Use of Artificial Intelligence in AAOCA

Use of Artificial Intelligence in
AAOCA
Jai Nahar, MD, MBA
Associate Professor of Pediatrics
The GeorgeWashington University School of
Medicine and Health Sciences
Division of Cardiology
Children’s National Medical Center
Washington, DC
Congenital Heart Surgeons Society
Fall work weekend
Nov. 2017,Toronto
Disclosures
• None
Agenda
1. AAOCA: Background, problem, questions to be addressed
2. Current Opportunity
3. Introduction to AI in medicine
4. PotentialApplication ofAI in AAOCA
5. Challenges
6. Future directions
AAOCA: Background
• Second leading cause of SCD in young athletes in USA
• Care of these patients involve three important challenges
1. Diagnosis: incidental diagnosis, lack of symptoms, initial presentation may
be SCD or sudden cardiac arrest
2. Risk Stratification: phenotypic heterogeneity
3. Ideal management
Risk
Stratification
Diagnosis
AAOCA
Ideal
Management
AAOCA:What causes the Critical Lethal event?
Critical Event :
Coronary ischemia
and lethal
Ventricular
Tachyarrhythmia
Decreased
coronary perfusion
due to Mechanical
factors, altered
blood flow
dynamics
Electrically unstable
myocardial
substrate
Unknown
Factors
?
• Acute angle take off and
Kinking of coronary artery at
its origin
• Flap like closure of abnormal
slit like coronary orifice
• Compression of anomalous
coronary artery between
Aorta and Pulmonary artery
during exercise
• Spasm of anomalous coronary
artery possibly secondary to
endothelial injury
Prior intermittent ischemia
Patchy Myocardial Fibrosis
• Local myocardial
metabolic factors
• Channelopathies
• Genetic
predisposition to
arrhythmia
Basso et al. (2000). Clinical profile of congenital coronary artery
anomalies with origin from the wrong aortic sinus leading to sudden
death in young competitive athletes. Journal of the American College of
Cardiology, 35(6), 1493-1501.
Problem
There are knowledge gaps/unknown variables which need to be filled/uncovered
to refine our risk stratification for AAOCA patients who are at highest risk of
sudden death
• Asymptomatic (hidden)
• Gray zone (symptoms of ? significance)
Task: Making the invisible, visible
AAOCA: Myocardial
ischemia, malignant
Ventricular
arrhythmia, sudden
death
Unknown/Invisible?
• Genetic make up
• Channelopathies
• Local myocardial/metabolic
factors
• Etc ??????
Questions
1. How can we uncover currently unknown phenotypes (cluster of variables with
non linear relation) which indicate high risk of sudden cardiac death?
2. How to develop good predictive models for risk stratification and prompt
detection of high risk AAOCA ?
Call for Action:Two step approach
Uncover unknown high risk
groups
Develop refined risk
stratification models
Deep
Phenotyping
Agenda
1. Define the problem, and questions to be addressed
2. Current Opportunity
3. Introduction to AI in medicine
4. Potential Application of AI to AAOCA
5. Challenges
6. Future directions
Current Opportunity : make the invisible, visible
• Data: CHSS AAOCA registry
• Artificial Intelligence Methods
Power of
Data
Leverage
AI
Refined risk
stratification
and patient
management
Dawn of New Era of
Augmented Intelligence
Physician and AI ( Human/Machine) synergy for facilitating better
• Diagnosis
• Disease management
• Clinical Decisions
Physicians Machines
Platform for
Precision Medicine
Agenda
1. Define the problem, and questions to be addressed
2. Current Opportunity
3. Introduction to AI in medicine
4. Potential Application of AI to AAOCA
5. Challenges
6. Future directions
Medical Intelligence: AI in Medicine
Big Data and Artificial Intelligence in Pediatric Cardiology
Anthony C. Chang, MD, MBA, MPH
Artificial Intelligence in Medicine
Machine Learning
Andrew Ng
“Is the Science of getting computers to learn, without being explicitly programmed”
Full spectrum application in CV medicine
Machine
Learning
Diagnosis/Risk
stratification
Treatment
Prevention
Research
Machine Learning types
1. Supervised
2. Unsupervised
3. Reinforcement
Supervised Learning
• Goal is to predict a known output orTarget
• Algorithm is taught with right answers (labels) for examples used in
training data set.
• Can be categorized as:
 Classification problem: predicting categories, discrete value output
(0,1 etc.)
 Regression problem: predict continuous values
