1 / 30

Handout # 6: Computer Networks & Healthcare

Handout # 6: Computer Networks & Healthcare. SII 199 – Computer Networks and Society. Professor Yashar Ganjali Department of Computer Science University of Toronto yganjali@cs.toronto.edu http://www.cs.toronto.edu/~yganjali. Announcements. Assignment # 1

anne
Download Presentation

Handout # 6: Computer Networks & Healthcare

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. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Handout # 6:Computer Networks & Healthcare SII 199 – Computer Networks and Society Professor Yashar Ganjali Department of Computer Science University of Toronto yganjali@cs.toronto.edu http://www.cs.toronto.edu/~yganjali

  2. Announcements • Assignment # 1 • Submission deadline: 5PM on Friday Oct. 5th • E-mail your solutions to me; or • Slide them under my office door • BA5238 • Volunteer for lecture notes? University of Toronto – Fall 2012

  3. The Story So Far … • Introduction to computer networks • Internet vs. mail • The science of networks • Characteristics, graphs, scale-free networks, … • This week: Computer networks and healthcare University of Toronto – Fall 2012

  4. Outline • Motivational example • Information flow • Data collection • Universal access • Public awareness • Networks and awareness • How networking technology helps with healthcare • Detour: sensor networks • Science of networks • Epidemic prediction/control • Big Idea … University of Toronto – Fall 2012

  5. Traditional Uses of Networks in Healthcare • Communication • Phone • Video • Teleconferencing • … • Data transfer • Fax • E-mail University of Toronto – Fall 2012

  6. Motivational Example: WiFi for Rural Connectivity • Very low cost • Why? • Unlicensed spectrum (mostly!) • What is spectrum? • Incremental deployment • Limited capital • Start small, grow over time University of Toronto – Fall 2012

  7. New World Record – 382 Kms Pico El Aguila, Venezuela Elev: 4200 meters University of Toronto – Fall 2012

  8. Routers used: (a) Linksys WRT54GL, (b) PC Engines Wrap Boards, Costs: (a) $50, (b) $140 AirJaldi Rural WiFi ISP • North India • Tibetan Community • WiLD links + APs • Links are 10–40 km long • Achieve 4–5 Mb/s per link • VoIP + Internet • 10,000 users Hybrid: closed mesh for backhaul University of Toronto – Fall 2012

  9. Rural Telemedicine • Aravind Eye Hospitals • Tamil Nadu, India • 5 hospitals • But too far for most to walk • Need: • 15M blind in India • 70% of blindness treatable • 7% in rural areas get care • Goals: • 50 rural vision centers • Diagnosis and prevention University of Toronto – Fall 2012

  10. University of Toronto – Fall 2012

  11. Real Impact • Over 130,000 patients so far • Centers are cash-flow positive • Over 20,000 patients have recovered sight • Growing to 50 centers covering 2.5M people • Hoping to replicate in Lumbini, Nepal University of Toronto – Fall 2012

  12. Remote Diagnosis • Use network (the Internet) as a medium to help with diagnosis • Not a perfect tool • Can lead to incorrect diagnosis • Might work in some situations • Internet can also help with follow up and consulting sessions that do not require physical presence • Even in more advanced regions University of Toronto – Fall 2012

  13. Outline • Motivational example • Information flow • Data collection • Universal access • Public awareness • Networks and awareness • How networking technology helps with healthcare • Detour: sensor networks • Science of networks • Epidemic prediction/control • Big Idea … University of Toronto – Fall 2012

  14. Medical Information Flow • Many sources of information • Patient history • Lab records • Electrocardiogram (EGG or EKG) • CAT scan • Magnetic resonance imaging (MRI) • Ultrasound • Digital X rays • Doctor’s diagnosis, prescription, … • Traditionally • Go back to the same doctor, or • Transfer the data Computer networks can help here. University of Toronto – Fall 2012

