kai zheng phd qiaozhu mei phd david a hanauer md university of michigan n.
Skip this Video
Download Presentation
Kai Zheng, PhD, Qiaozhu Mei, PhD, David A. Hanauer, MD University of Michigan

Loading in 2 Seconds...

play fullscreen
1 / 46

Kai Zheng, PhD, Qiaozhu Mei, PhD, David A. Hanauer, MD University of Michigan - PowerPoint PPT Presentation

  • Uploaded on

Developing an Intelligent and Socially Oriented Search Query Recommendation Service for Facilitating Information Retrieval in Electronic Health Records. Kai Zheng, PhD, Qiaozhu Mei, PhD, David A. Hanauer, MD University of Michigan.

I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
Download Presentation

PowerPoint Slideshow about 'Kai Zheng, PhD, Qiaozhu Mei, PhD, David A. Hanauer, MD University of Michigan' - verity

Download Now An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
kai zheng phd qiaozhu mei phd david a hanauer md university of michigan

Developing an Intelligent and Socially Oriented Search Query Recommendation Service for Facilitating Information Retrieval in Electronic Health Records

Kai Zheng, PhD, Qiaozhu Mei, PhD, David A. Hanauer, MD

University of Michigan

- On Behalf of William Wilcox, Danny Wu,and Lei Yang

information retrieval in ehr
Information Retrieval in EHR


Millions of patient records

Specialized language

Rich, implicit intra/inter document structures

Deep NLP/Text Mining is necessary

Complicated information needs

Privacy is a big concern

problem statement
Problem Statement

Electronic health records (EHR), through its capability of acquiring and storing vast volumes of data, provides great potential to help create a “rapid learning” healthcare system

However, retrieving information from narrative documents stored in EHRs is extraordinarily challenging, e.g., due to frequent use of non-standard terminologies and acronyms

problem statement cont
Problem Statement (Cont.)

Similar to how Google has changed the way people find information on the web, a Google-like, full-text search engine can be a viable solution to increasing the value of unstructured clinical narratives stored in EHRs

However, average users are often unable to construct effective and inclusive search queries due to their lack of search expertise and/or domain knowledge

proposed solution
Proposed Solution

An intelligent query recommendation service that can be used by any EHR search engine to

  • Artificial Intelligence: augment human cognition so that average users can quickly construct high quality queries in their EHR search 
  • Collective (social) Intelligence: engender a collaborative and participatory culture among users so that search queries can be socially formulated and refined, and search expertise can be preserved and diffused across people and domains
a typical ir system architecture
A Typical IR System Architecture
















EMERSE - Electronic Medical Record Search Engine

Full-text search engine

Created by David Hanauer

Widely used in UMHS since 2005 (and VA)

Boolean keyword queries

Routinely utilized by frontline clinicians, medical coding personnel, quality officers, and researchers at the University of Michigan Health System

The test platform for the solutions being built through this project

specific aims of the project
Specific Aims of the Project

Aim #1: Developing AI-based Query Recommendation Algorithms

Aim #2: Leveraging Social Intelligence to Enhance EHR Search

Aim #3: Defining a Flexible Service Architecture

aim 1 developing ai based query recommendation algorithms
Aim #1: Developing AI-based Query Recommendation Algorithms

Clinicians find great difficulty to formulate queries to express their information needs

EMERSE provide “semi-automatic” query suggestion (synonyms, spelling, etc.)

Example: uti  uti "urinary tract infection"

25% adoption rate!

Text mining/machine learning methods to automatically select alternative query terms

Technical details left later in the talk

aim 2 leveraging social intelligence to enhance ehr search
Aim #2: Leveraging Social Intelligence to Enhance EHR Search

Enhancing AI-based algorithms with social intelligence:

  • Allow users to bundle search terms and share
  • Social appraisal
  • Classifying search terms bundles for easy retrieval
  • Other community features
  • Enhancing collaboration among user communities across institutions
aim 3 defining a flexible service architecture
Aim #3: Defining a Flexible Service Architecture

A service-oriented architecture serving general search knowledge

Locally implementable APIs

Implementation of the community features

to challenge us why bother
To Challenge Us – Why Bother?

Q1: Is this different from PubMed?

  • EHRs have very different properties

Q2: Is this different from Google?

