Sorting out AI, ML, DL, and NLP

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

Have you heard any PopHealth Minutes on the radio yet? On this PopHealth Minute: Descriptive, Predictive and Prescriptive Analytics, listen to Fred Goldstein, president and founder of Accountable Health, LLC as he gives tips, observations and insights into the broad and growing field of population health.

In the News

Novarad Launches New COVID-19 Artificial Intelligence Software, Available for Free Download Worldwide
Novarad (@NovaradCorp), a transformative imaging technologies company, is launching its new COVID-19 AI Diagnostic Assistant worldwide to make fast, accurate diagnosis of COVID-19 possible – free of charge. In partnership with Intel Corp., and leveraging Azure, Microsoft’s cloud computing service, Novarad is offering free use of a diagnostic system that combines DICOM routing, encryption, an AI processing engine, and secure reporting for the detection of COVID-19 from CT scans. This unique algorithm can produce diagnostic results in seconds, rather than days, enabling clinicians to rapidly isolate and treat patients who are likely suffering from COVID.

Covera Health Enhances its Radiology Center of Excellence Program with Mammography AI for Breast Cancer Detection
Covera Health (@coverahealth), a provider of clinical analytics solutions to reduce medical misdiagnoses and improve healthcare quality, announced the integration of ScreenPoint Medical’s artificial intelligence (AI) tools into its quality analytics platform. Covera plans to leverage these tools to improve early detection of breast cancer for both patients and providers, which has been proven to drive more effective –– and often less invasive –– treatment, improving outcomes for women nationwide.

Confidence in Artificial Intelligence Increases as Health Industry Leaders Project Faster Return on Investment, Signal Growing Need for Broad Range of AI Expertise
Health care executives today believe artificial intelligence (AI) will deliver value for the industry faster than previously thought, according to a new survey of 500 senior health care executives representing leading hospitals, health plans, life sciences and employers. The third annual Optum (@OptumIQ) Survey on Artificial Intelligence (AI) in Health Care found that 59% of executives surveyed expect their organizations will see a full return on their AI investments in under three years, nearly double the 31% of leaders surveyed in 2018 who expected to break even that quickly.

Revint and Triage Become Cloudmed™, The Industry’s Most Comprehensive and Intelligent Revenue Integrity Platform
Revint, a data-driven revenue integrity solutions company for healthcare providers, announced it has completed its merger with Triage Consulting Group, the nation’s leading hospital revenue review company. Together, the two companies are now rebranded Cloudmed. The merger creates a unique, first-of-its-kind, single source enterprise platform that delivers Revenue Intelligence™ for a smarter, more predictive way for hospitals and health systems to realize all potential revenue from the care they provide.

Patient Forecaster’s Precision Staffing Tool Now Includes Predicted Hourly Bed Capacity, Patient Volumes and Hospital Admissions for Regional COVID-19 and Expected Flu Figures
Patient Forecaster (@PatientForecas1), an AI-powered precision staffing platform, announced the latest release of its emergent and urgent staffing tool. This breakthrough technology offers emergency department and urgent care center leaders’ greater predictability of patient volumes, bed capacity, hospital admissions and staff scheduling. Better predictability allows for tighter alignment of staffing with patient demand, thus lowering overall cost of care. It also improves the joy of work for providers as they are better matched to serve the needs of patients and their families.

MedTech Startup See-Mode Technologies Receives FDA Clearance for AI Software That Automatically Analyses and Reports Vascular Ultrasound Scans
See-Mode Technologies, a MedTech startup based in Singapore and Australia that seeks to empower clinicians to better predict stroke, announced that it has received 510(k) clearance from the U.S. Food and Drug Administration (FDA) for its debut product, Augmented Vascular Analysis (AVA), a world-first medical Artificial Intelligence (AI) software for automated analysis and reporting of vascular ultrasound scans.

Startup 98point6 Announces $118 Million Series E
98point6 (@98point6Inc) offers patients easy access to primary care in the same way they’ve grown accustomed to receiving the majority of services today—on their schedule and via a mobile app. Pairing artificial intelligence (AI) and machine learning with the expertise of board-certified physicians, its patient-focused and technology-augmented solution makes primary care more accessible and affordable, leading to better health and total cost-of-care savings. This innovative approach is enjoying rapid adoption, and employer partners are experiencing, on average, 8x higher utilization of the 98point6 service than with their previous, traditional telemedicine solutions.

GE Healthcare Introduces New Edge Technology Designed to Give Clinicians Rapid Access to Critical Data
GE Healthcare (@GEHealthcare) introduced Edison HealthLink, new edge computing technology designed specifically for the needs of healthcare providers, that allows clinicians to collect, analyze and act upon critical data closer to its source. With 10 applications already available through Edison HealthLink – including TrueFidelity image reconstruction, Mural Virtual Care and CT Smart Subscription – the solution gives healthcare providers another entry point into the Edison ecosystem.


RSNA 2020
When: November 29 – December 5, 2020
Hashtag: #RSNA20

Join the brightest minds during the most important week in radiology and experience the ease of an all-virtual event. RSNA 2020 is where you’ll find fresh opportunities to connect with the global radiology community and get a front row seat to the latest research, education and technological advancements.

AI Showcase
Experience the possibilities of artificial intelligence (AI) firsthand. The AI Showcase is your central hub for all things related to AI and is where you can visit and network with our featured AI showcase exhibitors, learn about the latest innovations and technical solutions in the AI Theater, and see the winners of the AI Challenge. Also, get a peek into the future of clinical practice at the AI Imaging in Practice demonstration.

To Read

In this article from Nature, they describe how a collaboration among data scientists, electronic health record (EHR) programmers (vendor- and health system-based), clinical informaticians, frontline physicians, and clinical leadership led to the development, prospective validation, and implementation of a machine learning model for real-time prediction of favorable outcomes within a 96 h window among hospitalized COVID-19 patients.

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.