This paper is in the following e-collection/theme issue:

Posters - Connected Health Symposium 2016 (46) Big Data (216) Wearable Devices and Sensors (812)

Published on in Vol 2, No 1 (2016): December

Disruptive Innovation in Neurosurgical Outcomes Research: The Impact of Big Data, Predictive Analytics, and Wearable Technology

Disruptive Innovation in Neurosurgical Outcomes Research: The Impact of Big Data, Predictive Analytics, and Wearable Technology

Disruptive Innovation in Neurosurgical Outcomes Research: The Impact of Big Data, Predictive Analytics, and Wearable Technology

Authors of this article:

Aditya V Karhade1 Author Orcid Image ;   Joeky Senders2 ;   Marike L Broekman2 ;   William B Gormley1 ;   Timothy R Smith1
Article Authors Cited by (1) Tweetations Metrics

    Poster

    1Cushing Neurosurgery Outcomes Center, Department of Neurosurgery, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, United States

    2Department of Neurosurgery, University Medical Center, Utrecht, Utrecht, Netherlands

    Corresponding Author:

    Timothy R Smith, MD, PhD, MPH

    Cushing Neurosurgery Outcomes Center, Department of Neurosurgery

    Brigham and Women's Hospital

    Harvard Medical School

    15 Francis Street

    Boston, MA, 02115

    United States

    Phone: 1 617 732 5500

    Fax:1 617 734 8342

    Email: trsmith@partners.org


    Background: The value agenda in healthcare has created legislative reform, merit-based reimbursement systems, public reporting of surgeon scorecards, and patient-centered neurosurgical outcomes tracking. Though technological innovations for the intra-operative experience continue to abound, technological advances such as artificial intelligence, big data, and wearable technology have yet to become standard tools for outcomes measures in neurosurgery.

    Objective: The purpose of this work was to review existing tools for outcomes research in neurosurgery and to characterize the disruptive innovation created by artificial intelligence, big data, and wearable technology.

    Methods: Gold standards for neurosurgical patient-reported outcomes were compared to ongoing work in our center as well as major developments in the fields of mobile health, computer science, and health informatics.

    Results: The gold standards for neurosurgical outcomes measures (pain scale, Oswestry Disability Index, Euro-Qol 5D, Short Form Health Survey, etc.) provide limited information on time-dependent, longitudinal patient recovery outside of the clinical setting. Our work with smartphone-enabled passively collected data allows for continuous, real-time monitoring of 9 different data streams generating over 1 million data points per day per patient. Artificial intelligence capabilities, including natural language processing and machine learning, quantify and digitize patient quality of life from electronic medical records, audio recordings, and free text notes. Quantification of patient outcomes is further aided by the creation of wearable physiological sensors specific to neurosurgery, such as a serum sodium sensing wearable with WiFi communication capabilities to prevent complications and readmissions of delayed symptomatic hyponatremia post-transsphenoidal surgery.

    Conclusions: Systems-level risk adjustment, high-value care, and real-time tracking of functional recovery is enabled by passively collected data. The future of outcomes measures in neurosurgery requires the translation of validated, gold standard assessments into the modern era of big data, artificial intelligence, and wearable technology.

    iproc 2016;2(1):e10

    doi:10.2196/iproc.6129

    Keywords

    neurosurgery; outcomes measures; artificial intelligence; big data; wearable technology; predictive analytics 

    ‎

    Multimedia Appendix 1

    Poster.

    PDF File (Adobe PDF File), 1MB

    Edited by T Hale; submitted 06.06.16; peer-reviewed by CHS Scientific Program Committee; accepted 02.08.16; published 14.12.16

    Copyright

    ©Aditya V Karhade, Joeky Senders, Marike L Broekman, William B Gormley, Timothy R Smith. Originally published in Iproceedings (http://www.iproc.org), 14.12.2016.

    This is an open-access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in Iproceedings, is properly cited. The complete bibliographic information, a link to the original publication on http://www.iproc.org/, as well as this copyright and license information must be included.