SlideShare a Scribd company logo
1 of 19
Early Hospital Mortality Prediction using
Vital Signals
By
Reza Sadeghi
http://knoesis.org/Reza
Advisor
Dr. Banerjee
Mar 2018
2
Outline
β€’ The importance of early mortality prediction
β€’ Challenges in early mortality prediction in ICU patients
β€’ Previous work pros and cons
β€’ The proposed methods
β€’ Experiments
β€’ Conclusion
β€’ The more accurate and quick decision provides the more benefit for patients
and health care resources
1. ICU departments consume 22% of total hospital costs in the United States [1]
2. Increasing ICU length of stay is associated with higher 1-year mortality [2]
[1] Tan, S. S., Bakker, J., Hoogendoorn, M. E., Kapila, A., Martin, J., Pezzi, A., ... & Hakkaart-van Roijen, L. (2012). Direct cost analysis of intensive care
unit stay in four European countries: applying a standardized costing methodology. Value in health, 15(1), 81-86.
[2] Moitra, V. K., Guerra, C., Linde-Zwirble, W. T., & Wunsch, H. (2016). Relationship between ICU length of stay and long-term mortality for elderly ICU
survivors. Critical care medicine, 44(4), 655.
3
Why early mortality prediction is important?
β€’ The ICU patient is highly monitored using electronic equipment
β€’ A decision support systems for intensivists
β€’ The higher quality and lower cost of treatment
4
How we can contribute to this field?
Challenges in early mortality prediction
in ICU patients
β€’ Big data
2.4 TB The MIMIC-III Waveform Database Matched Subset
β€’ Real time application
β€’ Costly fault
β€’ Distributed systems
β€’ Missing data
β€’ Comorbidity
β€’ Parallel processing
5
Hot topic
6
Previous work pros and cons
Customized models
Score based models
Data mining models
- perform better than traditional scores [1]
- patients may suffering from heterogeneous diseases then selecting the
proper model is hard job
- rely on panels of experts or statistical models
- refined for use within specified geographical areas
- extracting features from Electronic Medical Records
- only few models are designed for early mortality
- low discrimination power
- many of them required attributes which are not always available at ICU
admission
- higher performance rather than the previous methods
- descriptive modelling as it explains hidden clinical implications
- the results of different algorithm on different data set are not constant.
- it depends on the population of interest, the variables measured and the
outcome being tested
Missing Data Type:
1. missing completely at random (MCAR)
2. missing at random (MAR)
3. Missing not at random (MNAR) [2]
Missing Data Handling:
1. interpretation
2. ignoring those records from the dataset that
are not complete
3. substitute the missing value by the mean or
mode value of each attribute.
("ReplaceMissing-Valuesβ€œ filter in weka)
4. predicted by using a learning algorithm, such
as Multiple Imputation or EMImputation [3]
Imbalance data Handling:
1. re-sampling : under sampling and
oversampling.
2. making the classifier 'cost sensitive'
3. hybrid method
4. One class classifiers
Data mining models issues
Interpretability:
1. Deep learning
2. Ensemble methods
Our main contributions
β€’ A signal-based model for early mortality prediction
β€’ A clinical decision support system which focuses on using only the
initial one hour of heart rate signal
β€’ Faster feedback to healthcare professionals
β€’ No dependency on many clinical records which contain missing values
β€’ A real time system due to not associated with laboratory test results
needed to be processed
9
MIMIC-III
10
The age distribution over the Whole MIMIC-III and the
Matched Subset
β€’ MIMIC-III database comprising the records of 46520 patients
β€’ The Matched Subset contains records of 10282 patients
β€’ 2.4 TB The MIMIC-III Waveform Database Matched Subset
Causality
11
diseases of the
circulatory system
β€’ High heart rate has been shown to be an independent risk factor for all-cause
and cardiovascular death in general population studies [1]
β€’ Epidemiological studies have reported increased risk of cardiovascular disease,
cancer and all-cause mortality with greater resting heart rate [2]
[1]https://www.medicographia.com/2010/07/recommendations-on-how-to-measure-resting-heart-rate/
[2] Aune, D., Sen, A., Γ³'Hartaigh, B., Janszky, I., Romundstad, P. R., Tonstad, S., & Vatten, L. J. (2017). Resting heart rate and
the risk of cardiovascular disease, total cancer, and all-cause mortality–A systematic review and dose–response meta-analysis of
prospective studies. Nutrition, Metabolism and Cardiovascular Diseases, 27(6), 504-517
Signal processing
12
β€’ Handling noise due to different recording systems
β€’ Moving average filtering
𝑆′ 𝑑 =
1
𝑇
𝑑=1
𝑇
𝑆 𝑑 𝜌 β‰₯ 𝑇 β‰₯ 1
1
𝜌
𝑑=𝑇
π‘‡βˆ’πœŒ+1
𝑆 𝑑 𝐿 βˆ’ 𝜌 β‰₯ 𝑇 β‰₯ 𝜌
1
𝑇
𝑑=πΏβˆ’πœŒ+1
𝐿
𝑆 𝑑 𝐿 βˆ’ 𝜌 + 1 β‰₯ 𝑇 β‰₯ 𝐿
β€’ Resampling using the anti-aliasing finite impulse response low-pass filter
Feature extraction
Each signal is described in terms of 12 statistical
and signal-based features
- The averaged power of a finite discrete-time
signal is defined as the mean of the signal’s energy
𝑃 =
𝐸
𝑛2 βˆ’ 𝑛1 + 1
=
1
𝑛2 βˆ’ 𝑛1 + 1
𝑛1
𝑛2
𝑆[𝑛]2
- The signal power is computed by taking the
integral of the power spectral density (PSD)
𝑃 =
βˆ†π‘‡
𝑁
𝑛=0
π‘βˆ’1
𝑆[𝑛]π‘’βˆ’π‘–2πœ‹πœŒ
13
Column Feature
Passed away
patients
Alive
patients
1 Maximum 97.82 90.92
2 Minimum 80.69 76.24
3 Mean 88.46 81.92
4 Median 88.45 81.81
5 Mode 85.25 79.98
6 Standard deviation 2.63 2.25
7 Variance 15.84 11.56
8 Range 17.13 14.68
9 Kurtosis 17.48 17.85
10 Skewness 0.83 1.02
11 Averaged power 8186.02 7045.04
12 Energy spectral density 5114.78 4420.38
Unbiased and efficient modeling
β€’ Avoid biasing toward minority class (Imbalance data challenging)
Using adaptive semi-unsupervised weighted oversampling (A-SUWO)
β€’ Robust against time dependency of samples
Design experiments based on 10-fold cross-validation strategy
β€’ Handling high computational complexity of big data
Leveraging parallel programming
β€’ Efficiency vs. Transparency
Comparing both black-box and interpretable classifiers
14
Classification
15
Classifier Precision Recall F1-score Interpretability
Random forest 0.97 0.97 0.97 Hard
Gaussian SVM 0.95 0.96 0.96 Hard
Decision tree 0.90 0.92 0.91 Easy
Boosted trees 0.91 0.83 0.87 Hard
K-NN 0.80 0.85 0.82 Hard
Logistic regression 0.77 0.67 0.72 Easy
Linear
Discriminant
0.78 0.66 0.71 Easy
Linear SVM 0.80 0.63 0.70 Easy
Transparency and Feature importance
16
β€’ Special thank to Dr. Banerjee
Accessing MIMIC-III, processing and storing this big data, consultant
with physicians, weekly meeting and guidance
The paper has been sent to the CHASE 2018
The paper and this slides are accessible via following links
https://arxiv.org/abs/1803.06589
https://www.slideshare.net/RezaSadeghi4
The code will be published in my GitHub soon
https://github.com/RezaSadeghiWSU
17
Thank you for your attention!
Extra
β€’ Gini index
𝐺𝐷𝐼 = 1 βˆ’
𝑖
(𝑝 𝑖 )2
β€’ The risk of splitting
π‘…π‘–π‘ π‘˜ π‘₯ = 𝐺𝐷𝐼 π‘₯ . π‘ƒπ‘Ÿπ‘œπ‘π‘Žπ‘π‘–π‘™π‘–π‘‘π‘¦(π‘₯)
β€’ The node probability is defined as the number of records reaching the node,
divided by the total number of records.
β€’ We utilize a resampling method called adaptive semi-unsupervised
weighted oversampling (A-SUWO)
19

