automating the contextualization of population-based cdss in
TRANSCRIPT
Hadi Kharrazi, MHI, MD, PhD
Johns Hopkins [email protected]
Automating the Contextualization of Population-Based CDSS in Tethered EHR/PHRs
DHSI/CPHIT Grand RoundOct.19.2012
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
2
Hadi Kharrazi reports having a financial relationship with Indiana University from Aug 2008 to Aug 2012.
Hadi Kharrazi reports having a financial relationship with Johns Hopkins University since Aug 2012.
Hadi Kharrazi reports that he has no financial relationship with any commercial interest.
Disclosures
Speaker: Hadi Kharrazi, MHI, MD, PhD
Health Sciences Informatics Grand Rounds Oct 19.2012
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
3
Describe the types of HIT solutions (e.g., EHR, PHR) and how they complement Population Health IT (PopHI)
Explain the relationship among CPGs, CDS languages, and CDS systems
Demonstrate how CDSS can be automated and applied in the context of PopHI
Explain how population-based CDSS can bridge the gap between clinical informatics and PubHI
Discuss the opportunities and challenges of population-based CDSS
Lecture Objectives
Title: Automating the Contextualization of Population-Based CDSS in Tethered EHR/PHRs
Speaker: Hadi Kharrazi, MHI, MD, PhD
Health Sciences Informatics Grand Rounds Oct 19.2012
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
4
Introduction
Backgroundo Clinical Informatics (CI)o Public Health Informatics (PubHI)o Health Information Exchange (HIE) role in PubHIo Population Health Informatics (PopHI) - bridging the gap between CI and PubHIo Clinical Decision Support (CDS) continuum and PopHI
Regenstrief Institute / INPC / Indiana HIE
Previous Worko Developing renewable CDS systemso Application and results of CDS automation in INPC RMRSo Contextualizing CDSS in CHI Platforms (PHR)o Population-based CDSS
Center for Population Health IT (CPHIT) / Future Work
Q & A
The presentation in a nutshell
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
6
• Hadi Kharrazi, MHI, MD, PhD
“You are a doctor who is lost in cyberspace!” (my wife)
Current affiliation: JHSPH-HPM (Aug 2012)Associate Director CPHITDirector: Dr. J. Weiner
Previous affiliation: Indiana UniversityDalhousie University
Research interests: Population Health IT CDSS/QM in HIE environments
Personal Health Records (PHR)
Introduction
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
7
Molecular Research Health Research
Introduction
Biomedical informatics as a basic science
Basic Research
Applied Research
Biomedical informatics methods, techniques, and theories
Bioinformatics
ImagingInformatics
ClinicalInformatics
Public HealthInformatics
Consumer HealthInformatics
PopHI
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
9
Background > Clinical Informatics (CI)
Administrative
Accounting
Clinical Inpatient
Clinical Outpatient
Imaging
Laboratory
Clin
ical
Inf
orm
atio
n Sy
stem
s
EHREMRJHH EPR
Clinical Informatics
CDSS
If patient has x, y then do z
QM, KD…
Non-clinical
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
10
EHR
2
Background > Public Health Informatics (PubHI)
Public Health InformaticsClaims
Non-clinical
Registries
Commun. Diseases
SyndromicSurveillance
Quality Measures
EHR
1
Reports
?
?
Public Health
Periodic public reports and alerts
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
11
EHR
n
EHR
…
Background > Health Information Exchange (HIE)
EHR
1
Other sources
HIE
Public Health Informatics
Registries
Commun. Diseases
SyndromicSurveillance
Quality Measures
Public Health
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
12
Population Health Info.
Background > Population Health Informatics (PopHI)
Population Health Data-warehouse
HIE Public Health Informatics
A
B
C
Publ
ic H
ealth
Clin
ical
Inf
orm
atic
s
Personal Health
Records
Population Health Analytics
Insurance Data
Admin data repositoriesRx Data
CI
to P
ubH
I
CI
to P
ubH
I
PubH
Ito
CI
PubH
Ito
CI
EHRs
1…n
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
13
Background > Clinical Decision Support (CDS) Continuum
Publ
ic H
ealth
Inf
o
Clin
ical
Inf
orm
atic
s
Bio
info
rmat
ics
Org
aniz
atio
nal I
nfo.
