SlideShare uma empresa Scribd logo
1 de 31
Predicting Hospital Readmission
using TreeNet™
Robert Aronoff MD
The vision …..

Streamlined sequence of processes


            EMR                    Predictive Model               Decision Support
     Clinical Workflow                 Creation                    at Point of Care

  Capture data entered as     Automated E-T-L                Vendor ‘neutral’ scoring
   part of routine clinical     processes                       tools:
   workflow                    Machine learning                    Intranet based
                                algorithms for target class         JSON serialization
                                prediction
Agenda / Table of contents

1   Readmission after Heart Failure


2   Data Structure of an Electronic Medical Record


3   TreeNet™ Modeling with our Dataset


4   Lessons Learned and Next Step(s)
PREFACE:
Data Modeling Paradigm




© Salford Systems, 2011
Model Accuracy


Completeness of Set                       Feature Selection
                                                Feature Fit




                                              Target Class




Kattan MW, EuroUro. 2011; (59): 566-567
Model Error: The Bias – Variance Decomposition




              Prediction Error = Irreducible Error + Bias² + Variance

Hastie T, Tibshirani R, Friedman JH. The elements of statistical learning :
Data mining, inference, and prediction. New York, NY: Springer; 2009.
Model caveats



 Association does not prove causality


 Models are retrospective (observational)
 and therefore hypothesis generating (i.e.
 not hypothesis proving)
READMISSION AFTER HEART FAILURE
Congestive Heart Failure


 Common cause for admission.
 Readmission in excess of 23%.                                     Bueno, H. et al.
                                                           JAMA 2010;303:2141-2147
 Risk factors for readmission extensively studied.
 Published reviews cite over 120 studies.
 - Methods: Logistic regression; Cox proportional hazard
 - C-statistic in 0.6-0.7 range

 Reduction of readmission has been declared a national goal.
 Improved risk models have the potential to more effectively deploy
  targeted disease management.
EMR data structure

 Data collected for clinical workflow.
 Large volume
 - Multiple observations; repeated measures
 - Many interactions and interdependencies

 Complex dataset
 - Continuous, Ordinal, Nominal (low and high order), Binary
 - ‘High-order variable-dimension nominal variables’

 Missing data:
 - May represent error or practice patterns

 Unbalanced classes
 Outliers and Entry errors
Preliminary Dataset
- 1612 consecutive heart failure discharges abstracted
- 1280 candidate predictors screened
- Target class: Readmission at 30 days ( binary )
Administrative candidate predictors             Clinical candidate predictors
•Admission source, status, service          •Specialty medical services consulted
•Age, gender, race                          •Specialty ancillary services consulted
•Primary/secondary payers                   •Blood laboratory values
•Primary/secondary diagnoses (names         •Medications name / therapeutic class
and condition categories)                   •Dosages of medications
•Total length of stay, ICU length of stay   •Patient weights during hospitalization
•Hospital costs and charges                 •Transfusions during hospitalization
•Discharge status and disposition           •Nursing assessments
•All-cause same-center admission in         •Education topics
preceding year                              •Diagnostic tests ordered
                                            •Ordersets utilized



  Preliminary Unpublished Data
Benefits of Stochastic Gradient Boosting
             Friedman JH. Stochastic gradient boosting. Computational Statistics and Data Analysis 2002; 38(4):367- 378.



 Input and processing                                   Output
 Does not require data                               High model accuracy
  transformation
                                                      Classification and regression
 Handles large numbers of
                                                      Non-parametric application of
  categorical and continuous                           logistic , L1, L2, or Huber-M
  variables                                            loss function
 Has mechanisms for:
 - Feature selection
 - Managing missing values
 - Assessing the relationship of
   predictors to target
 Robust to:
 - Data entry errors, Outliers,
   Target misclassification
TreeNet™ Modeling with our Dataset


1   Parameters of ‘feature fit’

2   Parameters of ‘feature selection’

3   Elements of insight

4   Putting it all together
TreeNet – parameters of ‘feature fit’

     Do not forget the manual …..
Feature selection – variable importance

                                  Variable Importance
                                      Calculation

                              Squared relative improvement
                               is the sum of squared
                               improvements (in squared
                               error risk) over all internal
                               nodes for which the variable
                               was chosen as the splitting
                               variable
                              Measurements are relative
                               and is customary to express
                               largest at 100 and scale other
                               variables appropriately
Insight into the model
Illuminating the ‘black box’ with partial dependence




   Preliminary Unpublished Data
Approach to feature selection

Domain ‘Neutral’ vs. Domain ‘Centric’


      Domain Neutral                 Both                   Domain Centric

  Start with a subset      Know your data             Use all potential
   based on univariate      Univariate stats            predictors
   significance (i.e. P-                                Use knowledge of
   value below a given      Application of Variable
                             Importance                  target and predictors to
   level) or variance                                    make decisions on
   above a given            Screening with              inclusion (or rejection)
   threshold                 batteries                   of predictor
                            Forward and backward
                             stepwise progression
Model Variability
Establishing AUC precision and accuracy

                Variation                          Accuracy / Precision
  The model is fit via sampling (i.e.    S.E.M.= S.D. / sqrt ( N )
   stochastic) process.                   Precision (95%) ≈ 4 * S.E.M.




                                          S.D. = 0.03
                                              N trials       10        30     300
                                          S.E.M.            .0095 .0055       .0017
                                          Precision (95%)   .038       .022   .007
Precision and predictor selection
         STEP_1 (197) (0.531)             STEP_66 (737) (0.703)
            0.75
                                                                  Min      = 0.5057
                                                                  Median   = 0.6738
                    0.70                                          Mean     = 0.6500
                                                                  Max      = 0.7034
         Avg. ROC



                    0.65
                                                                              Test ROC
                    0.60


                    0.55


                    0.50




 AUC estimated using CV-10 ( = 10 trees)  SEM .0095 and
  precision (95%) of .038
 Repeating CV-10 (using CVR battery) 30 times  SEM .0017 and
  precision (95%) of .007
 Profound implication on dimensionality of model achievable without
  domain knowledge input.
How much of a change in AUC is clinically relevant ?

