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.


From Harlow on Healthcare, host David Harlow sits down with Yann Fleureau, co-founder and CEO of Cardiologs, go deep into AI, algorithms that read 5000 EKGs a month all over the world, and the empathy that is the irreplaceable core of the clinician in an encounter with a patient, no matter how sophisticated our tools become.

In the News

Identify, Predict & Track Patients at Risk for COVID-19
Healthcare AI company, Pieces Technologies (@PiecesTech), announced it has developed a COVID-19 module that will aid health systems’ response to the novel coronavirus. Using the company’s proprietary AI framework, Pieces DS, a specifically configured COVID-19 module will track potentially at-risk patients, pre and post testing; monitor patients for clinical deterioration directly in a hospital’s electronic medical record; and support resource planning and risk stratification for health system administrators.

HealthTap Announces Free COVID-19 Virtual Doctor Visits In Partnership With Doctors Across U.S.
HealthTap (@HealthTap), a virtual primary care provider, announced that it will offer a free virtual doctor visit to anyone in the U.S. who is worried about symptoms that could be related to COVID-19. Doctors from the company’s network of 90,000 US board-certified physicians are volunteering their time to provide these visits by text, phone, or video. HealthTap uses proprietary technology similar to those of ride-sharing and delivery companies to match patients with doctors in real time and at scale.

BioDuro Initiates Effort to Develop COVID-19 Nanobody Therapeutic
BioDuro LLC (@BioDuroLLC), a global life sciences contract research and development organization, announced that it has initiated a COVID-19 nanobody therapeutic program, leveraging the company’s biologics discovery platform and a specialized COVID-19 dedicated team. The cornerstone of the effort includes screening more than 10 billion human synthetic antibodies generated using Artificial Intelligence (AI) computing and high-speed DNA mutagenesis technology.

PhysIQ’s Proprietary Personalized Analytics to be Used for COVID-19 Care with Newly Broadened FDA Labeling
The FDA has sanctioned labeling for pinpointIQ®, physIQ’s (@PhysIQ) continuous remote monitoring system for use in the COVID-19 pandemic, including application of its proprietary Multivariate Change Index. During this pandemic, pinpointIQ may be used to provide continuous physiologic remote monitoring to homebound or quarantined patients with confirmed or suspected COVID-19 or those whose high-risk profile that requires continuous remote monitoring, for example, those with heart failure, COPD, or hypertension. By passively collecting wearable sensor data and applying advanced analytics, pinpointIQ may ease burden on hospitals and other healthcare facilities and reduce the risk of exposure for patients and healthcare providers to SARS-CoV-2 and conserve resources for the very sickest.

Nanox Announces Agreement With CureMetrix For AI-based Assistive Diagnostic Tool to Support Nanox Cloud Platform
NANO-X IMAGING LTD (@NanoxVision), an innovative medical imaging company, announces its collaboration with CureMetrix® (@CureMetrix), a global healthcare technology company that develops AI-driven software for radiology, to integrate the CureMetrix advanced AI diagnostics solution into Nanox’s planned cloud-based software platform, the Nanox.CLOUD.

Core Scientific Offers Free Access for COVID-19 Research
Core Scientific announced it is making its powerful Cloud for Data Scientists™ available at no charge for those entities engaged directly in research related to the containment or eradication of the COVID-19 virus, or other healthcare research organizations whose data scientists have been displaced due to restricted facility access. The Cloud for Data Scientists™ combines NVIDIA DGX systems for compute and high-performance, flash storage technology, providing accelerated GPU compute, tuned to the demands of deep learning.

Start-up BlueSpot AI launches the first national platform for people to find Coronavirus Temporary Testing Locations across the U.S.
BlueSpot AI Inc. (@BlueSpotAI), an artificial intelligence start-up, launched FindCoronaTest, the first national website for people to find Coronavirus temporary testing locations in the US. The website allows people to search for temporary testing locations all across the country, based on publicly available information that has been verified. People who may be experiencing COVID-19 symptoms can filter by state or enter their zip code to find the closest testing location. Right now, there are a limited number of temporary testing locations across the country, however, the BlueSpot AI team is committed to keeping this website as up-to-date as possible throughout the time of this pandemic.

Kyruus and GYANT Announce Partnership to Facilitate Chat-Based Patient-Provider Matching and Scheduling
Kyruus (@kyruus), the leader in provider search and scheduling solutions for health systems, and GYANT (@Gyant), the leading artificial intelligence-enabled virtual assistant for healthcare, announced a new partnership to help health systems enhance consumer access and self-service on their websites. The two companies will join forces to combine the power of Kyruus’ routing and scheduling platform with GYANT’s chat-based virtual assistant to help consumers find and book appropriate care through a conversational experience.

CynergisTek’s Seasoned Privacy Investigators Leverage Artificial Intelligence for the Detection of Snooping Related to the Coronavirus
CynergisTek (@cynergistek), a leader in cybersecurity, privacy, and compliance, has updated its Patient Privacy Monitoring Services (PPMS) to support the proactive identification of insider snooping related to cases of the coronavirus/COVID-19, which has taken over the headlines. Information related to cases such as who has been tested or who has been diagnosed is extremely valuable during these moments when there are a lot of unknowns and misinformation. This will lead to curiosity from the workforce around those seeking care for associated symptoms, ultimately compromising the patient’s privacy in a time of need.

Rapid Diagnosis Test for Coronavirus COVID-19 Now Available
Surgisphere Corporation announces the availability of a rapid diagnostic tool for novel coronavirus. Leveraging the power of its global research network and advanced machine learning, Surgisphere has developed an intelligent tool that uses as few as three common laboratory tests to identify patients likely to have coronavirus infection. With a sensitivity of 93.7% and specificity of 99.9%, this highly accurate test can help limit transmission of this deadly virus by identifying and isolating affected patients sooner, mobilizing appropriate public health resources, and avoiding the delays associated with current testing.

To Read

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.