Population Health Informatics
If patient has x, y and lives in Baltimore
then do z’
If patient has x, y and is in high risk
population then do z’
If patient has x, y and is Hispanic then do z’
If patient has x, y with insurance q then do z’
If patient has x, y, and gene w
then do z’
If patient has x, y and you don’t have an MRI
then do z’
If patient has x, y then do z
If patient has x, y, has gene w, lives in Baltimore, is high risk, is Hispanic, has insurance q, and more population health rules…, and you don’t have an MRI then do z”
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
14
Regenstrief Institute / INPC / Indiana HIE
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
15
• Established in 1969 by philanthropist Sam Regenstrief
• Regenstrief receives $3 million per year in core support from the Regenstrief Foundation
• Annual operating budget of approximately $23 million derived from grants and contracts
• Logical Observation Identifiers Names and Codes (LOINC) system, a standard nomenclature that enables the electronic transmission of clinical data from laboratories
• Regenstrief Medical Records System (RMRS) was developed 35 yrs ago. RMRS has a database of 6 million patients, with 900 million on-line coded results, 20 million full reports including diagnostic studies, procedure results, operative notes and discharge summaries, and 65 million radiology images.
• Indiana Network for Patient Care (INPC) was created in 1996. It is a city-wide clinical informatics network of 11 different hospital facilities and more than 100 geographically distributed clinics and day surgery facilities
Copyright Regenstrief Institute
Regenstrief Institute > INPC
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
16
The Indiana HIE (IHIE) includes (as of mid-2011):
• Federated Consistent Databases• 22 hospital systems ~70 hospitals• 5 large medical groups and clinics & 5 payors• Several free-standing labs and imaging centers• State and local public health agencies• 10.75 million unique patients• 20 million registration events • 3 billion coded results • 38 million dictated reports • 9 million radiology reports • 12 million drug orders• 577,000 EKG tracings• 120 million radiology images
Copyright Regenstrief Institute
Regenstrief Institute > Indiana HIE (IHIE)
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
17
Copyright Regenstrief Institute
Regenstrief Institute > PubHI > ELR Data Completeness
Overhage JM, Grannis S, McDonald CJ. Am J Public Health. 2008 Feb
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
18
Copyright Regenstrief Institute
Regenstrief Institute > PubHI > Timeliness of Data (CC vs ICD9)
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
19
Copyright Regenstrief Institute
Regenstrief Institute > PubHI > Notifiable Condition Detector (NCD)
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
20
Copyright Regenstrief Institute
Regenstrief Institute > PubHI > Syndromic Surveillance Service (SSS)
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
22
AHRQ’s NGC (guideline.gov)
*Blood Pressure, Weight/Body Mass Index (BMI) - Every visit. For adults: Blood pressure target goal <130/80 mm Hg; BMI (body mass index) <25 kg/m2.
For children: Blood pressure target goal <90th percentile adjusted for age, height, and gender; BMI-for-age <85th percentile.
Foot Exam (for adults) - Thorough visual inspection every diabetes care visit; pedal pulses, neurological exam yearly.
Dilated Eye Exam (by trained expert) - Type 1: Five years post diagnosis, then every year.
Depression - Probe for emotional/physical factors linked to depression yearly; treat aggressively with counseling, medication, and/or referral.
Arden Syntax:
logic:if (creatinine is not number) or (calcium is
not number) or(phosphate is not number) then
conclude false;endif;product := calcium * phosphate;
-----------------------------------------------------CARE Language:
BEGIN BLOCK CHOLESTEROL
DEFINE "MALE_PT" {VALUE} AS "SEX" IS = 'M'DEFINE "CHOLESTEROL LAST" AS LAST "CHOL TESTS" [BEFORE "DATE"] EXIST IF "CHOLESTEROL LAST" WAS AFTER 5 YEARS AGOTHEN EXIT CHOLESTEROLELSE CONTINUE
Computerized CPGs (Know.Rep.Lang.)
