Over a million developers have joined DZone.
{{announcement.body}}
{{announcement.title}}

Machine Learning in Healthcare — From Theory to Practice

DZone's Guide to

Machine Learning in Healthcare — From Theory to Practice

Patient-facing machine learning systems may be some way off, but ML could soon be found to support diagnostic, prognostic and supportive decisions in clinical settings.

· AI Zone ·
Free Resource

Insight for I&O leaders on deploying AIOps platforms to enhance performance monitoring today. Read the Guide.

Machine Learning (ML) research in the healthcare field has been ongoing for decades, but almost exclusively in the lab rather than in the doctor’s office. The problem of implementing ML in patient-facing settings largely stems from two barriers:

  • Regulation: in a highly regulated industry like healthcare, there currently exist very few guidelines on the use of ML. This is beginning to change, as just last month the US Food and Drug Administration announced a new regulatory framework designed to promote the use of AI-based technologies.
  • Litigation: ML “mistakes” do not fit comfortably in either the “doctor’s negligence” or “defective product” lawsuits we typically see in healthcare today. Determining compensation for patients injured by the use of ML may require new laws, or else a compensation scheme similar to vaccine complications.

As a result, we’re most likely to see the implementation of ML solutions in clinical systems first. For example:

  • Prognoses: data drawn from electronic health records or claims databases will help refine prognosis ML models, enabling more accurate predictions of medical outcomes.
  • Diagnoses: ML is set to improve diagnostic accuracy, which will result in reduced incidences of overtesting as the ML algorithm learns to send patients for high-value tests only.
  • Decision Support: ML systems based on medical imaging recognition will greatly aid in the work of radiologists and anatomical pathologists. ML models are also likely to be applied to streaming data (e.g., life signs monitoring) to automate many of the tasks now taken on by anesthesiologists and critical care personnel.

As barriers are removed and progress into the clinic is achieved, more and more companies are starting to invest in ML for healthcare. In 2012, there were fewer than 20 artificial intelligence startups focused on healthcare; last year there were almost 70. That number is sure to increase as diagnostics, genetics, and disease treatment data — complex, multivariate data uniquely suited for ML use — continues to grow at an unprecedented pace.

With an aging population and skyrocketing healthcare costs, the rewards for ML solution providers keep growing. In fact, McKinsey predicts that “ML in pharma and medicine could generate a value of up to $100B annually, based on better decision-making, optimized innovation, improved efficiency of research/clinical trials, and new tool creation for physicians, consumers, insurers, and regulators.”

Download our Machine Learning in Healthcare Guide, which provides practical information on how to get started in ML along with recent examples of successful solutions.

TrueSight is an AIOps platform, powered by machine learning and analytics, that elevates IT operations to address multi-cloud complexity and the speed of digital transformation.

Topics:
advanced machine learning in python ,healthcare market research ,telemarketing script for healthcare ,healthcare market research reports ,appointment setting script for healthcare ,artificial intelligence ,ai

Published at DZone with permission of

Opinions expressed by DZone contributors are their own.

{{ parent.title || parent.header.title}}

{{ parent.tldr }}

{{ parent.urlSource.name }}