Next Generation Neonatal Health Informatics with Artemis Carolyn - - PowerPoint PPT Presentation

▶
next generation neonatal health informatics with artemis
SMART_READER_LITE
LIVE PREVIEW

Next Generation Neonatal Health Informatics with Artemis Carolyn - - PowerPoint PPT Presentation

Apr 19, 2023 144 likes •352 views

Next Generation Neonatal Health Informatics with Artemis Carolyn McGregor a, , Christina Catley a , Andrew James b , and James Padbury c a University of Ontario Institute of Technology, Oshawa, ON, Canada b The Hospital for Sick Children,

slide-1
SLIDE 1

Next Generation Neonatal Health Informatics with Artemis

Carolyn McGregora,, Christina Catleya, Andrew Jamesb, and James Padburyc

a University of Ontario Institute of Technology, Oshawa, ON, Canada b The Hospital for Sick Children, University of Toronto, Toronto, ON, Canada c Women & Infant's Hospital of Rhode Island, The Warren Alpert Medical

School of Brown University, Providence, RI, USA carolyn.mcgregor@uoit.ca

slide-2
SLIDE 2

Baby 1 Baby 3 Baby 2 Diagnosis Absolute times 16/11/06 15/11/06 Diagnosis Diagnosis

2

Motivation: Earlier Onset Detection

  • Hourly spot readings from medical devices

recorded on paper or electronic charts.

  • Babies weight between 2.5-3kg at discharge.

Paper notes can weight 6kg

slide-3
SLIDE 3

Motivation

slide-4
SLIDE 4

Baby 1 Baby 3 Baby 2 Diagnosis Absolute times 16/11/06 15/11/06 Diagnosis Diagnosis

4

Motivation: Earlier Onset Detection

slide-5
SLIDE 5

Motivation

  • Behaviour of physiological data streams that

describe respiratory and cardiac function . . .

– Pneumothorax (McIntosh et al, 2000) – Nosocomial infection (Griffin and Moorman, 2001) – Periventricular leucomalacia (Shankaran et al, 2006) – Intraventricular haemorrhage (Fabres et al, 2006; Tuzcu et al, 2009)

slide-6
SLIDE 6

Knowledge Translation Challenge

  • Retrospective Analysis
  • Not implemented in clinical practice
  • Not scalable
  • Either or combination of:

– Patient centric – Condition centric – Stream centric

slide-7
SLIDE 7

Objectives

  • The provision of this knowledge requires a

multidimensional approach:

– multiple conditions – multiple streams of data – for which multiple behaviours can exist

  • In addition, integrate of

– real-time synchronous medical device data – asynchronous clinical data

slide-8
SLIDE 8

Diagnoses

Apnea Sepsis Hypoglycemia

Streams/Behaviours Patients

HR RR IRW SpO2

Diagnoses

Apnea Sepsis Hypoglycemia

Streams/Behaviours Patients

HR RR IRW SpO2

Diagnoses

Apnoea Sepsis Hypoglycemia

Streams/Behaviours Patients

HR RR IRW SpO2

Locations UOIT SickKids WIHRI

Neonatologist

Care ¡provider ¡views

slide-9
SLIDE 9

9

Data Integration Mgr Knowledge Extraction Data Miner HIR Data Mover InfoSphere Streams Runtime Ontology Driven Rule Modifier Deployment Server

Alert Sink Op

QRS BP RR PT FA WT AR Sepsis BPA EP WTA

HR Source Op SpO2 Source Op BP Source Op CIS Source Op

Patient Stream

SPADE IDE USER INTERFACE

Medical Data Hub

CIS Adapter Configuration Server

CapsuleTech Server

MP50 Babylog8000

Clinical Information System

ECG SpO2 BP HR

Cognos

Data Aquisition Online Analysis Knowledge Extraction (Re)deployment Result Presentation Stream Persistency

Artemis

slide-10
SLIDE 10

10

Data Integration Mgr Knowledge Extraction Data Miner HIR Data Mover InfoSphere Streams Runtime Ontology Driven Rule Modifier Deployment Server

Alert Sink Op

QRS BP RR PT FA WT AR Sepsis BPA EP WTA

HR Source Op SpO2 Source Op BP Source Op CIS Source Op

Patient Stream

SPADE IDE USER INTERFACE

Medical Data Hub

CIS Adapter Configuration Server

CapsuleTech Server

MP50 Babylog8000

Clinical Information System

ECG SpO2 BP HR

Cognos

Data Aquisition Online Analysis Knowledge Extraction (Re)deployment Result Presentation Stream Persistency

SickKids (a)

Stream Persistency

slide-11
SLIDE 11

SickKids (a)

  • Clinical research into new earlier onset

detection of LONS.