mysql_connect(‘localhost’, ‘root’, ‘pass’, ‘ehr');
mysql_query(‘SELECT patient_id FROM patient WHERE patient.Fname = ‘peter’ AND patient.Lname = ‘Johnson’’);
$results = mysql_fetch();
$patient_id = $results[‘patient_id’];
mysql_query (‘SELECT * FROM lab WHERE patient_id = $patient_id’ and lab_term = ‘HBA1c’);
$results = mysql_fetch();
$lab_result = $results[‘lab_term’];
IF ($lab_result > 9){ECHO “Patient has a high HBA1c level”;
}
Computerized DSS
Patient has diabetes and has not had an eye exam in two years. Based on guideline xxx you may want to consider asking for an eye consultation.
Popup alert
Previous Work > Developing Renewable CDSS
Clinical Practice Guidelines
Computerized CPG(CARE, Arden syntax)
Manual Programming for each CPG
Relational DB
One patient at the time
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
23
Issues with current CDSS
Often successful CDS RCTs are not replicable (renewable) in other clinical settings.
CDS knowledge interchange standards have existed for as long as clinical data interchange standards (about 2 decades), yet sharing of computable, actionable knowledge in practice is extremely limited
Current computerized knowledge languages representing CPGs are not standardized: Arden syntax, CARE, GELLO, GLIF
The majority of the current CDSS systems are hard coded, as experienced in a simpler format in CHI studies, which make them very limited due to maintenance issues.
Previous Work > Developing Renewable CDSS
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
24
Previous Work > Developing Renewable CDSS
Clinical Practice Guidelines
Computerized CPG(CARE, Arden syntax)
Manual Programming for each CPG
Relational DB 1
One patient at the time All patient at the time
Automated for all CPGs
CDSS SQL 1
CDSSSQL 2
CDSSSQL…
CDSSSQL n
Relational DB 2
Relational DB…
Relational DB n
NQF QM eMeasures
Population Health Informatics
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
25
Phases to Develop Renewable CDSS
1. Lexical Integration (mapping of idiosyncratic codes to standard terms)
2. Syntactic Mapping of Different Concrete Representation Languages
Parse original content as XML (e.g., Chaperon)
XSLT Transformation (e.g., SAXON)
3. Semantic Integration of Procedural Knowledge into Declarative Rules (SQL commands)
4. Pragmatic Integration (query enhancements, implementation and evaluation)
Previous Work > Developing Renewable CDSS
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
26
Previous Work > Developing Renewable CDSS
Generating Renewable CDSS
CPG NQF
CAREArden
XMLCDSSSQL 1
CPG
Con
sort
ium
Syntactic Mapping
Semantic Integration
Relational DB 1
CDSSSQL 2
CDSSSQL…
CDSSSQL n
Relational DB 2
Relational DB…
Relational DB n
Rene
wab
le
Lexical Integration
XSLT trans.
Pragmatic Integration
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
27
Previous Work > Developing Renewable CDSS
Language Specific Language Free
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
28
Previous Work > Developing Renewable CDSS
Sample CARE Rule Block
BEGIN BLOCK CHOLESTEROL
DEFINE "MALE_PT" {VALUE} AS "SEX" IS = 'M'
DEFINE "CHOLESTEROL LAST" AS LAST "CHOL TESTS" [BEFORE "DATE"] EXIST
IF "CHOLESTEROL LAST" WAS AFTER 5 YEARS AGOTHEN EXIT CHOLESTEROLELSE CONTINUE
IF "MALE_PT" EXISTS AND "AGE" WAS >= 35THEN REMIND Male patients over the age of 35 should have their total cholesterol measured every 5 years.AND ORDER CHOLESTEROL (SCREEN)AND SAVE "UNO" AS "CHOL_SCN" {INTEGER}AND EXIT CHOLESTEROL
END BLOCK CHOLESTEROL
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
29
Previous Work > Developing Renewable CDSS
Intermediate XML
<?xml version="1.0" encoding="UTF-8"?><rule xmlns="http://regenstrief.org/xcare"> <let name="AGE"> <and> <filter>
<reference name="BIRTH"/> <and> <not-equal op="NE" component="VALUE">
<literal type="integer" value="0"/> </not-equal> <less-than op="LT" component="VALUE">
<literal type="time" value="now"/> </less-than> </and>
</filter> <division>
<subtraction> <literal type="time" value="now"/> <reference name="BIRTH"/>
</subtraction> <literal type="real" value="365.25"/>….