More Related Content

What's hot

Clinical data analytics
Clinical data analyticsClinical data analytics
Clinical data analyticsSB BHATTACHARYYA
Β 
Biostatistics worksheet exercises
Biostatistics worksheet exercisesBiostatistics worksheet exercises
Biostatistics worksheet exercisesDina Ghoraba
Β 
Diagnosis of rheumatoid arthritis using an ensemble learning approach
Diagnosis of rheumatoid arthritis using an ensemble learning approachDiagnosis of rheumatoid arthritis using an ensemble learning approach
Diagnosis of rheumatoid arthritis using an ensemble learning approachcsandit
Β 
Disease prediction and doctor recommendation system
Disease prediction and doctor recommendation systemDisease prediction and doctor recommendation system
Disease prediction and doctor recommendation systemsabafarheen
Β 
K-Nearest Neighbours based diagnosis of hyperglycemia
K-Nearest Neighbours based diagnosis of hyperglycemiaK-Nearest Neighbours based diagnosis of hyperglycemia
K-Nearest Neighbours based diagnosis of hyperglycemiaijtsrd
Β 
Estimating the Statistical Significance of Classifiers used in the Predictio...
Estimating the Statistical Significance of Classifiers used in the  Predictio...Estimating the Statistical Significance of Classifiers used in the  Predictio...
Estimating the Statistical Significance of Classifiers used in the Predictio...IOSR Journals
Β 
Biostatistics
BiostatisticsBiostatistics
BiostatisticsDina Ghoraba
Β 
The role of statistics in Medicine
The role of statistics in MedicineThe role of statistics in Medicine
The role of statistics in Medicineyinka ADENIRAN
Β 
Diabetes Prediction by Supervised and Unsupervised Approaches with Feature Se...
Diabetes Prediction by Supervised and Unsupervised Approaches with Feature Se...Diabetes Prediction by Supervised and Unsupervised Approaches with Feature Se...
Diabetes Prediction by Supervised and Unsupervised Approaches with Feature Se...IJARIIT
Β 
An Experimental Study of Diabetes Disease Prediction System Using Classificat...
An Experimental Study of Diabetes Disease Prediction System Using Classificat...An Experimental Study of Diabetes Disease Prediction System Using Classificat...
An Experimental Study of Diabetes Disease Prediction System Using Classificat...IOSRjournaljce
Β 
COMPARISON AND EVALUATION DATA MINING TECHNIQUES IN THE DIAGNOSIS OF HEART DI...
COMPARISON AND EVALUATION DATA MINING TECHNIQUES IN THE DIAGNOSIS OF HEART DI...COMPARISON AND EVALUATION DATA MINING TECHNIQUES IN THE DIAGNOSIS OF HEART DI...
COMPARISON AND EVALUATION DATA MINING TECHNIQUES IN THE DIAGNOSIS OF HEART DI...ijcsa
Β 
Project on disease prediction
Project on disease predictionProject on disease prediction
Project on disease predictionKOYELMAJUMDAR1
Β 
A NOVEL PROBABILISTIC ARTIFICIAL NEURAL NETWORKS APPROACH FOR DIAGNOSING HEAR...
A NOVEL PROBABILISTIC ARTIFICIAL NEURAL NETWORKS APPROACH FOR DIAGNOSING HEAR...A NOVEL PROBABILISTIC ARTIFICIAL NEURAL NETWORKS APPROACH FOR DIAGNOSING HEAR...
A NOVEL PROBABILISTIC ARTIFICIAL NEURAL NETWORKS APPROACH FOR DIAGNOSING HEAR...ijfcstjournal
Β 
Machine learning and operations research to find diabetics at risk for readmi...
Machine learning and operations research to find diabetics at risk for readmi...Machine learning and operations research to find diabetics at risk for readmi...
Machine learning and operations research to find diabetics at risk for readmi...John Frias Morales, DrBA, MS
Β 
A Hybrid Apporach of Classification Techniques for Predicting Diabetes using ...
A Hybrid Apporach of Classification Techniques for Predicting Diabetes using ...A Hybrid Apporach of Classification Techniques for Predicting Diabetes using ...
A Hybrid Apporach of Classification Techniques for Predicting Diabetes using ...ijtsrd
Β 
Evaluating the Quality of Trauma Care A Literature Review
Evaluating the Quality of Trauma Care A Literature ReviewEvaluating the Quality of Trauma Care A Literature Review
Evaluating the Quality of Trauma Care A Literature ReviewKaylie Butt
Β 
Big Data Analytics for Healthcare
Big Data Analytics for HealthcareBig Data Analytics for Healthcare
Big Data Analytics for HealthcareChandan Reddy
Β 
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
Β 
Machine learning in disease diagnosis
Machine learning in disease diagnosisMachine learning in disease diagnosis
Machine learning in disease diagnosisSushrutaMishra1
Β 

What's hot (20)