Gain Curve complements ROC curve




 Preliminary Unpublished
           Data
Useful batteries for feature selection
Methods of forward and backward selection




                                                  STEPWISE

                                             Testing set to CV-10
                                             Select predictor 1-2 at
                                              a time
                                             Confirm with CVR
                                              battery

                                                   SHAVING
BUILDING A MODEL                                                 **Each change confirmed with
                                                                 CVR (30 reps). Review partial
This is a multi-step process                                     dependence plot.


Run model with all candidate             Use backward and forward           Re-examine discarded
predictors. Select N highest             selection to reduce                  predictors in smaller
important predictors.                    preliminary model to a core        groups. Use backward
N= 2-3 x final size                      5 -15 predictors.**               and forward selection.**



     Step 1                   Step 2                 Step 3          Step 4            Step 5


                      Run batteries to assess                 Review predictors and use domain
                      parameters of feature ‘fit’.            knowledge to eliminate redundant
                      Assess model (AUC)                      (dependent) predictors and consider
                      variability. Repeat as                  predictors of known value. **
                      needed through process.
Initial runs
Information content and irreducible error
                                           #287 (0.519) #287 (0.519) (0.436)
 0.576                   0.6
         Cross Entropy




 0.576                   0.5
                         0.4
                         0.3
                                                                                                                                                   Train
                         0.2
                         0.1
                                                                                                                                                   Test    6 Nodes
                         0.0
                               0   100   200    300      400     500     600      700   800    900     1000    1100    1200   1300   1400   1500

                                                                               Number of Trees




                                                                                         #880 (0.518) #880 (0.518) (0.457)
 0.576                   0.6
         Cross Entropy




 0.577                   0.5
                         0.4
                         0.3
                                                                                                                                                   Train
                         0.2
                         0.1
                                                                                                                                                   Test    2 Nodes
                         0.0
                               0   100   200    300      400     500     600      700   800    900     1000    1100    1200   1300   1400   1500

                                                                               Number of Trees




     Preliminary Unpublished Data
Sample Model
                    GAIN CURVE    ROC CURVE

                      FEATURE SELECTION SET




                       MODEL TRAINING SET




 Preliminary Unpublished Data
Sample partial dependence plots
The value of non-parametric regression

                    Admissions within prior year        ICU Days




                            Anion Gap                Initial Systolic BP




                             Final BNP             BUN-Creatinine Ratio




   Preliminary Unpublished Data
Prospective application
Additional heart failure discharges can be scored against the model

                GAIN curve                          ROC curve




                                                    Preliminary Unpublished
             Causes for performance shift                     Data
  Overfitting in the original model
  Concomitant intervention programs are altering
   patient risk of readmission
Non-influential candidate predictors

Models favor continuous over binary ‘dummy’ variables

 Diagnoses and QualNet Condition Categories
 Medications and Therapeutic Categories
 Diagnostic Tests
 Ordersets Submitted




  Preliminary Unpublished Data
Lessons learned
 TreeNet ( stochastic gradient boosting) is extremely well suited to
  data structure of EMR data.
 Insight in to dataset is a rich feature (in and above prediction
  performance).
 Model performance variance is important in feature selection.
 - Consequence of limited information content in our dataset.

 Batteries are useful.
   - PARTITION – Variability assessment
   - CVR – Model assessment
   - STEPWISE – Forward selection
   - SHAVING – Backward selection

 There is great value in learning on a non-trivial dataset within a
  familiar domain.
Next steps ……


Explore options to manage model variability
and increase dimensionality of predictor set.

Extend analysis of predictor interactions.

Develop mechanism of ‘point-of-care’ patient
scoring.

Apply techniques to new problems and
dataset.
Any Questions?




raronoff@hmc.psu.edu

Mais conteúdo relacionado

Mais procurados

Non-inferiority and Equivalence Study design considerations and sample size
Non-inferiority and Equivalence Study design considerations and sample sizeNon-inferiority and Equivalence Study design considerations and sample size
Non-inferiority and Equivalence Study design considerations and sample sizenQuery
 
2010 smg training_cardiff_day2_session1_salanti
2010 smg training_cardiff_day2_session1_salanti2010 smg training_cardiff_day2_session1_salanti
2010 smg training_cardiff_day2_session1_salantirgveroniki
 
day1(2010 smg training_cardiff)_session2b (1of 2) lewis
day1(2010 smg training_cardiff)_session2b (1of 2) lewisday1(2010 smg training_cardiff)_session2b (1of 2) lewis
day1(2010 smg training_cardiff)_session2b (1of 2) lewisrgveroniki
 
Power and sample size calculations for survival analysis webinar Slides
Power and sample size calculations for survival analysis webinar SlidesPower and sample size calculations for survival analysis webinar Slides
Power and sample size calculations for survival analysis webinar SlidesnQuery
 
Sample size
Sample sizeSample size
Sample sizezubis
 
Sample Size Estimation and Statistical Test Selection
Sample Size Estimation  and Statistical Test SelectionSample Size Estimation  and Statistical Test Selection
Sample Size Estimation and Statistical Test SelectionVaggelis Vergoulas
 
Practical Methods To Overcome Sample Size Challenges
Practical Methods To Overcome Sample Size ChallengesPractical Methods To Overcome Sample Size Challenges
Practical Methods To Overcome Sample Size ChallengesnQuery
 
5 essential steps for sample size determination in clinical trials slideshare
5 essential steps for sample size determination in clinical trials   slideshare5 essential steps for sample size determination in clinical trials   slideshare
5 essential steps for sample size determination in clinical trials slidesharenQuery
 
2010 smg training_cardiff_day1_session4_harbord
2010 smg training_cardiff_day1_session4_harbord2010 smg training_cardiff_day1_session4_harbord
2010 smg training_cardiff_day1_session4_harbordrgveroniki
 
Use of the Crowdsourcing Methodology to Generate a Problem-Laboratory Test Kn...
Use of the Crowdsourcing Methodology to Generate a Problem-Laboratory Test Kn...Use of the Crowdsourcing Methodology to Generate a Problem-Laboratory Test Kn...
Use of the Crowdsourcing Methodology to Generate a Problem-Laboratory Test Kn...Allison McCoy
 
Combination of informative biomarkers in small pilot studies and estimation ...
Combination of informative  biomarkers in small pilot studies and estimation ...Combination of informative  biomarkers in small pilot studies and estimation ...
Combination of informative biomarkers in small pilot studies and estimation ...LEGATO project
 