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
30
Previous Work > Developing Renewable CDSS
SQL Statement (adaptable for new schemas)
SELECT id,sys_id_value,numeric_value,time_value,text_value,boolean_value,code_value,data_type,institution_id,patient_id,service_code,primary_time FROM(
select t_from.* from (SELECT id,sys_id_value,numeric_value,time_value,text_value,boolean_value,code_value,data_type,institution_id,patient_id,service_code,primary_time ,
myrankFROM(
SELECT * FROM(SELECT
id,sys_id_value,numeric_value,time_value,text_value,boolean_value,code_value,data_type,institution_id,patient_id,service_code,primary_time, rank() OVER
(PARTITION BY INSTITUTION_ID,PATIENT_ID ORDER BY primary_time DESC) myrank FROM (select TO_NUMBER(NULL) as id,To_NUMBER(NULL) as sys_id_value,1 as numeric_value,DATE_OF_BIRTH as time_value, TO_CHAR(NULL) as text_value,To_CHAR(null) as boolean_value,TO_CHAR(NULL) as code_value,'T' as data_type, …
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
31
Limitations
The process does not start directly with free text CPG. Knowledge Representation languages such as CARE or Arden are required.
If originating CPG does not conform to a standard terminology, lexical integration is required again.
Fuzzy or probabilistic representational languages are currently not incorporated.
Mismatched data granularity or ignored data sets will create database integration complicated.
Each CDSS SQL is mutually exclusive of other CDSS thus limiting the merger of SQLs that can result in a combined CDSS.
Previous Work > Developing Renewable CDSS
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
32
Application Areas
Clinical: CDSS reminder rules (e.g., CPOE integration) popup CDSS alerts for providers
Population-based:
o Healthcare quality measures (e.g., NQF, ACO) Quality monitoring dashboard
o Consumer Health Informatics (e.g., tethered PHRs)
o Public Health Informatics (PHI) (e.g., notifiable complex conditions)
o Transition of care (e.g., CCD-based CDSS for inpatient to outpatient)
Previous Work > Developing Renewable CDSS
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
33
Previous Work > CDSS Application in EHR
RMRS sample database was used in this research
a subset of the INPC database
CLINICAL_VARIABLE 42,666,350 records
PATIENT 453,518 (unique)
INSTITUTION 118 providers
CARE KRL 74 Rules (SQL)
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
34
Previous Work > CDSS Application in EHR
Rules Population One patient*
CD4_1.sql 59 0.18CHOLESTEROL_1.sql 180 0.11CHOLESTEROL_2.sql 1 0.12DIABETES_1.sql 541 0.56DIABETES_2.sql 1561 0.47DIABETES_3.sql 182 0.40DIABETES_4.sql 121 0.40DIABETES_5.sql 1620 1.51
…. … …
TCL_2.sql 67 0.12TCL_3.sql 69 0.18TCL_4.sql 61 0.17TETANUS_SHOT_1.sql 1 0.07WHOLE_1.sql 127 0.16WHOLE_2.sql 129 0.13
Average (sec) 1249 0.73
Runtime per second
* each row shows average of 20 individual runs
