Florida Doctor

FLDR 2019 Spring

Florida Doctor Magazine. Helping Doctors to a better practice and better life

Issue link: https://issues.floridadoctormag.com/i/1092670

Contents of this Issue

Navigation

Page 37 of 59

38 f l o r i d a d o c t o r rtificial intelligence is providing significant growth opportuni- ties for healthcare providers and increasingly impacting patient care, but there are significant challenges to understand and overcome. ere are three components of artificial intelligence. e primary application of AI is a program that can sense, reason, act and adapt. Machine Learning is a growing subset of AI and uses an algorithm whose performance adjusts and "learns" as it is exposed to more data over time. is is also called predictive analysis. A subset of machine learning is called deep-learning, which is a multilayered neural network derived from vast amounts of data. Pilot phases in machine learning and deep-learning models have improved the ability of some healthcare organizations to predict the health of a patient popula- tion before they arrive at the hospital or operating room. Machine Learning e name machine learning was first coined in 1959 by Arthur Samuel. Ma- chine learning applies the construction of algorithms by various data sets that will learn to make predictions. e field of machine learning in healthcare was developed in Ontario in 2004. It first used statistical techniques to give computer systems the ability to "learn" and improve its performance on a specific task based on massive volumes of data points that were programmed. is barometer used in machine learning is called the LACE Index and has become a widely accept- ed measure of quality. e LACE Index essentially predicts future healthcare outcomes based on past medical records and various data points such as length of stay (LOS), diagnosis, the acuity of the patient based on their admission(s) in the last six months and other factors. e program can identify readmission risks or mortality rates within 30 days of a patient's discharge from the hospital. Like the mantra within the financial services industry, "Past performance is no guaran- tee of future results", the LACE Index and applied predictive analysis cannot guaran- tee future patient outcomes. However, it can be a tool for healthcare organizations to enable their medical professionals to treat patients and allocated resources accordingly. Deep Learning In many ways, deep learning helps solves problems that machine learning cannot. Deep learning assists medical profession- als and researchers to find opportunities to serve its patients, and the healthcare industry as a whole, better through data. It structures specific algorithms in layers to create a "neural network" that can learn Artificial Intelligence in Healthcare Growing Trends and Opportunities of AI are Impacting Innovation, Research and Investment in the Healthcare Industry BETTER PRACTICE: Technology Innovation Michael Marzoug, Director of Neurology, Baptist Health Jacksonville A

Articles in this issue

Archives of this issue

view archives of Florida Doctor - FLDR 2019 Spring