trend analysis in stulong data
DESCRIPTION
Trend Analysis in Stulong Data. Ji ří Kléma , Lenka Nov áková, Filip Karel , Olga Štěpánková. The Gerstner laboratory for intelligent decision making and control. Department of Cybernetics, Czech Technical University, Prague. PKDD 2004, Discovery Challenge. Outline. Previous CTU entry - PowerPoint PPT PresentationTRANSCRIPT
Trend Analysis in Stulong Data
The Gerstner laboratory for intelligent decision making and
control
Jiří Kléma, Lenka Nováková, Filip Karel, Olga Štěpánková
PKDD 2004, Discovery Challenge
Department of Cybernetics, Czech Technical University,
Prague
Outline Previous CTU entry
– subgroup discovery (ENTRY), general CVD model
– trend analysis: global approach vs. windowing
Role of windowing in mining trends – KM, Cox models in medicine
– (symbolic) temporal trends in data mining
Development of windowing approach– temporal CVD definition
– role of the window length
– multi-feature interactions
Ordinal association rules– processing of the windowed features
STULONG Data Four tables: Entry, Control, Letter, Death Dependent variable: (static) CVD
– CardioVascular Diseases
– Boolean attribute derived of A2 questionnaire (Control table)
CVD = false The patient has no coronary disease.
CVD = true The patient has one of these attributes true (Hodn1, Hodn2, Hodn3, Hodn11, Hodn13, Hodn14)
We remove patients who have diabetes (Hodn4)or cancer (Hodn15) only.
positive angina
pectoris
(silent)myocardial infarction
cerebrovascular accident
ischemic heart
disease
ENTRY - subgroup discovery AQ no.6: Are there any differences in the ENTRY
examination for different CVD groups? Statistica 6.0
– module for interactive decision tree induction
– two tailed t-test or chi-square test to asses significance of subgroups
Dependencies are relatively weak Interesting dependencies found
– social characteristics: derived attribute AGE_of_ENTRY
– alcohol: “positive effect” of beer, no effect of wine
– sugar consumption increases CVD risk
– well-known dependencies are not mentioned (smoking, BMI, cholesterol)
ENTRY - general model General CVD model (in WEKA)
– feature selection + modeling (e.g., decision trees)
– tends to generate trivial models (always predicting false)
– asymmetric error-cost matrix does not help
Predict CVD risk– Identify principal variables
(Chi-squared test)
– Naïve Bayes + ROC evaluation
– three independent variables
– discretized AGE_of_ENTRY
– discretized BMI
– Cholrisk - derived of CHLST
– AUC = 0.66
CONTROL - trend analysis AQ no.7: Are there any differences in development
of risk factors for different CVD groups?– increasing BMI makes a contribution to CVD appearance
ENTRY table CONTR table
ICO – primary keyYear of birthYear of entrySmokingAlcoholCholesterolBody Mass IndexBlood pressure
ICO
Risk factors followedduring 20 years
Motivation focus on development – trend gradients possibilities
– contemporary statistical methods used in medicine
• KM, Cox models – analyze sth else than we want
• ANOVA etc. – features have to be developed anyway, lack of data
– complex sequential data mining
• introduction of structural patterns and then e.g., association rules
• interesting but again needs more data
our approach– introduction of simple aggregates
– application of windowing
– statistical evaluation for simple dependencies
– ordinal association rules for more complex relations
Survival curves Kaplan-Meier or Cox method
– typical example of temporal analysis in medicine
– regards survival period, BUT disregards development of RFs
– typical scenario
• distinguish groups of patients (ENTRY table)
• follow their “survival” periods (DEATH or CONTROL table)
Derived trend attributes
Intercept
Gradient
Correlation coefficient
Standard deviation
x (decimal time ~ year + 1/12 month)
y (observed variable)
referential time (1975)
Mean
Global Approach Risk factors to be observed are selected
– SYST, DIAST, TRIGL, BMI, CHLSTMG
Selected control examinations are transformed– pivoting
Patients with no control entries are removed – about 60 patients
Trend aggregates are calculated
ICO Entry Contr1 Contr2 Aggr1 AggrN... ContrM ...