 Anomaly detection problem: predict unusual pattern
Supervised Learning Applications
• Document classification
• Pattern recognition: Automated interpretation of
EKG
• Image Analysis in CV imaging
• Predicting Risk
Supervised Learning Algorithms
• Artificial Neural Network (ANN)
• SupportVector Machine
• DecisionTree
• Random Forests
• Naive Bayes classifier
• Fuzzy Logic
• K-Nearest Neighbor (KNN)
Unsupervised Learning
• Goal is to learn the intrinsic structure within data.
• No outputs to predict
• Task is to find hidden pattern/structure in data,
without human feedback
Cluster2
Cluster3
Cluster
1
Unsupervised Learning Application
Identify novel disease mechanisms, genotypes,
phenotypes: Filling the knowledge gaps
Identify Novel
Disease
Mechanisms
New
paths/approach
to therapy
Precision
Medicine
initiative
Unsupervised Learning Algorithms
• Clustering algorithms: K-Means, Hierarchical clustering
 Used to cluster unlabeled data into different groups
 Used when no obvious natural grouping
• Association rule- learning algorithm:
 Help to uncover relationships between seemingly unrelated data items
• PrincipalComponent Analysis
• Sparse Coding
Hierarchical Clustering
http://www.statisticshowto.com/hierarchi
cal-clustering/
Dendrogram
K-Means clustering Algorithms
(left) K-means in 2d. (right) K-means in 3d. You have
to imagine k-means in 4d.
http://stanford.edu/~cpiech/cs221/handouts/kmeans.html
Reinforcement learning
Reinforcement learning led to AlphaGo’s stunning victory over a human Go
champion
https://www.technologyreview.com/s/603501/10-breakthrough-technologies-2017-reinforcement-
learning/
Reinforcement learning is
learning by trial-and-error,
solely from rewards or
punishments.
https://deepmind.com/blog/deep-reinforcement-
learning/
Can be viewed as hybrid
of supervised and
unsupervised learning
Artificial Neural Network (ANN)
ANN are modeled after human neurons
• Nodes are like neurons
• Input layer: input data/ predictor variables/ features
• Hidden layer: processing of input
• Output layer:Target (prediction of class or value)
Lee, J.-G., Jun, S., Cho, Y.-W., Lee, H., Kim, G. B., Seo, J. B., & Kim, N. (2017). Deep Learning in Medical Imaging: General
Overview. Korean Journal of Radiology, 18(4), 570–584. http://doi.org/10.3348/kjr.2017.18.4.570
Deep Learning
• Part of Machine Learning
• Uses multiple layers of ANN
• Mimics the working of human brain
Lee, J.-G., Jun, S., Cho, Y.-W., Lee, H., Kim, G. B., Seo, J. B., & Kim, N. (2017). Deep Learning in Medical Imaging: General
Overview. Korean Journal of Radiology, 18(4), 570–584. http://doi.org/10.3348/kjr.2017.18.4.570
Deep Learning
Three types of Network:
1. Deep Neural Networks: Google’s Deep mind Alpha Go
2. Recurrent Neural Networks (RNN): natural language
processing, handwriting and speech recognition
3. Convolutional Neural Networks (CNN): Computer
vision, image recognition, CV imaging
Cognitive Computing
Systems mimicking human cognition, help
replicate human capabilities across the spectrum of sensory
perception, deduction, reasoning, learning and knowledge.
Upcoming inWorld of AI
• Quantum Computing: accelerate the data processing speed
• Neuromorphic chips
• Partnership with other technologies
 AI and AR
 AI and Robotics
Agenda
1. AAOCA: Background, problem, questions to be addressed
2. Current Opportunity
3. Introduction to AI in medicine
4. Potential Application of AI in AAOCA
5. Challenges
6. Future directions
First : A Machine Learning overview
Machine Learning in Medicine
Rahul C. Deo
Circulation. 2015;132:1920-1930, originally published November 16, 2015
https://doi.org/10.1161/CIRCULATIONAHA.115.001593
A: Matrix representation of the supervised
and unsupervised learning problem.
B: Decision trees map features to
outcome (Supervised Learning)
C: Neural networks predict outcome based
on transformed representations of
features. (Supervised Learning)
D:The k-nearest neighbor algorithm
assigns class based on the values of the
most similar training examples.
(Supervised Learning)
Phenomapping
Use of unsupervised machine learning in Phenotypic
classification of a heterogeneous clinical syndrome into discrete
phenogroups
PG1
PG2
PG3
PG4
PG5
Phenomapping
Phenotypic classification (Phenomapping)
A: Phenotype heat map of HFpEF.
B: BIC analysis for the identification of the
