towards acost-effective homecare for acaregiver assistance ... · towards acost-effective homecare...

Slide 1Slide 1

Towards a Cost-Effective Homecare for

a Caregiver Assistance System in Brazil

MAURO OLIVEIRA

LAR-AComputer Network Laboratory of Aracati

Slide 216th Healthcom October 16th, 2014 Natal - RN Slide 2

Mauro OliveiraFederal Institute of Ceará (IFCE)

Aracati, Brazilamauroboliveira@gmail.com

Odorico AndradeFederal University of Ceara (UFC)

Fortaleza, Brazilodorico0811@gmail.com

Marcos SantosState University of Ceara (UECE)

Fortaleza, Brazilmarcos.eduardo@uece.br

Roberto AlcântaraFederal Institute of Ceará (IFCE)

Aracati, Brazilrobertoalcantara@gmail.com

Germanno TelesNortheast Bank of Brazil(BNB)

Fortaleza, Brazilgermanno@bnb.gov.br

Nazim AgoulmineJoseph Fourier University (UJF) Université d´Evry Val dÉssone Nazim.Agoulmine@ufrst.univ-

evry.fr

Towards a Cost-Effective Homecare for

a Caregiver Assistance System In Brazil

Team working on this project

Slide 3

1. Contextualization

2. Application Scenario

3. Brazilian Digital TV

4. LARIISA Project

5. Prototype

Conclusion

Summary

Slide 4

1. Contextualization

Slide 5

Health System - Information EraBased on Disease PREVENTIONC

ost

s

¢

Encouraged

Discouraged Fonte: K. Jennings, K. Miller, S. Materna (1997)

Hospital (specialits)

Health Agent

Primary

Health Care

$

CONTEXTUALIZATION

Descentralization of PublicHealth System

Slide 6

PROBLEM

ManagementInformation

Message

Data

Acquisition

CONTEXTUALIZATION �

Increasing Complexity ofHealth Management for

Decision-making

Slide 7

CONTEXT-AWARE FRAMEWORK

SOLUTION

ONTOLOGY

BAYESIAN

NETWORK

MetadataGeolocation

Decision-Making

Information

Health Knowledge

InferenceMechanism

PROBLEM �CONTEXTUALIZATION �

LARIISA: an Intelligent System tosupport decision-making process

DATA MINING

Slide 8

Data Acquisition(Patient CONTEXT)

DECISION-MAKING

LARIISA’s Scenario: a context-aware framework

METADATA

Option 1

Option 3

Option 2

LARIISA: A Context-Aware Framework

ONTOLOGY BAYESIAN NETWORKS

DATA MINING

Slide 9

2. Application Scenario

Slide 10

Scenario for LARIISA ApplicationCAREGIVER - an unpaid or paid person who helps another individual

with an impairment with his or her activities of daily living.

2. Motivation :The Brazilian Digital TV

LARIISA can helpSpecialized person

Or NON specialized person

Slide 11Prague, Czech Republic July/2013

Data acquisition - CONTEXT

Slide 12

LARIISA Data Acquisition

Slide 13

ONTOLOGY BAYESIAN NETWORKS

DARA MININGData Acquisition

(CONTEXT)METADATA

DECISION-MAKING

LARIISA: Next Generation

Slide 14

3. The Brazilian Digital TV

Slide 15

AnalógicoAnalógico

Today Interactive Digital TV

The Brazilian Digital TV

Slide 16

Network

Audio

Video

Data

Data Carrossel

1. MOTIVATION

Interactive Digital TV

Slide 17

Interactive Digital TV

The Brazilian Digital TV

Slide 18Prague, Czech Republic July/2013

Architecture of the Brazilian Digital TV

GINGA, a recommendation H.761 of the International Telecommunications Union (ITU-T).

Slide 19

4. LARIISA Project

Slide 20

Medical Sensors

Humidity SensorAtmosphericPressure Sensor

Temperature SensorDigital CameraGlobal Positioning

System (GPS)AccelerometerInternet ConnectionLight SensorProximity SensorCompassGyroscope

GeographicalInformation System (GIS)

LARIISA: a Context-Aware Framework

Slide 2115th Healthcom October 10th, 2013 Lisbon, Portugal Slide 21

LARIISA: a Context-Aware Framework

The photo IMG001 was taken at lat=S 3° 45' 48.6532“,

lon=W 38° 36' 28.7332“ on February 2nd, 2013 at 8:00AM. Address =Av. G, 162-229-Conj. Ceará,

Fortaleza – CE. Local Temperatura=29°C. Comment=

Dengue Habitat.

