--- title: "Personalize depression tx: predict dx, severity. | Sutter Health" description: "We develop and evaluate computational models that use EHR data to predict the diagnosis and severity of depression, and response to treatment." url: "https://www.sutterhealth.org/research/publications/personalize-depression-tx-predict-dx-severity-1055312636" --- 1. [Home](https://www.sutterhealth.org/) / 2. [Research](https://www.sutterhealth.org/research) / 3. [Research publications](https://www.sutterhealth.org/research/publications) / 4. Personalize depression tx: predict dx, severity. # Toward personalizing treatment for depression: predicting diagnosis and severity. Huang SH, LePendu P, Iyer SV, Tai-Seale M, Carrell D, & Shah NH. _J Am Med Inform Assoc. pii: amiajnl-2014-002733. doi: 10.1136/amiajnl-2014-002733. \[Epub ahead of print\]_ 2014-07-02 ## Abstract OBJECTIVE: Depression is a prevalent disorder difficult to diagnose and treat. In particular, depressed patients exhibit largely unpredictable responses to treatment. Toward the goal of personalizing treatment for depression, we develop and evaluate computational models that use electronic health record (EHR) data for predicting the diagnosis and severity of depression, and response to treatment. MATERIALS AND METHODS: We develop regression-based models for predicting depression, its severity, and response to treatment from EHR data, using structured diagnosis and medication codes as well as free-text clinical reports. We used two datasets: 35 000 patients (5000 depressed) from the Palo Alto Medical Foundation and 5651 patients treated for depression from the Group Health Research Institute. RESULTS: Our models are able to predict a future diagnosis of depression up to 12 months in advance (area under the receiver operating characteristic curve (AUC) 0.70-0.80). We can differentiate patients with severe baseline depression from those with minimal or mild baseline depression (AUC 0.72). Baseline depression severity was the strongest predictor of treatment response for medication and psychotherapy. CONCLUSIONS: It is possible to use EHR data to predict a diagnosis of depression up to 12 months in advance and to differentiate between extreme baseline levels of depression. The models use commonly available data on diagnosis, medication, and clinical progress notes, making them easily portable. The ability to automatically determine severity can facilitate assembly of large patient cohorts with similar severity from multiple sites, which may enable elucidation of the moderators of treatment response in the future. [PubMed abstract](http://www.ncbi.nlm.nih.gov/pubmed/24988898) ## Research topics - [Medical Informatics](https://www.sutterhealth.org/research-search-results?query=%22%5C%22Medical+Informatics%5C%22%22) - [Mental Health](https://www.sutterhealth.org/research-search-results?query=%22%5C%22Mental+Health%5C%22%22) ## Related publications [View all publications](https://www.sutterhealth.org/research-search-results?verticalKey=research_publication) - Publication ### [Balancing digital information-sharing and patient privacy when engaging families in the intensive care unit.](https://www.sutterhealth.org/research/publications/digital-info-sharing-pt-privacy-families-icu-1055312450) Brown SM, Aboumatar HJ, Francis L, Halamka J, Rozenblum R, Rubin E, Sarnoff Lee B, Sugarman J, Turner K, Vorwaller M, Frosch DL; Privacy, Access, and Engagement Task Force of the Libretto Consortium of the Gordon and Betty Moore Foundation. J Am Med Inform Assoc. pii: ocv182. doi: 10.1093/jamia/ocv182. \[Epub ahead of print\] 2016 Mar 16 - Publication ### [Serious mental illness and health-related factors associated with regional emergency department utilization.](https://www.sutterhealth.org/research/publications/serious-mental-illness-and-regional-er-use-1055312801) Azar KMJ, Petersen JP, Shen Z, Nasrallah C, Pesa J, LaMori J, Pressman A. Popul Health Manag. doi: 10.1089/pop.2019.0161. \[Epub ahead of print\] 2019 Dec 09 - Publication ### [Physicians’ well-being linked to in-basket messages generated by algorithms In electronic health records.](https://www.sutterhealth.org/research/publications/md-well-being-and-in-basket-messages-from-ehr-algorithms-1055312699) Tai-Seale M, Dillon EC, Yang Y, Nordgren R, Steinberg R, Nauenberg T, Lee TC, Meehan A, Li J, Chan AS, Frosch D. Health Aff. 38(7): https://doi.org/10.1377/hlthaff.2018.05509. 2019 Jul 01 - Publication ### [Variability in engagement and progress in efficacious integrated collaborative care for primary care patients with obesity and depression: within-treatment analysis in the RAINBOW trial.](https://www.sutterhealth.org/research/publications/obesity-depression-rainbow-trial-within-treatment-analysis-1055312741) Lv N, Xiao L, Majd M, Lavori PW, Smyth JM, Rosas LG, Venditti EM, Snowden MB, Lewis MA, Ward E, Lesser L, Williams LM, Azar KMJ, Ma J. PLoS One. 15(4):e0231743. doi: 10.1371/journal.pone.0231743. eCollection 2020. 2020 Apr 21 - Publication ### [The relationship between primary care physician burnout and patient-reported care experiences: a cross-sectional study.](https://www.sutterhealth.org/research/publications/primary-care-md-burnout-and-pt-reported-care-experiences-1055312771) Chung S, Dillon EC, Meehan AE, Nordgren R, Frosch DL. J Gen Intern Med. doi: 10.1007/s11606-020-05770-w. \[Epub ahead of print\]. 