IRJET- Drugs Selection in Medical Field: A Survey
IRJET- Drugs Selection in Medical Field: A SurveyIRJET- Drugs Selection in Medical Field: A Survey
IRJET- Drugs Selection in Medical Field: A SurveyIRJET Journal
 
Analysis of Medication Possession Ratio for Improved Blood Pressure Control
Analysis of Medication Possession Ratio for Improved Blood Pressure ControlAnalysis of Medication Possession Ratio for Improved Blood Pressure Control
Analysis of Medication Possession Ratio for Improved Blood Pressure ControlHealth Informatics New Zealand
 
Clinical Research Statistics for Non-Statisticians
Clinical Research Statistics for Non-StatisticiansClinical Research Statistics for Non-Statisticians
Clinical Research Statistics for Non-StatisticiansBrook White, PMP
 
Sample size calculation - a brief overview
Sample size calculation - a brief overviewSample size calculation - a brief overview
Sample size calculation - a brief overviewAzmi Mohd Tamil
 
ICU Patient Deterioration Prediction : A Data-Mining Approach
ICU Patient Deterioration Prediction : A Data-Mining ApproachICU Patient Deterioration Prediction : A Data-Mining Approach
ICU Patient Deterioration Prediction : A Data-Mining Approachcsandit
 
How to calculate Sample Size
How to calculate Sample SizeHow to calculate Sample Size
How to calculate Sample SizeMNDU net
 

Mais procurados (20)

Non-inferiority and Equivalence Study design considerations and sample size
Non-inferiority and Equivalence Study design considerations and sample sizeNon-inferiority and Equivalence Study design considerations and sample size
Non-inferiority and Equivalence Study design considerations and sample size
 
2010 smg training_cardiff_day2_session1_salanti
2010 smg training_cardiff_day2_session1_salanti2010 smg training_cardiff_day2_session1_salanti
2010 smg training_cardiff_day2_session1_salanti
 
day1(2010 smg training_cardiff)_session2b (1of 2) lewis
day1(2010 smg training_cardiff)_session2b (1of 2) lewisday1(2010 smg training_cardiff)_session2b (1of 2) lewis
day1(2010 smg training_cardiff)_session2b (1of 2) lewis
 
Power and sample size calculations for survival analysis webinar Slides
Power and sample size calculations for survival analysis webinar SlidesPower and sample size calculations for survival analysis webinar Slides
Power and sample size calculations for survival analysis webinar Slides
 
Sample size
Sample sizeSample size
Sample size
 
Sample Size Estimation and Statistical Test Selection
Sample Size Estimation  and Statistical Test SelectionSample Size Estimation  and Statistical Test Selection
Sample Size Estimation and Statistical Test Selection
 
Practical Methods To Overcome Sample Size Challenges
Practical Methods To Overcome Sample Size ChallengesPractical Methods To Overcome Sample Size Challenges
Practical Methods To Overcome Sample Size Challenges
 
5 essential steps for sample size determination in clinical trials slideshare
5 essential steps for sample size determination in clinical trials   slideshare5 essential steps for sample size determination in clinical trials   slideshare
5 essential steps for sample size determination in clinical trials slideshare
 
2010 smg training_cardiff_day1_session4_harbord
2010 smg training_cardiff_day1_session4_harbord2010 smg training_cardiff_day1_session4_harbord
2010 smg training_cardiff_day1_session4_harbord
 
Use of the Crowdsourcing Methodology to Generate a Problem-Laboratory Test Kn...
Use of the Crowdsourcing Methodology to Generate a Problem-Laboratory Test Kn...Use of the Crowdsourcing Methodology to Generate a Problem-Laboratory Test Kn...
Use of the Crowdsourcing Methodology to Generate a Problem-Laboratory Test Kn...
 
Combination of informative biomarkers in small pilot studies and estimation ...
Combination of informative  biomarkers in small pilot studies and estimation ...Combination of informative  biomarkers in small pilot studies and estimation ...
Combination of informative biomarkers in small pilot studies and estimation ...
 
IRJET- Drugs Selection in Medical Field: A Survey
IRJET- Drugs Selection in Medical Field: A SurveyIRJET- Drugs Selection in Medical Field: A Survey
IRJET- Drugs Selection in Medical Field: A Survey
 
Biostatistics in cancer RCTs
Biostatistics in cancer RCTsBiostatistics in cancer RCTs
Biostatistics in cancer RCTs
 
Predictive Medicine
Predictive Medicine Predictive Medicine
Predictive Medicine
 
Analysis of Medication Possession Ratio for Improved Blood Pressure Control
Analysis of Medication Possession Ratio for Improved Blood Pressure ControlAnalysis of Medication Possession Ratio for Improved Blood Pressure Control
Analysis of Medication Possession Ratio for Improved Blood Pressure Control
 
Clinical Research Statistics for Non-Statisticians
Clinical Research Statistics for Non-StatisticiansClinical Research Statistics for Non-Statisticians
Clinical Research Statistics for Non-Statisticians
 
Sample size calculation - a brief overview
Sample size calculation - a brief overviewSample size calculation - a brief overview
Sample size calculation - a brief overview
 
Sample size calculation final
Sample size calculation finalSample size calculation final
Sample size calculation final
 
ICU Patient Deterioration Prediction : A Data-Mining Approach
ICU Patient Deterioration Prediction : A Data-Mining ApproachICU Patient Deterioration Prediction : A Data-Mining Approach
ICU Patient Deterioration Prediction : A Data-Mining Approach
 
How to calculate Sample Size
How to calculate Sample SizeHow to calculate Sample Size
How to calculate Sample Size
 

Destaque

Applied Multivariable Modeling in Public Health: Use of CART and Logistic Reg...
Applied Multivariable Modeling in Public Health: Use of CART and Logistic Reg...Applied Multivariable Modeling in Public Health: Use of CART and Logistic Reg...
Applied Multivariable Modeling in Public Health: Use of CART and Logistic Reg...Salford Systems
 
Broadscale Predictive Modeling and Marketing Optimization in Retail Sales
Broadscale Predictive Modeling and Marketing Optimization in Retail SalesBroadscale Predictive Modeling and Marketing Optimization in Retail Sales
Broadscale Predictive Modeling and Marketing Optimization in Retail SalesSalford Systems
 
