• Share
  • Email
  • Embed
  • Like
  • Save
  • Private Content
From Data to Knowledge: Discovery of Medical Laboratory Demand Patterns through Visualisation Techniques
 

From Data to Knowledge: Discovery of Medical Laboratory Demand Patterns through Visualisation Techniques

on

  • 1,075 views

Poster presented at ALISE 2012, Dallas, TX, January 17-20, 2012

Poster presented at ALISE 2012, Dallas, TX, January 17-20, 2012
http://www.alise.org/conferences

Statistics

Views

Total Views
1,075
Views on SlideShare
862
Embed Views
213

Actions

Likes
0
Downloads
1
Comments
0

5 Embeds 213

http://socialmedialab.ca 205
http://translate.googleusercontent.com 3
http://tweets.lauraogrady.ca 2
https://twitter.com 2
http://a0.twimg.com 1

Accessibility

Upload Details

Uploaded via as Adobe PDF

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment

    From Data to Knowledge: Discovery of Medical Laboratory Demand Patterns through Visualisation Techniques From Data to Knowledge: Discovery of Medical Laboratory Demand Patterns through Visualisation Techniques Presentation Transcript

    • Funded by: Conrad Ng (c.ng@dal.ca), Anatoliy Gruzd (gruzd@dal.ca) – School of Information Management, Dalhousie University Calvino Cheng, Bryan Crocker, Don Doiron, Kent Stevens – Capital District Health Authority, Halifax, Nova Scotia, Canada Introduction Seasonal Patterns Clinic to Clinic Network Physician to Clinic Network This research uses data visualization techniques and Average Weekly Referrals social network analysis to determine the status and 12000 efficiency of laboratory ordering for the outpatient 10000 system in Nova Scotia, Canada. Average # of Referrals 8000 Currently, the Capital District Health Authority (CDHA) 6000 model demonstrates that approximately 60% of laboratory ordering originates in the outpatient setting 4000 and is costing the province approximately $3.3 million 2000 May 2009 - April 2010 per month. May 2010 - April 2011 0 The goal of this pilot project is to turn the vast amount May Jul Oct Nov Dec Jun Jan Feb Mar May Apr Aug Sep of data in the CDHA’s laboratory information system into usable information and allow the CDHA to identify usage trends to better understand the future demands  This chart confirms seasonal patterns based on  The nodes (dots) are clinics; the size of the nodes on lab testing and allow policymakers more insight holidays and long weekends. represents the total number of unique referrals from that clinic.  Connection = physician’s affiliation with a clinic(s) into the Nova Scotia primary care landscape.  There are consistently less tests ordered during  Node Size = # of patients major holidays (see the “valleys” in the chart), often  Two nodes (clinics) are connected if they share 50 or  Most physicians who work at the Family Focus and Method followed by a spike of these orders. more patients (“strong” connections). Walk-in clinic groups also work at other clinics. 1. Extracted anonymized, outpatient lab test orders  While the Family Focus and Walk-in clinics only account for about 10% of all lab testing referrals, they Conclusions from CDHA’s Laboratory Information Systems for Demographic by Clinic Type the period from May 2009 to May 2011 appear to be relatively “central” in this network.  Even relatively simple visualizations can offer useful 2. Re-indexed and cleaned records (e.g. assign  This network visualization can be used to identify insights to managers and other health professionals unique identifiers and work addresses to physicians “well connected” clinics, ideal for disseminating new while helping them build a predictive model of and clinics) information to physicians and patients. laboratory utilization. Network Density of Clinic-to-Clinic Networks  The network visualizations uncovered hidden Dataset Summary for Different Age Groups connections between clinics and provided some # of Records 925,680 0.12 additional insights into the migration practices of # of Clinics 196 0.1 0.08 patients among clinics. Density 0.06 # of Physicians 426 0.04 0.02  These visualizations can also be applied to make # of Patients 278,689 more effective health spending and planning decisions 0 Patients Age Group in other similar healthcare systems. 3. Descriptive analysis & visualization with Microsoft  Density = # of actual connections in the network Excel 2010  Walk-in, Family Focus, and Specialist type clinics are divided by the number of possible connections. Acknowledgements 4. Network analysis & visualization with ORA 2.3.2 more likely to refer younger patients (18-30 years of This project is funded by MITACS and CDHA. We also thank  The densest networks corresponded to the age (developed by CASOS at Carnegie Mellon age) to the outpatient laboratory testing facilities, while the CDHA Pathology Informatics Group for assisting in the data General-type clinics are more likely to refer older group between ~20 and 35. University) based on the 3 networks: extraction and verification process.  Clinic to Clinic (C2C), Physician to Clinic (P2C), patients (48-66 years of age).  This suggests that young adults are less likely to More information on this and related projects can be found at Physician to Physician (P2P) stay with the same clinic. www.SocialMediaLab.caTEMPLATE DESIGN © 2008www.PosterPresentations.com