optimal number of phenotypic clusters
(pheno groups).
C: Kaplan–Meier curves
Survival free of cardiovascular (CV)
hospitalization or death stratified by
pheno groups.
Machine Learning in Medicine
Rahul C. Deo
Circulation. 2015;132:1920-1930
Stepwise approach for AAOCA
Detection of
High Risk
Cases
Develop
Supervised
model for
disease
prediction
Novel
phenogroup
selection using
Unsupervised
learning
Proposed Framework for AAOCA
Demographic
Data
Stress
lab/Nuclear
Medicine
Data
EP data
Surgical
data
Cath data
Imaging
data
Clinical
Data
Unsupervised learning based
Pheno-groups identification
Supervised Learning
based Model for
Risk stratification
High
Medium
Low
Expert
Knowledge
Challenges
• Deep learning:
 Problem of model overfitting
 Need for large data sets, multi Institutional collaboration
 Setting a neural network is time consuming
• Need for sharing of machine learning expertise
• Need for Novel informative features to build improved models
• Need for refined biomarkers to access myocardial status
Future Directions
Seamless data collaboration across institutions, and enhanced Computer- Human
synergy lead Augmented intelligence will refine the path of precisionCardiovascular
Medicine.
Precision
Medicine
Big Data
Collaboration
Augmented
Intelligence
(Human/Machine
Partnership)
Conclusion
To optimally harness the power of Big Data and AI in
Medicine we need Multi Institutional collaboration
between Physicians, Data Scientists and Machine
Learning Experts.
Thanks forYourTime
References
1. Basso, C., Maron, B. J., Corrado, D., & Thiene, G. (2000). Clinical profile of congenital coronary artery anomalies with origin from the wrong aortic
sinus leading to sudden death in young competitive athletes. Journal of the American College of Cardiology, 35(6), 1493-1501.
2. Betancur, J., Otaki, Y., Motwani, M., Fish, M. B., Lemley, M., Dey, D., . . . Sharir, T. (2017). Prognostic value of combined clinical and myocardial
perfusion imaging data using machine learning. JACC: Cardiovascular Imaging,
3. Brothers, J. A. (2017). Introduction to anomalous aortic origin of a coronary artery. Congenital Heart Disease, 12(5), 600-602. doi:10.1111/chd.12497
4. Chang, A. C. (2016). Big data in medicine: The upcoming artificial intelligence. Progress in Pediatric Cardiology, 43, 91-94.
5. Chang, A. P., & Musen, M. (2012). Artificial Intelligence in Pediatric Cardiology: An Innovative Transformation in Patient Care, Clinical Research, and
Medical Education. Congenital Cardiology, 10, 1-9
6. Deo, R. C. (2015). Machine learning in medicine. Circulation, 132(20), 1920-1930. doi:10.1161/CIRCULATIONAHA.115.001593 [doi]
7. Krittanawong, C., Zhang, H., Wang, Z., Aydar, M., & Kitai, T. (2017). Artificial intelligence in precision cardiovascular medicine. Journal of the
American College of Cardiology, 69(21), 2657-2664.
8. Lee, J., Jun, S., Cho, Y., Lee, H., Kim, G. B., Seo, J. B., & Kim, N. (2017). Deep learning in medical imaging: General overview. Korean Journal of
Radiology, 18(4), 570-584.
9. Maron, B. J., Doerer, J. J., Haas, T. S., Tierney, D. M., & Mueller, F. O. (2009). Sudden deaths in young competitive athletes: Analysis of 1866 deaths
in the united states, 1980-2006. Circulation, 119(8), 1085-1092. doi:10.1161/CIRCULATIONAHA.108.804617 [doi]
10. Shah, S. J., Katz, D. H., Selvaraj, S., Burke, M. A., Yancy, C. W., Gheorghiade, M., . . . Deo, R. C. (2015). Phenomapping for novel classification of
heart failure with preserved ejection fraction. Circulation, 131(3), 269-279. doi:10.1161/CIRCULATIONAHA.114.010637 [doi]
11. Van Hare, G. F., Ackerman, M. J., Evangelista, J. A., Kovacs, R. J., Myerburg, R. J., Shafer, K. M., . . . American Heart Association Electrocardiography
and Arrhythmias Committee of Council on Clinical Cardiology, Council on Cardiovascular Disease in Young, Council on Cardiovascular and Stroke
Nursing, Council on Functional Genomics and Translational Biology, and American College of Cardiology. (2015). Eligibility and disqualification
recommendations for competitive athletes with cardiovascular abnormalities: Task force 4: Congenital heart disease: A scientific statement from
the american heart association and american college of cardiology. Circulation, 132(22), e281-91. doi:10.1161/CIR.0000000000000240 [doi]
Any Questions
1 de 43