  • Very different information needs in EHR search

Q3: Could “social search” even work?

dictated notes vs typed notes
Dictated Notes vs Typed Notes

Hypothesis: there exists a considerable amount of lexical and structural differences. Such differences could have a significant impact on the performance of natural language processing tools, necessitating these two different types of documents being differentially treated

Data: 30,000 dictated notes and 30,000 typed notes of deceased patients, randomly sampled

Same genre: encounter notes that physicians composed to describe an outpatient encounter or to communicate with other clinicians regarding patient conditions

comparison vocabulary
Comparison: Vocabulary


> 80%



UMLS+: English dictionaries + commonly used medical terminologies + all concepts/terms in UMLS

comparative analysis perplexity
Comparative Analysis: Perplexity

Fewer occurrences

Sparser information!

Less functional words

Words repeat less

Higher perplexity/randomness

* Typed notes have higher variance of almost all document measures

lessons learned
Lessons Learned

Clinical notes are much noisier than biomedical literature

Among them, notes typed-in by physicians are much noisier and sparser than notes dictated.

What about different genres of notes?

These differences of linguistic properties imply potential difficulty in natural language processing

analysis of emerse query log
Analysis of EMERSE Query Log

Hours of a day

Days of a week (Mon - Sun)

202,905 queries collected over 4 years

533 users (medical professionals in UMHS)

35,928 user sessions (sequences of queries)

query distribution not a power law
Query Distribution – Not a Power Law!

Long tail –

but no fat head

a categorization of ehr search queries
A Categorization of EHR Search Queries

Almost no navigational queries; most queries are informational/transactional

Using the top-level concepts of SNOMED CT

comparison to web search
Comparison to Web Search

Almost no navigational queries (Web: ~ 30%);

Average query length (Web: 2.3):

  • User typed in: 1.7
  • All together (typed in + query suggestions + bundles): 5.0

Queries with Acronym: 18.9% (Web: ~5%)

Dictionary coverage: 68% (Web: 85%-90%)

Average length of session: 5.64 queries (Web: 2.8)

Query suggestions adopted: 25.9% (Web: < 10%)

lessons learned1
Lessons Learned

Question: Can the users help each other to formulate queries?

Medical search is much more challenging than Web search

  • More complicated information need
  • Longer queries, more noise

Users have substantial difficulty to formulate their queries

  • Longer search sessions
  • High adoption rate of system generated suggestions
social collaborative search in emerse
“Social” (Collaborative) Search in EMERSE

- Zheng, Mei, Hanauer. Collaborative search in electronic health records. JAMIA2011

Changing a search experience into a social experience

Users create search bundles (bundled query)

  • Collection of keywords that are found effective as a query
  • Reuse search bundles
  • Share them with other users

Public sharing vs. private sharing

Search knowledge diffuses from bundle creators to bundle users

the effectiveness of collaborative search
The Effectiveness of Collaborative Search

Search bundles (as of Dec. 2009):

  • 702 bundles
  • 58.7% of active users
  • Almost half of the pageviews
  • 19.3% of all queries (as of Dec. 2010)
  • 27.7% search sessions ended with a search bundle (as of Dec. 2010)
  • Bundle creator: 188
  • Bundle sharers: 91
  • Bundle leechers: 77
example bundles
Example Bundles

GVHD: "GVHD” "GVH” "Graft-Versus-Host-Disease” "Graft-Versus-Host Disease” "Graft Versus Host Disease” "Graft Versus Host” "Graft-Versus-Host” "Graft vs. Host Disease” "Graft vs Host Disease” "Graft vs. Host” "Graft vs Host"

example bundle cont
Example Bundle (cont.)

