Limits...
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 (2014)

Bottom Line: In particular, depressed patients exhibit largely unpredictable responses to treatment.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.

View Article: PubMed Central - PubMed

Affiliation: Stanford Center for Biomedical Informatics Research, Stanford University, Stanford, California, USA.

Show MeSH

Related in: MedlinePlus

Selection of depression and control cohorts from the Palo Alto Medical Foundation (PAMF) dataset. ICD-9, International Classification of Diseases, Ninth Revision.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4215055&req=5

AMIAJNL2014002733F1: Selection of depression and control cohorts from the Palo Alto Medical Foundation (PAMF) dataset. ICD-9, International Classification of Diseases, Ninth Revision.

Mentions: We used EHR data from the Palo Alto Medical Foundation (PAMF) and Group Health Research Institute (GHRI), both of which use the Epic EHR system. From the 1.16 million patients in the PAMF dataset, we selected 5000 depressed patients and 30 000 non-depressed patients (see the ‘PAMF cohort definition and validation’ section and figure 1). From the 600 000 patients in the GHRI dataset, we extracted a subset of 5651 patients treated for depression who have been scored using the Patient Health Questionnaire (PHQ-9) both at the start of treatment and after 90 days of treatment. The PHQ-9 is used for screening, diagnosing, and assessing the severity of depression; it comprises nine questions that are each worth three points, for a total score ranging from 0 to 27, divided into bins from minimal to severe depression (table 1).


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 (2014)

Selection of depression and control cohorts from the Palo Alto Medical Foundation (PAMF) dataset. ICD-9, International Classification of Diseases, Ninth Revision.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4215055&req=5

AMIAJNL2014002733F1: Selection of depression and control cohorts from the Palo Alto Medical Foundation (PAMF) dataset. ICD-9, International Classification of Diseases, Ninth Revision.
Mentions: We used EHR data from the Palo Alto Medical Foundation (PAMF) and Group Health Research Institute (GHRI), both of which use the Epic EHR system. From the 1.16 million patients in the PAMF dataset, we selected 5000 depressed patients and 30 000 non-depressed patients (see the ‘PAMF cohort definition and validation’ section and figure 1). From the 600 000 patients in the GHRI dataset, we extracted a subset of 5651 patients treated for depression who have been scored using the Patient Health Questionnaire (PHQ-9) both at the start of treatment and after 90 days of treatment. The PHQ-9 is used for screening, diagnosing, and assessing the severity of depression; it comprises nine questions that are each worth three points, for a total score ranging from 0 to 27, divided into bins from minimal to severe depression (table 1).

Bottom Line: In particular, depressed patients exhibit largely unpredictable responses to treatment.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.

View Article: PubMed Central - PubMed

Affiliation: Stanford Center for Biomedical Informatics Research, Stanford University, Stanford, California, USA.

Show MeSH
Related in: MedlinePlus