e-Health

76
e-Health Jim Hunter

description

e-Health. Jim Hunter. Outline. What is e-Health? Stuart Scott GP/Clinical Director e-Health NHS Grampian Tuesday 5 th December e-Health research at Aberdeen. e-Health - Definitions. - PowerPoint PPT Presentation

Transcript of e-Health

Page 1: e-Health

e-Health

Jim Hunter

Page 2: e-Health

2

Outline

• What is e-Health?• Stuart Scott

GP/Clinical Director e-Health NHS GrampianTuesday 5th December

• e-Health research at Aberdeen

Page 3: e-Health

3

e-Health - Definitions

EUThe use of modern information and communication technologies to meet needs of citizens, patients, healthcare professionals, healthcare providers, as well as policy makers.

World Health Organisation (WHO):

eHealth is the cost-effective and secure use of information and communications technologies in support of health and health-related fields, including health-care services, health surveillance, health literature, and health education, knowledge and research.

Page 4: e-Health

4

NHS – Connecting for Health

National Programme for Information Technology (2002-2010)• CRS: "a secure, shared national Care Records Service for England".

Designed to replace existing electronic and paper based systems for all patients in England.

• Choose and Book - electronic appointment booking system for GPs/hospitals and patients

• ETP - Electronic Transmission of Prescriptions: a system designed to support the electronic transmission of prescriptions between GPs (General Practitioners), pharmacies and the Prescription Pricing Authority (PPA)

• HealthSpace: a web service allowing patients to access their own NHS care records

• Picture Archiving and Communications Systems (PACS)

• Quality Management and Analysis System (QMAS) (for primary care)

Page 5: e-Health

5

NHS – Connecting for Health

• N3: a new national network to provide broadband network capacity and support interoperability between above applications and activities such as telemedicine and telecare.

• the Spine: the "core data storage and messaging system" underlying and integrating the CRS and associated functionality. Standard terminologies will include SNOMED CT. Health Language Inc.'s language engine technology will support interoperability, including integrating and sharing patient data.

• Decision support: the electronic prescribing programme (support for prescribing in different care settings); online knowledge and library systems: integrated care pathways; NICE clinical recommendations; National Service Frameworks (NSFs); e-referral support; support for ordering clinical investigations; "accredited protocols of care, procedures and clinical guidance".

Page 6: e-Health

6

Healthcare

• Pervasive – involves everyone• I’ve never used eBay but …

• Large • NHS employs about 1 M people

• Diverse• different rates of change

• Political

Page 7: e-Health

7

Healthcare - Costs

Expensive

EU - 2002

• expenditure on total health care as % of GDP: from: 10.7% (Germany) to 6.7% (Ireland) –

say 8% overall

• European GDP ~ €10,000 B (1000 M)

• so EU health care expenditure ~ €800 B (£570 B)

UK

2002/3 2003/4 2004/5 2005/6 £56 B £64 B £69 B £76 B (estimated)

Page 8: e-Health

8

Healthcare - People

• Patient • Doctor• Nurse• Other health care professional

• Pharmacist, Radiographer, Pathologist, …

• Administrator• Finance, Human resources, Appointments,

• Researchers• Students

Page 9: e-Health

9

Healthcare - Professionals

Professionals• Long Training (6+ years for doctors)

• Large body of knowledge – constantly changing

• Medicine is not an absolute science – uncertainty

• Time pressures

• Dealing with patients (not insurance quotes)

Page 10: e-Health

10

Healthcare - Locations

• Home• Primary care and local clinic• District general hospital

many departments

• Tertiary hospital+ more specialised departments

• Research laboratory• Classroom• Everywhere! …

Page 11: e-Health

11

Healthcare - Sensitivity

• Need for• Privacy• Security• Access

Right people Right time

Page 12: e-Health

12

Healthcare - Change

Not all organisations at the same stage.

Distinguish• What is all pervasive

• What has been adopted by some but not by others

• What is ready to be deployed

• What is still ‘blue skies’ research

Page 13: e-Health

13

Informatics

Input

Transmit

Store

Process

Retrieve

Transmit

Output

Home

Page 14: e-Health

14

Healthcare Informatics

Input

Transmit

Store

Process

Retrieve

Transmit

Output

Agent

Location

PatientDoctor

Nurse…

HomeSurgery

…Hospital

Home

Page 15: e-Health

15

Computers vs Humans

Research and development

Treatment

Reasoning (diagnosis and treatment planning)

Processing

Data Acquisition, Storage and Retrieval

Data Transmission

Computer

Human

Page 16: e-Health

16

Data Transmission

Use ‘standard’ technologies• fax• phone• email• intra-net• web• etc.