Clinical data analytics
Clinical data analyticsClinical data analytics
Clinical data analytics
Β 
Biostatistics worksheet exercises
Biostatistics worksheet exercisesBiostatistics worksheet exercises
Biostatistics worksheet exercises
Β 
Diagnosis of rheumatoid arthritis using an ensemble learning approach
Diagnosis of rheumatoid arthritis using an ensemble learning approachDiagnosis of rheumatoid arthritis using an ensemble learning approach
Diagnosis of rheumatoid arthritis using an ensemble learning approach
Β 
Disease prediction and doctor recommendation system
Disease prediction and doctor recommendation systemDisease prediction and doctor recommendation system
Disease prediction and doctor recommendation system
Β 
K-Nearest Neighbours based diagnosis of hyperglycemia
K-Nearest Neighbours based diagnosis of hyperglycemiaK-Nearest Neighbours based diagnosis of hyperglycemia
K-Nearest Neighbours based diagnosis of hyperglycemia
Β 
Estimating the Statistical Significance of Classifiers used in the Predictio...
Estimating the Statistical Significance of Classifiers used in the  Predictio...Estimating the Statistical Significance of Classifiers used in the  Predictio...
Estimating the Statistical Significance of Classifiers used in the Predictio...
Β 
Biostatistics
BiostatisticsBiostatistics
Biostatistics
Β 
Introduction of Biostatistics
Introduction of BiostatisticsIntroduction of Biostatistics
Introduction of Biostatistics
Β 
The role of statistics in Medicine
The role of statistics in MedicineThe role of statistics in Medicine
The role of statistics in Medicine
Β 
Diabetes Prediction by Supervised and Unsupervised Approaches with Feature Se...
Diabetes Prediction by Supervised and Unsupervised Approaches with Feature Se...Diabetes Prediction by Supervised and Unsupervised Approaches with Feature Se...
Diabetes Prediction by Supervised and Unsupervised Approaches with Feature Se...
Β 
An Experimental Study of Diabetes Disease Prediction System Using Classificat...
An Experimental Study of Diabetes Disease Prediction System Using Classificat...An Experimental Study of Diabetes Disease Prediction System Using Classificat...
An Experimental Study of Diabetes Disease Prediction System Using Classificat...
Β 
COMPARISON AND EVALUATION DATA MINING TECHNIQUES IN THE DIAGNOSIS OF HEART DI...
COMPARISON AND EVALUATION DATA MINING TECHNIQUES IN THE DIAGNOSIS OF HEART DI...COMPARISON AND EVALUATION DATA MINING TECHNIQUES IN THE DIAGNOSIS OF HEART DI...
COMPARISON AND EVALUATION DATA MINING TECHNIQUES IN THE DIAGNOSIS OF HEART DI...
Β 
Project on disease prediction
Project on disease predictionProject on disease prediction
Project on disease prediction
Β 
A NOVEL PROBABILISTIC ARTIFICIAL NEURAL NETWORKS APPROACH FOR DIAGNOSING HEAR...
A NOVEL PROBABILISTIC ARTIFICIAL NEURAL NETWORKS APPROACH FOR DIAGNOSING HEAR...A NOVEL PROBABILISTIC ARTIFICIAL NEURAL NETWORKS APPROACH FOR DIAGNOSING HEAR...
A NOVEL PROBABILISTIC ARTIFICIAL NEURAL NETWORKS APPROACH FOR DIAGNOSING HEAR...
Β 
Machine learning and operations research to find diabetics at risk for readmi...
Machine learning and operations research to find diabetics at risk for readmi...Machine learning and operations research to find diabetics at risk for readmi...
Machine learning and operations research to find diabetics at risk for readmi...
Β 
A Hybrid Apporach of Classification Techniques for Predicting Diabetes using ...
A Hybrid Apporach of Classification Techniques for Predicting Diabetes using ...A Hybrid Apporach of Classification Techniques for Predicting Diabetes using ...
A Hybrid Apporach of Classification Techniques for Predicting Diabetes using ...
Β 
Evaluating the Quality of Trauma Care A Literature Review
Evaluating the Quality of Trauma Care A Literature ReviewEvaluating the Quality of Trauma Care A Literature Review
Evaluating the Quality of Trauma Care A Literature Review
Β 
Big Data Analytics for Healthcare
Big Data Analytics for HealthcareBig Data Analytics for Healthcare
Big Data Analytics for Healthcare
Β 
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.
Β 
Machine learning in disease diagnosis
Machine learning in disease diagnosisMachine learning in disease diagnosis
Machine learning in disease diagnosis
Β 

Similar to Early Hospital Mortality Prediction using Vital Signals

Early hospital mortality prediction of intensive care unit patients using an ...
Early hospital mortality prediction of intensive care unit patients using an ...Early hospital mortality prediction of intensive care unit patients using an ...
Early hospital mortality prediction of intensive care unit patients using an ...Reza Sadeghi
Β 
Jessica Rudd, PhD Student, Analytics and Data Science, Kennesaw State Univers...
Jessica Rudd, PhD Student, Analytics and Data Science, Kennesaw State Univers...Jessica Rudd, PhD Student, Analytics and Data Science, Kennesaw State Univers...
Jessica Rudd, PhD Student, Analytics and Data Science, Kennesaw State Univers...MLconf
Β 
Cadth 2015 c2 tt eincea_cadth_042015
Cadth 2015 c2 tt eincea_cadth_042015Cadth 2015 c2 tt eincea_cadth_042015
Cadth 2015 c2 tt eincea_cadth_042015CADTH Symposium
Β 
Clinical Genomics and Medicine
Clinical Genomics and MedicineClinical Genomics and Medicine
Clinical Genomics and MedicineWarren Kibbe
Β 
Extrapolation of time-to-event data
Extrapolation of time-to-event dataExtrapolation of time-to-event data
Extrapolation of time-to-event dataSheily Kamra
Β 
A Data-centric perspective on Data-driven healthcare: a short overview
A Data-centric perspective on Data-driven healthcare: a short overviewA Data-centric perspective on Data-driven healthcare: a short overview
A Data-centric perspective on Data-driven healthcare: a short overviewPaolo Missier
Β 
The Effect of Multidisciplinary Rounds on Intensive Care Unit Mortality 6.3.09
The Effect of Multidisciplinary Rounds on Intensive Care Unit Mortality 6.3.09The Effect of Multidisciplinary Rounds on Intensive Care Unit Mortality 6.3.09
The Effect of Multidisciplinary Rounds on Intensive Care Unit Mortality 6.3.09Leonard Davis Institute of Health Economics
Β 
Evaluation of the clinical value of biomarkers for risk prediction
Evaluation of the clinical value of biomarkers for risk predictionEvaluation of the clinical value of biomarkers for risk prediction
Evaluation of the clinical value of biomarkers for risk predictionEwout Steyerberg
Β 
Metanalysis Lecture
Metanalysis LectureMetanalysis Lecture
Metanalysis Lecturedrmomusa
Β 
Common statistical pitfalls & errors in biomedical research (a top-5 list)
Common statistical pitfalls & errors in biomedical research (a top-5 list)Common statistical pitfalls & errors in biomedical research (a top-5 list)
Common statistical pitfalls & errors in biomedical research (a top-5 list)Evangelos Kritsotakis
Β 
Interpretable and robust hospital readmission predictions from Electronic Hea...
Interpretable and robust hospital readmission predictions from Electronic Hea...Interpretable and robust hospital readmission predictions from Electronic Hea...
Interpretable and robust hospital readmission predictions from Electronic Hea...Paolo Missier
Β 
DIAGNOSIS OF RHEUMATOID ARTHRITIS USING AN ENSEMBLE LEARNING APPROACH
DIAGNOSIS OF RHEUMATOID ARTHRITIS USING AN ENSEMBLE LEARNING APPROACH DIAGNOSIS OF RHEUMATOID ARTHRITIS USING AN ENSEMBLE LEARNING APPROACH
DIAGNOSIS OF RHEUMATOID ARTHRITIS USING AN ENSEMBLE LEARNING APPROACH cscpconf
Β 
ISCB 2023 Sources of uncertainty b.pptx
ISCB 2023 Sources of uncertainty b.pptxISCB 2023 Sources of uncertainty b.pptx
ISCB 2023 Sources of uncertainty b.pptxBenVanCalster
Β 
Clinical Prediction Rules
Clinical Prediction RulesClinical Prediction Rules
Clinical Prediction RulesJen-Hsiang Chuang
Β 
Lung Cancer Risk Prediction Models
Lung Cancer Risk Prediction ModelsLung Cancer Risk Prediction Models
Lung Cancer Risk Prediction ModelsThaoNgo60
Β 
D1 0950 big data in healthcare hongkong2016
D1 0950 big data in healthcare hongkong2016D1 0950 big data in healthcare hongkong2016
D1 0950 big data in healthcare hongkong2016Dr. Wilfred Lin (Ph.D.)
Β 
The methodology for handling missing data during development of predictive model
The methodology for handling missing data during development of predictive modelThe methodology for handling missing data during development of predictive model
The methodology for handling missing data during development of predictive modelpingxiaoou
Β 
The methodology for handling missing data during development of predictive model
The methodology for handling missing data during development of predictive modelThe methodology for handling missing data during development of predictive model
The methodology for handling missing data during development of predictive modelpingxiaoou
Β 

