19
12 June 2004 Clinical algorithms in pu blic health 1 Seminar on “Intelligent data analysis and data mining – Application in medicine” Research on poisonings Research on poisonings in children: public in children: public health perspective for health perspective for the development of the development of clinical algorithms clinical algorithms by Dr Sergio Pièche

Seminar on “Intelligent data analysis and data mining – Application in medicine”

  • Upload
    talor

  • View
    28

  • Download
    0

Embed Size (px)

DESCRIPTION

Seminar on “Intelligent data analysis and data mining – Application in medicine”. Research on poisonings in children: public health perspective for the development of clinical algorithms by Dr Sergio Pi èche. Developing clinical algorithms in public health. The problem The target - PowerPoint PPT Presentation

Citation preview

Page 1: Seminar on “Intelligent data analysis and data mining – Application in medicine”

12 June 2004 Clinical algorithms in public health 1

Seminar on “Intelligent data analysis and data mining – Application in medicine”

Research on poisonings Research on poisonings in children: public in children: public

health perspective for health perspective for the development of the development of clinical algorithmsclinical algorithms

byDr Sergio Pièche

Page 2: Seminar on “Intelligent data analysis and data mining – Application in medicine”

12 June 2004 Clinical algorithms in public health 2

Developing clinical algorithms in public health

The problem

The target

Principles

Research

Page 3: Seminar on “Intelligent data analysis and data mining – Application in medicine”

12 June 2004 Clinical algorithms in public health 3

Developing clinical algorithms in public health: The The

problemproblem

InjuriesInjuries

• Mortality: causing deaths• Morbidity: burden of the

condition• Age group at risk• Costs: hospital and primary

health care• Likely impact of interventions

Page 4: Seminar on “Intelligent data analysis and data mining – Application in medicine”

12 June 2004 Clinical algorithms in public health 4

Developing clinical algorithms in public health: The targetThe target

Health providers at primary health care level:

– Health background: doctors, medical assistants, nurses, other health workers

– Type of facility: equipment, supply, access to referral facility

Page 5: Seminar on “Intelligent data analysis and data mining – Application in medicine”

12 June 2004 Clinical algorithms in public health 5

Developing clinical algorithms in public health: PrinciplesPrinciples

• Safe and effective guidelines: Sensitive and specific clinical signs

Minimum number of clinical signs

Requiring simple skills to be used

Standard and simple assess-classify-treat system

Possible to teach and learn

Minimum number of essential drugs

Best care possible for severe cases

• Safe and effective guidelines: Sensitive and specific clinical signs

Minimum number of clinical signs

Requiring simple skills to be used

Standard and simple assess-classify-treat system

Possible to teach and learn

Minimum number of essential drugs

Best care possible for severe cases

Page 6: Seminar on “Intelligent data analysis and data mining – Application in medicine”

12 June 2004 Clinical algorithms in public health 6

Clinical algorithm

ASSESSMENT:signs

CLASSIFICATION:for action

TREATMENT:the action

Danger signs SEVEREReferral:

pre-referral treatment

Other signs MODERATETreatment (follow-up

needed)

Other signs or no signs

MILD Home care

Page 7: Seminar on “Intelligent data analysis and data mining – Application in medicine”

12 June 2004 Clinical algorithms in public health 7

Developing clinical algorithms in public health: ResearchResearch

•Hydrocarbon poisoning

•Organophosphate poisoning

Page 8: Seminar on “Intelligent data analysis and data mining – Application in medicine”

12 June 2004 Clinical algorithms in public health 8

Developing clinical algorithms in public health: Research Research

on poisoning: prospective on poisoning: prospective studystudy

Clinical predictors of severity of accidental poisoning from hydrocarbons and organophosphates in children below 5 years old

Page 9: Seminar on “Intelligent data analysis and data mining – Application in medicine”

12 June 2004 Clinical algorithms in public health 9

Developing clinical algorithms in public health: Research on Research on

poisoning: aimpoisoning: aim

…to develop an algorithm for the

outpatient management of

children with hydrocarbon and

organophosphate poisonings at

primary health care facilities in

developing countries.