  15. Electronic Health Record (EHR) System • Collect all information related to a patient in digital format • Universal access • Doctor’s can access this data from anywhere • More information  better decisions • Less space to store • Faster access • Quick sharing/transfer • Reduced possibility of some errors • Easy to access and verify • Great resource for research • Data is extremely valuable in medical research University of Toronto – Fall 2012

  16. Possible Concerns • Requires many resources • EHR system • Setup • Maintenance • Network • Doctor time to collect data • Might introduce new types of errors • Example? • Privacy issues • Who has access? • Hackers, … University of Toronto – Fall 2012

  17. Awareness • Networks can help with raising awareness in healthcare • Many resources available on the Web • Information for specialists: • Medical journals, papers • PubMed, … • Information for all • Symptoms, available treatments, side effects, … • WebMD, BabyCenter, … • We have great search engines: Google, Bing, … • Online forums and support groups • No need to be physically close • Low cost (time and money) One should be careful about these resources. Not all are trustworthy. University of Toronto – Fall 2012

  18. Outline • Motivational example • Information flow • Data collection • Universal access • Public awareness • Networks and awareness • How networking technology helps with healthcare • Detour: sensor networks • Science of networks • Epidemic prediction/control • Big Idea … University of Toronto – Fall 2012

  19. How Technology Made This Possible? • Large and reliable storage • Store high volumes of data at very low cost • Small probability of error (or loss) • High speed networks • Make access possible • To store and retrieve • No need to store locally • Large scale information management systems • It is not just a pile of data University of Toronto – Fall 2012

  20. Technology Helps with Data Collection • Many medical devices today collect data in digital format • Easy to transfer and analyze • Can be kept in an EHR system • We can also collect data using non-traditional devices • Sensor networks University of Toronto – Fall 2012

  21. What Are Sensor Networks • Tiny electronic devices • Equipped with a sensor to collect • Temperature, humidity, … • Use a wireless network to transfer data to a base-station • Usually in an ad hoc manner • Used to collect various forms of data with applications in • Wildlife, environment, military, healthcare, … University of Toronto – Fall 2012

  22. Sending Data to the Base Station • What if topology changes constantly? • Quickly moving nodes • Highly dynamic environment • ... • We might not find a path to send data to the base station University of Toronto – Fall 2012

  23. Volcano Routing Scheme (VRS) • Lava flows towards the sea (low altitude) • Local balancing of load • Obstacles do not stop lava • No explicit route discovery • Reordering layers doesn’t disrupt the flow University of Toronto – Fall 2012

  24. Volcano Routing Scheme University of Toronto – Fall 2012

  25. Multi-Flow Volcano Routing University of Toronto – Fall 2012

  26. Science of Networks: Epidemics • We can use the science of networks to predicting and control epidemics • Propagation of viruses similar to … • Diffusion of information in social network • In random networks • Either the entire network is infected, or • It dies out • Depends on spreading rate • Above a threshold all nodes will be infected • Below that threshold  spread will die out • In scale-free networks however • No epidemic threshold • Steady state of small persistence rate University of Toronto – Fall 2012

  27. Outline • Motivational example • Information flow • Data collection • Universal access • Public awareness • Networks and awareness • How networking technology helps with healthcare • Detour: sensor networks • Science of networks • Epidemic prediction/control • Big Idea … University of Toronto – Fall 2012

  28. The Big Idea … University of Toronto – Fall 2012

  29. Discussion • Extremely valuable dataset • What is the incentive of people to help? • Can we create similar incentives in other situations? • How reliable is the results gained from this system? • Can doctors rely on the results? • Do we need extra checks? • Can we integrate a system like this with today’s online social networks? • Facebook maybe? • What are the pros and cons? University of Toronto – Fall 2012

  30. Summary and Discussion • Computer networks are extremely useful in healthcare • Help with information flow • Data collection • Data management • … • Assuming extremely fast networks, high capacity storage, … • What other areas can you think of? • What are the technologies we need to work on today? University of Toronto – Fall 2012

More Related