Similar to Early Hospital Mortality Prediction using Vital Signals (20)

Early hospital mortality prediction of intensive care unit patients using an ...
Early hospital mortality prediction of intensive care unit patients using an ...Early hospital mortality prediction of intensive care unit patients using an ...
Early hospital mortality prediction of intensive care unit patients using an ...
Β 
Jessica Rudd, PhD Student, Analytics and Data Science, Kennesaw State Univers...
Jessica Rudd, PhD Student, Analytics and Data Science, Kennesaw State Univers...Jessica Rudd, PhD Student, Analytics and Data Science, Kennesaw State Univers...
Jessica Rudd, PhD Student, Analytics and Data Science, Kennesaw State Univers...
Β 
Cadth 2015 c2 tt eincea_cadth_042015
Cadth 2015 c2 tt eincea_cadth_042015Cadth 2015 c2 tt eincea_cadth_042015
Cadth 2015 c2 tt eincea_cadth_042015
Β 
Clinical Genomics and Medicine
Clinical Genomics and MedicineClinical Genomics and Medicine
Clinical Genomics and Medicine
Β 
Extrapolation of time-to-event data
Extrapolation of time-to-event dataExtrapolation of time-to-event data
Extrapolation of time-to-event data
Β 
A Data-centric perspective on Data-driven healthcare: a short overview
A Data-centric perspective on Data-driven healthcare: a short overviewA Data-centric perspective on Data-driven healthcare: a short overview
A Data-centric perspective on Data-driven healthcare: a short overview
Β 
The Effect of Multidisciplinary Rounds on Intensive Care Unit Mortality 6.3.09
The Effect of Multidisciplinary Rounds on Intensive Care Unit Mortality 6.3.09The Effect of Multidisciplinary Rounds on Intensive Care Unit Mortality 6.3.09
The Effect of Multidisciplinary Rounds on Intensive Care Unit Mortality 6.3.09
Β 
Quantitative Synthesis I
Quantitative Synthesis IQuantitative Synthesis I
Quantitative Synthesis I
Β 
Evaluation of the clinical value of biomarkers for risk prediction
Evaluation of the clinical value of biomarkers for risk predictionEvaluation of the clinical value of biomarkers for risk prediction
Evaluation of the clinical value of biomarkers for risk prediction
Β 
Metanalysis Lecture
Metanalysis LectureMetanalysis Lecture
Metanalysis Lecture
Β 
Common statistical pitfalls & errors in biomedical research (a top-5 list)
Common statistical pitfalls & errors in biomedical research (a top-5 list)Common statistical pitfalls & errors in biomedical research (a top-5 list)
Common statistical pitfalls & errors in biomedical research (a top-5 list)
Β 
Interpretable and robust hospital readmission predictions from Electronic Hea...
Interpretable and robust hospital readmission predictions from Electronic Hea...Interpretable and robust hospital readmission predictions from Electronic Hea...
Interpretable and robust hospital readmission predictions from Electronic Hea...
Β 
Journal Club: 2015 August; START study
Journal Club: 2015 August; START studyJournal Club: 2015 August; START study
Journal Club: 2015 August; START study
Β 
DIAGNOSIS OF RHEUMATOID ARTHRITIS USING AN ENSEMBLE LEARNING APPROACH
DIAGNOSIS OF RHEUMATOID ARTHRITIS USING AN ENSEMBLE LEARNING APPROACH DIAGNOSIS OF RHEUMATOID ARTHRITIS USING AN ENSEMBLE LEARNING APPROACH
DIAGNOSIS OF RHEUMATOID ARTHRITIS USING AN ENSEMBLE LEARNING APPROACH
Β 
ISCB 2023 Sources of uncertainty b.pptx
ISCB 2023 Sources of uncertainty b.pptxISCB 2023 Sources of uncertainty b.pptx
ISCB 2023 Sources of uncertainty b.pptx
Β 
Clinical Prediction Rules
Clinical Prediction RulesClinical Prediction Rules
Clinical Prediction Rules
Β 
Lung Cancer Risk Prediction Models
Lung Cancer Risk Prediction ModelsLung Cancer Risk Prediction Models
Lung Cancer Risk Prediction Models
Β 
D1 0950 big data in healthcare hongkong2016
D1 0950 big data in healthcare hongkong2016D1 0950 big data in healthcare hongkong2016
D1 0950 big data in healthcare hongkong2016
Β 
The methodology for handling missing data during development of predictive model
The methodology for handling missing data during development of predictive modelThe methodology for handling missing data during development of predictive model
The methodology for handling missing data during development of predictive model
Β 
The methodology for handling missing data during development of predictive model
The methodology for handling missing data during development of predictive modelThe methodology for handling missing data during development of predictive model
The methodology for handling missing data during development of predictive model
Β 