Recomendados

IRJET - An Effective Stroke Prediction System using Predictive Models por
IRJET -  	  An Effective Stroke Prediction System using Predictive ModelsIRJET -  	  An Effective Stroke Prediction System using Predictive Models
IRJET - An Effective Stroke Prediction System using Predictive ModelsIRJET Journal
46 vistas7 diapositivas
Stroke Prediction por
Stroke PredictionStroke Prediction
Stroke PredictionMamathaGuntu1
1.5K vistas15 diapositivas
Deep Learning in Healthcare por
Deep Learning in HealthcareDeep Learning in Healthcare
Deep Learning in HealthcareYang Li Hector Yee
881 vistas31 diapositivas
AI for Precision Medicine (Pragmatic preclinical data science) por
AI for Precision Medicine (Pragmatic preclinical data science)AI for Precision Medicine (Pragmatic preclinical data science)
AI for Precision Medicine (Pragmatic preclinical data science)Paul Agapow
359 vistas23 diapositivas
Prediction, Big Data, and AI: Steyerberg, Basel Nov 1, 2019 por
Prediction, Big Data, and AI: Steyerberg, Basel Nov 1, 2019Prediction, Big Data, and AI: Steyerberg, Basel Nov 1, 2019
Prediction, Big Data, and AI: Steyerberg, Basel Nov 1, 2019Ewout Steyerberg
1.5K vistas59 diapositivas
Big Data Analytics for Healthcare por
Big Data Analytics for HealthcareBig Data Analytics for Healthcare
Big Data Analytics for HealthcareChandan Reddy
13.6K vistas46 diapositivas