  • 174 patients, representing 4.1 patient

years of data.

  • Currently supporting eight concurrent

patients and collecting approximately 1250 readings a second

slide-12
SLIDE 12

Artemis Cloud WIHRI

Data Integration Manager Knowledge Extraction Temporal Data Miner Data Mover Ontology Driven Rule Modifier Deployment Server

Alert Sink Op QRS BP RR PT FA WT AR Sepsis BPA EP WTA HR Source Op SpO2 Source Op BP Source Op CIS Source Op

Patient Stream

InfoSphere Streams Runtime

Patient Stream TAs

Clinical Web Service Physiological Web Service

Artemis Cloud

ECG SpO2 BP HR ECG SpO2 BP HR

Analyse Web Service

Hospital

Monitor Web Service Define Web Service

TA Rules

Clinical Rule Web Service

McGregor, C., 2011, “A Cloud Computing Framework for Real-time Rural and Remote Service of Critical Care”, IEEE Computer Based Medical Systems, Bristol, UK, 6 pages CDROM

slide-13
SLIDE 13

WIHRI

  • Clinical research into neonatal instability
  • Enrolled 203 patients, representing 10.6

patient years of data

  • Spot readings every minute
slide-14
SLIDE 14

14

Data Integration Mgr Knowledge Extraction Data Miner HIR Data Mover InfoSphere Streams Runtime Ontology Driven Rule Modifier Deployment Server

Alert Sink Op

QRS BP RR PT FA WT AR Sepsis BPA EP WTA

HR Source Op SpO2 Source Op BP Source Op CIS Source Op

Patient Stream

SPADE IDE USER INTERFACE

Medical Data Hub

CIS Adapter Configuration Server

CapsuleTech Server

MP50 Babylog8000

Clinical Information System

ECG SpO2 BP HR

Cognos

Data Aquisition Online Analysis Knowledge Extraction (Re)deployment Result Presentation Stream Persistency

SickKids (b)

slide-15
SLIDE 15

SickKids (b)

  • Clinical research into new earlier onset

detection of LONS.

  • Nearly two years of 30 second spot

reading data

  • Obtained from 1151 patients
slide-16
SLIDE 16

Conclusion

  • Artemis provides clinical decision support

in a flexible and transparent manner and instantiate clinical knowledge into the information processing pathway.

  • This is in direct contrast to many CDSSs

based on complex mathematical processing, such as artificial neural networks, which from the clinicians’ viewpoint operate as black boxes

slide-17
SLIDE 17

Future Work

  • Artemis has quickly become ubiquitous as

it is used to support the clinical research

  • Clinical result publication is pending
  • We are currently installing Artemis in two

NICUs in China to support cross cultural clinical research

  • We expanding the clinical research studies
slide-18
SLIDE 18

Artemis Clinical Partners

Nepean Hospita Westmead Hosp

Shenzhen Maternity & Child Health Hospital 深圳市妇幼保健院

slide-19
SLIDE 19

Funding Acknowledgements

TJ Watson Research Center, NY Canada

slide-20
SLIDE 20

Next Generation Neonatal Health Informatics with Artemis

Carolyn McGregora,, Christina Catleya, Andrew Jamesb, and James Padburyc

a University of Ontario Institute of Technology, Oshawa, ON, Canada b The Hospital for Sick Children, University of Toronto, Toronto, ON, Canada c Women & Infant's Hospital of Rhode Island, The Warren Alpert Medical

School of Brown University, Providence, RI, USA carolyn.mcgregor@uoit.ca