More from Reza Sadeghi

Predicting Subjective Sleep Quality Using Objective Measurements in Older Adults
Predicting Subjective Sleep Quality Using Objective Measurements in Older AdultsPredicting Subjective Sleep Quality Using Objective Measurements in Older Adults
Predicting Subjective Sleep Quality Using Objective Measurements in Older AdultsReza Sadeghi
Β 
Sleep quality prediction in caregivers using physiological signals
Sleep quality prediction in caregivers using physiological signalsSleep quality prediction in caregivers using physiological signals
Sleep quality prediction in caregivers using physiological signalsReza Sadeghi
Β 
A review on Analyzing Multiple Medical Corpora Using Word Embedding
A review on Analyzing Multiple Medical Corpora Using Word EmbeddingA review on Analyzing Multiple Medical Corpora Using Word Embedding
A review on Analyzing Multiple Medical Corpora Using Word EmbeddingReza Sadeghi
Β 
A review on Exploiting experts’ knowledge for structure learning of bayesian ...
A review on Exploiting experts’ knowledge for structure learning of bayesian ...A review on Exploiting experts’ knowledge for structure learning of bayesian ...
A review on Exploiting experts’ knowledge for structure learning of bayesian ...Reza Sadeghi
Β 
Signal processing of heart signals
Signal processing of heart signalsSignal processing of heart signals
Signal processing of heart signalsReza Sadeghi
Β 
Strengthening support vector classifiers based on fuzzy logic and evolutionar...
Strengthening support vector classifiers based on fuzzy logic and evolutionar...Strengthening support vector classifiers based on fuzzy logic and evolutionar...
Strengthening support vector classifiers based on fuzzy logic and evolutionar...Reza Sadeghi
Β 
Strengthening support vector classifiers based on fuzzy logic and evolutionar...
Strengthening support vector classifiers based on fuzzy logic and evolutionar...Strengthening support vector classifiers based on fuzzy logic and evolutionar...
Strengthening support vector classifiers based on fuzzy logic and evolutionar...Reza Sadeghi
Β 
A review on typing on flat glass
A review on typing on flat glassA review on typing on flat glass
A review on typing on flat glassReza Sadeghi
Β 
ProtΓ©gΓ©
ProtΓ©gΓ©ProtΓ©gΓ©
ProtΓ©gΓ©Reza Sadeghi
Β 
Web navigation based on markov and anthology
Web navigation based on markov and anthologyWeb navigation based on markov and anthology
Web navigation based on markov and anthologyReza Sadeghi
Β 
Modeling, Simulation and Analysis of Fuzzy Systems in Mat lab
Modeling, Simulation and Analysis of Fuzzy Systems in Mat labModeling, Simulation and Analysis of Fuzzy Systems in Mat lab
Modeling, Simulation and Analysis of Fuzzy Systems in Mat labReza Sadeghi
Β 
Oracle log miner
Oracle log minerOracle log miner
Oracle log minerReza Sadeghi
Β 
Invitation for master thesis defence
Invitation for master thesis defenceInvitation for master thesis defence
Invitation for master thesis defenceReza Sadeghi
Β 
Secure routing for wireless NANs
Secure routing for wireless NANsSecure routing for wireless NANs
Secure routing for wireless NANsReza Sadeghi
Β 

More from Reza Sadeghi (14)

Predicting Subjective Sleep Quality Using Objective Measurements in Older Adults
Predicting Subjective Sleep Quality Using Objective Measurements in Older AdultsPredicting Subjective Sleep Quality Using Objective Measurements in Older Adults
Predicting Subjective Sleep Quality Using Objective Measurements in Older Adults
Β 
Sleep quality prediction in caregivers using physiological signals
Sleep quality prediction in caregivers using physiological signalsSleep quality prediction in caregivers using physiological signals
Sleep quality prediction in caregivers using physiological signals
Β 
A review on Analyzing Multiple Medical Corpora Using Word Embedding
A review on Analyzing Multiple Medical Corpora Using Word EmbeddingA review on Analyzing Multiple Medical Corpora Using Word Embedding
A review on Analyzing Multiple Medical Corpora Using Word Embedding
Β 
A review on Exploiting experts’ knowledge for structure learning of bayesian ...
A review on Exploiting experts’ knowledge for structure learning of bayesian ...A review on Exploiting experts’ knowledge for structure learning of bayesian ...
A review on Exploiting experts’ knowledge for structure learning of bayesian ...
Β 
Signal processing of heart signals
Signal processing of heart signalsSignal processing of heart signals
Signal processing of heart signals
Β 
Strengthening support vector classifiers based on fuzzy logic and evolutionar...
Strengthening support vector classifiers based on fuzzy logic and evolutionar...Strengthening support vector classifiers based on fuzzy logic and evolutionar...
Strengthening support vector classifiers based on fuzzy logic and evolutionar...
Β 
Strengthening support vector classifiers based on fuzzy logic and evolutionar...
Strengthening support vector classifiers based on fuzzy logic and evolutionar...Strengthening support vector classifiers based on fuzzy logic and evolutionar...
Strengthening support vector classifiers based on fuzzy logic and evolutionar...
Β 
A review on typing on flat glass
A review on typing on flat glassA review on typing on flat glass
A review on typing on flat glass
Β 
ProtΓ©gΓ©
ProtΓ©gΓ©ProtΓ©gΓ©
ProtΓ©gΓ©
Β 
Web navigation based on markov and anthology
Web navigation based on markov and anthologyWeb navigation based on markov and anthology
Web navigation based on markov and anthology
Β 
Modeling, Simulation and Analysis of Fuzzy Systems in Mat lab
Modeling, Simulation and Analysis of Fuzzy Systems in Mat labModeling, Simulation and Analysis of Fuzzy Systems in Mat lab
Modeling, Simulation and Analysis of Fuzzy Systems in Mat lab
Β 
Oracle log miner
Oracle log minerOracle log miner
Oracle log miner
Β 
Invitation for master thesis defence
Invitation for master thesis defenceInvitation for master thesis defence
Invitation for master thesis defence
Β 
Secure routing for wireless NANs
Secure routing for wireless NANsSecure routing for wireless NANs
Secure routing for wireless NANs
Β 

