P7: A New Paradigm for Health Care in the 21st Century
Scientific Session at AAAS2019 Annual Meeting
https://aaas.confex.com/aaas/2019/meetingapp.cgi/Session/21133
https://cra.org/ccc/ccc-at-aaas/2019-sessions/
Asthma is a chronic multifactorial disease and traditional clinical practice requires patients to meet their clinician in a timely yet infrequently meetings scheduled once in 3-6 months depending on the patient’s condition. The clinical diagnosis relies on the patient’s description of their current health condition. The patient’s description need not be accurate at times and may lack some important aspects needed for accurate diagnosis. We at Kno.e.sis work with clinicians and their pediatric asthma patients at the Dayton Children's Hospital to evaluate an IoT/mobileApp enabled personalized digital health management. We built a kHealth system for continuous monitoring and improved tracking of 30 parameters including the child’s symptoms, activities, sleep, and treatment adherence. It can allow precise determination of asthma triggers and a reliable assessment of medication compliance and effectiveness.
More at: https://aaas.confex.com/aaas/2019/meetingapp.cgi/Paper/23000
Cardiac Output, Venous Return, and Their Regulation
kHealth: Semantic Multi-sensory Mobile Approach to Personalized Asthma Care
1. Prof. Amit. P. Sheth
LexisNexisOhioEminentScholar, ExecutiveDirector, Kno.e.sis
WrightStateUniversity
Background: http://bit.ly/k-APH,http://bit.ly/kAsthma,http://j.mp/PARCtalk
Icon source used in the entire presentation - https://thenounproject.com
kHealth: Semantic Multisensory
Mobile Approach to Personalized
Asthma Care
P7: A New Paradigm for Health Care in the 21st Century
AAAS 2019 Annual Meeting:
Washington DC February 15, 2019
2. Internet of Medical Things
● Episodic to Continuous Monitoring
● Clinician-centric to Patient-centric
● Clinician controlled to Patient-empowered
● Disease Focused to Wellness-focused
● Sparse data to Multimodal Big Data
Medical
Internet
of Things
3. Augmented Personalised Health
Big Data to Smart Data
Augmented Personalised Health(APH) is a vision to enhance the healthcare by using AI
techniques on semantically integrated PGHD, environmental data, clinical data, public
health data & social data.
Data Components
PGHD, Clinical data,
environmental data and Social
Data
Smart Data
meaningful data obtained after
contextualised processing
Image Source - http://www.dqchannels.com/big-data-and-smart-data-big-drivers-for-smart-decision-making/
4. 1. Self Monitoring
Constant and remote
monitoring of
disease specific
health indicators for
any given patient
2. Self Appraisal
Interpretation of
the data collected
with respect to
disease context for
the patient to
evaluate themselves
3. Self
Management
Identify the deviation
from normal and assist
patients to get back to
prescribed care plan
4. Intervention
Change in the care
plan - with the
converted smart data
by APH, provide
decision support for
treatment
adjustments
5. Disease
Progression and
Tracking
Longitudinal data
collection and
analysis to enhance
patients health over
the time
Sheth, et.al. How will the Internet of Things enable Augmented Personalized Health?
Health Management Strategies of APH
5. kHealth Asthma: A multisensory approach for personalised asthma care in children
6. Data Collection so far
110
patients
30
parameters
1852
data points per
patient per day
66%
Kit compliance
● Data Collection: Since Dec 2016
● Active sensing: 18 data
points/day (Peak flow meter and
Tablet)
● Passive sensing: 1834 data
points/ day (Foobot, Fitbit,
Outdoor environmental data)
5-17
years of age
1 or 3
months of
monitoring
7.
8. Utkarshani Jaimini, Krishnaprasad
Thirunarayan, Maninder Kalra, Revathy
Venkataramanan, Dipesh Kadariya, Amit
Sheth, “How Is My Child’s Asthma?” Digital
Phenotype and Actionable Insights for
Pediatric Asthma”, JMIR Pediatr Parent
2018;1(2):e11988, DOI: 10.2196/11988.
