25
EHR-based Phenome Wide Association Study in Pancreatic Cancer Tomasz Adamusiak MD PhD @7omasz

EHR-based Phenome Wide Association Study in Pancreatic Cancer

Embed Size (px)

DESCRIPTION

Presented at 2014 AMIA Joint Summits, April 9, 2014, San Francisco, CA BACKGROUND. Pancreatic cancer is one of the most common causes of cancer-related deaths in the United States, it is difficult to detect early and typically has a very poor prognosis. We present a novel method of large-scale clinical hypothesis generation based on phenome wide association study performed using Electronic Health Records (EHR) in a pancreatic cancer cohort. METHODS. The study population consisted of 1,154 patients diagnosed with malignant neoplasm of pancreas seen at The Froedtert & The Medical College of Wisconsin academic medical center between the years 2004 and 2013. We evaluated death of a patient as the primary clinical outcome and tested its association with the phenome, which consisted of over 2.5 million structured clinical observations extracted out of the EHR including labs, medications, phenotypes, diseases and procedures. The individual observations were encoded in the EHR using 6,617 unique ICD-9, CPT-4, LOINC, and RxNorm codes. We remapped this initial code set into UMLS concepts and then hierarchically expanded to support generalization into the final set of 10,164 clinical concepts, which formed the final phenome. We then tested all possible pairwise associations between any of the original 10,164 concepts and death as the primary outcome. RESULTS. After correcting for multiple testing and folding back (generalizing) child concepts were appropriate, we found 231 concepts to be significantly associated with death in the study population. CONCLUSIONS. With the abundance of structured EHR data, phenome wide association studies combined with knowledge engineering can be a viable method of rapid hypothesis generation.

Citation preview

Page 1: EHR-based Phenome Wide Association Study in Pancreatic Cancer

EHR-based Phenome Wide Association Study

in Pancreatic Cancer

Tomasz Adamusiak MD PhD

@7omasz

Page 2: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Conflict of interest disclosure

Tomasz Adamusiak has no real or apparent conflicts of interest to report

2

Page 3: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Learning Objectives

• Recognize the value of structured clinical information

• Identify computational and terminology challenges in big data analytics

3

Page 4: EHR-based Phenome Wide Association Study in Pancreatic Cancer

phe·no·type

n. Clinical Informatics

all clinically relevant features contained in patient’s electronic health record

4

Page 5: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Phenome

5

0% 10% 20% 30% 40% 50% 60% 70%

Other

Labs

Medications

Procedures

Problems

Concepts (7k)

Observations (2M)

Page 6: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Re-transform data on demand

6

Page 7: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Focused on discrete data elements

Categorical variables:

• Ethnicity

• Problems

• Procedures

• Medications

• Clinical results

– laboratory tests

– vitals

7

Page 8: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Meaningful Use context

Categorical variables:

• Ethnicity

• Problems

• Procedures

• Medications

• Clinical results

– laboratory tests

– vitals

Clinical terminologies:

• OMBSNOMED CT

• ICD9/10

• HCPCS/CPT-4

• Medi-SpanRxNorm

• CPT-4

• LOINC

8

Page 9: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Pancreatic cancer has an extremely poor prognosis

• Survival: For all stages combined,

• 1-year relative survival rates 25%

• 5-year relative survival rates 6%

Source: http://www.cancer.org/acs/groups/content/@nho/documents/document/acspc-024113.pdf

9

Page 10: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Test all associations with pancreatic cancer and death as primary outcome

10

1298 patients

2 359 265 observations

2004 - 2013

ICD 9/10, SNOMED CT, CPT-4, LOINC,

RxNorm

6 617 codes

10 164 concepts 231 significant

associations

Page 11: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Single terminology

11

Page 12: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Add other terminologies to the mix

12

Page 13: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Use relations other than subsumption (non-isa)

13

Page 14: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Use relations other than subsumption (non-isa) to increase statistical power

14

Histamine H2 Antagonists

Cimetidine

Cimetidine 300 MG

Cimetidine 300 MG Oral Tablet

Cimetidine 400 MG

Cimetidine 400 MG Oral Tablet

constitutes

ingredient_of

isa RxNorm

Page 15: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Use meta-categorization (UMLS Semantic Network)

