Behavioral Health Dataset
This dataset includes patients who were diagnosed with common mental health diseases, including Substance Use Disorder, Schizophrenia, Bipolar Disorder, Depression, Anxiety and PTSD in 2022. Data contains all the EHR medical history and follow-up including demographics, diagnosis/comorbidities, lab tests, encounters, medications, Height/Weight/BMI, Social Determinant of Health (SDoH) and ADI/SVI.
How big is this Dataset?
The Dataset is huge with approximately 150k+ unique patients and corresponding demographics including Age (at visit in 2022), Sex, Race, Ethnicity, and 3 digit Zip Code. This dataset also includes more than 20,000,000 diagnoses and around 100,000,000 visits.
The dataset is consistent and has all encounter types from 01/2017 - 07/2023. Please note prior to 2017, the outpatient visit data is not comprehensive.
Patients’ count in cohort year(2022) – 151283 patients in total.
Breakdown of the Dataset
|
Mental Health Disease |
Patient Count |
Ratio of whole cohort |
|
Anxiety |
73044 |
48.3% |
|
Depression |
48018 |
31.7% |
|
Substance Use Disorder |
60929 |
40.3% |
|
Schizophrenia |
5632 |
3.7% |
|
Bipolar Disorder |
11901 |
7.9% |
|
PTSD |
5711 |
3.8% |
Who are the Patients?
Breakdown of patients demographic, emphasis on health disparities and equity.
Race
Ethnicity
Gender
What is the available data at glance?
| Domain | Example Variables | Description |
|---|---|---|
|
Person |
Sex, Race, Ethnicity |
Demographic characteristics from EHR |
|
Diagnosis |
Diagnosis Type, Diagnosis name, Diagnosis Priority, Diagnosis Time, ICD Code |
All Medical Diagnosis Records(History and Follow-up) for all patients who are in this cohort. |
|
Encounter |
Encounter ID, Registration or Admission time, Discharge Time, Reason for Visit, Encounter Type |
Healthcare utilization (e.g., ER, inpatient, and outpatient visits) |
|
Medication |
Order Mnemonic, Order Details, Original Order Time, Order Category, Encounter ID |
Lists of all medications with the category name and order details |
|
Health Labs |
Lab Value, Normal High, Normal Low, Event name, Event Time, Encounter ID |
Lab test results on encounter level |
|
BMI/Height/Weight |
Value, Event Name, Encounter ID |
All BMI/Height/Weight Information for all patients who are in this cohort |
|
SVI/ADI |
SVI/ADI Index |
Social Vulnerability Index and Area Deprivation Index based on patient’s residence address, including ADI National Rank, State Rank and SVI 5 RPL_Themes |
|
SDoH |
Event Name, Category, Status, Response |
Social history factors information such as Substance Use, Nutrition, Exercise, Alcohol, Education, Home/Environment |