Encryption

Page 17: e-Health

17

Telemedicine

Patient (home)

GP

Local Hospital

Remote Hospital

National serviceRemote monitoring for chronic illnesses

• Diabetes• Renal failure• Cardiac problems•…

Page 18: e-Health

18

Telemedicine

Patient (home)

GP

Local Hospital

Remote Hospital

National service

24 hour call centres• NHS Direct (England & Wales)• NHS 24 (Scotland)

Page 19: e-Health

19

Telemedicine

Patient (home)

GP

Local Hospital

Remote Hospital

National service

Sharing expertise• Video conferencing• Data sharing

Page 20: e-Health

20

Data Acquisition

• Human input

• Unstructured - e.g. word documents

• Semi-structured - e.g. free text in an input box

• Structured (coded) – selection from a fixed list, check boxes, etc

• Machine input (often with analogue/digital conversion)

• Single point in time Laboratory results Images

• Continuous Physiological data

Page 21: e-Health

21

X-Rays

Page 22: e-Health

22

CT Scans

Page 23: e-Health

23

ECG

Page 24: e-Health

24

ICU

Page 25: e-Health

25

Data Storage and Retrieval

• ‘Standard’ database technologies

• Can be very large • especially if picture achieving is involved

(terabytes – 1012 bytes)

• Coding is a real problem• signs (what the doctor can see and feel)

• symptoms (what the patient says)

• diagnoses

• treatments

Page 26: e-Health

26

Formal medical languages

• Name objects and events in the external world

• Need for sharing

• Computerisation increases the need for precision• communication

• audit

• research

• resource management

• decision support

Page 27: e-Health

27

Formal medical languages

• Need for structuring• retrieval

• abstraction

• Hierarchies – dimensions/attributes/axes

part-whole

body

arm

hand

finger

kind-of

infection

hepatitis

viral hepatitis

hepatitis-A

causal

plaque

thrombosis

infarction

arrhythmia

Page 28: e-Health

28

Formal medical languages

Enumerative

• List all the possibilities in advance (and structure them)

• International Classification of Diseases (ICD) 9/10

Compositional

• Agree on a set of primitives which are combined acute bacterial septicemia

• Knowledge which controls the way in which terms can be combined can’t say: a fractured lung can say: a fracture of the second bone in the third toe of the left

foot

Common

• SNOMED, UMLS (USA)

• Read (UK)

Page 29: e-Health

29

Processing

Repetitious and formalised computations• construction of CT scans

• 3-D reconstruction

• image analysis

• ECG analysis

• radiation dose calculation

• finance and accounting

• administration

Page 30: e-Health

30

ReasoningDiagnostic/Therapeutic Cycle

Patient

Observation

Diagnosis(Interpretation)

TherapyPlan

Observe

Reason Reason

Treat

Page 31: e-Health

31

Clinical Guidelines and Protocols

Clear statements of the optimal management for a specific group of patients which, when properly applied, will improve the quality of the care they receive.

Guideline• often formulated nationally or internationally• often evidence-based• widely disseminated

Protocol• more detailed• local (one clinician or group of clinicians)• often mandatory

Page 32: e-Health

32

Computerised Protocols

Represent the protocol in a formal language

Apply the protocol automatically to the electronic patient record (EPR)

Present the advice from the protocol to the doctor or nurse

Page 33: e-Health

33

Page 34: e-Health

34

Aberdeen Research

• Neonatal Intensive Care

• BabyTalk

• Computerised Guidelines

• TSNet

Page 35: e-Health

35

A Neonatal ICU

Page 36: e-Health

36

Page 37: e-Health

37

Data in intensive care

Continuous:

Monitor (one second resolution) : heart rate, blood pressures, O2, CO2,

temperatures ... (i.e. 86,400 samples/channel/patient/day)

Sporadic:

Ventilator : Mode, pressures, FiO2, respiration rate …

Incubator : O2, temperature, humidity

On-ward blood gases : pH, pO2, pCO2 ...

