Creating a Smart and Aware Pervasive Healthcare Environment

Creating a Smart and Aware Pervasive Healthcare Environment

Loading
Loading Social Plug-ins...
Language: English
Save to myLibrary Download PDF
Go to Page # Page of 33

Description: To develop a novel architecture for unobtrusive pervasive sensing to link physiological/metabolic parameters and lifestyle patterns for improved well-being monitoring and early detection of changes in disease. By sensing under normal physiological conditions combined with intelligent trend analysis, SAPHE opens up new opportunities for the UK ICT and healthcare sectors in meeting the challenges of demographic changes associated with the aging population.

 
Author: Guang-Zhong Yang (Fellow) | Visits: 2003 | Page Views: 2103
Domain:  Medicine Category: Practice Mngmnt Subcategory: E-health 
Upload Date:
Short URL: http://www.wesrch.com/medical/pdfME1MS1PAXUXFI
Loading
Loading...



px *        px *

* Default width and height in pixels. Change it to your required dimensions.

 
Contents:
SAPHE
Smart and Aware Pervasive Healthcare Environment

Supported by DTI Technology Programme

www.saphe.info

Guang-Zhong Yang, Imperial College London

Technical Objectives
� � Miniaturised sensing with self-management and configuration Local data abstraction and sensor fusion/inferencing with low power sensor and wireless data path Processing-on-node technology for context aware sensing Automated trust-based decision support and "affective computing" for improved human-computer interfacing Intelligent trend analysis and large scale data mining

� �



Project Overview
� To develop a novel architecture for unobtrusive pervasive sensing to link physiological/metabolic parameters and lifestyle patterns for improved well-being monitoring and early detection of changes in disease.

By sensing under normal physiological conditions combined with intelligent trend analysis, SAPHE opens up new opportunities for the UK ICT and healthcare sectors in meeting the challenges of demographic changes associated with the aging population
DTI Technology Programme

Evolution of Computer Technologies
Moore's Law
Estimate 9

Pentium D P4 Prescott Pentium M Pentium 4

Actual

8

7

6 Transistors (log)

Pentium III Pentium Pentium II 80386 80486

5

4

3

2

1

80286 8086 4004 8008 80386 Pentium II Pentium 8008 8080 4-bit 108kHz 8080 32-bit 233MHz 8086 Pentium D 32-bit Pentium III 80286 8-bit 108kHz 20MHz 4004 300MIPS 3.2 GHz 8-bit P4 Prescott 80486 66MHz 16-bit 450-500MHz M 16-bit Pentium 6MIPS 16kB 0.06MIPS 7.5M transistors 15GIPS 2.8-3.4 GHz 25MHz 100MIPS 2Mhz 8MHz Pentium 4 510MIPS 12MHz 600Mhz-1.6GHz 275K transistors 1997 230M 125M transistors 20MIPS 3.2M transistors 0.06MIPS 2.3K transistors 0.64MIPS0.8MIPS 2.7MIPS 1985 1.4&1.5GHz 9.5M transistors 6.5GIPS 2005 7GIPS 1.2M transistors 1993 1971 3.5K transistors 29K transistors transistors 1.7GIPS 1999 77M transistors 134K 6k transistors 2004 1989 42M transistors 1972 1982 2003 1974 1978 2000
1971 1976 1981 1986 Year 1991 1996 2003

0

http://velox.stanford.edu/group/chips_micropro_body.html http://www.theregister.co.uk/2004/02/02/intel_prescott_90nm_pentium/ http://www.intel.com/products/processor/pentiumm/image.htm http://www.pc-erfahrung.de/Index.html?ProzessormodelleIntelItanium2.html

http://www.pc-erfahrung.de/ http://www.granneman.com/ http://home.datacomm.ch/fmeyer/cpu/ http://trillian.randomstuff.org.uk/~stephen/history

Evolution of Computer Technologies
Bell's Law
New computing class every decade New applications and contents develop around each new class

log (people per computer/price)

year

Mote Evolution

What does BSN Cover?