2020 Mar 23 [View all publications](https://www.sutterhealth.org/research-search-results?verticalKey=research_publication) ```json {"@context":"https://schema.org","@type":"MedicalOrganization","name":"Sutter Health","@id":"https://www.sutterhealth.org/#medicalorganization","url":"https://www.sutterhealth.org","logo":"https://www.sutterhealth.org/static/images/sutter-health-logo.svg","address":{"@type":"PostalAddress","streetAddress":"2200 River Plaza Drive","addressLocality":"Sacramento","addressRegion":"CA","postalCode":"95833","addressCountry":"US"},"areaServed":{"@type":"AdministrativeArea","name":"California"},"sameAs":["https://www.facebook.com/SutterHealth","https://www.instagram.com/sutterhealth/","https://x.com/SutterHealth","https://www.youtube.com/sutterhealth","https://www.linkedin.com/company/sutter-health","https://en.wikipedia.org/wiki/Sutter_Health"]} ``` ```json {"@context":"https://schema.org","@type":"BreadcrumbList","@id":"https://www.sutterhealth.org/research/publications/personalize-depression-tx-predict-dx-severity-1055312636#breadcrumblist","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://www.sutterhealth.org/"},{"@type":"ListItem","position":2,"name":"Research","item":"https://www.sutterhealth.org/research"},{"@type":"ListItem","position":3,"name":"Research publications","item":"https://www.sutterhealth.org/research/publications"},{"@type":"ListItem","position":4,"name":"Personalize depression tx: predict dx, severity."}]} ``` ```json {"@context":"https://schema.org","@type":"MedicalScholarlyArticle","@id":"https://www.sutterhealth.org/research/publications/personalize-depression-tx-predict-dx-severity-1055312636#medicalscholarlyarticle","name":"Toward personalizing treatment for depression: predicting diagnosis and severity.","headline":"Personalize depression tx: predict dx, severity.","abstract":"OBJECTIVE: Depression is a prevalent disorder difficult to diagnose and treat. In particular, depressed patients exhibit largely unpredictable responses to treatment. Toward the goal of personalizing treatment for depression, we develop and evaluate computational models that use electronic health record (EHR) data for predicting the diagnosis and severity of depression, and response to treatment. MATERIALS AND METHODS: We develop regression-based models for predicting depression, its severity, and response to treatment from EHR data, using structured diagnosis and medication codes as well as free-text clinical reports. We used two datasets: 35 000 patients (5000 depressed) from the Palo Alto Medical Foundation and 5651 patients treated for depression from the Group Health Research Institute. RESULTS: Our models are able to predict a future diagnosis of depression up to 12 months in advance (area under the receiver operating characteristic curve (AUC) 0.70-0.80). We can differentiate patients with severe baseline depression from those with minimal or mild baseline depression (AUC 0.72). Baseline depression severity was the strongest predictor of treatment response for medication and psychotherapy. CONCLUSIONS: It is possible to use EHR data to predict a diagnosis of depression up to 12 months in advance and to differentiate between extreme baseline levels of depression. The models use commonly available data on diagnosis, medication, and clinical progress notes, making them easily portable. The ability to automatically determine severity can facilitate assembly of large patient cohorts with similar severity from multiple sites, which may enable elucidation of the moderators of treatment response in the future.","description":"We develop and evaluate computational models that use EHR data to predict the diagnosis and severity of depression, and response to treatment.","keywords":["Medical Informatics","Mental Health"],"datePublished":"2014-07-02","url":"https://www.sutterhealth.org/research/publications/personalize-depression-tx-predict-dx-severity-1055312636","inLanguage":"en-US","identifier":[{"@type":"PropertyValue","propertyID":"PMID","value":"24988898"},{"@type":"PropertyValue","propertyID":"DOI","value":"10.1136/amiajnl-2014-002733"}],"sameAs":["https://pubmed.ncbi.nlm.nih.gov/24988898/","https://doi.org/10.1136/amiajnl-2014-002733"],"isPartOf":{"@type":"Periodical","name":"J Am Med Inform Assoc"},"author":[{"@type":"Person","name":"Huang SH"},{"@type":"Person","name":"LePendu P"},{"@type":"Person","name":"Iyer SV"},{"@type":"Person","name":"Tai-Seale M"},{"@type":"Person","name":"Carrell D"},{"@type":"Person","name":"Shah NH"}],"sourceOrganization":{"@type":"MedicalOrganization","name":"Palo Alto Medical Foundation Research Institute"},"about":[{"@type":"DefinedTerm","name":"Medical Informatics","url":"https://www.sutterhealth.org/research-search-results?facets=%5B%7B%22i%22%3A%22c_researchTopics.name%22%2C%22v%22%3A%5B%22Medical+Informatics%22%5D%7D%5D&verticalKey=research_publication"},{"@type":"DefinedTerm","name":"Mental Health","url":"https://www.sutterhealth.org/research-search-results?facets=%5B%7B%22i%22%3A%22c_researchTopics.name%22%2C%22v%22%3A%5B%22Mental+Health%22%5D%7D%5D&verticalKey=research_publication"}],"mainEntityOfPage":{"@type":"WebPage","@id":"https://www.sutterhealth.org/research/publications/personalize-depression-tx-predict-dx-severity-1055312636","breadcrumb":{"@id":"https://www.sutterhealth.org/research/publications/personalize-depression-tx-predict-dx-severity-1055312636#breadcrumblist"}}} ```