Sorting out AI, ML, DL, and NLP

TOPICS:

Posted By: Roberta Mullin December 9, 2020

The alphabet soup of acronyms in the world Artificial Intelligence. What are they? What do they mean? What is the difference between them? This is our ongoing reporting on AI and how it is being integrated into healthcare technology. We are seeking out the thought leaders and innovations that are moving the needle forward using artificial intelligence. Read more posts on Artificial Intelligence in Healthcare.

Follow the hashtag #AIinHealthcare.

To Listen

From Harlow on Healthcare, host David Harlow speaks with Jeremy Orr, MD, CEO of Medial Early Sign about applying the power of AI to lab data to identify and prioritize care for high risk patients so that scarce resources can be targeted where they can do the most good.

In the News

Biofourmis Announces National Rollout of the Biovitals® Hospital@Home™ Platform to Help Deliver Hospital-Level Care in the Home Aligned with New CMS Program
Biofourmis (@biofourmis), a Boston-based global company in digital therapeutics and virtual care that powers personalized predictive care, announces the national rollout of Biovitals® Hospital@HomeTM—an artificial intelligence-based, turnkey technology platform that enables hospitals and health systems to quickly deploy a “hospital at home” program.

New Study Highlights State of Artificial Intelligence in the Healthcare Industry
Healthcare organizations seeking to implement and extend their artificial intelligence (AI) capabilities struggle with finding skilled personnel and sufficient, high quality data, according to a new IDC White Paper, sponsored by InterSystems (@InterSystems), AI In Healthcare: Early Stage with Steady March to Maturity.

Canon Medical Offers AI-Powered Stroke Triage With Automation Platform AUTOStroke Solution for CT
With stroke, the key to improving outcomes is speed. However, busy facilities don’t always have the luxury of knowing when an immediate intervention is needed. To help clinicians identify and triage stroke as quickly as possible, Canon Medical Systems USA, Inc. (@CanonMedicalUS) is launching Automation Platform AUTOStroke, an artificial intelligence (AI)-powered deep-learning clinical workflow automation solution for CT. AUTOStroke integrates a comprehensive set of applications that automatically delivers accurate and fast clinical insights to emergency and stroke teams.

GE Healthcare Expands AI, Digital and Imaging Solutions at #RSNA2020, Helping Shape Future of Healthcare in the COVID Era
GE Healthcare (@GEHealthcare) unveiled a slate of new intelligently efficient solutions to help clinicians solve today’s two-part challenge of delivering high quality care while managing greater capacity and workflow issues, exacerbated by the impact of COVID-19. Building on continuing investments in innovation and digital health momentum, GE Healthcare is expanding its AI offerings and Edison ecosystem, and also introducing breakthrough imaging innovations that will help shape the future of healthcare.

Diagnoss Launches AI-based Medical Coding Assistant to Augment Tedious, Time-Consuming, and Error-Prone Coding Process
In 2019, the U.S. spent more than $3 trillion on healthcare, 95% of which was dispersed through an insurance company, where every dollar must be codified. To respond to that fundamental – and still very inefficient – element of our healthcare system, Diagnoss announced the first AI-based medical coding assistant that augments, not just automates, the medical coding process. The Artificial Intelligence Engine delivers providers and billing teams alike with real-time feedback on their documentation and coding, constantly learning to improve each clinic’s system’s accuracy.

3rd Annual Optum Survey on AI in Health Care
The third annual Optum Survey on AI in Health Care (@Optum) showed that optimism about AI is fueled by seeing more and more tangible benefits, including improving health care outcomes and business performance. Most importantly, these insights demonstrate that as those in late-stage AI implementation grow more familiar with AI — as well as the benefits it yields — they in turn become more comfortable and confident, generating momentum in which AI grows more beneficial more quickly.

Google Cloud: Healthcare Gets More Productive with New Industry-Specific AI Tools
Google Cloud (@googlecloud) is launching in public preview a suite of fully-managed AI tools designed to help with these challenges: Healthcare Natural Language API and AutoML Entity Extraction for Healthcare. These tools assist healthcare professionals with the review and analysis of medical documents in a repeatable, scalable way. The hope is that this technology will help reduce workforce burnout and increase healthcare productivity, both in the back-office and in clinical practice.

Product & Company News

Neuroglee Therapeutics to Attack Alzheimer’s Disease Through Personalized AI-Powered Digital Therapeutics
Neuroglee Therapeutics (@neuroglee), which builds personalized evidence-based prescription digital therapeutics for neurodegenerative diseases, has announced its company launch with $2.3 million in pre-seed funding. Neuroglee’s technology leverages artificial intelligence (AI), machine learning and novel digital biomarkers with the goal of slowing the progression of neurogenerative diseases—starting with Alzheimer’s disease.

AliveCor Raises $65 Million for Remote Cardiology Platform
AliveCor (@AlivecorIndia), an AI-enabled (medical-grade) mobile electrocardiogram device, raised $65 million in a Series E financing round led by existing investors OMRON, Khosla Ventures, WP Global Partners, Qualcomm Ventures, and Bold Capital Partners.

To Read

Matthew Lamons

To Follow

The Basics and Resources

From the leading text book around the world, Artificial Intelligence: A Modern Approach.

Artificial Intelligence is composed of six different disciplines:

  1. Natural Language Processing to enable it to communicate successfully in English
  2. Knowledge Representation to store what it knows or hears
  3. Automated Reasoning to use the stored information to answer questions and to draw new conclusions
  4. Machine Learning to adapt to new circumstances and to detect and extrapolate patterns
  5. Computer Vision to perceive objects
  6. Robotics to manipulate objects and move about

To build a generally intelligent agent, you need machine learning in addition to the other aspects mentioned above.

Machine Learning is roughly the science of prediction. Given certain knowns (features), you wish to predict some unknowns (targets). The unknown could be structured (e.g. numeric) or unstructured (e.g. a string response).

Deep Learning is a sub field of machine learning where concepts are learned hierarchically. The simplest concepts emerge first, followed by more complicated concepts that build on the simpler ones. Usually, this leads to a simple layered hierarchy of concepts.

Optum Resource Library

Natural Language Processing: AI with an ROI
Health care providers need to see a return on any analytic investment they make. Natural language processing (NLP) is one way AI can help providers convert the potential within their health data into quality improvement and cost savings. Natural language processing is an AI technology that actually makes sense for health care.

IBM Analytics

Navigating the A.I. and Cognitive Maze – If you work in the area of Artificial Intelligence (AI) and Cognitive Computing, you might use buzz words and phrases which to others might be perceived as confusing jargon. This article attempts to explain what these terms mean, how they relate to one other and where they all fit along the AI and cognitive time continuum. I include a glossary of my top 20 useful AI/cognitive terms — and advice on getting started on your AI/cognitive journey.