Recently uploaded

Call Girls Kukatpally 7001305949 all area service COD available Any Time
Call Girls Kukatpally 7001305949 all area service COD available Any TimeCall Girls Kukatpally 7001305949 all area service COD available Any Time
Call Girls Kukatpally 7001305949 all area service COD available Any Timedelhimodelshub1
Β 
Russian Call Girls in Goa Samaira 7001305949 Independent Escort Service Goa
Russian Call Girls in Goa Samaira 7001305949 Independent Escort Service GoaRussian Call Girls in Goa Samaira 7001305949 Independent Escort Service Goa
Russian Call Girls in Goa Samaira 7001305949 Independent Escort Service Goanarwatsonia7
Β 
Call Girls Hyderabad Kirti 9907093804 Independent Escort Service Hyderabad
Call Girls Hyderabad Kirti 9907093804 Independent Escort Service HyderabadCall Girls Hyderabad Kirti 9907093804 Independent Escort Service Hyderabad
Call Girls Hyderabad Kirti 9907093804 Independent Escort Service Hyderabaddelhimodelshub1
Β 
Call Girls Dilsukhnagar 7001305949 all area service COD available Any Time
Call Girls Dilsukhnagar 7001305949 all area service COD available Any TimeCall Girls Dilsukhnagar 7001305949 all area service COD available Any Time
Call Girls Dilsukhnagar 7001305949 all area service COD available Any Timedelhimodelshub1
Β 
Call Girl Chandigarh Mallika β€οΈπŸ‘ 9907093804 πŸ‘„πŸ«¦ Independent Escort Service Cha...
Call Girl Chandigarh Mallika β€οΈπŸ‘ 9907093804 πŸ‘„πŸ«¦ Independent Escort Service Cha...Call Girl Chandigarh Mallika β€οΈπŸ‘ 9907093804 πŸ‘„πŸ«¦ Independent Escort Service Cha...
Call Girl Chandigarh Mallika β€οΈπŸ‘ 9907093804 πŸ‘„πŸ«¦ Independent Escort Service Cha...High Profile Call Girls Chandigarh Aarushi
Β 
Call Girls Gurgaon Parul 9711199012 Independent Escort Service Gurgaon
Call Girls Gurgaon Parul 9711199012 Independent Escort Service GurgaonCall Girls Gurgaon Parul 9711199012 Independent Escort Service Gurgaon
Call Girls Gurgaon Parul 9711199012 Independent Escort Service GurgaonCall Girls Service Gurgaon
Β 
hyderabad call girl.pdfRussian Call Girls in Hyderabad Amrita 9907093804 Inde...
hyderabad call girl.pdfRussian Call Girls in Hyderabad Amrita 9907093804 Inde...hyderabad call girl.pdfRussian Call Girls in Hyderabad Amrita 9907093804 Inde...
hyderabad call girl.pdfRussian Call Girls in Hyderabad Amrita 9907093804 Inde...delhimodelshub1
Β 
VIP Call Girls Hyderabad Megha 9907093804 Independent Escort Service Hyderabad
VIP Call Girls Hyderabad Megha 9907093804 Independent Escort Service HyderabadVIP Call Girls Hyderabad Megha 9907093804 Independent Escort Service Hyderabad
VIP Call Girls Hyderabad Megha 9907093804 Independent Escort Service Hyderabaddelhimodelshub1
Β 
College Call Girls Hyderabad Sakshi 9907093804 Independent Escort Service Hyd...
College Call Girls Hyderabad Sakshi 9907093804 Independent Escort Service Hyd...College Call Girls Hyderabad Sakshi 9907093804 Independent Escort Service Hyd...
College Call Girls Hyderabad Sakshi 9907093804 Independent Escort Service Hyd...delhimodelshub1
Β 
Russian Call Girls Hyderabad Saloni 9907093804 Independent Escort Service Hyd...
Russian Call Girls Hyderabad Saloni 9907093804 Independent Escort Service Hyd...Russian Call Girls Hyderabad Saloni 9907093804 Independent Escort Service Hyd...
Russian Call Girls Hyderabad Saloni 9907093804 Independent Escort Service Hyd...delhimodelshub1
Β 
Russian Escorts Aishbagh Road * 9548273370 Naughty Call Girls Service in Lucknow
Russian Escorts Aishbagh Road * 9548273370 Naughty Call Girls Service in LucknowRussian Escorts Aishbagh Road * 9548273370 Naughty Call Girls Service in Lucknow
Russian Escorts Aishbagh Road * 9548273370 Naughty Call Girls Service in Lucknowgragteena
Β 
Call Girls in Hyderabad Lavanya 9907093804 Independent Escort Service Hyderabad
Call Girls in Hyderabad Lavanya 9907093804 Independent Escort Service HyderabadCall Girls in Hyderabad Lavanya 9907093804 Independent Escort Service Hyderabad
Call Girls in Hyderabad Lavanya 9907093804 Independent Escort Service Hyderabaddelhimodelshub1
Β 
Call Girls Service Bommasandra - Call 7001305949 Rs-3500 with A/C Room Cash o...
Call Girls Service Bommasandra - Call 7001305949 Rs-3500 with A/C Room Cash o...Call Girls Service Bommasandra - Call 7001305949 Rs-3500 with A/C Room Cash o...
Call Girls Service Bommasandra - Call 7001305949 Rs-3500 with A/C Room Cash o...narwatsonia7
Β 
Call Girl Service ITPL - [ Cash on Delivery ] Contact 7001305949 Escorts Service
Call Girl Service ITPL - [ Cash on Delivery ] Contact 7001305949 Escorts ServiceCall Girl Service ITPL - [ Cash on Delivery ] Contact 7001305949 Escorts Service
Call Girl Service ITPL - [ Cash on Delivery ] Contact 7001305949 Escorts Servicenarwatsonia7
Β 
Gurgaon Sector 68 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few ...
Gurgaon Sector 68 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few ...Gurgaon Sector 68 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few ...
Gurgaon Sector 68 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few ...ggsonu500
Β 
Gurgaon Sector 90 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few ...
Gurgaon Sector 90 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few ...Gurgaon Sector 90 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few ...
Gurgaon Sector 90 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few ...ggsonu500
Β 
Russian Call Girls Hyderabad Indira 9907093804 Independent Escort Service Hyd...
Russian Call Girls Hyderabad Indira 9907093804 Independent Escort Service Hyd...Russian Call Girls Hyderabad Indira 9907093804 Independent Escort Service Hyd...
Russian Call Girls Hyderabad Indira 9907093804 Independent Escort Service Hyd...delhimodelshub1
Β 

Recently uploaded (20)