12. Evidence based Path to Personalization
Absenceof Pollen
First 6 weeks
Presenceof Pollen
Rest of the 7 weeks
LearningPeriod
4 weeks
PredictionPeriod
2 weeks
LearningPeriod
4 weeks
PredictionPeriod
3 weeks
Pollen 0 Pollen 0 days Pollen 17 days Pollen 3 days
PM2.5 20 days PM2.5 5 days PM2.5 14 days PM2.5 2 days
Ozone 1 day Ozone 0 Ozone 0 Ozone 1 day
Asthma
Episodes
21 days Asthma
Episodes
5 days Asthma
Episodes
17 days Asthma
Episodes
3 days
Patient-A was monitored for 13 weeks encompassing winter to spring 2018
● Absence of Pollen - PM2.5 is the trigger
● Presence of Pollen - Pollen and PM2.5. Severe symptoms occurred in this period. Presence of both PM2.5 and Pollen
increased the intensity of asthma episodes
13. APH for kHealth Asthma
1. Self Monitoring
Show me the data
that is relevant to
asthma (Eg:AQI,
Pollen)
2. Self Appraisal
What is my asthma
control level?
3. Self
Management
Given all my asthma
related data, do I need
to take SABA(Short
Acting Beta Agonists)?
4. Intervention
Based on poor asthma
control, the system
encourages clinical
consultation(before
routine examination).
5. Disease
Progression and
Tracking
How was my asthma
control since last
year?
14. kBOT for kHealth Asthma
Many Sources of Highly Diverse Data
(& collection methods: Active + Passive):
Up to 1852 data points/ patient /day
kBot with screen
interface for conversation
Images
Text
Speech
★ Episodic to Continuous Monitoring
★ Clinician-centric to Patient-centric
★ Clinician controlled to Patient-empowered
★ Disease Focused to Wellness-focused
★ Sparse data to Multimodal Big Data
*(Asthma-Obesity)
15. Contextualization and
Personalization
kBOT initiates greeting
conversation.
Understands the patient’s health
condition (allergic reaction to high
ragweed pollen level) via the
personalized patient’s knowledge
graph generated from EMR, PGHD,
and prior interactions with the kBOT.
Generates predictions or
recommended course of actions.
Inference based on patient’s
historical records and background
health knowledge graph containing
contextualized (domain-specific)
knowledge.
Figure: Example kBOT conversation which
utilizes background health knowledge graph
and patient’s knowledge graph to infer and
generate recommendation to patients.
★ Conversing only information relevant
to the patient
Context enabled by relevant
healthcare knowledge including
clinical protocols.
16. kHealth TeamMembers
Revathy Venkataramanan
(Graduate Student)
Utkarshani Jaimini
(Graduate Student)
Hong Yung Yip
(Graduate Student)
Dipesh Kadaria
(Graduate Student)
Tanvi Banerjee
(Faculty)
Dr. KrishnaPrasad
Thirunarayan
(Faculty)
Dr. Maninder Kalra
(Pulmonologist at Dayton Children’s
Hospital)
Clinical collaborator
Acknowledgement: This research is
supported by NICHD/NIH under the Grant
Number: 1R01HD087132. The content is
solely the responsibility of the authors and
does not necessarily represent the official
views of the National Institutes of Health.
Notes de l'éditeur
Lower the Digital Phenotype Score and Higher the Asthma Control test score the more controlled is the asthma. The graph shows the correlation between asthma control level calculated using the asthma control test scores and digital phenotype score - > High correlation. A negative Kendall Tau correlation = −0.509 (P<.01)
Patient was deployed for 13 weeks in winter to spring. The deployment period was divided into two (absence of pollen and presence of pollen) to disambiguate triggers. The first 6 weeks, absence of pollen, was divided further into learning period(where we learn the association between triggers and asthma symptoms) and prediction period (use what we learned to predict the symptoms).