Myocardial infarction:

NSTEMI STEMI ~AMI "non-stelevation” "non stelevation” "st elevation MI” "stelevation” "acute myocardial infarction” "myocardial infarction” "myocardial infarct” "anterior infarction” "anterolateralinfarction” "inferior infarction” "lateral infarction” "anteroseptalinfarction” "anterior MI” "anterolateralMI” "inferior MI” "lateral MI” "anteroseptalMI” infarcted infarction infarct infract "Q wave MI” "Q-wave MI” "Q wave” "Q-wave” "st segment depression” "t wave inversion” "t-wave inversion” "acute coronary syndrome” "non-specific ST wave abnormality” "non specific ST wave abnormality” "ST wave abnormality” "ST-wave abnormality” "CPK-MB” "CPK MB” "troponin” ~^MI -$"MI \s*\d{5}” -systemic

bundle sharing across individual users
Bundle Sharing Across Individual Users

Red links: cross department links

bundle sharing facilitated diffusion of information
Bundle Sharing Facilitated Diffusion of Information

Quantitative network analysis of search knoweldge diffusion networks

Giant component exists

Small world (high clustering coefficient & short paths)

Publically shared bundles better facilitates knowledge diffusion

  • Privately shared bundles adds on top of public bundles

Users tends to share bundles to people in the same department; but specialty is a more natural representation of communities. (based on modularity)

lessons learned2
Lessons Learned

Medical search is much more challenging than Web search

Users have substantial difficulty to formulate their queries

  • Longer search sessions
  • High adoption rate of system generated suggestions
  • High usage of search bundles

Collaborative search has facilitated the sharing/diffusion of search knowledge

  • Public bundles are more effective than private
  • 30% bundle users are leechers; half of the bundle creators don’t share
automatic query recommendation methods
Automatic Query Recommendation: Methods

Similarity based (kNN)


Semantic term expansion

Network-based ranking

Learning to rank (much labeled training data needed)

automatic query recommendation available information
Automatic Query Recommendation: Available Information

Information to leverage:

  • Co-occurrence within queries
  • Transition in query sessions
  • Co-occurrence within clinical documents
  • Annotation by ontological concepts
  • Ontology structures
  • Morphological closeness
  • Clickthrough
random walk and hitting time
Random Walk and Hitting Time

P = 0.3






P = 0.7


Hitting Time

  • TA: the first time that the random walk is at a vertex in A

Mean Hitting Time

  • hiA: expectation of TA given that the walk starts from vertex i
computing hitting time
Computing Hitting Time

hiA = 0.7 hjA + 0.3 hkA + 1

  • TA: the first time that the random walk is at a vertex in A

h = 0





  • hiA: expectation of TA given that the walk starting from vertex i


Apparently, hiA = 0 for those


Iterative Computation

generate query suggestion
Generate Query Suggestion


  • Construct a (kNN) subgraph centered by the query term (s)
  • Could be bipartite
  • Compute transition probabilities (based on co-occurrence/similarity)
  • Compute hitting time hiA
  • Rank candidate queries using hiA









urinary tract infection

other network based methods
Other Network-based Methods

Stationary distribution

Absorbing probability

Commute time

Other measures

More general: network regularization

ranking with multiple networks
Ranking with Multiple Networks














Query transitions

Distributional similarity

Ontology structures

Ranking/Transductive Learning with Multiple Views (e.g., Zhou et al. 2007, Muthukrishnan et al. 2010)

Suggested Queries


Cranfield evaluation (adopted by TREC)

  • Sample information needs  queries
  • Fixed test document collection
  • Pool results of multiple candidate systems
  • Human annotation of relevance judgments
  • IR Evaluation (e.g., MAP, NDCG)

Directly rating by users (bucket testing)

towards the next generation ehr search engine
Towards the Next Generation EHR Search Engine

Better understanding of information needs by medical professionals

  • frontline clinicians, administrative personnel, and clinical/translational researchers

Better natural language processing for patient records

Better mechanisms of automatic query recommendation in the medical context

Better ways to facilitate collaborative search and preserve search knowledge

Better ways to improve the comprehensibility of medical data by patients and families (future)

publications to date
Publications to Date

Kai Zheng, Qiaozhu Mei, David A. Hanauer. Collaborative search in electronic health records. JAMIA. 2011;18(3):282–91.

Lei Yang, Qiaozhu Mei, Kai Zheng, David A. Hanauer. Query log analysis of an electronic health record search engine. AMIA Annual Symposium Proc. 2011. (forthcoming)

Kai Zheng, Qiaozhu Mei, Lei Yang, Frank J. Manion, Balis UJ, David A. Hanauer. Voice-dictated versus typed-in clinician notes: Linguistic properties and the potential implications on natural language processing. AMIA Annual Symposium Proc. 2011. (forthcoming)