80%-90% likelihood of being withDengue (Local Context)

Information: lat=S 3° 45' 48.6429“, lon=W 38° 36' 28.7434“ on March 3rd, 2013 at 5:00PM. Body temperature=40°C, Heart rate=110 bpm,

Blood pressure=140/90. Address=Av. F, 126-298-Conj. Ceará, Fortaleza

– CE. Local Temperature=25°C. Symptoms=Headache, Vomiting, Body aches. Patient B

Patient A

Health Agent

Relocating a health agent for the Patient B’s house

Information: lat=S 2° 22' 32.9483“, lon=W 34° 33' 21.4657“ on March

24th, 2013 at 3:00PM. Body temperature=37°C, Heart rate=90 bpm,

Blood pressure=120/80. Address= Av. da Sé, n° 227, Conj. Palmeiras,

Fortaleza – CE. Local Temperature=32°C. Symptoms=Chills, Diarrhea.

Who is the patient? Are Data Structured?

Slide 22

<lat>3° 45' 48.6429"</lat>

<lon>38° 36' 28.7434"</lon>

<time>17:00</time>

<date>03/02/2013</date>

<loc_name>Av. F, 126-298-Conj. Ceará, Fortaleza - CE</loc_name>

<sus_id>209968974640021</sus_id>

<symptom>A, B, C</symptom>

<body_temp>40°C</body_temp>

<heart_rate>110bpm</heart_rate>

<blood_pressure>140/90</blood_pressure>

<lat=S 3° 45' 48.6429“>, <lon=W 38° 36' 28.7434“>, <time=17:00h>,

<date=03/02/2013>, <body_temp=40°C>, <heart_rate=110 bpm>,

<blood_press=140/90>, <loc_add=Av. F, 126-298-Conj. Ceará,

Fortaleza – CE>, <loc_weather=25°C>, <symptom=A, B, C>,

<sus_id=209968974640021>

metadata file

Building a metadata

file

Geolocation

Patient Identification

Health Information

Slide 23

Context Providers

Data Processing

Data Acquisition

Publishing

User

Device

Internet Health Agent

DeviceSymptoms + sus_id

Global

Context

Local

Context

Inference

Rules

Context Aggregator (CA)

Health Managers

System

Health Managers

System

Security Protocol

Metadata

LARIISA’s Architecture: a context-aware framework

Slide 24

IN

LARIISA_BAY Inference Module

Patient

Health Agent

Specialist

DecisionModule

Interface

Specialist DecisionModule

11Specialist Decision:

f(%)

33Pass

ThroughA �f(%)

A = A’

22Specialist

Validation:A �f(%)

A ≠ A’

RB

%

SITUATION ROOM

Health Agent

OUT

A’

B’

C’

A’

B’

C’

C

B

A

A

C

B

OTHER CONTEXT

PROVIDERS

A’

B’

C’

LARIISA

INFERENCE MODULE

Sensors

Health Center Ambulance

METADATA

User Interface

Inference

Rules

Global Context

Repository

Local Context

Repository

Patient Specialist

Epidemic Graph

Manager

LARIISA: Functional Diagram

Slide 25

5. Prototype

Slide 26

Data Acquisition(Patient CONTEXT)

DECISION-MAKING

LARIISA’s Prototype

METADATA

Option 1

Option 3

Option 2

LARIISA: A Context-Aware Framework

ONTOLOGY BAYESIAN NETWORKS

Slide 27

Local health context model

Global health context model

Prototype: Dengue Fever Case Study

Metadata

Slide 28

ENTRADA DO

SISTEMA

Módulo de Inferência do LARIISA_Bay

Paciente

Agente de Saúde

Especialista

Interface Módulo de

Decisão

Módulo de Decisão

11Decisão do

Especialista: f(%)

33Pass

ThroughA �f(%)

A = A’

22Validação do Especialista:

A �f(%)A ≠ A’

RB

%

SALA DE SITUAÇÃO

Agente de Saúde

SAÍDA DO SISTEMA

A’

B’

C’

A’

B’

C’

C

B

A

A

C

B

OUTROSPROVEDORES DE CONTEXTO

A’

B’

C’

LARIISA

LARIISA_Bay

Sensores

Posto de Saúde Ambulância

METADADO

Interface do Usuário

Regras de

Inferência

Repositório de

Contexto Global

Repositório de

Contexto Local

Paciente Especialista

Gráfico de Epidemias

Gestor

Screens of theproposed System

Patient

Health Agent

Specialist

Slide 29

Slide 30

Conclusion

Slide 31

Conclusão

Diga Saude (FUNCAP)

SISA (FIOCRUZ)

LARIISA (IFCE)

GISSA (FINEP)

Next Saude (DATASUS / Min Saúde)

Sponsors

LARIISA project is being sponsored since 2004 by

the Science and Technology Ministry of Brazil and others

Brazilian Research Agencies

It will be applied to the brazilian public health system

Slide 3215th Healthcom October 10th, 2013 Lisbon, Portugal Slide 32

Mauro Oliveiramauro.oliveira@fortalnet.com.br

+55 85 9705 4321

www.maurooliveira.com.br

Slide 33

MUITO OBRIGADO