Title: Reuse of Data Coded with High-Quality Terminologies: Practical Examples from Patient Care Settings
1Reuse of Data Coded with High-Quality
Terminologies Practical Examples from Patient
Care Settings
- James J. Cimino, M.D.
- Department of Biomedical Informatics
- Columbia University College of Physicians and
Surgeons
2Case Presentation
- The patient is a 50 year old, Native American
female who present to the emergency room with the
chief complaint of cough and chest pain. The
patient reports that she has had a productive
cough for three days but that chest pain
developed one hour ago. - She gives a history of hypertension and states
that she was getting a "capsule, half green, half
blue-green" from her private doctor. She also
reports that she was treated in the past for
tuberculosis while she was pregnant, but doesn't
remember what she was treated with or for how
long. She reports that she was at another
hospital on the other side of town, where she had
a liver biopsy. She reports that she thinks the
diagnosis was Hepatitis C. - The patient reports an allergy to Bufferin.
- Physical examination revealed a well-developed,
well-nourished female in moderate respiratory
distress. Vital signs showed a pulse of 90, a
respiratory rate of 22, an oral temperature of
100.3, and a blood pressure of 150/100.
Examination revealed rales and rhonchi in the
left upper chest. Abdominal exam revealed a
tender, palpable liver edge. - Labs
- Chem7 (serum) Glucose 100 (70-105) Chem7
(plasma) Glucose 150 (75-110) - CBC Hgb 15 (12.0-15.8), Hct 45 (42.4-48.0), WBC
11,000 (3,540-9,060), Plate. 145K (165-415K) - A fingerstick blood sugar was 80
- Urinalysis showed protein of 1 and glucose of 0
- A blood culture was positive for
methicillin-resistant Staphylococcus aureus
(MRSA) - ECG - Sinus Rhythm, 74BPM, Axis -30 degrees, ST
segment 2mm elevated and - T-waves down in leads I, L, V5 and V6
- Chest X-ray Left upper lobe infiltrate, left
ventricular hypertrophy - The patient was admitted to the hospital, started
on antibiotics and aspirin. - A medical student reviewing the case is concerned
about the risk of MRSA in patients with pneumonia
and a recent myocardial infarction. She decides
to do a literature search.
3Case Presentation
- The patient is a 50 year old, Native American
female who present to the emergency room with the
chief complaint of cough and chest pain. The
patient reports that she has had a productive
cough for three days but that chest pain
developed one hour ago. - She gives a history of hypertension and states
that she was getting a "capsule, half green, half
blue-green" from her private doctor. She also
reports that she was treated in the past for
tuberculosis while she was pregnant, but doesn't
remember what she was treated with or for how
long. She reports that she was at another
hospital on the other side of town, where she had
a liver biopsy. She reports that she thinks the
diagnosis was Hepatitis C. - The patient reports an allergy to Bufferin.
- Physical examination revealed a well-developed,
well-nourished female in moderate respiratory
distress. Vital signs showed a pulse of 90, a
respiratory rate of 22, an oral temperature of
100.3, and a blood pressure of 150/100.
Examination revealed rales and rhonchi in the
left upper chest. Abdominal exam revealed a
tender, palpable liver edge. - Labs
- Chem7 (serum) Glucose 100 (70-105) Chem7
(plasma) Glucose 150 (75-110) - CBC Hgb 15 (12.0-15.8), Hct 45 (42.4-48.0), WBC
11,000 (3,540-9,060), Plate. 145K (165-415K) - A fingerstick blood sugar was 80
- Urinalysis showed protein of 1 and glucose of 0
- A blood culture was positive for
methicillin-resistant Staphylococcus aureus
(MRSA) - ECG - Sinus Rhythm, 74BPM, Axis -30 degrees, ST
segment 2mm elevated and - T-waves down in leads I, L, V5 and V6
- Chest X-ray Left upper lobe infiltrate, left
ventricular hypertrophy - The patient was admitted to the hospital, started
on antibiotics and aspirin. - A medical student reviewing the case is concerned
about the risk of MRSA in patients with pneumonia
and a recent myocardial infarction. She decides
to do a literature search.
