3 Ways Machine Learning is Making a Difference in the Healthcare Industry 2164 Views Oct 05, 2018

blg1 The IT industry is constantly on the lookout for improvements and innovations in any of the codes that the developers write down on a daily basis. Improvements and innovations consume time and efforts (I don’t need to tell you this by matter of fact) But nowadays, things are improving on their own! Gone are the days when software developers had to sit down for hours and troubleshoot some random coding problem, or incorporate a new functionality into an existing piece of software. Machine Learning (ML), coupled with Artificial Intelligence (AI), has found applications across diverse industry verticals. And the healthcare industry is no exception to it! Now, ML finds limitless applications in the healthcare industry and providing a detailed account of each of them is beyond the scope of a single article. So, in this blog I’ll tell you the three prime areas of healthcare wherein ML has made things easier for patients and doctors alike –
  1. Sorting Through the Hefty Medical Records
  2. Disease Management
  3. Reduce Mortality Rates
Now, let’s get onto these –
  1. Sorting Through the Hefty Medical Records
Ever heard of neural networks? Well, it’s a form of artificial intelligence software that does a reasonably good job of using data to automatically learn and improve its algorithms. ‘Data’ in this context means those hefty medical records buried between the cardboard files, which are just considered another stack of papers. This is where neural networks come into the picture! These networks, or rather algorithms we can say, can seamlessly sift through data previously out of reach: notes buried in PDFs or scribbled on old charts. And consequently come out with valuable predictions regarding the patient’s treatment outcomes. All this has been developed by none other than Google The outcome was that it reduced the cumbersome paperwork and medical professionals could devote more time on saving precious lives.
  1. Disease Management
For explaining this, we’ll take the one of the top 10 deadly diseases in the world – Diabetes. ML has already come far when it comes to effective management of diseases. But, let’s peek into the background of this concept. The idea came into the foray whenAyasdi’s Chief Medical Officer, Dr. FX Campion detailed the important clinical impact that machine learning software for healthcare industry. Case study:Researchers at Mount Sinai Hospital ran Ayasdi’s topological data analytical models on the data residing in Sinai’s EHR system on patients with type 2 diabetes. From this, they discovered three subtypes of type 2 diabetes: one subtype was more susceptible to kidney disease and eye disease, the second had higher rates of cancer and cardiovascular disease, and the third had a prevalence of neurological issues. Below image represents these subtypes: blg2 Caption: Computational model showing study participants with type 2 diabetes grouped into three subtypes, based on similarities in data contained in their electronic health records. Such information included age, gender (red/orange/yellow indicates females; blue/green, males), health history, and a range of routine laboratory and medical tests. Credit: Dudley Lab, Icahn School of Medicine at Mount Sinai, New York According to Dr. Campion, patients can be sub typed by pathology professionals at the onset of type 2 diabetes, and with this they’ll be able to map the best course of treatment. “We are at the dawn of precision medicine,” Campion said on the occasion.
  1. Reduce Mortality Rates
Now, this is something researchers have strived for years together! ML, along with AI, has taken leaps in this arena, too. Instead of explaining the complex algorithms that have made this possible, I’ll quickly run you through a recent case study that bears testimony to the fact that machine learning has indeed been instrumental in reducing the mortality rates of hospital patients – Case study:This is the case of Cabell Huntington Hospital in Huntington, West Virginia. Last year, it faced sepsis head-on and came out on top. Implementing machine learning technology specifically designed to fight sepsis in part through clinician alerts, the organization saw the sepsis-related in-hospital mortality rate was 33.5 percent lower during the post-implementation period and the average sepsis-related hospital length of stay was 17.1 percent lower during the same period. Analyses included 2,298 adult patients in the emergency department and intensive care unit. Cabell Huntington Hospital clinicians and I.T. staff initially built an electronic Systemic Inflammatory Response Syndrome (SIRS) and sepsis alerting system in Cerner based upon a rules-based model they learned about from Methodist Memphis Le Bonheur. There were two types of alerts: 1) A SIRS alert that appears in the EHR when a patient has three or more critical vital signs or certain laboratory result values, and 2) A sepsis alert when a patient meets two or more SIRS criteria and also has a lab result indicating organ dysfunction. These alerts were intended to prompt clinicians to initiate a sepsis treatment bundle. (For full article: https://www.healthcareitnews.com/news/hospital-leans-machine-learning-reduce-sepsis-related-mortality-rate) Apart from this, here are some statistics that backs up such use-cases: blg3 Outcomes in (A) sepsis-related mortality, (B) sepsis-related length of stay and (C) sepsis-related 30-day readmissions before implementation of the machine learning algorithm and in each post-implementation period, including the April–May post-implementation steady state. Source: McCoy A, Das R Reducing patient mortality, length of stay and readmissions through machine learning-based sepsis prediction in the emergency department, intensive care unit and hospital floor units BMJ Open Qual 2017;6:e000158. doi: 10.1136/bmjoq-2017-000158 What’s in Store? As human beings, we would never be able to predict the scope of such technologies and the impact that it can have on humanity. Innovations tend to get better with time. Although in this article we saw just three major dimensions of ML and how it is changing the healthcare scenario for the better, there are many more! Just take an example – Google has built algorithms that have successfully predicted when a patient will die! Personalized medicine and autonomous robotic surgery are also in the offing. And, brace yourselves for many such novelties in the future! 5/5 (217)

Rate Us!

Leave a Reply

Your email address will not be published. Required fields are marked *

Lets start discussing your concept

Let`s Connect