15

Page 16: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Not all codes are created equal

16

Page 17: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Expansion in UMLS across MU sources

17

Diabetes mellitus without mention of complication,

type II or unspecified type, not stated as

uncontrolled

ICD-9

ICD-10

SNOMED CT

NDF-RT

Situation with explicit

context

Metabolic diseases

roots:

Page 18: EHR-based Phenome Wide Association Study in Pancreatic Cancer

6o of terminological Kevin Bacon

Acute myocardial infarction

Myocardial ischemia

Vascular Diseases

Disorder of soft tissue

Collagen Diseases

Connective Tissue Diseases

Epidermal and dermal conditions

Skin and subcutaneous tissue disorders

Dermatologic disorders

18

Page 19: EHR-based Phenome Wide Association Study in Pancreatic Cancer

UMLS is ideal for integration of heterogeneous clinical data

• Translational potential (OMIM, GO, NCIt)

• Single entry point to MU terminologies

• Cross-walk between MU terms

• Terminology-agnostic

• Text-mining

19

Page 20: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Extracting genetic information out of EHR is a major challenge

Encounter due to genetic counseling

Yes No

Outcome Deceased 2 813

Alive 3 336

20

Background reference

Methods: • Chi-squared test • Bonferroni correction • RR estimate of effect size

Page 21: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Statistically significant highlights

Decreased Risk (RR < 1)

• sevoflurane Inhalant Solution

• Ionic iodinated contrast media

Increased Risk (RR > 1)

• cytopathology

• cimetidine

21

Resource utilization

Page 22: EHR-based Phenome Wide Association Study in Pancreatic Cancer

CORRELATION DOES NOT IMPLY CAUSATION

Private traits and attributes are predictable from digital records of human behavior. Kosinski M1, Stillwell D, Graepel T. PMID: 23479631

22 By Jono Winn (Flickr) [CC-BY-2.0], via Wikimedia Commons

Page 23: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Future work: cohort profiles

1. Malignant neoplasm of pancreas (C0346647) 2. Digestive System Neoplasms (C0012243) 3. Glucose test, blood by glucose monitoring device(s) cleared by the FDA

specifically for home use (C0373627) 4. Hepatic function panel This panel must include the following: Albumin (82040)

Bilirubin, total (82247) Bilirubin, direct (82248) Phosphatase, alkaline (84075) Protein, total (84155) Transferase, alanine amino (ALT) (SGPT) (84460) Transferase, aspartate amino (AST) (SGOT) (C0812554)

5. Basic metabolic panel (Calcium, total) This panel must include the following: Calcium, total (82310) Carbon dioxide (bicarbonate) (82374) Chloride (82435) Creatinine (82565) Glucose (82947) Potassium (84132) Sodium (84295) Urea nitrogen (BUN) (84520) (C0519823)

6. Regular Insulin, Human 100 UNT/ML Injectable Solution (C0977794) 7. heparin sodium, porcine 10 UNT/ML Injectable Solution (C0977415) 8. Pancreatic Diseases (C0030286) 9. Dexamethasone 4 MG/ML Injectable Solution (C0976136) 10. Sodium Chloride 0.154 MEQ/ML Injectable Solution (C0980221)

23

Page 24: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Limitations

• Gaps in data

– Out of network

– Provider-related

– Terminology-related

24

Page 25: EHR-based Phenome Wide Association Study in Pancreatic Cancer

Thank you

Co-authors:

Mary Shimoyama, PhD

[email protected]

@7omasz

25

Results

http://dx.doi.org/10.6084/m9.figshare.816958

For more background information

Next-generation phenotyping using the Unified Medical Language System (UMLS). Adamusiak T, Shimoyama N, Shimoyama M, JMIR Med Inform. doi:10.2196/medinform.3172

Acknowledgements

We thank Stacy Zacher, Glenn Bushee, and Bradley Taylor for their help.

This project was funded in part by the Advancing a Healthier Wisconsin endowment at the Medical College of Wisconsin and the National Center for Research Resources and the National Center for Advancing Translational Sciences, National Institutes of Health, through grant UL1 RR031973.