REGRESSION ANALYSIS ON HEALTH INSURANCE COVERAGE RATE
REGRESSION ANALYSIS ON HEALTH INSURANCE COVERAGE RATEREGRESSION ANALYSIS ON HEALTH INSURANCE COVERAGE RATE
REGRESSION ANALYSIS ON HEALTH INSURANCE COVERAGE RATEChaoyi WU
 
Churn Modeling-For-Mobile-Telecommunications
Churn Modeling-For-Mobile-Telecommunications Churn Modeling-For-Mobile-Telecommunications
Churn Modeling-For-Mobile-Telecommunications Salford Systems
 
Analysis Of A Binary Outcome Variable
Analysis Of A Binary Outcome VariableAnalysis Of A Binary Outcome Variable
Analysis Of A Binary Outcome VariableArthur8898
 
Case Study: American Family Insurance Best Practices for Automating Guidewire...
Case Study: American Family Insurance Best Practices for Automating Guidewire...Case Study: American Family Insurance Best Practices for Automating Guidewire...
Case Study: American Family Insurance Best Practices for Automating Guidewire...CA Technologies
 
Data Mining: Text and web mining
Data Mining: Text and web miningData Mining: Text and web mining
Data Mining: Text and web miningDatamining Tools
 
Improve Your Regression with CART and RandomForests
Improve Your Regression with CART and RandomForestsImprove Your Regression with CART and RandomForests
Improve Your Regression with CART and RandomForestsSalford Systems
 
Lecture 3: Structuring Unstructured Texts Through Sentiment Analysis
Lecture 3: Structuring Unstructured Texts Through Sentiment AnalysisLecture 3: Structuring Unstructured Texts Through Sentiment Analysis
Lecture 3: Structuring Unstructured Texts Through Sentiment AnalysisMarina Santini
 
Predictive Modeling in Insurance in the context of (possibly) big data
Predictive Modeling in Insurance in the context of (possibly) big dataPredictive Modeling in Insurance in the context of (possibly) big data
Predictive Modeling in Insurance in the context of (possibly) big dataArthur Charpentier
 
Hospital information system
Hospital information systemHospital information system
Hospital information systemBLUEZ09
 
Hospital information system[1]
Hospital information system[1]Hospital information system[1]
Hospital information system[1]Prasit Chanarat
 
Sibyl HIMS: Hospital Information & Management System
Sibyl HIMS: Hospital Information & Management SystemSibyl HIMS: Hospital Information & Management System
Sibyl HIMS: Hospital Information & Management SystemAmarnath Gupta
 
Hospital Information System
Hospital Information SystemHospital Information System
Hospital Information SystemLikithe
 

Destaque (20)

Applied Multivariable Modeling in Public Health: Use of CART and Logistic Reg...
Applied Multivariable Modeling in Public Health: Use of CART and Logistic Reg...Applied Multivariable Modeling in Public Health: Use of CART and Logistic Reg...
Applied Multivariable Modeling in Public Health: Use of CART and Logistic Reg...
 
Broadscale Predictive Modeling and Marketing Optimization in Retail Sales
Broadscale Predictive Modeling and Marketing Optimization in Retail SalesBroadscale Predictive Modeling and Marketing Optimization in Retail Sales
Broadscale Predictive Modeling and Marketing Optimization in Retail Sales
 
REGRESSION ANALYSIS ON HEALTH INSURANCE COVERAGE RATE
REGRESSION ANALYSIS ON HEALTH INSURANCE COVERAGE RATEREGRESSION ANALYSIS ON HEALTH INSURANCE COVERAGE RATE
REGRESSION ANALYSIS ON HEALTH INSURANCE COVERAGE RATE
 
Churn Modeling-For-Mobile-Telecommunications
Churn Modeling-For-Mobile-Telecommunications Churn Modeling-For-Mobile-Telecommunications
Churn Modeling-For-Mobile-Telecommunications
 
Analysis Of A Binary Outcome Variable
Analysis Of A Binary Outcome VariableAnalysis Of A Binary Outcome Variable
Analysis Of A Binary Outcome Variable
 
Case Study: American Family Insurance Best Practices for Automating Guidewire...
Case Study: American Family Insurance Best Practices for Automating Guidewire...Case Study: American Family Insurance Best Practices for Automating Guidewire...
Case Study: American Family Insurance Best Practices for Automating Guidewire...
 
Data Mining: Text and web mining
Data Mining: Text and web miningData Mining: Text and web mining
Data Mining: Text and web mining
 
Improve Your Regression with CART and RandomForests
Improve Your Regression with CART and RandomForestsImprove Your Regression with CART and RandomForests
Improve Your Regression with CART and RandomForests
 
Lecture 3: Structuring Unstructured Texts Through Sentiment Analysis
Lecture 3: Structuring Unstructured Texts Through Sentiment AnalysisLecture 3: Structuring Unstructured Texts Through Sentiment Analysis
Lecture 3: Structuring Unstructured Texts Through Sentiment Analysis
 
Text mining tutorial
Text mining tutorialText mining tutorial
Text mining tutorial
 
Predictive Modeling in Insurance in the context of (possibly) big data
Predictive Modeling in Insurance in the context of (possibly) big dataPredictive Modeling in Insurance in the context of (possibly) big data
Predictive Modeling in Insurance in the context of (possibly) big data
 
Decision tree and random forest
Decision tree and random forestDecision tree and random forest
Decision tree and random forest
 
Logistic regression
Logistic regressionLogistic regression
Logistic regression
 
Hospital information system
Hospital information systemHospital information system
Hospital information system
 
Hmis
HmisHmis
Hmis
 
Attune Mobility Solutions
Attune Mobility SolutionsAttune Mobility Solutions
Attune Mobility Solutions
 
Hospital information system[1]
Hospital information system[1]Hospital information system[1]
Hospital information system[1]
 
Caresoft presentation
Caresoft presentationCaresoft presentation
Caresoft presentation
 
Sibyl HIMS: Hospital Information & Management System
Sibyl HIMS: Hospital Information & Management SystemSibyl HIMS: Hospital Information & Management System
Sibyl HIMS: Hospital Information & Management System
 
