Let us look back at the history: How did we reach here?
Over past 3-4 decades our interaction with computers has progressed through the GUI, www revolution, mobile revolution including TUI and now Voice revolution, VUI and conversational AI.
The Era of VUI has great promise
as Voice is Natural mode of communication
Convenient
Scalable
Rich Content
Metadata
1989: World Wide Web invention
Jan 2007: First I phone released, beginning of smart phone era
2011 –present: Era of Conversational AI ( Siri) -- home Pod (2018)
Google now--- Google assitant
The Era of VUI has great promise
Foundation of conversational AI is NLP, hence lets us start with it.
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).
It includes smart voice enabled devices, chat bots and virtual assistants
Two common applications of Conversational AI are virtual assistants and chatbots, these are also known as virtual or conversational agents.
A virtual assistant (e.g. Apple’s Siri, Google Assistant, and Amazon Alexa) is an AI-inspired software agent that is capable of performing certain tasks or services via text or voice.
A chat bot is a conversational AI application that is capable of providing information to the user. Virtual voice assistant helps the user in performing simple daily tasks
We as intelligent human beings perform 4 important tasks, perceive the environment around us through our sensory organs, understand what we sense and act/execute accordingly and also learn from our past actions and experiences.
For intelligent machines to indulge in natural conversation, 4 human like capabilities are needed.
Machine Perception of speech/voice takes thru speech/voice recognition
Machine Comprehension occurs thru NLP
Machine Execution occurs via NLG
Learning from prior actions or results, which occurs thru ML
There are many ways in we encounter conversational AI in our daily lives. These are in form of smart speakers,
Smart displays next evolution of smart speakers and include Voice + touch screen Display : Amazon Echo show, Google home hub, Facebook portal
Conversational AI (CAI) in health care delivery brings few considerations:
How can we use use it to ease our daily life?
Augment care we provide, leveraging its optimum use?
How can we Foster its development as a community?
Understand and overcome the challenges in its adoption?
Voice technology can be used to achieve:
Improve clinician experience/decrease physician burnout
Improved patient experience and engagement
Ultimately leading to better outcomes
Ambient clinical intelligence (ACI) — a comprehensive, AI-powered, voice-enabled solution — uses ambient sensing technology to securely listen to clinician-patient encounter conversations while offering workflow and knowledge automation to complement the EHR. It has three components:
Ambient sensing technology: Clinicians engage in conversation with their patient while a wall-mounted purpose built healthcare device uses a multi-microphone array and integrated machine vision to capture and track audio.
2. User-initiated virtual assistants: Simply say “Hey Dragon” to get information in and out of the EHR. Use natural language to reduce the time it takes to document care, navigate patient charts, and follow up on documentation details.
3. Automated Documentation Services: During an encounter, every spoken word is diarized with speech recognition and automatically translated into a draft clinical note using discrete data that’s delivered to the clinician for authentication directly through the EHR.
https://www.nuance.com/healthcare/ambient-clinical-intelligence.html
Voice technology can be used to enhance patient experience at various points in their health care journey.
This slide illustrates the Functional Spectrum of Voice Enabled Virtual Health Assistant.
There are 3 important functional groups.
First is assistance with information, care navigation and education.
Second is use as digital interface between pt and provider thus helping for home based remote monitoring which is evolving as an important component of virtual care.
Third is Chronic care management and promotion of wellness specially important for high risk patients such as CHF, HTN, diabetes
Let us look at second value proposition of voice: in improving patient experience.
This slide shows 3
This slide illustrates an innovative care delivery model which I have labelled as Voice Integrated Connected Intelligence
This is a good example of man-machine intelligence synergy and leverages technology such as remote monitoring devices, voice, virtual assistants, AI to connect patient to the care providers, augmenting care delivery at home.
This has 3 important interconnected components. First is remotely monitored patient, and voice enabled virtual assistant, second is the AI engine and third is the multidisciplinary care delivery team.
Patient’s voice commands and digital remote monitoring signals are transmitted via the virtual voice assistant (gateway) to the AI engine and as needed to Care delivery team.
The AI Engine enables RTAP of this input and in conjunction with care provider team, provides personalized and actionable health promoting insights, delivered back to the patient via voice enabled virtual assistant.
Let us look at the challenges in Conversational AI adoption. These include:
Maintenance of Privacy and security of confidential Health Information,
Accuracy and reliability of information provided by the CAI
Building of trust by the end user.
Ethical use of exchanged health information
And last but not the least optimum design and smooth work flow integration for the end user.
Looking ahead in future, consideration should be given to humanizing the VA by making their response proactive, incorporating context specific empathy for the end user, cognitive capabilities and On-device AI, so they can be great companion and asset for the end user.
In future consideration should be given to
1. Designing Smart Voice enabled Clinician friendly workflows
2. Development of Advanced HCI solutions: Voice integrated Proactive Humanoid Virtual Assistants with integrated
Cognition & Empathy.
4. Hybrid technology: integration of CAI+AR to form intelligent reality , CAI +Robotics can be used to design children Friendly applications
5. Voice integrated RPM
6. Integrated Voice biomarkers in multimodal AI solutions
In conclusion
CAI can be used as Intelligent user interface for patients and providers in augmenting care delivery
Good UX enabled by Human Centered design, Smooth workflow integration, Data privacy and security are integral to successful implementation.
Voice technology is emerging as the new digital health utility
Field of Voice Biomarkers is an emerging frontier and can be used as adjunct to other digital biomarkers, for risk prediction in early warning systems