Más contenido relacionado

La actualidad más candente

Healthcare Predicitive Analytics for Risk Profiling in Chronic Care: A Bayesi... por
Healthcare Predicitive Analytics for Risk Profiling in Chronic Care: A Bayesi...Healthcare Predicitive Analytics for Risk Profiling in Chronic Care: A Bayesi...
Healthcare Predicitive Analytics for Risk Profiling in Chronic Care: A Bayesi...MIS Quarterly
928 vistas33 diapositivas
Bias in covid 19 models por
Bias in covid 19 modelsBias in covid 19 models
Bias in covid 19 modelsLaure Wynants
395 vistas63 diapositivas
Day 1 (Lecture 3): Predictive Analytics in Healthcare por
Day 1 (Lecture 3): Predictive Analytics in HealthcareDay 1 (Lecture 3): Predictive Analytics in Healthcare
Day 1 (Lecture 3): Predictive Analytics in HealthcareAseda Owusua Addai-Deseh
45K vistas70 diapositivas
Clinical data analytics por
Clinical data analyticsClinical data analytics
Clinical data analyticsSB BHATTACHARYYA
2.4K vistas40 diapositivas
Machine learning in medicine: calm down por
Machine learning in medicine: calm downMachine learning in medicine: calm down
Machine learning in medicine: calm downBenVanCalster
568 vistas74 diapositivas
Big Data Provides Opportunities, Challenges and a Better Future in Health and... por
Big Data Provides Opportunities, Challenges and a Better Future in Health and...Big Data Provides Opportunities, Challenges and a Better Future in Health and...
Big Data Provides Opportunities, Challenges and a Better Future in Health and...Cirdan
276 vistas43 diapositivas

La actualidad más candente(20)

Healthcare Predicitive Analytics for Risk Profiling in Chronic Care: A Bayesi... por MIS Quarterly
Healthcare Predicitive Analytics for Risk Profiling in Chronic Care: A Bayesi...Healthcare Predicitive Analytics for Risk Profiling in Chronic Care: A Bayesi...
Healthcare Predicitive Analytics for Risk Profiling in Chronic Care: A Bayesi...
MIS Quarterly928 vistas
Bias in covid 19 models por Laure Wynants
Bias in covid 19 modelsBias in covid 19 models
Bias in covid 19 models
Laure Wynants395 vistas
Machine learning in medicine: calm down por BenVanCalster
Machine learning in medicine: calm downMachine learning in medicine: calm down
Machine learning in medicine: calm down
BenVanCalster568 vistas
Big Data Provides Opportunities, Challenges and a Better Future in Health and... por Cirdan
Big Data Provides Opportunities, Challenges and a Better Future in Health and...Big Data Provides Opportunities, Challenges and a Better Future in Health and...
Big Data Provides Opportunities, Challenges and a Better Future in Health and...
Cirdan276 vistas
Dichotomania and other challenges for the collaborating biostatistician por Laure Wynants
Dichotomania and other challenges for the collaborating biostatisticianDichotomania and other challenges for the collaborating biostatistician
Dichotomania and other challenges for the collaborating biostatistician
Laure Wynants2.2K vistas
Str-AI-ght to heaven? Pitfalls for clinical decision support based on AI por BenVanCalster
Str-AI-ght to heaven? Pitfalls for clinical decision support based on AIStr-AI-ght to heaven? Pitfalls for clinical decision support based on AI
Str-AI-ght to heaven? Pitfalls for clinical decision support based on AI
BenVanCalster93 vistas
How to establish and evaluate clinical prediction models - Statswork por Stats Statswork
How to establish and evaluate clinical prediction models - StatsworkHow to establish and evaluate clinical prediction models - Statswork
How to establish and evaluate clinical prediction models - Statswork
Stats Statswork101 vistas
Evaluation of Logistic Regression and Neural Network Model With Sensitivity A... por CSCJournals
Evaluation of Logistic Regression and Neural Network Model With Sensitivity A...Evaluation of Logistic Regression and Neural Network Model With Sensitivity A...
Evaluation of Logistic Regression and Neural Network Model With Sensitivity A...
CSCJournals529 vistas
Heart disease prediction por Ariful Haque
Heart disease predictionHeart disease prediction
Heart disease prediction
Ariful Haque742 vistas
Development and evaluation of prediction models: pitfalls and solutions (Part... por BenVanCalster
Development and evaluation of prediction models: pitfalls and solutions (Part...Development and evaluation of prediction models: pitfalls and solutions (Part...
Development and evaluation of prediction models: pitfalls and solutions (Part...
BenVanCalster419 vistas
Disease Prediction And Doctor Appointment system por KOYELMAJUMDAR1
Disease Prediction And Doctor Appointment  systemDisease Prediction And Doctor Appointment  system
Disease Prediction And Doctor Appointment system
KOYELMAJUMDAR11.7K vistas
A Survey on Heart Disease Prediction Techniques por ijtsrd
A Survey on Heart Disease Prediction TechniquesA Survey on Heart Disease Prediction Techniques
A Survey on Heart Disease Prediction Techniques
ijtsrd73 vistas
Open science LMU session contribution E Steyerberg 2jul20 por Ewout Steyerberg
Open science LMU session contribution E Steyerberg 2jul20Open science LMU session contribution E Steyerberg 2jul20
Open science LMU session contribution E Steyerberg 2jul20
Ewout Steyerberg254 vistas
ENSEMBLE LEARNING MODEL FOR SCREENING AUTISM IN CHILDREN por ijcsit
ENSEMBLE LEARNING MODEL FOR SCREENING AUTISM IN CHILDRENENSEMBLE LEARNING MODEL FOR SCREENING AUTISM IN CHILDREN
ENSEMBLE LEARNING MODEL FOR SCREENING AUTISM IN CHILDREN
ijcsit11 vistas
A Survey on Various Disease Prediction Techniques por ijtsrd
A Survey on Various Disease Prediction TechniquesA Survey on Various Disease Prediction Techniques
A Survey on Various Disease Prediction Techniques
ijtsrd52 vistas
Machine Learning for Preclinical Research por Paul Agapow
Machine Learning for Preclinical ResearchMachine Learning for Preclinical Research
Machine Learning for Preclinical Research
Paul Agapow406 vistas