Hospital Information System
Hospital Information SystemHospital Information System
Hospital Information System
 

Semelhante a Predicting Hospital Readmission Using TreeNet

Usp chemical medicines & excipients - evolution of validation practices
Usp    chemical medicines & excipients - evolution of validation practicesUsp    chemical medicines & excipients - evolution of validation practices
Usp chemical medicines & excipients - evolution of validation practicesNational Institute of Biologics
 
Bridging the Gap: Machine Learning for Ubiquitous Computing -- Evaluation
Bridging the Gap: Machine Learning for Ubiquitous Computing -- EvaluationBridging the Gap: Machine Learning for Ubiquitous Computing -- Evaluation
Bridging the Gap: Machine Learning for Ubiquitous Computing -- EvaluationThomas Ploetz
 
02trainingmaterialformsa (1) 111030062223-phpapp02
02trainingmaterialformsa (1) 111030062223-phpapp0202trainingmaterialformsa (1) 111030062223-phpapp02
02trainingmaterialformsa (1) 111030062223-phpapp02Junelly Grace Catalan-Tecson
 
Quality assurance of treatment planning system by Rahim Gohar
Quality assurance of treatment planning system by Rahim GoharQuality assurance of treatment planning system by Rahim Gohar
Quality assurance of treatment planning system by Rahim GoharRahim Gohar
 
Features of new installed linac Trilogy At Dr Ziauddin Hospital Karachi
Features of new installed linac Trilogy At Dr Ziauddin Hospital KarachiFeatures of new installed linac Trilogy At Dr Ziauddin Hospital Karachi
Features of new installed linac Trilogy At Dr Ziauddin Hospital KarachiRahim Gohar
 
ANALYTICAL VARIABLES IN QUALITY CONTROL.pptx
ANALYTICAL VARIABLES IN QUALITY CONTROL.pptxANALYTICAL VARIABLES IN QUALITY CONTROL.pptx
ANALYTICAL VARIABLES IN QUALITY CONTROL.pptxDr. Jagroop Singh
 
Data Science Project: Advancements in Fetal Health Classification
Data Science Project: Advancements in Fetal Health ClassificationData Science Project: Advancements in Fetal Health Classification
Data Science Project: Advancements in Fetal Health ClassificationBoston Institute of Analytics
 
02training material for msa
02training material for msa02training material for msa
02training material for msa營松 林
 
Boost model accuracy of imbalanced covid 19 mortality prediction
Boost model accuracy of imbalanced covid 19 mortality predictionBoost model accuracy of imbalanced covid 19 mortality prediction
Boost model accuracy of imbalanced covid 19 mortality predictionBindhuBhargaviTalasi
 
SPC WithAdrian Adrian Beale
SPC WithAdrian Adrian BealeSPC WithAdrian Adrian Beale
SPC WithAdrian Adrian BealeAdrian Beale
 
How to Measure Uncertainty
How to Measure UncertaintyHow to Measure Uncertainty
How to Measure UncertaintyRandox
 
Machine learning Mind Map
Machine learning Mind MapMachine learning Mind Map
Machine learning Mind MapAshish Patel
 
Heart Disease Identification Method Using Machine Learnin in E-healthcare.
Heart Disease Identification Method Using Machine Learnin in E-healthcare.Heart Disease Identification Method Using Machine Learnin in E-healthcare.
Heart Disease Identification Method Using Machine Learnin in E-healthcare.SUJIT SHIBAPRASAD MAITY
 
Summer 2015 Internship
Summer 2015 InternshipSummer 2015 Internship
Summer 2015 InternshipTaylor Martell
 
my poster presentation in the jcms2011 conference
my poster presentation in the jcms2011 conferencemy poster presentation in the jcms2011 conference
my poster presentation in the jcms2011 conferencePawitra Masa-ah
 
QCP user manual EN.pdf
QCP user manual EN.pdfQCP user manual EN.pdf
QCP user manual EN.pdfEmerson Ceras
 

Semelhante a Predicting Hospital Readmission Using TreeNet (20)

TESCO Evaluation of Non-Normal Meter Data
TESCO Evaluation of Non-Normal Meter DataTESCO Evaluation of Non-Normal Meter Data
TESCO Evaluation of Non-Normal Meter Data
 
Usp chemical medicines & excipients - evolution of validation practices
Usp    chemical medicines & excipients - evolution of validation practicesUsp    chemical medicines & excipients - evolution of validation practices
Usp chemical medicines & excipients - evolution of validation practices
 
Bridging the Gap: Machine Learning for Ubiquitous Computing -- Evaluation
Bridging the Gap: Machine Learning for Ubiquitous Computing -- EvaluationBridging the Gap: Machine Learning for Ubiquitous Computing -- Evaluation
Bridging the Gap: Machine Learning for Ubiquitous Computing -- Evaluation
 
02trainingmaterialformsa (1) 111030062223-phpapp02
02trainingmaterialformsa (1) 111030062223-phpapp0202trainingmaterialformsa (1) 111030062223-phpapp02
02trainingmaterialformsa (1) 111030062223-phpapp02
 
Quality assurance of treatment planning system by Rahim Gohar
Quality assurance of treatment planning system by Rahim GoharQuality assurance of treatment planning system by Rahim Gohar
Quality assurance of treatment planning system by Rahim Gohar
 
Features of new installed linac Trilogy At Dr Ziauddin Hospital Karachi
Features of new installed linac Trilogy At Dr Ziauddin Hospital KarachiFeatures of new installed linac Trilogy At Dr Ziauddin Hospital Karachi
Features of new installed linac Trilogy At Dr Ziauddin Hospital Karachi
 
ANALYTICAL VARIABLES IN QUALITY CONTROL.pptx
ANALYTICAL VARIABLES IN QUALITY CONTROL.pptxANALYTICAL VARIABLES IN QUALITY CONTROL.pptx
ANALYTICAL VARIABLES IN QUALITY CONTROL.pptx
 
Data Science Project: Advancements in Fetal Health Classification
Data Science Project: Advancements in Fetal Health ClassificationData Science Project: Advancements in Fetal Health Classification
Data Science Project: Advancements in Fetal Health Classification
 
Linear regression analysis
Linear regression analysisLinear regression analysis
Linear regression analysis
 
