3. Physician’s Brain and Machine-Equivalent
capabilities
Chang A. Analytics and Algorithms, Big Data, Cognitive Computing, and Deep Learning in Medicine
and Health Care. AI Med Ebook; 2017
Language and
Speech:
Broca’s and
Wernicke’s areas
4. Natural Language Processing (NLP)
• This AI methodology allows the computer to understand spoken as well as
written human language
• NLP = NL Understanding (NLU)+ NL Generation (NLG)
Chang A. Analytics and Algorithms, Big Data, Cognitive Computing, and Deep Learning in Medicine and Health Care. AI Med Ebook; 2017
5. Clinical NLP: Use cases
MD Work Flow
Augmentation
Care Delivery
Revenue
Optimization
Research
Patient Portal
UX
Conversational
AI
This session will focus on NLP and Conversational AI (using voice as human-machine communication interface) and applications of this technology in patient and physician facing solutions.
At the onset it is good to Understand machine intelligence functions in context of Natural Intelligence. This figure taken from Dr Chang’s E book referenced below, relates the
Speech and Language function of human brain Served by Brain’s Broca’s and Wernicke’s areas with Machine equivalent capability of Natural Language processing.
Let us define NLP
Let us look at the use cases of NLP in context of clinical care. This figure illustrates the broad functional groups where NLP can be applied.
Physician Work flow augmentation: Speech recognition and EHR documentation
Care delivery: Clinical decision support, Risk stratification and predictive analytics
Revenue optimization: Computer assisted coding, Automatic preauthorization, No show prediction
Research: Clinical trial matching, Registry reporting
Conversational AI: Conversational agents (Virtual agents, chatbots), Voice Biomarker analysis
Patient portal UX: NLP tools linking medical terms in portal documents to simple definitions and explanations for the patient, will help to improve patient’s EHR understanding and portal user experience
As illustrated in previous figure, An important application of NLP is in conversational AI.
Conversational AI: Human Machine interaction through the use of conversation, utilizing voice user interface and Machine Intelligence.
This is made possible by synergistic convergence of Voice technology, and Artificial Intelligence technology (Natural Language processing, Machine and Deep Learning).
There are three important reasons why it is opportune time for Health care sector to adopt Conversational AI technology
1. Voice is convenient to use since it is most natural form of Human communication, additionally it offers rich content, context, and metadata which can be appropriately leveraged depending on the use case. There is also increase in use of VUI.
2. Advancement in Natural language processing, deep learning, and cloud computing, are enabling increase in functionality of voice enabled applications.
3. From perceptive of Economics, the decrease in price point at which these voice technologies are currently being offered in the market, has increased affordability and potential for widespread adoption.
It is time to also think of the New care delivery model in Voice augmented world, where patients, providers and machines can interact with each other through the user of CAI
With this introduction lets us Let’s hear from our Panelists regarding few key takeaways from this sessions
First: What is Current State and what are the Future Prospects of NLP and CAI ?
Second: what the Challenges in Conversational AI Adoption
I would like to close with this thought provoking question for all: Will there be a Voice First World?