Page 10: Seminar on “Intelligent data analysis and data mining – Application in medicine”

12 June 2004 Clinical algorithms in public health 10

Developing clinical algorithms in public health: Research Research

stepssteps

• Derivation of clinical decision

rule (factors with predictive power)

• Prospective validation of the algorithm in different settings

• Provider performance analysis

• Impact

Page 11: Seminar on “Intelligent data analysis and data mining – Application in medicine”

12 June 2004 Clinical algorithms in public health 11

Developing clinical algorithms in public health: Research Research

approachapproach• Identification and standard

definition of signs and symptoms

• Gold standards for diagnoses

• Definition of outcomes

• Observer variability and bias

• Procedures (protocol and instruments; training, supervision)

Page 12: Seminar on “Intelligent data analysis and data mining – Application in medicine”

12 June 2004 Clinical algorithms in public health 12

Developing clinical algorithms in public health: Research Research

methodology - 1methodology - 1

EnrolmentEnrolment• Children 2 to 59 months old

• History: unintentional exposure to hydrocarbons or organophosphates

• Acute exposure

• Seen within 48 hours of exposure to poison

• New cases

Page 13: Seminar on “Intelligent data analysis and data mining – Application in medicine”

12 June 2004 Clinical algorithms in public health 13

Developing clinical algorithms in public health: Research Research

methodology - 2methodology - 2ProceduresProcedures

• All children admitted for at least 48 hours post-exposure irrespective of severity (written consent and free admission)

• Examined by study physician + investigations upon admission

• Followed up at 6, 12, 24, 48 hours post-exposure

• No delay or interference with quality care

Page 14: Seminar on “Intelligent data analysis and data mining – Application in medicine”

12 June 2004 Clinical algorithms in public health 14

Follow-up

Post-exposure

OPD/ER6 hours

Follow-up

12 hours

Follow-up

24 hours

Follow-up

48 hours

Follow-upDischarge

/ death

Cl. exam.(Lab tests;

X-ray)

Intermediate outcomesFinal

outcome

Page 15: Seminar on “Intelligent data analysis and data mining – Application in medicine”

12 June 2004 Clinical algorithms in public health 15

E.g. Hydrocarbon poisoning

•Respiratory signs:cough, fast breathing,etc•Vomiting•…

Chemicalpneumonitis

OutcomeBacterial

pneumonia

Severity

Page 16: Seminar on “Intelligent data analysis and data mining – Application in medicine”

12 June 2004 Clinical algorithms in public health 16

Developing clinical algorithms in public health: Research Research

methodology - 3methodology - 3

Sample sizeSample size• To detect the overall association and prediction

of common symptoms and signs with poisoning severity and outcome

• To account in the analysis for stratification of cases in sub-groups based on time of exposure to poison

Page 17: Seminar on “Intelligent data analysis and data mining – Application in medicine”

12 June 2004 Clinical algorithms in public health 17

Key questions

• Which common clinical signs and symptoms best predict poisoning severity and outcome?

• How long is the safe clinical observation period before sending home a child who has been exposed to hydrocarbons or organophosphates?

Page 18: Seminar on “Intelligent data analysis and data mining – Application in medicine”

12 June 2004 Clinical algorithms in public health 18

Developing clinical algorithms in public health: Research: Research:

AnalysisAnalysis

• Chi-square statistics or Fisher exact test, risk differences, risk ratios, odds ratios

• Multivariate logistics regression - incl. stepwise techniques

• Data mining techniques to be considered• Sensitivity, specificity, predictive accuracy

Page 19: Seminar on “Intelligent data analysis and data mining – Application in medicine”

12 June 2004 Clinical algorithms in public health 19

Data analysis:

The challenge!

The challenge!