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
35
Previous Work > CDSS Application in EHR
Some rules are never hit for institute 1 (not shown in this diagram)
Applying all applicable CARE rules for Institute-1
0
10000
20000
30000
40000
50000
60000
70000
OBFO
RM_1.sql
OBFO
RM_3.sql
OBFO
RM_2.sql
OBFO
RM_5.sql
MEDICIN
E_2.sql
PREVENT_PAP_1.sql
PREVENT_STO
OL_2.sql
CHOLESTERO
L_2.sql
CHOLESTERO
L_1.sql
PREVENT_M
AM_2.sql
PNVX2_1.sql
FLU_SH
OT_4.sql
HEPVAX_B_1.sql
FLU_SH
OT_3.sql
PEDS_10.sql
PEDS_11.sql
PEDS_1.sql
PEDS_7.sql
PEDS_8.sql
PEDS_9.sql
TETANUS_SH
OT_1.sql
LIPID_MAN
AGEM
ENT_1.sql
TCL_2.sql
FLU_SH
OT_1.sql
PREVENT_M
AM_3.sql
K_2.sql
DIABETES_1.sql
PREVENT_STO
OL_4.sql
WHO
LE_2.sql
TCL_1.sql
DIABETES_5.sql
FLU_SH
OT_5.sql
K_1.sql
PREVENT_M
AM_1.sql
OBFO
RM_6.sql
IDC_REM_1.sql
TCL_4.sql
WHO
LE_1.sql
CD4_1.sql
PREVENT_STO
OL_1.sql
TCL_3.sql
HIV_PT_1.sql
MEDICIN
E_1.sql
Institute 1: All CDS Hits (regardless of missed proportion)
applicable CARE rules
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
36
Previous Work > CDSS Application in EHR
Academic/Primary hospitals have the highest rates of hitsThis peak might be simply because of their higher population of patients (needs population adjustment)
Number of CARE rule hits against the RMRS sample database based on each healthcare provider / institute (zero-hit institutes are removed)
0
100,000
200,000
300,000
400,000
500,000
600,000
700,000
800,000
900,000
1,000,000
11 1 25 118
124
120
20 47 2 7
103 9
116
31 109
110
102
123
22 13 125
18 14 16 21 107
119
23 46 48 114
15 5 30 32 17 29 49 40 43 56 41 44 55
Total Hits
Academic Hospitals
institutes
0
10000
20000
30000
40000
50000
60000
70000
OBFO
RM_1.sql
OBFO
RM_3.sql
OBFO
RM_2.sql
OBFO
RM_5.sql
MEDICIN
E_2.sql
PREVENT_PAP_1.sql
PREVENT_STO
OL_2.sql
CHOLESTERO
L_2.sql
CHOLESTERO
L_1.sql
PREVENT_M
AM_2.sql
PNVX2_1.sql
FLU_SH
OT_4.sql
HEPVA
X_B_1.sql
FLU_SH
OT_3.sql
PEDS_10.sql
PEDS_11.sql
PEDS_1.sql
PEDS_7.sql
PEDS_8.sql
PEDS_9.sql
TETANUS_SH
OT_1.sql
LIPID_MAN
AGEM
ENT_1.sql
TCL_2.sql
FLU_SH
OT_1.sql
PREVENT_M
AM_3.sql
K_2.sql
DIABETES_1.sql
PREVENT_STO
OL_4.sql
WHOLE_2.sql
TCL_1.sql
DIABETES_5.sql
FLU_SH
OT_5.sql
K_1.sql
PREVENT_M
AM_1.sql
OBFO
RM_6.sql
IDC_REM
_1.sql
TCL_4.sql
WHOLE_1.sql
CD4_1.sql
PREVENT_STO
OL_1.sql
TCL_3.sql
HIV_PT_1.sql
MEDICIN
E_1.sql
Institute 1: All CDS Hits (regardless of missed proportion)
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
37
Previous Work > CDSS Application in EHR
Percentage of rule hits is suddenly smaller in the left side of the diagram (i.e., primary hospitals)
Number of CARE rule hits against the RMRS sample database based on ever healthcare provider institute (population adjusted percentage)
0.00%
10.00%
20.00%
30.00%
40.00%
50.00%
60.00%
70.00%
80.00%
90.00%
100.00%
11 1
25
118
124
120
20
47 2 7
103 9
116
31
109
110
102
123
22
13
125
18
14
16
21
107
119
