IBM Medical Records Text Analytics Solution Helps UNC Healthcare Improve the Quality of Hospital Discharges Session Number ECA-1419A Carlton Moore, MD UNC Healthcare Fiodar Zboichyk IBM.

Download Report

Transcript IBM Medical Records Text Analytics Solution Helps UNC Healthcare Improve the Quality of Hospital Discharges Session Number ECA-1419A Carlton Moore, MD UNC Healthcare Fiodar Zboichyk IBM.

IBM Medical Records Text Analytics
Solution Helps UNC Healthcare Improve
the Quality of Hospital Discharges
Session Number ECA-1419A
Carlton Moore, MD
UNC Healthcare
Fiodar Zboichyk
IBM
Overview
• Hospital Readmission Rates
– Medical and Economic Impact
• Reasons for High Readmission Rates
– Importance of discharge summary
• Proposed NLP solution
– Development issues (example, unstructured, inconsistent)
• Results (sensitivity, specificity)
• Future directions
1
30-Day Hospital Readmission Rates by State
Estimated annual cost to Medicare = $17.4B
Jencks S, Williams M, Coleman E. N Engl J Med 2009; 360 (14): 1418-28
2
Economic Impact on Hospitals
• In 2013 Medicare will start applying financial penalties to hospital with
higher than expected readmission rates
• Other health insurers are likely to follow Medicare’s lead!!
Sample Hospital
Condition
#of
Average
%Higher than
Patients Reimbursement
Expected
Potential Penalty
Heart Failure
600
$5,000
20%
$600,000
Heart Attack
400
$4,000
20%
$320,000
Pneumonia
350
$3,000
15%
$157,500
$1,107,500
Potential Penalty = (# of patients with condition) x (Avg. reimbursement for condition)
x (% Higher than expected)
3
Why are Hospital Readmission Rates So High?
4
Conceptual Framework
Patient discharged with unresolved medical issues
that need to be addressed after leaving hospital
follow-up physician visits
follow-up tests and procedures
Poor communication of
discharge instructions
Discharge instructions
not carried out
Adverse Event
Hospital Readmission
5
Discharge Instructions
a concise action plan
describing what needs
to occur after a patient
leaves the hospital
Only 50% of discharge
summaries are ever
received by patients’
physicians
Definition: condition worsens
because of inappropriate or
inadequate medical care
Discharge Instructions
Types of Discharge Instructions
(693 hospital discharges)
50% not completed
27% no completed
15% not completed
50%
40%
30%
20%
10%
48%
35%
17%
0%
Diagnostic
Physician Referrals
Lab Tests
Procedures
Moore C, McGinn T, Halm E. Arch Intern Med. 2007;167:1305-1311
6
Examples of Discharge Instructions not Completed
Types of Procedure
Reasons for Procedures
CT of Chest
Lung mass found on previous x-ray
CT scan of the abdomen
Abdominal abscess and kidney mass
Chest x-ray
Lung nodule on admission chest x-ray
Colonoscopy
Gastrointestinal bleeding
Physician Referrals
Reasons for Referrals
Psychiatry
Suicidal Ideation
Neurology
Seizures
Nephrology
Kidney failure
Surgery
Infected wound
Moore C, McGinn T, Halm E. Arch Intern Med. 2007;167:1305-1311
7
Adverse Events after Hospital Discharge
• 1 in 5 (20%) patients has an adverse event shortly after hospital
discharge
70%
60%
50%
40%
30%
20%
10%
0%
Types of Adverse Events, %
62%
16%
14%
5%
ADE
Procdeure
Related
Other
Infection
4%
Fall
ADE: adverse drug event
Other: incorrect treatment and/or missed diagnosis
Forster AJ, Murff HJ, Peterson JF, Gandhi TK, Bates DW. Ann Intern Med. 2003
8
Example of an Adverse Event
• A patient with heart failure started receiving spironolactone in the
hospital. The patient was sent home with a prescription for this medication
in addition to previous use of ramipril and potassium supplements.
