Sorting out AI, ML, DL, and NLP

TOPICS:

Posted By: Roberta Mullin September 15, 2021

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 The Incrementalist, host Dr. Nick van Terheyden, aka Dr. Nick, talks to Founder & CEO of Diagnoss, Abboud Chaballout. Discussion includes AI technology augmenting and learning from clinical context of patient and physician, real time insights to help the doctor pick clinical and billing codes, and provide better, faster more accurate billing.

Events

ONC
When: Wednesday, September 15, 2021  4:00 – 5:00 pm ET
Register for this event.

Training Data for Machine Learning (ML) to Enhance Patient-Centered Outcomes Research (PCOR) Data Infrastructure Project – ONC is hosting a webinar to present the outcomes of the Training Data for ML to Enhance PCOR Data Infrastructure Project. The PCOR ML Project worked to advance the application of AI and ML algorithms in PCOR by defining the requirements for high-quality training data sets. Join them to learn about the project’s goals, methodology, and findings from building the training dataset and ML models, and project resources available to researchers.

In the News

Jvion Drives Adoption of Prescriptive Intelligence and Clinical AI with New Peer-Reviewed Results, Platform Integrations and SDOH Solutions
Jvion (@JvionHealth), a prescriptive analytics company, has continued its growth in 2021 with new integrations and partnerships, peer-reviewed results, and social determinants of health solutions designed to help healthcare organizations manage patient populations holistically by addressing clinical and non clinical aspects impacting future risks and costs. The strong momentum reflects a growing awareness in the industry that AI-enabled prescriptive analytics can drive more holistic, cost-effective care.

Sensyne Health and Great Ormond Street Hospital Partner to Apply Ethical AI to Drive Research in Childhood Disease
Sensyne Health plc (@SensyneHealth), the ethical Clinical AI company, announces it has signed a five year non-exclusive Strategic Research Agreement (SRA) with Great Ormond Street Hospital (@GreatOrmondSt) for Children NHS Foundation Trust (GOSH) to analyse anonymised patient data using clinical artificial intelligence (Clinical AI) technology.

Hospitals Deploy Spending on Artificial Intelligence Coding Solutions to Reduce Costs & Payer Denials, Reports Black Book Survey
Black Book Research (@blackbookpolls) surveyed 1,012 health information management executives and revealed that 58% of healthcare organizations are using artificial intelligence in one basic form or another, and 92% of them expect widespread industry implementation in the next five years, despite the extended operational constraints and financial priorities caused by the resurging COVID-19 pandemic. Eleven percent of survey respondent hospitals acknowledge employing AI-powered coding solutions proficiently for at least one year.

OncoHost Wins Frost & Sullivan 2021 Technology Innovation Leadership Award for Excellence in Best Practices
OncoHost (@OncoHost), a next-generation precision oncology for improved personalized cancer therapy company, announced it has been awarded this year’s Best Practices Technology Innovation Leadership Award in the AI-based precision oncology industry by global growth strategy consulting and research firm Frost & Sullivan. The award recognizes a company that has introduced the best underlying technology for achieving remarkable product and customer success while driving future business value.

Product & Company News

Sensyne launches SENSIGHT – A Real World Patient Data Analytics Platform For the Life Science and Healthcare Industries
Sensyne Health plc (@SensyneHealth) also announced that it has launched SENSIGHTÔ, an AI enabled global data analytics platform for the healthcare and life sciences sectors. SENSIGHT is built on a rapidly growing, deep and broad set of de-identified patient data derived from the research partnerships Sensyne has entered into with U.S. health systems and NHS Hospital Trusts in the UK that currently covers more than 22.5 million patients across a range of disease areas.

Swoop Introduces New Products to Redefine Physician Engagement Beyond Typical 1:1 NPI Targeting and Revolutionize Heath Care Provider Marketing
Swoop, an AI-generated digital audiences for healthcare company, announced the release of its newest product offerings that uncover optimal healthcare provider (HCP) influencers for life sciences companies. This first-in-market approach re-imagines HCP targeting in digital advertising beyond conventional National Provider Identifier (NPI) targeting by applying machine learning and artificial intelligence (AI) against a proprietary real-world data universe to uncover HCPs with the highest propensity to be influential brand ambassadors.

Dosis Expands Kidney Care Platform With Iron Advisor Tool To Personalize Anemia Management
Dosis (@dosisinc), an artificial intelligence-powered precision dosing company, announced the expansion of its kidney care platform with the release of its Strategic Iron Advisor (SIA). It is being introduced as the first precision dosing tool on the market for intravenous iron.

Prevencio’s Novel AI-Driven HART CADhs Blood Test Significantly More Accurate than Troponin for Obstructive Heart Disease
Prevencio, Inc. (@Prevencioinc) announces the presentation of multinational patient data demonstrating its AI-driven HART CADhs blood test is more accurate than high sensitivity troponin in determining whether a patient has obstructive heart disease. Cardiologists from University Heart Center of Hamburg Germany, Massachusetts General Hospital, and Inova Heart and Vascular Institute collaborated to test 924 patients for blood diagnosis of heart disease. HART CADhs had 80% accuracy as compared to high sensitivity troponin’s accuracy of 63%.

RSIP Vision Announces Patient-Specific, Intraoperative Registration Module for Orthopedic Surgery
RSIP Vision (@RSIPvision), a clinically proven company in real-world AI solutions for medical image analysis, announced a novel 2D to 3D registration module that will improve the execution of Orthopedic surgeries, such as total hip arthroplasty. Utilizing a proprietary neural network, trained on patient-specific imaging, this module will enable powerful, automated intra-operative assessments in real time of the true location and positioning of the implants and bones increasing accuracy and improving the surgery execution.

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.

Linguamatics on NLP

What is Text Mining, Text Analytics and Natural Language Processing? – Text mining (also referred to as text analytics) is an artificial intelligence (AI) technology that uses natural language processing (NLP) to transform the free (unstructured) text in documents and databases into normalized, structured data suitable for analysis or to drive machine learning (ML) algorithms.

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.