Emerging Frontier in Health Care Delivery Conversational AI & - - PowerPoint PPT Presentation

emerging frontier in health care delivery conversational
SMART_READER_LITE
LIVE PREVIEW

Emerging Frontier in Health Care Delivery Conversational AI & - - PowerPoint PPT Presentation

Emerging Frontier in Health Care Delivery Conversational AI & Virtual Voice Assistants AIMed JAI NAHAR, MD, MBA 11-14 Dec. 2019 Associate Professor of Pediatrics George Washington University School of Medicine Laguna Niguel Attending,


slide-1
SLIDE 1

Emerging Frontier in Health Care Delivery Conversational AI & Virtual Voice Assistants

JAI NAHAR, MD, MBA Associate Professor of Pediatrics George Washington University School of Medicine Attending, Division of Cardiology Children’s National Hospital, Washington DC

AIMed 11-14 Dec. 2019 Laguna Niguel California

slide-2
SLIDE 2

1. Introductory concepts 2. History: How did we reach here? 3. Current State of Conversational AI 4. Potential uses: The Impact 5. Challenges in Adoption 6. Future Directions

Agenda Conversational AI

slide-3
SLIDE 3

Audience Question

How many of you have used a voice enabled device for your personal health care? Give some examples?

slide-4
SLIDE 4

Voice Augmented World

Health Care AI Voice

Health Care Conversational AI

slide-5
SLIDE 5

Introductory Concepts

Conversational AI: Technology which allows Human Machine interaction through the use of Natural conversation, utilizing voice user interface and Machine Intelligence.

Human Machine

Conversational AI

Voice Technology NLP ML, Deep Learning Synergistic Convergence Conversation

slide-6
SLIDE 6

Conversational AI

Natural Conversation using Machine intelligence

1 Perception/Sense 2 Understanding Comprehension 3 Action/Execution

Speech/Voice Recognition Natural Language processing Natural Language Generation

4 Learn from past actions/experiences

Machine Learning

slide-7
SLIDE 7

History: Human Computer Interaction

GUI WEB www Mobile VUI

1980s

1990s 2000s Present

Voice:

  • Natural mode of

communication

  • Convenient
  • Scalable
  • Rich Content
  • Metadata
slide-8
SLIDE 8

Audience Trivia: To which wave does CAI belong? Four Waves of AI: Dr. Kai-Fu Lee

  • Dr. Kai-Fu Lee, CEO of Sinovation Ventures, "The 4 Waves of Artificial Intelligence Application".

https://www.youtube.com/watch?v=VHuNWDDcEHY

slide-9
SLIDE 9

Audience Trivia Answer Four Waves of AI: Dr. Kai-Fu Lee

  • Dr. Kai-Fu Lee, CEO of Sinovation Ventures, "The 4 Waves of Artificial Intelligence Application".

https://www.youtube.com/watch?v=VHuNWDDcEHY

Conversational AI

slide-10
SLIDE 10

Current State Conversational AI Ecosystem

Smart Speakers Smart Displays Smart voice enabled devices Chatbots Virtual Assistants Ambient Clinical Intelligence

Conversational AI

Voice VUI AI

Ambient Sensors

slide-11
SLIDE 11

Putting Them Together

Conversational AI Health Care delivery

slide-12
SLIDE 12

Conversational AI in Health Care Delivery

  • Use it to ease our professional life?
  • Augment care we provide?
  • Understand and overcome the challenges in adoption?
  • Foster its development as a community?
slide-13
SLIDE 13

Conversational AI

Outpatient clinic

Home On the Go In Hospital

Conversational AI touchpoints in Health Care Delivery

  • 1. EHR documentation, navigation
  • 2. Clinical Decision Support
  • 3. Foreign Language

Interpretation

  • 1. Appointment Navigation
  • 2. Patient Education
  • 3. Patient Engagement
  • 4. Medication management
  • 5. Chronic care management:

bridging the care gap

  • 1. Mobile health units/EMS
  • 2. Patient Education
  • 3. Care Continuum
  • 4. Access to care providers
  • 5. Access to Information
  • 1. Patient Education, inpatient care

navigation

  • 2. Discharge preparation
  • 3. Clinical Decision Support
  • 4. Operating suites: Hands free clinical

documentation and information retrieval

Decreasing Physician Burnout: POC Tasks Home Health Optimization Easing the Hospital Journey Bridging the Care Gap

slide-14
SLIDE 14

AI Pipeline : Conversational Agent

EMR Data bases

Front End

Cardiologist

End User interaction

What was the Ejection Fraction on last Echocardiogram ?

40%

Conversational Platform: VUI (voice enabled device)

Speech Recognition ASR: Speech to Text

Dialogue management RNN LSTM

TTS: Text to speech engine

Input Output

NLG: Text to Speech Converts text to voice wave form Execution/ Fulfillment Engine NLU:

Comprehension engine Comprehension, Intent understanding

Back end

slide-15
SLIDE 15

ACI: Ambient Clinical Intelligence

Comprehensive Voice enabled AI solution

  • Decreases Physician administrative burden
  • Decreases Physician burnout
  • More attention to the patient
  • Increases patient satisfaction, better outcome

https://www.youtube.com/watch?time_continue=4&v=Fj3v8QQU0aA&feature=emb_logo

ACI

Ambient Sensing Technology User Initiated Virtual Assistant Automated Documentation service

slide-16
SLIDE 16

Real World Applications HIPAA compliant Alexa Health care skills

Alexa

Pharmacy

Health Insurance Health care system

Digital Health company

slide-17
SLIDE 17

Livongo for Diabetes program

HIPAA complaint Alexa Health care skill

  • Right information
  • Right time
  • Guides behavior and rational decision making

https://www.youtube.com/watch?v=ShCPsCcy_TM

Task: Information exchange, behavior modification, Rational decision making Technology: Alexa Environment: Patient’s home

slide-18
SLIDE 18

My Children’s Enhanced Recovery after surgery (ERAS) Boston Children's Hospital

  • Patient facing
  • Post operative recovery update
  • Post Op appointment information

https://www.voice.health/news/my-childrens-enhanced-recovery-after- surgery-eras-alexa-skill

Task: Information exchange Technology: Alexa Environment: Patient’s home

slide-19
SLIDE 19

Audience Question What are some of the challenges in using CAI solutions for health care?

slide-20
SLIDE 20

Challenges in Conversational AI Adoption ?

  • Privacy
  • Security
  • Accuracy
  • Reliability
  • Trust
  • Ethics
  • Design and smooth workflow integration
slide-21
SLIDE 21

Future Directions: Humanizing the Virtual Assistants

  • Context specific Empathy
  • Cognitive capabilities
  • Proactive versus reactive Assistants
slide-22
SLIDE 22

Conclusion CAI: Key Takeaways

Use case selection UX Co-Development Privacy, Security

1 2 3 4

slide-23
SLIDE 23

Thanks!

Thanks for your time