Laboratory : Haemoglobin, Na, K, Urea …

Manual: Notes, medication, ...

Page 38: e-Health

38

Complex high volume data

Page 39: e-Health

39

BabyTalk

Textual summarisation of Neonatal ICU data

Page 40: e-Health

40

Experiment: Graphs vs. Text

To compare the effects of • different presentations – graphical and textual

• of the physiological history of a neonate

• on decision-making

• in terms of 'accuracy‘ response time

Hypothesis• clinical staff will make more accurate decisions when informed by

graphical displays than by textual summaries.

Page 41: e-Health

41

Graphs

Page 42: e-Health

42

Text

Page 43: e-Health

43

Appropriate Actions

Proportion of total appropriate actions identified

Mean; Whisker: Mean-SE, Mean+SE

Graph Text

JN IN SN JD SD

GROUP

0.0

0.1

0.2

0.3

0.4

0.5

0.6

0.7

Page 44: e-Health

44

BabyTalk

EPSRC funded project• 4 years

• 2 research fellows and 2 research students

BT- 45: Replicate the original experiment with automatically generated text

BT- Doc: Summarise several hours for clinical decision support

BT- Nurse: Generate 12 hour nurse shift summary

BT- Family: Reports for family members

Page 45: e-Health

45

BabyTalk Architecture

Data Abstraction

Pattern Recognition

Content Determination

Text Generation

Numerical and Interval

Interval

Interval ++

Interval --

Text

Page 46: e-Health

46

Page 47: e-Health

47

AutomaticMedical staff have no time to answer questions

Protocols in the ICU

Clinical autonomy• advice must always be advisory, not mandatory• must cater for differences in practice

between units within units

Page 48: e-Health

48

Timing

• many medical decisions made at a daily or weekly ‘encounter’ with the patient

• ICU: continuous WHAT to do WHEN to do it

• advice provision system often has access to actions taken by staff

Protocols in the ICU

Page 49: e-Health

49

Access to data

• humans and computers have different ‘windows’ on to the patient

• computers have: monitor data, lab results, etc.

• humans have this plus: sight, touch, sound, (smell, (taste)) actions taken

Protocols in the ICU

Page 50: e-Health

50

Data abstraction

• protocols expressed in higher level clinical terms than the raw patient data

• try to ‘reconstruct’ sensory input

• deal with artefacts

Protocols in the ICU

Page 51: e-Health

51

Run-time Architecture

Abstraction Execution Engine

Patient Data

Visualisation

Formal Protocol

Recommendations

Page 52: e-Health

52

Protocol

Acquisition

• published guidelines

• local manuals

• knowledge-acquisition interviews with clinicians

Page 53: e-Health

53

Example Protocol

Maintain suitable oxygen (O2) level in the blood … by adjusting the fraction of inspired oxygen (FiO2) on the ventilator as follows:

O2-High

O2-Low

O2

FiO2 -

FiO2 +

8 kPa

6 kPa

if the O2 is above 8 kPa then reduce the FiO2 by 5%

if the O2 is below 6 kPa then increase the FiO2 by 10%

otherwise do nothing

Page 54: e-Health

54

Formal Languages for Guidelines and Protocols

Guide

Prodigy

GLIF

SAGE

EON

ProForma

Asbru (Shahar, Miksch and Johnson,1998)

Page 55: e-Health

55

Protocol Translation

Difficult and time consuming

Various approaches to (semi) automatic translation

Need for verification:• graphical presentations

• ? text

Page 56: e-Health

56

Example Protocol in Asbru

<!-- ################# PtcO2 too <!-- ################# PtcO2 too high--><if-then-else> <simple-condition> <comparison type="greater-than"> <left-hand-side> <parameter-ref name="PtcO2"/> </left-hand-side> <right-hand-side> <numerical-constant value="8"/> </right-hand-side> </comparison> </simple-condition> <then-branch> <variable-assignment variable="REC_SETTING:VENTILATOR:Rec_FiO2"> <operation operator="subtract"> <parameter-ref name="VENTILATOR:FiO2"/> <numerical-constant value="5"/> </operation> </variable-assignment> </then-branch></if-then-else> Coded by hand

if the O2 is above 8 kPa then reduce the FiO2 by 5%

Page 57: e-Health

57

Data Abstraction

Compression – median value every 60 seconds

Artefact removal (Cao et al., 1999)• limit-based detector

flags as artefact values outside extreme centiles

• deviation-based detector flags as artefact values which cause the standard deviation to exceed a limit