ICO_1
ICO_2
Windowing Approach Constant number of examinations for individuals Issues:
– window length
• time period vs. number of checkups
• how many checkups to select? 5, 8, 10 tested
– single distinct window or sliding window?
• entry is used as the first examination
• more records per patient records are not independent
– temporal CVD definition
• CVDi - time from the last examination to CVD
• yes/no (yes = CVD in the next year or CVD in future)
– missing values treatment
Windowing – missing values
approach 1: shift the series
approach 2:introduce a new value
Window length selection
3 different lengths tested, 5 risk factors considered
compared with the global approach
test used,
– null hypothesis: independence of trends and CVD
– p-values are shown
windowing: CVD1 vs. nonCVD group
global: CVD vs. nonCVD group
Window length effects
global approach is completely misleading
prefer shorter windowsdown-up effect
prefers longer windowsonly long term changes may have effect
ControlCount vs. CVD ControlCount
– number of examinations
– strong relation with CVD
– AUC = 0.35
– ControlCount CVD risk
– anachronistic attribute
– introduced by the design of the study
ControlCount has influence on the trend aggregates - ControlCount gradients tend to be more steep etc.
Conclusion: global approach cannot be applied (at least with the selected aggregates)
0.000
0.005
0.010
0.015
0.020
0.025
0.030
0.035
0.040
1 2 3 4 5
SYSTGrad group (equi-depth binning)
CV
D r
ate
1817
28
25
34
average rate
Influence of SYSTGrad (W5) 122 individual CVD1 observations in total
SYSTGrad (W5) equi-depth binned in 5 groups
representation CVD1 group significantly increases with increasing group number of SYSTGrad
130
132
134
136
138
140
142
9 8 7 6 5 4 3 2 1 0
Time to last examination [years]
Avg.
syst
olic
blo
od p
ress
ure
[m
m H
g] SystCVD SystHealthy
81
82
83
84
85
86
87
88
9 8 7 6 5 4 3 2 1 0
Time to last examination [years]
Avg.
dia
stolic
blo
od p
ress
ure
[m
m H
g]
DiastCVD DiastHealthy
Averaged blood pressure striking difference in CVD1 and nonCVD groups
– linear vs. down-up development
– can also be observed for the individuals – see the next slide
– cannot be distinguished by longer windows
Averaged body mass index
difference in CVD1 and nonCVD groups
– steady BMI in the nonCVD group
– increasing BMI in the CVD1 group
– longer windows express this trend better
– this graph shows that W10 may benefit from increase between examination 9 and 8
25.5
26
26.5
27
27.5
28
9 8 7 6 5 4 3 2 1 0
Time to last examination [years]
Avg.
dia
stolic
blo
od p
ress
ure
[m
m H
g]
BMICVD BMIHealthy
Influence of trend aggregates on CVD
– 9 gradients considered: SYST, DIAST, CHLSTMG, TRIGLMG, BMI, HDL, LDL, POCCIG and MOC
Identified relations
– decreasing HDL cholesterol level relates to the increasing risk of CVD (p=0.001)
– decreasing POCCIG (the average number of cigarettes smoked per day) relates to the increasing risk of CVD (p=0.0001)
Again: correlation vs. causality– statement 1 makes sense: HDL is a ’good’ cholesterol – statement 2 suggests spurious dependency
Trend factors – hypothesis testing
patient statecause
smoking habitseffect 1
CVD onseteffect 2
Group a – relations among trend factors
– a great prevalence of the rules joining together either blood pressures (DIASTGrad and SYSTGrad) or cholesterol attributes (HLDGrad, LDLGrad and CHLSTGrad)
Group b - hypothesis to be verified by experts
– insufficient target groups, 6% transactions makes 26 individuals, i.e., instead of 10 prospective diseased patients we actually observe 19
Overview of AR found
Conclusions The main scope
– AQ no.7: Are there any differences in development of risk factors for different CVD groups?
Contributions– Pitfalls of the global approach revealed
– Windowing enabling multivariate temporal analysis proposed, effects of various window lengths studied
– Development of the following risk factors may influence future CVD occurrence:
• DIAST, SYST, BMI, (HDL) cholesterol, (POCCICG)
– Other trends may have or intensify their influence under specific conditions (BMI trend and overweight, etc.) – we lack data to prove it