02training material for msa
02training material for msa02training material for msa
02training material for msa
 
Boost model accuracy of imbalanced covid 19 mortality prediction
Boost model accuracy of imbalanced covid 19 mortality predictionBoost model accuracy of imbalanced covid 19 mortality prediction
Boost model accuracy of imbalanced covid 19 mortality prediction
 
SPC WithAdrian Adrian Beale
SPC WithAdrian Adrian BealeSPC WithAdrian Adrian Beale
SPC WithAdrian Adrian Beale
 
Vanderbilt b
Vanderbilt bVanderbilt b
Vanderbilt b
 
Errors2
Errors2Errors2
Errors2
 
How to Measure Uncertainty
How to Measure UncertaintyHow to Measure Uncertainty
How to Measure Uncertainty
 
Machine learning Mind Map
Machine learning Mind MapMachine learning Mind Map
Machine learning Mind Map
 
Heart Disease Identification Method Using Machine Learnin in E-healthcare.
Heart Disease Identification Method Using Machine Learnin in E-healthcare.Heart Disease Identification Method Using Machine Learnin in E-healthcare.
Heart Disease Identification Method Using Machine Learnin in E-healthcare.
 
Summer 2015 Internship
Summer 2015 InternshipSummer 2015 Internship
Summer 2015 Internship
 
my poster presentation in the jcms2011 conference
my poster presentation in the jcms2011 conferencemy poster presentation in the jcms2011 conference
my poster presentation in the jcms2011 conference
 
QCP user manual EN.pdf
QCP user manual EN.pdfQCP user manual EN.pdf
QCP user manual EN.pdf
 

Mais de Salford Systems

Datascience101presentation4
Datascience101presentation4Datascience101presentation4
Datascience101presentation4Salford Systems
 
Improved Predictions in Structure Based Drug Design Using Cart and Bayesian M...
Improved Predictions in Structure Based Drug Design Using Cart and Bayesian M...Improved Predictions in Structure Based Drug Design Using Cart and Bayesian M...
Improved Predictions in Structure Based Drug Design Using Cart and Bayesian M...Salford Systems
 
The Do's and Don'ts of Data Mining
The Do's and Don'ts of Data MiningThe Do's and Don'ts of Data Mining
The Do's and Don'ts of Data MiningSalford Systems
 
Introduction to Random Forests by Dr. Adele Cutler
Introduction to Random Forests by Dr. Adele CutlerIntroduction to Random Forests by Dr. Adele Cutler
Introduction to Random Forests by Dr. Adele CutlerSalford Systems
 
9 Data Mining Challenges From Data Scientists Like You
9 Data Mining Challenges From Data Scientists Like You9 Data Mining Challenges From Data Scientists Like You
9 Data Mining Challenges From Data Scientists Like YouSalford Systems
 
Statistically Significant Quotes To Remember
Statistically Significant Quotes To RememberStatistically Significant Quotes To Remember
Statistically Significant Quotes To RememberSalford Systems
 
Using CART For Beginners with A Teclo Example Dataset
Using CART For Beginners with A Teclo Example DatasetUsing CART For Beginners with A Teclo Example Dataset
Using CART For Beginners with A Teclo Example DatasetSalford Systems
 
CART Classification and Regression Trees Experienced User Guide
CART Classification and Regression Trees Experienced User GuideCART Classification and Regression Trees Experienced User Guide
CART Classification and Regression Trees Experienced User GuideSalford Systems
 
Evolution of regression ols to gps to mars
Evolution of regression   ols to gps to marsEvolution of regression   ols to gps to mars
Evolution of regression ols to gps to marsSalford Systems
 
Data Mining for Higher Education
Data Mining for Higher EducationData Mining for Higher Education
Data Mining for Higher EducationSalford Systems
 
Comparison of statistical methods commonly used in predictive modeling
Comparison of statistical methods commonly used in predictive modelingComparison of statistical methods commonly used in predictive modeling
Comparison of statistical methods commonly used in predictive modelingSalford Systems
 
Molecular data mining tool advances in hiv
Molecular data mining tool  advances in hivMolecular data mining tool  advances in hiv
Molecular data mining tool advances in hivSalford Systems
 
TreeNet Tree Ensembles & CART Decision Trees: A Winning Combination
TreeNet Tree Ensembles & CART Decision Trees:  A Winning CombinationTreeNet Tree Ensembles & CART Decision Trees:  A Winning Combination
TreeNet Tree Ensembles & CART Decision Trees: A Winning CombinationSalford Systems
 
SPM User's Guide: Introducing MARS
SPM User's Guide: Introducing MARSSPM User's Guide: Introducing MARS
SPM User's Guide: Introducing MARSSalford Systems
 
Hybrid cart logit model 1998
Hybrid cart logit model 1998Hybrid cart logit model 1998
Hybrid cart logit model 1998Salford Systems
 
Session Logs Tutorial for SPM
Session Logs Tutorial for SPMSession Logs Tutorial for SPM
Session Logs Tutorial for SPMSalford Systems
 
Some of the new features in SPM 7
Some of the new features in SPM 7Some of the new features in SPM 7
Some of the new features in SPM 7Salford Systems
 
TreeNet Overview - Updated October 2012
TreeNet Overview  - Updated October 2012TreeNet Overview  - Updated October 2012
TreeNet Overview - Updated October 2012Salford Systems
 
TreeNet Tree Ensembles and CART Decision Trees: A Winning Combination
TreeNet Tree Ensembles and CART  Decision Trees:  A Winning CombinationTreeNet Tree Ensembles and CART  Decision Trees:  A Winning Combination
TreeNet Tree Ensembles and CART Decision Trees: A Winning CombinationSalford Systems
 

Mais de Salford Systems (20)

Datascience101presentation4
Datascience101presentation4Datascience101presentation4
Datascience101presentation4
 
Improved Predictions in Structure Based Drug Design Using Cart and Bayesian M...
Improved Predictions in Structure Based Drug Design Using Cart and Bayesian M...Improved Predictions in Structure Based Drug Design Using Cart and Bayesian M...
Improved Predictions in Structure Based Drug Design Using Cart and Bayesian M...
 