Call Girls Kukatpally 7001305949 all area service COD available Any Time
Call Girls Kukatpally 7001305949 all area service COD available Any TimeCall Girls Kukatpally 7001305949 all area service COD available Any Time
Call Girls Kukatpally 7001305949 all area service COD available Any Time
Β 
College Call Girls Dehradun Kavya πŸ” 7001305949 πŸ” πŸ“ Independent Escort Service...
College Call Girls Dehradun Kavya πŸ” 7001305949 πŸ” πŸ“ Independent Escort Service...College Call Girls Dehradun Kavya πŸ” 7001305949 πŸ” πŸ“ Independent Escort Service...
College Call Girls Dehradun Kavya πŸ” 7001305949 πŸ” πŸ“ Independent Escort Service...
Β 
Russian Call Girls in Goa Samaira 7001305949 Independent Escort Service Goa
Russian Call Girls in Goa Samaira 7001305949 Independent Escort Service GoaRussian Call Girls in Goa Samaira 7001305949 Independent Escort Service Goa
Russian Call Girls in Goa Samaira 7001305949 Independent Escort Service Goa
Β 
Call Girls Hyderabad Kirti 9907093804 Independent Escort Service Hyderabad
Call Girls Hyderabad Kirti 9907093804 Independent Escort Service HyderabadCall Girls Hyderabad Kirti 9907093804 Independent Escort Service Hyderabad
Call Girls Hyderabad Kirti 9907093804 Independent Escort Service Hyderabad
Β 
Call Girls Dilsukhnagar 7001305949 all area service COD available Any Time
Call Girls Dilsukhnagar 7001305949 all area service COD available Any TimeCall Girls Dilsukhnagar 7001305949 all area service COD available Any Time
Call Girls Dilsukhnagar 7001305949 all area service COD available Any Time
Β 
Call Girl Chandigarh Mallika β€οΈπŸ‘ 9907093804 πŸ‘„πŸ«¦ Independent Escort Service Cha...
Call Girl Chandigarh Mallika β€οΈπŸ‘ 9907093804 πŸ‘„πŸ«¦ Independent Escort Service Cha...Call Girl Chandigarh Mallika β€οΈπŸ‘ 9907093804 πŸ‘„πŸ«¦ Independent Escort Service Cha...
Call Girl Chandigarh Mallika β€οΈπŸ‘ 9907093804 πŸ‘„πŸ«¦ Independent Escort Service Cha...
Β 
Call Girls Gurgaon Parul 9711199012 Independent Escort Service Gurgaon
Call Girls Gurgaon Parul 9711199012 Independent Escort Service GurgaonCall Girls Gurgaon Parul 9711199012 Independent Escort Service Gurgaon
Call Girls Gurgaon Parul 9711199012 Independent Escort Service Gurgaon
Β 
hyderabad call girl.pdfRussian Call Girls in Hyderabad Amrita 9907093804 Inde...
hyderabad call girl.pdfRussian Call Girls in Hyderabad Amrita 9907093804 Inde...hyderabad call girl.pdfRussian Call Girls in Hyderabad Amrita 9907093804 Inde...
hyderabad call girl.pdfRussian Call Girls in Hyderabad Amrita 9907093804 Inde...
Β 
VIP Call Girls Hyderabad Megha 9907093804 Independent Escort Service Hyderabad
VIP Call Girls Hyderabad Megha 9907093804 Independent Escort Service HyderabadVIP Call Girls Hyderabad Megha 9907093804 Independent Escort Service Hyderabad
VIP Call Girls Hyderabad Megha 9907093804 Independent Escort Service Hyderabad
Β 
College Call Girls Hyderabad Sakshi 9907093804 Independent Escort Service Hyd...
College Call Girls Hyderabad Sakshi 9907093804 Independent Escort Service Hyd...College Call Girls Hyderabad Sakshi 9907093804 Independent Escort Service Hyd...
College Call Girls Hyderabad Sakshi 9907093804 Independent Escort Service Hyd...
Β 
Russian Call Girls Hyderabad Saloni 9907093804 Independent Escort Service Hyd...
Russian Call Girls Hyderabad Saloni 9907093804 Independent Escort Service Hyd...Russian Call Girls Hyderabad Saloni 9907093804 Independent Escort Service Hyd...
Russian Call Girls Hyderabad Saloni 9907093804 Independent Escort Service Hyd...
Β 
Russian Escorts Aishbagh Road * 9548273370 Naughty Call Girls Service in Lucknow
Russian Escorts Aishbagh Road * 9548273370 Naughty Call Girls Service in LucknowRussian Escorts Aishbagh Road * 9548273370 Naughty Call Girls Service in Lucknow
Russian Escorts Aishbagh Road * 9548273370 Naughty Call Girls Service in Lucknow
Β 
Call Girls in Hyderabad Lavanya 9907093804 Independent Escort Service Hyderabad
Call Girls in Hyderabad Lavanya 9907093804 Independent Escort Service HyderabadCall Girls in Hyderabad Lavanya 9907093804 Independent Escort Service Hyderabad
Call Girls in Hyderabad Lavanya 9907093804 Independent Escort Service Hyderabad
Β 
Call Girls Service Bommasandra - Call 7001305949 Rs-3500 with A/C Room Cash o...
Call Girls Service Bommasandra - Call 7001305949 Rs-3500 with A/C Room Cash o...Call Girls Service Bommasandra - Call 7001305949 Rs-3500 with A/C Room Cash o...
Call Girls Service Bommasandra - Call 7001305949 Rs-3500 with A/C Room Cash o...
Β 
Call Girl Dehradun Aashi πŸ” 7001305949 πŸ” πŸ’ƒ Independent Escort Service Dehradun
Call Girl Dehradun Aashi πŸ” 7001305949 πŸ” πŸ’ƒ Independent Escort Service DehradunCall Girl Dehradun Aashi πŸ” 7001305949 πŸ” πŸ’ƒ Independent Escort Service Dehradun
Call Girl Dehradun Aashi πŸ” 7001305949 πŸ” πŸ’ƒ Independent Escort Service Dehradun
Β 
Call Girl Service ITPL - [ Cash on Delivery ] Contact 7001305949 Escorts Service
Call Girl Service ITPL - [ Cash on Delivery ] Contact 7001305949 Escorts ServiceCall Girl Service ITPL - [ Cash on Delivery ] Contact 7001305949 Escorts Service
Call Girl Service ITPL - [ Cash on Delivery ] Contact 7001305949 Escorts Service
Β 
Gurgaon Sector 68 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few ...
Gurgaon Sector 68 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few ...Gurgaon Sector 68 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few ...
Gurgaon Sector 68 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few ...
Β 
Gurgaon Sector 90 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few ...
Gurgaon Sector 90 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few ...Gurgaon Sector 90 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few ...
Gurgaon Sector 90 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few ...
Β 
Russian Call Girls Hyderabad Indira 9907093804 Independent Escort Service Hyd...
Russian Call Girls Hyderabad Indira 9907093804 Independent Escort Service Hyd...Russian Call Girls Hyderabad Indira 9907093804 Independent Escort Service Hyd...
Russian Call Girls Hyderabad Indira 9907093804 Independent Escort Service Hyd...
Β 
VIP Call Girls Lucknow Isha πŸ” 9719455033 πŸ” 🎢 Independent Escort Service Lucknow
VIP Call Girls Lucknow Isha πŸ” 9719455033 πŸ” 🎢 Independent Escort Service LucknowVIP Call Girls Lucknow Isha πŸ” 9719455033 πŸ” 🎢 Independent Escort Service Lucknow
VIP Call Girls Lucknow Isha πŸ” 9719455033 πŸ” 🎢 Independent Escort Service Lucknow
Β 