4Use and Reuse of Clinical Data
- a) Automate the admission of the patient to a bed
- b) Summarize the patients blood sugar tests,
including serum, plasma and fingerstick (but not
urine) - c) Use patient history to help with automated
reminders - d) Aggregate the patients data for quality
assurance - e) Use patient history to prevent adverse drug
reactions - f) Use the laboratory test results for automated
diagnosis - g) Use the patients data to automate information
retrieval - h) Aggregate the patients data for epidemiologic
studies
5Automate the admission of the patient to a bed
- Patient is an 50 year old, Native American
female
6Automate the admission of the patient to a bed
- But how does the computer know that the patient
is female? - The record could say
- female
- Female
- FEMALE
- F
- Woman
- Girl
7Automate the admission of the patient to a bed
- Data element - gender
- Controlled terminology
- Male
- Female
- Unknown (dont know)
- Unknown (cant tell)
- Representation
- M,F,U1,U2
- 0,1,2,3
- What about other values?
- Genotypic
- Phenotypic
- Administrative
8Automate the admission of the patient to a bed
9Requirements for High-Quality Terminology
- Synonymy (not redundancy)
- Multiple levels of granularity
10Information Form and Reuse
11Information Form and Reuse
12Summarize patients blood sugar tests, including
serum, plasma and fingerstick (but not urine)
13Requirements for High-Quality Terminology
- Synonymy (not redundancy)
- Multiple levels of granularity
14New York Presbyterian HospitalClinical
Information Systems Architecture
15MED Structure
Medical Entity
CHEM-7
Plasma Glucose Test
16The MED Today
- Concept-based (101,130)
- Multiple hierarchy (150,480)
- Synonyms (250,000)
- Translations (180,000)
- Semantic links (180,000)
- Attributes (240,000)
17Using the MED for Summary Reporting
Lab Display
Serum Glucose Test
Fingerstick Glucose Test
Plasma Glucose Test
18(No Transcript)
19(No Transcript)
20(No Transcript)
21DOP Summary
Summarize patients blood sugar tests, including
serum, plasma and fingerstick (but not urine)
22WebCIS Summary
Summarize patients blood sugar tests, including
serum, plasma and fingerstick (but not urine)
23Eclipsys Summary
Summarize patients blood sugar tests, including
serum, plasma and fingerstick (but not urine)
24489 Tuberculosis Codes in ICD9-CM
Use patient history for automated reminders
011. PULMONARY TUBERCULOSIS 012. OTHER
RESPIRATORY TB 013. CNS TUBERCULOSIS 014. INTEST
INAL TB 015. TB OF BONE AND JOINT 016. GENITOURI
NARY TB 017. TUBERCULOSIS NEC 018. MILIARY
TUBERCULOSIS
- 010. PRIMARY TB INFECTION
- 010.0 PRIMARY TB COMPLEX
- 010.00 PRIM TB COMPLEX-UNSPEC
- 010.01 PRIM TB COMPLEX-NO EXAM
- 010.02 PRIM TB COMPLEX-EXM UNKN
- 010.03 PRIM TB COMPLEX-MICRO DX
- 010.04 PRIM TB COMPLEX-CULT DX
- 010.05 PRIM TB COMPLEX-HISTO DX
- 010.06 PRIM TB COMPLEX-OTH TEST
010.1 PRIMARY TB PLEURISY 010.8 PRIM PROGRESSIVE
TB NEC 010.9 PRIMARY TB INFECTION NOS
25More Tuberculosis in ICD9-CM
Use patient history for automated reminders
- 137. LATE EFFECT TUBERCULOSIS
- 137.0 LATE EFFECT TB, RESP/NOS
- 137.1 LATE EFFECT CNS TB
- 137.2 LATE EFFECT GU TB
- 137.3 LATE EFF BONE JOINT TB
- 137.4 LATE EFFECT TB NEC
- 647. INFECTIVE DIS IN PREG
- 647.3 TUBERCULOSIS IN PREG
- 647.30 TB IN PREG-UNSPECIFIED
- 647.31 TUBERCULOSIS-DELIVERED
- 647.32 TUBERCULOSIS-DELIV W P/P
- 647.33 TUBERCULOSIS-ANTEPARTUM
- 647.34 TUBERCULOSIS-POSTPARTUM
26Use patient history for automated reminders
Tuberculosis Infection
