MSDW Data Model

MSDW ecosystem uses the OHDSI collaborative’s OMOP Common Data Model to facilitate optimal data sharing and interoperability both internally (at Mount Sinai) and externally with research partners. The clinical data are extracted from Mount Sinai’s Epic Caboodle database and other ancillary systems, transformed to the OMOP Common Data Model (CDM) format, and loaded to the MSDW database. These data are updated daily.

 

MSDW Data Contents

The Mount Sinai Data Warehouse (MSDW) collects clinical and operational data for use in clinical and translational research, as well as quality improvement initiatives (see table below).

 

The MSDW provides researchers access to data on patients in the Mount Sinai Health System Epic EHR:

  • Over 12 million patient records
  • Over 105 million patient encounters

 

Table last updated April 5, 2025

OMOP Table Record Type Distinct Patients Record Count
person Patient Demographics 12,208,001 12,208,001
death Patient Date of Death 56,069 56,069
visit_occurrence Mobile Unit Encounter 101,461 172,479
visit_occurrence Inpatient Hospitalization from ED Visit 338,321 659,951
visit_occurrence Hospital Outpatient Visit 1,043,841 3,054,745
visit_occurrence Urgent Care Visit 7,213 7,909
visit_occurrence Chart Documentation Event 6,266,816 117,363,589
visit_occurrence Inpatient Hospitalization 681,721 1,021,069
visit_occurrence Outpatient Visit 4,754,611 95,080,165
visit_occurrence Telehealth Visit 802,493 3,745,062
visit_occurrence ED Visit 1,353,022 3,395,176
condition_occurrence Hospital Problem 959,209 4,021,542
condition_occurrence Encounter Diagnosis 4,381,551 127,499,950
condition_occurrence Billing Diagnosis 2,862,469 76,124,379
condition_occurrence Problem List 2,475,752 13,898,742
measurement Vital Signs 4,007,134 716,509,652
measurement Flowsheet Measurement 1,958,533 261,501,266
measurement Lab Component Result 4,371,190 1,146,648,429
drug_exposure Medication Order with Administration 1,711,561 142,245,037
drug_exposure Outpatient Medication Order with Dispense 29,328 296,563
drug_exposure Immunization Administration 1,183,096 8,143,337
drug_exposure Immunization from Procedure Order 798,103 3,679,305
drug_exposure Outpatient Medication Order 2,876,710 51,170,207
drug_exposure Medication Order with Dispense 1,037,108 16,801,981
drug_exposure Medication Order 1,124,856 14,135,270
drug_exposure Immunization from Medication Order 228,259 296,569
procedure_occurrence Procedure Inferred from Flowsheet 24,571 287,405
procedure_occurrence General Procedure 5,492,499 348,374,383
procedure_occurrence Surgical Procedure 384,309 1,532,320
observation Past Medical History 2,359,903 8,944,387
observation Patient Demographics 12,208,000 65,588,736
observation Family History 1,621,664 71,343,752
observation Surgical History Procedure 1,696,605 3,792,423
observation Allergy 3,589,101 4,359,486
observation Social History 3,495,125 154,304,000
observation Flowsheet Observation 2,345,300 117,567,252
note Lab Component Result Note 2,641,315 18,229,190
note Clinical Note 5,188,559 214,805,982
provider Provider   1,363,281
provider_attribute_xtn Personnel specialty   177,252
provider_attribute_xtn Physician specialty   605,016
location Provider Address   1,363,281
location Care Site Address   15,986
location Patient Address   12,208,000
care_site Service Area   50
care_site Care Area   814
care_site Bed   82,062
care_site Location   2,174
care_site Place of Service   7,255
care_site Department   6,455
care_site Room   7,461
concept EPIC SURGICAL PROCEDURE   36,259
concept EPIC DIAGNOSIS   1,594,594
concept EPIC ALLERGEN   40,559
concept EPIC VISIT TYPE   12,014
concept EPIC PROCEDURE   189,282
concept EPIC IMMUNIZATION   523
concept EPIC FLOWSHEET MEASURE   96,315
concept EPIC LAB COMPONENT   41,627
concept EPIC MEDICATION   142,946
concept EPIC FLOWSHEET TEMPLATE   3,998
vocabulary MSDW Vocabulary   7
vocabulary Epic Vocabulary   89
vocabulary Vocabulary   104
vocabulary PowerPath Vocabulary   8