Early Hospital Mortality Prediction using Vital Signals

  • 1. Early Hospital Mortality Prediction using Vital Signals By Reza Sadeghi http://knoesis.org/Reza Advisor Dr. Banerjee Mar 2018
  • 2. 2 Outline β€’ The importance of early mortality prediction β€’ Challenges in early mortality prediction in ICU patients β€’ Previous work pros and cons β€’ The proposed methods β€’ Experiments β€’ Conclusion
  • 3. β€’ The more accurate and quick decision provides the more benefit for patients and health care resources 1. ICU departments consume 22% of total hospital costs in the United States [1] 2. Increasing ICU length of stay is associated with higher 1-year mortality [2] [1] Tan, S. S., Bakker, J., Hoogendoorn, M. E., Kapila, A., Martin, J., Pezzi, A., ... & Hakkaart-van Roijen, L. (2012). Direct cost analysis of intensive care unit stay in four European countries: applying a standardized costing methodology. Value in health, 15(1), 81-86. [2] Moitra, V. K., Guerra, C., Linde-Zwirble, W. T., & Wunsch, H. (2016). Relationship between ICU length of stay and long-term mortality for elderly ICU survivors. Critical care medicine, 44(4), 655. 3 Why early mortality prediction is important?
  • 4. β€’ The ICU patient is highly monitored using electronic equipment β€’ A decision support systems for intensivists β€’ The higher quality and lower cost of treatment 4 How we can contribute to this field?
  • 5. Challenges in early mortality prediction in ICU patients β€’ Big data 2.4 TB The MIMIC-III Waveform Database Matched Subset β€’ Real time application β€’ Costly fault β€’ Distributed systems β€’ Missing data β€’ Comorbidity β€’ Parallel processing 5
  • 7. Previous work pros and cons Customized models Score based models Data mining models - perform better than traditional scores [1] - patients may suffering from heterogeneous diseases then selecting the proper model is hard job - rely on panels of experts or statistical models - refined for use within specified geographical areas - extracting features from Electronic Medical Records - only few models are designed for early mortality - low discrimination power - many of them required attributes which are not always available at ICU admission - higher performance rather than the previous methods - descriptive modelling as it explains hidden clinical implications - the results of different algorithm on different data set are not constant. - it depends on the population of interest, the variables measured and the outcome being tested
  • 8. Missing Data Type: 1. missing completely at random (MCAR) 2. missing at random (MAR) 3. Missing not at random (MNAR) [2] Missing Data Handling: 1. interpretation 2. ignoring those records from the dataset that are not complete 3. substitute the missing value by the mean or mode value of each attribute. ("ReplaceMissing-Valuesβ€œ filter in weka) 4. predicted by using a learning algorithm, such as Multiple Imputation or EMImputation [3] Imbalance data Handling: 1. re-sampling : under sampling and oversampling. 2. making the classifier 'cost sensitive' 3. hybrid method 4. One class classifiers Data mining models issues Interpretability: 1. Deep learning 2. Ensemble methods
  • 9. Our main contributions β€’ A signal-based model for early mortality prediction β€’ A clinical decision support system which focuses on using only the initial one hour of heart rate signal β€’ Faster feedback to healthcare professionals β€’ No dependency on many clinical records which contain missing values β€’ A real time system due to not associated with laboratory test results needed to be processed 9
  • 10. MIMIC-III 10 The age distribution over the Whole MIMIC-III and the Matched Subset β€’ MIMIC-III database comprising the records of 46520 patients β€’ The Matched Subset contains records of 10282 patients β€’ 2.4 TB The MIMIC-III Waveform Database Matched Subset
  • 11. Causality 11 diseases of the circulatory system β€’ High heart rate has been shown to be an independent risk factor for all-cause and cardiovascular death in general population studies [1] β€’ Epidemiological studies have reported increased risk of cardiovascular disease, cancer and all-cause mortality with greater resting heart rate [2] [1]https://www.medicographia.com/2010/07/recommendations-on-how-to-measure-resting-heart-rate/ [2] Aune, D., Sen, A., Γ³'Hartaigh, B., Janszky, I., Romundstad, P. R., Tonstad, S., & Vatten, L. J. (2017). Resting heart rate and the risk of cardiovascular disease, total cancer, and all-cause mortality–A systematic review and dose–response meta-analysis of prospective studies. Nutrition, Metabolism and Cardiovascular Diseases, 27(6), 504-517
  • 12. Signal processing 12 β€’ Handling noise due to different recording systems β€’ Moving average filtering 𝑆′ 𝑑 = 1 𝑇 𝑑=1 𝑇 𝑆 𝑑 𝜌 β‰₯ 𝑇 β‰₯ 1 1 𝜌 𝑑=𝑇 π‘‡βˆ’πœŒ+1 𝑆 𝑑 𝐿 βˆ’ 𝜌 β‰₯ 𝑇 β‰₯ 𝜌 1 𝑇 𝑑=πΏβˆ’πœŒ+1 𝐿 𝑆 𝑑 𝐿 βˆ’ 𝜌 + 1 β‰₯ 𝑇 β‰₯ 𝐿 β€’ Resampling using the anti-aliasing finite impulse response low-pass filter
  • 13. Feature extraction Each signal is described in terms of 12 statistical and signal-based features - The averaged power of a finite discrete-time signal is defined as the mean of the signal’s energy 𝑃 = 𝐸 𝑛2 βˆ’ 𝑛1 + 1 = 1 𝑛2 βˆ’ 𝑛1 + 1 𝑛1 𝑛2 𝑆[𝑛]2 - The signal power is computed by taking the integral of the power spectral density (PSD) 𝑃 = βˆ†π‘‡ 𝑁 𝑛=0 π‘βˆ’1 𝑆[𝑛]π‘’βˆ’π‘–2πœ‹πœŒ 13 Column Feature Passed away patients Alive patients 1 Maximum 97.82 90.92 2 Minimum 80.69 76.24 3 Mean 88.46 81.92 4 Median 88.45 81.81 5 Mode 85.25 79.98 6 Standard deviation 2.63 2.25 7 Variance 15.84 11.56 8 Range 17.13 14.68 9 Kurtosis 17.48 17.85 10 Skewness 0.83 1.02 11 Averaged power 8186.02 7045.04 12 Energy spectral density 5114.78 4420.38
  • 14. Unbiased and efficient modeling β€’ Avoid biasing toward minority class (Imbalance data challenging) Using adaptive semi-unsupervised weighted oversampling (A-SUWO) β€’ Robust against time dependency of samples Design experiments based on 10-fold cross-validation strategy β€’ Handling high computational complexity of big data Leveraging parallel programming β€’ Efficiency vs. Transparency Comparing both black-box and interpretable classifiers 14
  • 15. Classification 15 Classifier Precision Recall F1-score Interpretability Random forest 0.97 0.97 0.97 Hard Gaussian SVM 0.95 0.96 0.96 Hard Decision tree 0.90 0.92 0.91 Easy Boosted trees 0.91 0.83 0.87 Hard K-NN 0.80 0.85 0.82 Hard Logistic regression 0.77 0.67 0.72 Easy Linear Discriminant 0.78 0.66 0.71 Easy Linear SVM 0.80 0.63 0.70 Easy
  • 16. Transparency and Feature importance 16
  • 17. β€’ Special thank to Dr. Banerjee Accessing MIMIC-III, processing and storing this big data, consultant with physicians, weekly meeting and guidance The paper has been sent to the CHASE 2018 The paper and this slides are accessible via following links https://arxiv.org/abs/1803.06589 https://www.slideshare.net/RezaSadeghi4 The code will be published in my GitHub soon https://github.com/RezaSadeghiWSU 17
  • 18. Thank you for your attention!
  • 19. Extra β€’ Gini index 𝐺𝐷𝐼 = 1 βˆ’ 𝑖 (𝑝 𝑖 )2 β€’ The risk of splitting π‘…π‘–π‘ π‘˜ π‘₯ = 𝐺𝐷𝐼 π‘₯ . π‘ƒπ‘Ÿπ‘œπ‘π‘Žπ‘π‘–π‘™π‘–π‘‘π‘¦(π‘₯) β€’ The node probability is defined as the number of records reaching the node, divided by the total number of records. β€’ We utilize a resampling method called adaptive semi-unsupervised weighted oversampling (A-SUWO) 19

Editor's Notes

  1. The Photo originated from https://articles.mercola.com/sites/articles/archive/2010/03/13/hospitals-now-kill-48000-in-us-per-year-up-nearly-500-percent.aspx
  2. The Photo originated from https://www.rand.org/topics/health-care-cost-inflation.html
  3. The Photo originated from
  4. The Photo originated from https://www.statnews.com/2016/09/07/hospital-icu-modernize/
  5. The news titles accessible from internet: 1. Stanford's AI Predicts Death for Better End-of-Life Care https://spectrum.ieee.org/the-human-os/biomedical/diagnostics/stanfords-ai-predicts-death-for-better-end-of-life-care 2. NEW SOFTWARE MEASURES MORTALITY RISK AT ADMISSION https://ryortho.com/breaking/new-software-measures-mortality-risk-at-admission/ 3. TEAM DEVELOPS EARLY MORTALITY RISK PREDICTION TOOL FOR INTENSIVE CARE http://www.porthosp.nhs.uk/PHTNEWS/Team-develops-early-mortality-risk-prediction-tool-for-intensive-care.htm
  6. [1]-> [11]
  7. 1.interpretation: if an individual patients record has multiple entries missing, it may be explained that this is because they were regarded as being less sick than others, so they were not prioritized. Equally, the patient may have been regarded as being extremely sick, so they died before much can be done. Distinguishing these cases is not simple in the absence of other information. [2] -> [42] [3] -> [44] [4,5] -> [42, 45]
  8. The diseases of circulatory system formed the biggest category of primary issues in the patients admissions recorded in the whole MIMIC-III.
  9. The PSD is the Fourier transform of the biased estimate of the autocorrelation sequence.