27Requirements for High-Quality Terminology
- Synonymy (not redundancy)
- Multiple levels of granularity
- Data model has terms too
28Reuse the patients data for quality assurance
29Reuse the patients data for quality assurance
select patient_id , time primary_time from
visit2004_diagnosis where diagnosis_code
2618 and b.primary_time between '01/01/2000'
and '01/01/2005' and b.comp_code 28144
30Use patient history to prevent drug reactions
- Method 1 Write a rule to check for each reaction
- Method 2 Include allergy codes for each
medication - Method 3 Include definitional information and
infer
Aspirin
Bufferin
Enteric-Coated Aspirin
IF allergic drug X has ingredient Y AND
ordered drug Z has ingredient Y THEN send
alert
31Requirements for High-Quality Terminology
- Synonymy (not redundancy)
- Multiple levels of granularity
- Data model has terms too
- Multiple hierarchies
- Include definitional knowledge
32Use test results for automated diagnosis
Serum Potassium Test
Hypokalemia
33Use test results for automated diagnosis
34Use test results for automated diagnosis
35Use test results for automated diagnosis
36Requirements for High-Quality Terminology
- Synonymy (not redundancy)
- Multiple levels of granularity
- Data model has terms too
- Multiple hierarchies
- Include definitional knowledge
- Support automated translation
37Use data for automated information retrieval
38(No Transcript)
39(No Transcript)
40(No Transcript)
41(No Transcript)
42(No Transcript)
43(No Transcript)
44(No Transcript)
45Reuse the patients data for epidemiologic studies
1995
1996
Diagnosis ICD9-CM Code ICD9-CM Name
Hepatitis A 070.1 Hepatitis A
Hepatitis B 070.3 Hepatitis B
Hepatitis C 070.5 Hepatitis NEC
Hepatitis E 070.5 Hepatitis NEC
Diagnosis ICD9-CM Code ICD9-CM Name
Hepatitis A 070.1 Hepatitis A
Hepatitis B 070.3 Hepatitis B
Hepatitis C 070.4 Hepatitis C
Hepatitis E 070.5 Hepatitis NEC
46Requirements for High-Quality Terminology
- Synonymy (not redundancy)
- Multiple levels of granularity
- Data model has terms too
- Multiple hierarchies
- Include definitional knowledge
- Support automated translation
- Avoid Not Elsewhere Classified (NEC)
47Reuse the patients data for epidemiologic studies
NEC
- Can never have a formal definition
- Terminology changes induce semantic drift
48Accommodating NEC
49Accommodating NEC
Viral Hepatitis
Hepatitis A
Hepatitis, NEC
Hepatitis B
Hepatitis E
Hepatitis C
50Accommodating NEC
Viral Hepatitis
Hepatitis A
Retired
Hepatitis B
Hepatitis C
Hepatitis E
51Use and Reuse of Clinical Data
- a) Automate the admission of the patient to a bed
- b) Summarize the patients blood sugar tests,
including serum, plasma and fingerstick (but not
urine) - c) Use patient history to help with automated
reminders - d) Aggregate the patients data for quality
assurance - e) Use patient history to prevent adverse drug
reactions - f) Use the laboratory test results for automated
diagnosis - g) Use the patients data to automate information
retrieval - h) Aggregate the patients data for epidemiologic
studies
52Requirements for High-Quality Terminology
- Synonymy (not redundancy)
- Multiple levels of granularity
- Data model has terms too
- Multiple hierarchies
- Include definitional knowledge
- Support automated translation
- Avoid Not Elsewhere Classified (NEC)
53Requirements for High-Quality Terminology
- MED has features of a high-quality terminology
- MED supports reuse of clinical data
- Try to find high-quality standards
- How do you determine terminology quality?