23
46
48
114
15 5
30
32
17
29
49
40
43
56
41
44
55
Adj Population
Other Hospitals
Percentage of rule hits is larger in the right side of the diagram (i.e., other hospitals)
Percentage > creates higher patient risk at a certain instituteRaw number > forms internal policies / economical road maps
0
100,000
200,000
300,000
400,000
500,000
600,000
700,000
800,000
900,000
1,000,000
11 1 25
118
124
120
20
47 2 7
103 9
116
31
109
110
102
123
22
13
125
18
14
16
21
107
119
23
46
48
114
15 5 30
32
17
29
49
40
43
56
41
44
55
Total Hits
institutes
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
38
Previous Work > CDSS Application in EHR
Institute versus Rules (Raw Numbers) (zero rules / zero institutes are removed)
institutes
rules
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
39
Previous Work > CDSS Application in EHR
Manual process of deciphering the rules (hit-means-miss OR hit-means-hit-only)The lower the better (less missed)
Missed applicable CARE rules for institute-1(CDSS-generated QM fingerprint)
0.00%
5.00%
10.00%
15.00%
20.00%
25.00%
30.00%
HIV_PT_1.sql
MEDICIN
E_1.sql
PREVENT_M
AM_1.sql
TCL_3.sql
WHOLE_1.sql
DIABETES_1.sql
PEDS_8.sql
FLU_SH
OT_5.sql
TCL_2.sql
TETANUS_SHO
T_1.sql
MEDICIN
E_2.sql
TCL_4.sql
FLU_SH
OT_4.sql
K_1.sql
OBFO
RM_5.sql
PREVENT_STO
OL_2.sql
CHOLESTERO
L_2.sql
FLU_SH
OT_3.sql
PREVENT_STO
OL_1.sql
PREVENT_PAP_1.sql
DIABETES_5.sql
OBFO
RM_1.sql
PEDS_10.sql
PNVX2_1.sql
OBFO
RM_6.sql
OBFO
RM_2.sql
CHOLESTERO
L_1.sql
WHOLE_2.sql
PREVENT_STO
OL_4.sql
LIPID_MAN
AGEMEN
T_1.sql
PEDS_11.sql
IDC_REM_1.sql
PEDS_9.sql
FLU_SH
OT_1.sql
OBFO
RM_3.sql
K_2.sql
CD4_1.sql
TCL_1.sql
PEDS_1.sql
PEDS_7.sql
PREVENT_M
AM_3.sql
PREVENT_M
AM_2.sql
HEPVAX_B_1.sql
Institute 1: Percentage of Hit / Miss Rules
Percent
%13.49Avg
applicable CARE rules
~12.3%
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
40
0.00%
5.00%
10.00%
15.00%
20.00%
25.00%
30.00%
CD4_1.sql
FLU_SH
OT_1.sql
HIV_PT_1.sql
IDC_REM_1.sql
OBFO
RM_6.sql
PEDS_7.sql
PEDS_9.sql
TCL_4.sql
WHOLE_2.sql
PREVENT_PAP_1.sql
FLU_SH
OT_4.sql
PEDS_1.sql
PEDS_8.sql
OBFO
RM_2.sql
TETANUS_SHO
T_1.sql
PEDS_11.sql
OBFO
RM_3.sql
MEDICIN
E_2.sql
CHOLESTERO
L_1.sql
CHOLESTERO
L_2.sql
FLU_SH
OT_3.sql
K_2.sql
K_1.sql
PREVENT_M
AM_3.sql
OBFO
RM_1.sql
PEDS_10.sql
PNVX2_1.sql
OBFO
RM_5.sql
TCL_2.sql
LIPID_MAN
AGEM
ENT_1.sql
HEPVAX_B_1.sql
PREVENT_STO
OL_4.sql
PREVENT_STO
OL_2.sql
PREVENT_M
AM_2.sql
Institute 2: Inverse Percentage of Hit / Miss Rules
Percent
%3.47Avg
Previous Work > CDSS Application in EHR
Manual process of deciphering the rules (hit-means-miss OR hit-means-hit-only)The lower the better (less missed)
Missed applicable CARE rules for institute-2(CDSS-generated QM fingerprint)
applicable CARE rules
~5.5%
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
41
Previous Work > CDSS Application in EHR
The effect size of the missed rules depends on the population size.