Biosensor Design

Standards & Integration

Biocompatibility & Materials

BSN

Autonomic Sensing Low Power Design & Scavenging

Wireless Communication

Biosensor Design
Thermistor ECG SpO2 Glucose concentration Blood pressure
Implant blood pressure flow sensor (CardioMEMS) Oxymeter (Advanced Micronics) Glucose sensor (Glucowatch) Thermistor (ACR system)

Implant ECG recorder (Medtronics �Reveal)

pH measurement
Implant pH sensor (Metronics � Bravo)

Capsule endoscopy

Pill-sized camera (Given Imaging)

MEMS - Microelectromechanical System
Integrated micro devices or systems combining electrical and mechanical components Fabricated using integrated circuit (IC) batch processing techniques Size range from micrometers to millimetres Applications includes: accelerometers, pressure, chemical and flow sensors, micro-optics, optical scanners, and fluid pumps
Pressure Sensor for Clinical Use (SFU) Tactile Sensor for Endoscopic Surgery (SFU)

CMOS Micromachined Flow Sensor (SFU)

Biocompatibility and Materials
Biosensors Stents Tissue Engineering
Pattern and manipulate cells in micro-array format
Implant blood pressure flow sensor (CardioMEMS) Drug releasing stents Taxus stents - Boston Scientific Co.

Ozkan et. al (2003), Langmuir

Drug delivery systems
Smart Pill � Sun-Sentinel Co.

Carol Ezzell Webb, "Chip Shots", IEEE Spectrum Oct 2004

Power Scavenging
Photovoltaics (Solar cells) 15-20% efficiency (single crystal silicon solar cell) 15mW/cm2 (midday outdoor) to 10�W/cm2 (indoors) Temperature Gradients 1.6% efficiency (at 5oC above room temperature) 40 �W/cm2 (5oC differential, 0.5cm2, and 1V output) Human Power
Applied Digital Solutions � thermoelectric generator Panasonic BP-243318

Human body burns 10.5MJ/day (average power dissipation of 121W) 330 �W/cm2 (piezoelectric shoe) Wind/Air Flow 20-40% efficiency (windmills, with wind velocity 18mph) Vibrations Electromagnetic, electrostatic, and piezoelectric devices 200 �W (1cm3 power converter with vibration of 2.25 m/s2 at 120Hz) Nuclear microbatteries With 10 milligrams of polonium-210, it can produce 50mW for more than 4 months It can safely be contained by simple plastic package, as Nickel-63 or tritium can Cornell University - Nuclear micro-generator penetrate no more than 25 mm
(with a processor and a photo sensor)

MIT Media Lab

MIT � MEMS piezoelectric generator

Environment Sensors and Context

Trust, Security and Policy

Multi-sensor Analysis and Fusion

Self-configuration, healing, managing of software components

Network Storage and Decision Support Agents

Genetic Predisposition

DNA Developing mutation Molecular signature

First symptoms

Progressing disease

Today

Screening

Diagnosis & Staging

Treatment & Monitoring

Follow-up

Unspecific markers POC imaging Mammography

Diagnostic imaging Surgery Biopsies Cath lab Radiation therapy

Diagnostic imaging Unspecific marker

Tomorrow

Screening

Diagnosis & Staging

Treatment & Monitoring
Min invasive surgery Local/targeted drug Delivery Drug tracking Tissue analysis (MDx)

Follow-up

Specific markers Molecular imaging (MDx) Quantitative imaging Whole-body imaging Comp Aided Diagn.

Non-invasive and quantitative imaging Molecular imaging Molecular diagnostics (MDx)

Driver 1: The Aging Population
The proportion of elderly people is likely to double from 10% to 20% over the next 50 years. In the western world, the ratio of workers to retirees is declining. The number of people living alone is rising. A change of care provision is needed for these patients.

Driver 2: Chronic Disease
Ischemic heart disease Hypertension Diabetes Neuro-degenerative disease (Parkinsons, Alzheimers) Global deterioration (Dementias)

Driver 3: Acute Disease

Acute presentations Interventions Post elective care Post-operative monitoring

Driver 4: Diagnostics
History Special Tests Exam

Imaging Patient Peak Flow

Medical Records

Blood Pressure

ECG Blood Tests

O2 Sats

Only a SNAPSHOT of a patient's health

BSN for Healthcare
Dynamic Continuous use 24/7 Preventative Earlier diagnosis Home-based Post-operative monitoring Unobtrusive Minimal interventions Improving Quality-of-Life Anytime Anywhere Anybody