The Do's and Don'ts of Data Mining
The Do's and Don'ts of Data MiningThe Do's and Don'ts of Data Mining
The Do's and Don'ts of Data Mining
 
Introduction to Random Forests by Dr. Adele Cutler
Introduction to Random Forests by Dr. Adele CutlerIntroduction to Random Forests by Dr. Adele Cutler
Introduction to Random Forests by Dr. Adele Cutler
 
9 Data Mining Challenges From Data Scientists Like You
9 Data Mining Challenges From Data Scientists Like You9 Data Mining Challenges From Data Scientists Like You
9 Data Mining Challenges From Data Scientists Like You
 
Statistically Significant Quotes To Remember
Statistically Significant Quotes To RememberStatistically Significant Quotes To Remember
Statistically Significant Quotes To Remember
 
Using CART For Beginners with A Teclo Example Dataset
Using CART For Beginners with A Teclo Example DatasetUsing CART For Beginners with A Teclo Example Dataset
Using CART For Beginners with A Teclo Example Dataset
 
CART Classification and Regression Trees Experienced User Guide
CART Classification and Regression Trees Experienced User GuideCART Classification and Regression Trees Experienced User Guide
CART Classification and Regression Trees Experienced User Guide
 
Evolution of regression ols to gps to mars
Evolution of regression   ols to gps to marsEvolution of regression   ols to gps to mars
Evolution of regression ols to gps to mars
 
Data Mining for Higher Education
Data Mining for Higher EducationData Mining for Higher Education
Data Mining for Higher Education
 
Comparison of statistical methods commonly used in predictive modeling
Comparison of statistical methods commonly used in predictive modelingComparison of statistical methods commonly used in predictive modeling
Comparison of statistical methods commonly used in predictive modeling
 
Molecular data mining tool advances in hiv
Molecular data mining tool  advances in hivMolecular data mining tool  advances in hiv
Molecular data mining tool advances in hiv
 
TreeNet Tree Ensembles & CART Decision Trees: A Winning Combination
TreeNet Tree Ensembles & CART Decision Trees:  A Winning CombinationTreeNet Tree Ensembles & CART Decision Trees:  A Winning Combination
TreeNet Tree Ensembles & CART Decision Trees: A Winning Combination
 
SPM v7.0 Feature Matrix
SPM v7.0 Feature MatrixSPM v7.0 Feature Matrix
SPM v7.0 Feature Matrix
 
SPM User's Guide: Introducing MARS
SPM User's Guide: Introducing MARSSPM User's Guide: Introducing MARS
SPM User's Guide: Introducing MARS
 
Hybrid cart logit model 1998
Hybrid cart logit model 1998Hybrid cart logit model 1998
Hybrid cart logit model 1998
 
Session Logs Tutorial for SPM
Session Logs Tutorial for SPMSession Logs Tutorial for SPM
Session Logs Tutorial for SPM
 
Some of the new features in SPM 7
Some of the new features in SPM 7Some of the new features in SPM 7
Some of the new features in SPM 7
 
TreeNet Overview - Updated October 2012
TreeNet Overview  - Updated October 2012TreeNet Overview  - Updated October 2012
TreeNet Overview - Updated October 2012
 
TreeNet Tree Ensembles and CART Decision Trees: A Winning Combination
TreeNet Tree Ensembles and CART  Decision Trees:  A Winning CombinationTreeNet Tree Ensembles and CART  Decision Trees:  A Winning Combination
TreeNet Tree Ensembles and CART Decision Trees: A Winning Combination
 

Último

Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxMalak Abu Hammad
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationSafe Software
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphNeo4j
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesSinan KOZAK
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions
 
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Paola De la Torre
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksSoftradix Technologies
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitecturePixlogix Infotech
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 

Último (20)

Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen Frames
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping Elbows
 
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other Frameworks
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC Architecture
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 

