key":"bibr35-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2019.07.005"},{"key":"bibr36-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99133-7_10"},{"key":"bibr37-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2016.7849886"},{"key":"bibr38-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974348.49"},{"key":"bibr39-14604582211053259","unstructured":"Fleming G, Bruce P. Responsible data science. Mountain View, CA: Google Play Books, 2021, p. 74."},{"key":"bibr40-14604582211053259","volume-title":"\u201cWhen and Why Tree-Based Models (Often) Outperform Neural Networks\u201d","author":"Andre Ye"},{"key":"bibr41-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2013.07.041"},{"key":"bibr42-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1016\/j.seizure.2017.09.010"},{"key":"bibr43-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1080\/16506070801969005"},{"key":"bibr44-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1007\/s00127-014-0855-7"},{"key":"bibr45-14604582211053259","doi-asserted-by":"publisher","DOI":"10.4088\/JCP.14m09475"},{"issue":"12","key":"bibr46-14604582211053259","first-page":"827","volume":"88","author":"Warner CH","year":"2013","journal-title":"Am Family Physician"},{"key":"bibr47-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596486"},{"key":"bibr48-14604582211053259","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-018-0617-7"},{"key":"bibr49-14604582211053259","volume-title":"Many heads are better than one: making the case for ensemble learning","author":"Jay B"}],"container-title":["Health Informatics Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/14604582211053259","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/14604582211053259","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/14604582211053259","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:31:40Z","timestamp":1777501900000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/14604582211053259"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":49,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,10]]}},"alternative-id":["10.1177\/14604582211053259"],"URL":"https:\/\/doi.org\/10.1177\/14604582211053259","relation":{},"ISSN":["1460-4582","1741-2811"],"issn-type":[{"value":"1460-4582","type":"print"},{"value":"1741-2811","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10]]},"article-number":"14604582211053259"}}