Missed rate by institute
institutes
rules
RulesMissed %
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
42
Previous Work > CDSS Application in EHR
Web Interface (http://aurora.regenstrief.org:8080/ClinicalKnowledgeHub/)
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
43
Previous Work > CDSS Application in EHR
Preventive Care Quality Improvement Reminder Forms
Applying all CARE rules against the RMRS sample database
Copyright Regenstrief Institute
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
44
Previous Work > CDSS Application in PHR
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
45
Previous Work > CDSS Application in PHR
Dynamically generated CDSS SQL commands
CHI Framework (Tx Group)
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
46
Traditional PubHI versus CDSS-based PopHI
Previous Work > Population-based CDSS
Item Traditional CDSS-based
Focus n-Patient-at-a-time 1-Patient-at-a-time
Model Statistical (probabilistic) CPG (rule-based)
Updatability Delayed (Hard coded) Immediate (Dynamic)
HIE Integration Possible Already Exists
Portability Major Change Req. Minimal Change Req.
Data Source EHR Subsets (limited) Complete EHR, PHR, …
Contextualization Complex SQL Driven
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
47
Consider the potentials with Population-based CDSS integration Copyright Regenstrief Institute
Previous Work > Population-based CDSS
Simple statistics based on numerical statistics
PopHI will reveal the
causes, and…
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
49
The Johns Hopkins Center for Population Health Information Technology
(CPHIT, or “see-fit”)
The mission of CPHIT is to improve the health and wellbeing of populations by advancing the state-of-the-art of Health Information Technology and e-health tools used by public health agencies and private health care organizations.
CPHIT’s focus will be on the application of EHRs, PHRs and other digitally-supported health improvement interventions targeted at communities, special need populations and groups of consumers cared for by integrated delivery systems.
Director: Dr. J. Weiner
www.jhsph.edu/cphit
CPHIT / Future Work
Copyright Dr. J. Weiner
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
50
CPHIT / Future Work
Copyright Dr. J. Weiner
CPHIT
JH Health System
External PH/IDS Orgs.
JHU Academic Departments
and other R&D centers
JH Healthcare Solutions,
LLC
BusinessPartners
IndustryFoundations Government
CPHIT Organizational Linkages
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
51
2009 HITECH Policies
Sta
ge 1
Sta
ge 2
Sta
ge 3
Meaningful Use
CPHIT / Future Work
HIT-Enabled Health Reform
2011 Criteria(Capture & Share)
2013 Criteria(CDSS) 2015 Criteria
(Improved Outcome)
Population Health Informatics
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
52
MPI
CPHIT / Future Work
Federated Consistent Databases(1) Data gathered centrally in separate physical files, “mirrors” of remote sites;
(2) Standardized at the time it comes in.
Population-based CDSS across databases
Population-based HIE
EHRs
Claims
PACS LABs
Registries
PHRs
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
53
ProviderHIE
EHREHR
ACO
Patient
CPHIT / Future Work
EHR
PHR
CPOE
Rx
Labs
Insurance
Imaging
Sensors…
Outpatient
CDSS
PDSS
Tethered
Public Health
Predictive Modeling
Risk Assess.
MU1
MU2
MU3
CPG
EHR
Quality Measure
Care Manage.
Pay for Perform. Po
pula
tion
Hea
lth I
nfor
mat
ics
2.0
© Hadi Kharrazi @ JHSPH-HPM
Automating Population-Based CDSS …
54
CPHIT’s initial R&D Priorities: Natural language processing (NLP) and pattern recognition that improve
population based interventions.
Effective approaches for integration of consumer-focused m-health/PHRs/ e-health with provider-focused EHRs.
Development of “e-measures” of population health status, risk, safety/quality using EHR/HIT systems.
EHR based tools to identify high risk populations for preventive and/or chronic care outreach.
Approaches for integrating current functions of public health agencies into interoperable EHR networks.
Approaches for applying HIT to population-based evidence-generation / research.
CPHIT / Future Work
Copyright Dr. J. Weiner