Predicting Hospital Readmission Using TreeNet

  • 1. Predicting Hospital Readmission using TreeNet™ Robert Aronoff MD
  • 2. The vision ….. Streamlined sequence of processes EMR Predictive Model Decision Support Clinical Workflow Creation at Point of Care  Capture data entered as  Automated E-T-L  Vendor ‘neutral’ scoring part of routine clinical processes tools: workflow  Machine learning  Intranet based algorithms for target class  JSON serialization prediction
  • 3. Agenda / Table of contents 1 Readmission after Heart Failure 2 Data Structure of an Electronic Medical Record 3 TreeNet™ Modeling with our Dataset 4 Lessons Learned and Next Step(s)
  • 5. Data Modeling Paradigm © Salford Systems, 2011
  • 6. Model Accuracy Completeness of Set Feature Selection Feature Fit Target Class Kattan MW, EuroUro. 2011; (59): 566-567
  • 7. Model Error: The Bias – Variance Decomposition Prediction Error = Irreducible Error + Bias² + Variance Hastie T, Tibshirani R, Friedman JH. The elements of statistical learning : Data mining, inference, and prediction. New York, NY: Springer; 2009.
  • 8. Model caveats Association does not prove causality Models are retrospective (observational) and therefore hypothesis generating (i.e. not hypothesis proving)
  • 10. Congestive Heart Failure  Common cause for admission.  Readmission in excess of 23%. Bueno, H. et al. JAMA 2010;303:2141-2147  Risk factors for readmission extensively studied.  Published reviews cite over 120 studies. - Methods: Logistic regression; Cox proportional hazard - C-statistic in 0.6-0.7 range  Reduction of readmission has been declared a national goal.  Improved risk models have the potential to more effectively deploy targeted disease management.
  • 11. EMR data structure  Data collected for clinical workflow.  Large volume - Multiple observations; repeated measures - Many interactions and interdependencies  Complex dataset - Continuous, Ordinal, Nominal (low and high order), Binary - ‘High-order variable-dimension nominal variables’  Missing data: - May represent error or practice patterns  Unbalanced classes  Outliers and Entry errors
  • 12. Preliminary Dataset - 1612 consecutive heart failure discharges abstracted - 1280 candidate predictors screened - Target class: Readmission at 30 days ( binary ) Administrative candidate predictors Clinical candidate predictors •Admission source, status, service •Specialty medical services consulted •Age, gender, race •Specialty ancillary services consulted •Primary/secondary payers •Blood laboratory values •Primary/secondary diagnoses (names •Medications name / therapeutic class and condition categories) •Dosages of medications •Total length of stay, ICU length of stay •Patient weights during hospitalization •Hospital costs and charges •Transfusions during hospitalization •Discharge status and disposition •Nursing assessments •All-cause same-center admission in •Education topics preceding year •Diagnostic tests ordered •Ordersets utilized Preliminary Unpublished Data
  • 13. Benefits of Stochastic Gradient Boosting Friedman JH. Stochastic gradient boosting. Computational Statistics and Data Analysis 2002; 38(4):367- 378. Input and processing Output  Does not require data  High model accuracy transformation  Classification and regression  Handles large numbers of  Non-parametric application of categorical and continuous logistic , L1, L2, or Huber-M variables loss function  Has mechanisms for: - Feature selection - Managing missing values - Assessing the relationship of predictors to target  Robust to: - Data entry errors, Outliers, Target misclassification
  • 14. TreeNet™ Modeling with our Dataset 1 Parameters of ‘feature fit’ 2 Parameters of ‘feature selection’ 3 Elements of insight 4 Putting it all together
  • 15. TreeNet – parameters of ‘feature fit’ Do not forget the manual …..
  • 16. Feature selection – variable importance Variable Importance Calculation  Squared relative improvement is the sum of squared improvements (in squared error risk) over all internal nodes for which the variable was chosen as the splitting variable  Measurements are relative and is customary to express largest at 100 and scale other variables appropriately
  • 17. Insight into the model Illuminating the ‘black box’ with partial dependence Preliminary Unpublished Data
  • 18. Approach to feature selection Domain ‘Neutral’ vs. Domain ‘Centric’ Domain Neutral Both Domain Centric  Start with a subset  Know your data  Use all potential based on univariate  Univariate stats predictors significance (i.e. P-  Use knowledge of value below a given  Application of Variable Importance target and predictors to level) or variance make decisions on above a given  Screening with inclusion (or rejection) threshold batteries of predictor  Forward and backward stepwise progression
  • 19. Model Variability Establishing AUC precision and accuracy Variation Accuracy / Precision  The model is fit via sampling (i.e.  S.E.M.= S.D. / sqrt ( N ) stochastic) process.  Precision (95%) ≈ 4 * S.E.M.  S.D. = 0.03 N trials 10 30 300 S.E.M. .0095 .0055 .0017 Precision (95%) .038 .022 .007
  • 20. Precision and predictor selection STEP_1 (197) (0.531) STEP_66 (737) (0.703) 0.75 Min = 0.5057 Median = 0.6738 0.70 Mean = 0.6500 Max = 0.7034 Avg. ROC 0.65 Test ROC 0.60 0.55 0.50  AUC estimated using CV-10 ( = 10 trees)  SEM .0095 and precision (95%) of .038  Repeating CV-10 (using CVR battery) 30 times  SEM .0017 and precision (95%) of .007  Profound implication on dimensionality of model achievable without domain knowledge input.
  • 21. How much of a change in AUC is clinically relevant ? Gain Curve complements ROC curve Preliminary Unpublished Data
  • 22. Useful batteries for feature selection Methods of forward and backward selection STEPWISE  Testing set to CV-10  Select predictor 1-2 at a time  Confirm with CVR battery SHAVING
  • 23. BUILDING A MODEL **Each change confirmed with CVR (30 reps). Review partial This is a multi-step process dependence plot. Run model with all candidate Use backward and forward Re-examine discarded predictors. Select N highest selection to reduce predictors in smaller important predictors. preliminary model to a core groups. Use backward N= 2-3 x final size 5 -15 predictors.** and forward selection.** Step 1 Step 2 Step 3 Step 4 Step 5 Run batteries to assess Review predictors and use domain parameters of feature ‘fit’. knowledge to eliminate redundant Assess model (AUC) (dependent) predictors and consider variability. Repeat as predictors of known value. ** needed through process.
  • 24. Initial runs Information content and irreducible error #287 (0.519) #287 (0.519) (0.436) 0.576 0.6 Cross Entropy 0.576 0.5 0.4 0.3 Train 0.2 0.1 Test 6 Nodes 0.0 0 100 200 300 400 500 600 700 800 900 1000 1100 1200 1300 1400 1500 Number of Trees #880 (0.518) #880 (0.518) (0.457) 0.576 0.6 Cross Entropy 0.577 0.5 0.4 0.3 Train 0.2 0.1 Test 2 Nodes 0.0 0 100 200 300 400 500 600 700 800 900 1000 1100 1200 1300 1400 1500 Number of Trees Preliminary Unpublished Data
  • 25. Sample Model GAIN CURVE ROC CURVE FEATURE SELECTION SET MODEL TRAINING SET Preliminary Unpublished Data
  • 26. Sample partial dependence plots The value of non-parametric regression Admissions within prior year ICU Days Anion Gap Initial Systolic BP Final BNP BUN-Creatinine Ratio Preliminary Unpublished Data
  • 27. Prospective application Additional heart failure discharges can be scored against the model GAIN curve ROC curve Preliminary Unpublished Causes for performance shift Data  Overfitting in the original model  Concomitant intervention programs are altering patient risk of readmission
  • 28. Non-influential candidate predictors Models favor continuous over binary ‘dummy’ variables Diagnoses and QualNet Condition Categories Medications and Therapeutic Categories Diagnostic Tests Ordersets Submitted Preliminary Unpublished Data
  • 29. Lessons learned  TreeNet ( stochastic gradient boosting) is extremely well suited to data structure of EMR data.  Insight in to dataset is a rich feature (in and above prediction performance).  Model performance variance is important in feature selection. - Consequence of limited information content in our dataset.  Batteries are useful. - PARTITION – Variability assessment - CVR – Model assessment - STEPWISE – Forward selection - SHAVING – Backward selection  There is great value in learning on a non-trivial dataset within a familiar domain.
  • 30. Next steps …… Explore options to manage model variability and increase dimensionality of predictor set. Extend analysis of predictor interactions. Develop mechanism of ‘point-of-care’ patient scoring. Apply techniques to new problems and dataset.

Notas do Editor

  1. Stochastic Gradient Boosting is the algorithm that underlies the TreeNet application. Discussing this at a Salford conference is like bringing coal to Newcastle – won’t embarrass myself –Extorts several characteristics that are attractive for EMR ( and most any) datasets