September 2016
Volume 57, Issue 12
Open Access
ARVO Annual Meeting Abstract  |   September 2016
Computational Methods for Analyzing Patient Data
Author Affiliations & Notes
  • Alexander B Crane
    Ophthalmology, Rutgers, Pine Brook, New Jersey, United States
  • Elliot Crane
    Ophthalmology, Rutgers, Pine Brook, New Jersey, United States
  • May Shum
    Ophthalmology, Rutgers, Pine Brook, New Jersey, United States
  • Jason S. Kim
    Ophthalmology, Rutgers, Pine Brook, New Jersey, United States
  • Eliott Kim
    Ophthalmology, Rutgers, Pine Brook, New Jersey, United States
  • David S Chu
    Ophthalmology, Rutgers, Pine Brook, New Jersey, United States
  • Footnotes
    Commercial Relationships   Alexander Crane, None; Elliot Crane, None; May Shum, None; Jason Kim, None; Eliott Kim, None; David Chu, None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science September 2016, Vol.57, 3320. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Alexander B Crane, Elliot Crane, May Shum, Jason S. Kim, Eliott Kim, David S Chu; Computational Methods for Analyzing Patient Data. Invest. Ophthalmol. Vis. Sci. 2016;57(12):3320.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : To develop and implement a computer algorithm that tracks patient health data and analyzes patterns.

Methods : MATLAB r2011 was used to implement a program that analyzed data from 45 subjects with intermediate uveitis, as identified from the billing database of a uveitis specialist. Data from both eyes of the 45 subjects was collected on four categories of ocular inflammation: anterior chamber cell, anterior chamber flare, vitreous cell, and vitreous haze. Any inflammation greater than 1+ in any category was considered active inflammation. A recurrence was defined as a period of active inflammation between visits without active inflammation for each eye. The program was used to output the average length and number of recurrences. If a patient was considered in a recurrence at the end of the data set, it did not count as part of the average length of recurrences, but did count towards the number of recurrences.

Results : The program was able to output the average length of and number of recurrences for each subject in each eye. On average, subjects had 1.3 recurrences in the right eye and 1.5 recurrences in the left eye, lasting 84 and 83 days on average, respectively. Of only patients that did experience recurrences of inflammation, there was an average of 2.4 and 2.3 recurrences in the right eye and left eye, respectively.

Conclusions : EMR systems are becoming more prevalent, and data detailing many clinical parameters are being increasingly organized by these systems. Automated computer algorithms, such as this one, will likely become increasingly useful tools for research as large amounts of data become increasingly prevalent. This tool was successfully able to track patient health data for ocular inflammation, and could easily be used to monitor fluctuations in other health data, such as intraocular pressure, medication dose, or liver function tests.

This is an abstract that was submitted for the 2016 ARVO Annual Meeting, held in Seattle, Wash., May 1-5, 2016.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×