Innovations in Social Media: Nursing Informatics at the Forefront

Transcription

1 Innovations in Social Media: Nursing Informatics at the Forefront Charles Boicey, MS, RN-BC, CPHIMS Informatics Solutions Architect University of California, Irvine This program is approved for continuing education (CE) hours for use in fulfilling the continuing education requirements of the Certified Professional in Healthcare Information and Management Systems (CPHIMS).

2 Conflict of Interest Disclosure Charles Boicey, MS, RN-BC, CPHIMS Has no real or apparent conflicts of interest to report.

3 Objectives 1. The participant will be able to identify three use cases for integrating social media into healthcare applications. 2. The participant will be able to define social noise in relation to social media data. 3. The participant will be able to discuss the key components of sentiment analysis.

4 I skate to where the puck is going to be, not where it has been Wayne Gretzky

5 Social Media Top Ten Twitter Facebook LinkedIn YouTube Pinterest Google Plus RSS Feed Foursquare Yelp Blog

6 Social Media Insights Population Health Disease Surveillance (MappyHealth) Reputation Management & Root Cause Analysis Brand Health Scoring Social Performance Measures Customer Service Patient Collected Data

7 MappyHealth Collaboration between two Nurse Informaticists and one computer science student. Team Members Brian Norris, MBA, RN-BC Charles Boicey, MS, RN-BC, CPHIMS Mark Silverberg, MIS Student at GWU

8 MappyHealth Now Trending 2012 Challenge Winners Office of the Assistant Secretary for Preparedness and Response (ASPR) Utilized technology from non-healthcare domains to build a healthcare application Currently working with the CDC on a POC

9 ASPR Now Trending 2012 Challenge Using open source Twitter data, we challenge you to create a web based application that will automatically deliver a list of the top-five trending illnesses from a specified geographic area in a twenty-four hour period. This data would be sent directly to state and local public health practitioners to use in a variety of ways including: building a baseline of trend data, engaging the public on trending health topics, serving as an indicators of potential health issues emerging in the population, or cross-referencing other data sources.

10 It started with a single tweet

11

12

13 More Tech Stuff Tracks 25 Conditions made up of 125 Associated Health Terms (many of these are diseases) Various Trend Views via Graphical Interfaces Ability to drill down to data graphically on the hour Trend matching of conditions and terms with qualifiers for deeper level analysis Geo Location and Profile Location Map View Ability to Print, Export, or Copy datasets associated with trends for deeper analysis form the user interface Works on any platform natively including mobile devices

14 What we have found so far Each condition and term has a pattern of regular activity we call the social noise Spikes (or higher volume) outside of this band can be attributed to events Tracked abnormal events (spikes) both positive and negative We have seen events (spikes) in the United States, Europe, South America and Malaysia

15 Pertussis and Whooping Cough Spike in Whooping Cough Tweets associated with Pertussis Spike due to Idaho Infant that died of Whooping Cough 71% of tweets over the two hour spike associated with this event (202/284) Social Noise Zone Represents a 116% spike over the last two hours Social noise zone 0 25 tweets per hour. Represents a 468% increase over the high-end of this zone

16 Meningitis Tweets related to two events. The first a 3 year old with severe Meningitis in south America The second a meningitis death in the United States Social Noise Zone NCIRE researcher dies from apparent lab-acquired meningitis infection Outbreak News Calif. lab worker dies after meningitis infection - A 25- year-old laboratory researcher has died after becoming infe

17 Demo

18 Eldercare Locator Text Text zip code to Follow the prompts STOP

19 Sentiment Analysis The application of natural language processing, computational linguistics and text analytics to identify and extract subjective information. What is being said about a person or about an organization. Sentiment can be positive or negative. Early identification of negative sentiment allows an organization to respond immediately and avoid being blindsided. Positive sentiment allows for marketing opportunities.

20

21

22 Use or opinion Students Residents Practicing physicians Has visited patient s or family member s profile 2.3% 3.9% 15.5% Is aware of patient or family member visiting your site 1.2% 8.2% 28.1% Has received friend requests from patients or family members 1.2% 7.8% 34.5% Has requested to be friends with patient or family member 0.0% 1.0% 5.3% Thinks it s OK for physicians to interact with patients on social media as part of patient care 19.9% 22.1% 16.2% Thinks social networking sites have potential for improving doctor-patient communication 28.0% 29.8% 21.2% Thinks communication on social media can be accomplished without compromising patient confidentiality 12.9% 13.7% 5.9% The Patient-Doctor Relationship and Online Social Networks: Results of a National Survey, Journal of General Internal Medicine, October 2011

23

24 Closing Thoughts Imagination is more important than knowledge Albert Einstein

25 References

26 Questions, Comments & Contact Info. Charles ~100M tweets available for research This program is approved for continuing education (CE) hours for use in fulfilling the continuing education requirements of the Certified Professional in Healthcare Information and Management Systems (CPHIMS).