The Ageing Body

Brain and nervous system Respiratory system

Visual and sensory systems

Musculoskeletal system

Circulatory system

Driver 4: Diagnostics
History Special Tests Exam

Imaging Patient Peak Flow

Medical Records

Blood Pressure

ECG Blood Tests

O2 Sats

Only a SNAPSHOT of a patient's health

Intelligent

We

t en bi

ar ab le

Am

802.16e (WiMAX) HSDPA/HSUPA LTE-UMTS WiBro CDMA 2000 802.11 (WLAN) 802.20 (MBWA)

WiBro CDMA 2000 802.11 (WLAN) 802.20 (MBWA)

802.16e (WiMAX) HSDPA/HSUPA LTE-UMTS

WSH WSH WSH WSH WSH

ASN

MSN MSN MSN MSN MSN

BSN

Sensing Development

Cardionetics ECG SAPHE eAR sensor

SAPHE environmental Blob sensor

PIR sensors SAPHE low power radio module SAPHE mobile hub

Door sensors

e-AR: e-AR does it work? How Sensor
Tiny vestibular organ 3 semicircular canals or hollow tubes Each tube detects the 3 different motions: pitch (x), roll (y) and yaw (z) Each tube filled with liquid, and the tube contains millions of microscopic hairs

z

y

x
Accelerometer

Running Gait
Impact peakthe impact (shock) of the foot to the ground Propulsion peak � propulsion of body forward (i.e. marking the end of deceleration and the beginning of acceleration)

Force
0

Time (s) Toe off

0.1

0.2

Initial contact

Stance phase reversal

Swing phase reverse

Initial contact

e-AR Ground Reaction Force

e-AR Sensor and Ankle injury
Accelerometer readings of the subject were recorded before and after the injury, and when the subject is fully recovered Distinctive patterns were found when the subject was suffering from the ankle injury

FFT of Normal Walking

FFT of Walking with Leg Injury

FFT of Walking when Recovered

FFT

1

51

101

151

201

251

301

351

401

451

501

1

51

101

151

201

251

301

351

401

451

501

1

51

101

151

201

251

301

351

401

451

501

Before Injury

After Injury

Fully Recovered

Ankle injury � Cont'd
STSOM � different clusters are formed for the different gait patterns (using features from FFT) KNN � clusters are formed for different gaits (using features from wavelet transform), and the recognition accuracy is above 90%

Normal gait

Injured gait

Clinical Gait Analysis
Gait abnormalities

Propulsive gait

Scissors gait

Spastic gait

Steppage gait

Waddling gait

Typical associated diseases
- Carbon monoxide poisoning - Manganese poisoning - Parkinson's disease - Temporary effects from drugs - Stroke - Cervical spondylosis with myelopathy - Liver failure - Multiple sclerosis - Pernicious anemia - Spinal cord trauma - Cerebral palsy - Brain abscess - Brain tumor - Stroke - Head trauma - Multiple sclerosis - Guillain-Barre syndrome - Herniated lumbar disk - Multiple sclerosis - Peroneal muscle atrophy - Peroneal nerve trauma - Poliomyelitis - Polyneuropathy - Spinal cord trauma - Congenital hip dysplasia - Muscular dystrophy - Spinal muscle atrophy

Benefits to Patients
� � � � � � � Truly pervasive, easy to wear and require minimal user interaction Early detection of the onset of the disease to avoid complication Used both for disease and well-being monitoring Smart to wear, multi-function (e.g with integrated music player) to avoid stigmatising Sensing under normal physiological conditions Reconfigurability of the devices means constant improvement of the system capability Intelligent ambient sensing can ultimately replace existing security and monitoring devices, and therefore brings significant cost benefit

Benefits to Health and Care Providers
� � � � � � Early detection means well informed care activities and improve resource management Trend analysis and decision support simplifies care workflow management and decreases (improves) staff/client ratio Truly pervasive, easy to install and customisation suggest minimal additional work for system deployment Sensing under normal physiological conditions ensures improved patient compliance and acceptance Reconfigurability of the devices means the ease of adaptation of the care/monitoring provision as the condition of the patient changes Pooled population data provides evidence based care provision and viable financial planning

Supported by DTI Technology Programme

www.saphe.info

Subscribe
x