• correlation-based detector: uses lower standard deviation limits when a ‘correlated’ channel is flagged

Page 58: e-Health

58

Detailed Architecture

Rec_Resp_Rate

MD[OX]+CMD[OX]OX

CO

Median

Median

ArtiDetector AsbruRTM

MD[CO]

Rec_FiO2

FiO2

Resp_Rate

Guideline

MD[CO]+C

channel

filter

Page 59: e-Health

59

Results

Page 60: e-Health

TSNet

A Distributed Architecture for Time Series Analysis

Page 61: e-Health

61

Need for collaborationand sharing

abstraction of complex time series is difficult

need to combine experience

demonstration of generality to help acceptance and standardisation

Page 62: e-Health

62

Realities

the ‘not invented here’ syndrome

people use different programming languages and are unwilling to re-write complex software- hence need to accommodate different languages

people may be unwilling to release source (or even compiled versions) - hence need to take the data to the algorithm

Page 63: e-Health

63

Distribution

Internet

Group S1:

Raw data

Group S2:

Filter (Java)

Group S3:

Filter (MatLab, S+, …)

Group C1:

Management and display

Client

Servers

Group C2:

Management and display

Page 64: e-Health

64

Channels

A channel is a named data stream• equi-sampled

numerical (floating point) boolean enumerated (0, 1, ...) spectrum

• a set of intervals start and end date/time attribute and value zero length interval = event

Page 65: e-Health

65

Examples of channels

Heart rate: equi-sampled numerical channel

Qualitative heart rate [low, normal, high]:equi-sampled enumerated channel

FiO2 (ventilator setting – fraction of inspired oxygen):interval channel

Artefact present:interval channel

Page 66: e-Health

66

Filters

A filter is anything that processes data in channels• 0, 1, 2, .... input channels

• 0, 1, 2, .... output channels

• data source (no input channels – data from files, database, ...)

• data sink (no output channels) plot to screen write to file, database, ...

Page 67: e-Health

67

Examples of filters

moving window: mean, median, slope, ...

segmentation

clinical guideline

equi-sampled numerical equi-sampled numerical

equi-sampled numerical interval

equi-sampled numerical interval

interval

equi-sampled numerical

Page 68: e-Health

68

Plots and displaysA plot is a user defined visual representation of one or more channels.

A display is a user-defined collection of plots.

Page 69: e-Health

69

Networks

F1

F2

F3

F4

F5

Data

source

P1

P2

Display

user-configurable

Page 70: e-Health

70

Distribution

Internet

Group S1:

Raw data

Group S2:

Filter (Java)

Group S3:

Filter (MatLab, S+, …)

Group C1:

Management and display

Client

Servers

Group C2:

Management and display

Page 71: e-Health

71

Client-Server architecture

Data management

User interface

External filter manager Internal filters

SOAP

CLIENT

SERVER

INTERNET

SOAP

Tomcat

Filter manager

Filters

Page 72: e-Health

72

Demo scenario

Asbru guideline to advise on the control of blood pressure using saline and then dopamine

• mean blood pressure (1 sec)

• smooth with a moving window median filter (1 min)

• remove artefacts (use data on HR, OX and CO2 if available)

• run Asbru guideline using the Asbru interpreter

• output is an interval channel containing recommendations

Page 73: e-Health

73

Demo at IDAMAP (Verona)Raw data source

Median filter

Artefact removal

Guideline application (Asbru)

BM

MD[BM]

MD[BM]+C

ABL(MD[BM]+C)

equi-sampled numerical (1/sec)

interval

equi-sampled numerical (1/min)

equi-sampled numerical (1/min)

ABERDEEN

internal

internal

LILLE

Plotinternal

Page 74: e-Health

74

Demo at IDAMAP

Aberdeen

Lille

Verona

Page 75: e-Health

75

Demo at IDAMAP

BM

MD[BM]

MD[BM]+C

ABL(MD[BM]+C)

Page 76: e-Health

76