• Blood tests were not monitored after hospital discharge even though it
was clearly documented in the discharge summary that the patient
needed follow-up blood tests.
• Two weeks later the patient developed extreme weakness and went to the
emergency room. Blood tests revealed a potassium level >7.5 mmol/L
(normal = 4.5 mmol/L).
Forster AJ, Murff HJ, Peterson JF, Gandhi TK, Bates DW. Ann Intern Med. 2003
9
Purpose of Project
• Extract key elements of the discharge instructions:
– Discharge medications
– Discharge diagnosis
– Follow-up appointments
• Convert the extracted data into structured format that can be:
– electronically transmitted to healthcare providers responsible for
care after hospital discharge
– used to generate reminders and alerts to healthcare providers
10
Discharge Instructions
11
Clinic
Physician
Scheduled
Date/Time
Internal
Medicine
Joseph
Morgan
Yes
8/10/2009
16:10
Cardiology - EP
Null
No
Null
Anticoagulation
Null
Yes
8/4/2009
8:45
Study Design
• Discharge instructions (Name, Type/Location, Time Frame) were
extracted from free-text hospital discharge summaries:
– Manual review (physician)
– IBM Content Analytics (ICA)
• Accuracy of ICA was calculated using manual physician review as the
“gold standard”
– Sensitivity, specificity
– Positive predictive value, negative predictive value
12
Measurement
• Overall Accuracy = (TP +TN)/(Total)
• Sensitivity
– % of records containing follow-up elements that were identified via
text analytics.
• Specificity
– % of records lacking follow-up elements that were not flagged via
text analytics.
• Positive Predictive Value (PPV)
– % of records flagged as containing follow-up elements using text
analytics that actually contained follow-ups
13
Results: Accuracy of Text Analytics in Identifying
Follow-up Appointments and Diagnoses
14
Element
Overall
Accuracy
Precision
Sensitivity
(Recall)
Specificity
PPV
Diagnoses
78%
90%
80%
68%
90%
Followup
79%
95%
74%
91%
95%
UNC Health Care Solution Component Architecture
Medical Terminology
Health Language Inc.
UNC Health Care
Language Engine
Terminology
IBM Content Analytics
SNOMED,
RxNorm, ICD-9
ICD-10, CPT-4
Document Server
(UIMA Pipeline)
ICA-LanguageWare Resource
Workbench
Apache Lucene Search Engine
Extended ICA JDBC Crawler
Lucene
Index
ICA-Text Miner
Web
Application
IBM InfoSphere Guardium
Data Redaction
UNC Health Care Clinical Data
Warehouse
Pathology Reports
Discharge Summary Reports
Echocardiogram Reports
15
Discharge Follow-up
Reporting
Business
Intelligence
Tool
Project Lessons Learned
• Medical texts are more complicated than we thought… again.
• Standard terminology (RxNorm, SNOMED CT, ICD9, …)
– Absolutely required, but not good enough for dictionary matches
– “tick-born disease”, but not “tick borne illness”.
• Diagnoses
– Negation is actually just part of the range – “rule out”, “possible”.
– “Left femur fracture” and “fracture, left femur”.
– “Discharge diagnosis: same as above”.
• Follow-ups. Sometimes just “fup”.
– Usually “Dr. Good”, but sometimes “her cardiologist”.
– Usually “Vascular Surgery Clinic”, but sometimes “heme-onc”.
16
Summary
• NLP will improve communication of discharge instructions:
– Improve patient care (reduce hospital readmissions)
– Reduce risk of Medicare penalties to the hospital
17
Future Directions
•
•
•
•
•
Cohort identification for researchers and quality improvement specialists
Cancer diagnoses in pathology reports
Findings in radiology reports
Extracting quality measure data for the hospital
Researchers
– 156 current NIH-funded grants ($75M) utilizing NLP
18