Similar a Use of Artificial Intelligence in AAOCA

Artificial Intelligence: Connecting the dots and relieving the pain in Health... por
Artificial Intelligence: Connecting the dots and relieving the pain in Health...Artificial Intelligence: Connecting the dots and relieving the pain in Health...
Artificial Intelligence: Connecting the dots and relieving the pain in Health...JAI NAHAR, MD MBA
161 vistas58 diapositivas
C0344023028 por
C0344023028C0344023028
C0344023028inventionjournals
275 vistas6 diapositivas
ICACR 2023 final (1).pptx por
ICACR 2023 final (1).pptxICACR 2023 final (1).pptx
ICACR 2023 final (1).pptxSaadAli105813
6 vistas24 diapositivas
Jiang2017 por
Jiang2017Jiang2017
Jiang2017VISHALGUPTA931215
35 vistas14 diapositivas
Artificial intelligence and precision medicine does the health economist need... por
Artificial intelligence and precision medicine does the health economist need...Artificial intelligence and precision medicine does the health economist need...
Artificial intelligence and precision medicine does the health economist need...Augustin Terlinden
738 vistas51 diapositivas
Artificial intelligence in healthcare past,present and future por
Artificial intelligence in healthcare past,present and futureArtificial intelligence in healthcare past,present and future
Artificial intelligence in healthcare past,present and futureErrepe
198 vistas13 diapositivas

Similar a Use of Artificial Intelligence in AAOCA(20)

Artificial Intelligence: Connecting the dots and relieving the pain in Health... por JAI NAHAR, MD MBA
Artificial Intelligence: Connecting the dots and relieving the pain in Health...Artificial Intelligence: Connecting the dots and relieving the pain in Health...
Artificial Intelligence: Connecting the dots and relieving the pain in Health...
JAI NAHAR, MD MBA161 vistas
Artificial intelligence and precision medicine does the health economist need... por Augustin Terlinden
Artificial intelligence and precision medicine does the health economist need...Artificial intelligence and precision medicine does the health economist need...
Artificial intelligence and precision medicine does the health economist need...
Augustin Terlinden738 vistas
Artificial intelligence in healthcare past,present and future por Errepe
Artificial intelligence in healthcare past,present and futureArtificial intelligence in healthcare past,present and future
Artificial intelligence in healthcare past,present and future
Errepe198 vistas
Artificial intelligence in medicine (projeck) por YasserAli152984
Artificial intelligence in medicine (projeck)Artificial intelligence in medicine (projeck)
Artificial intelligence in medicine (projeck)
YasserAli152984167 vistas
Artificial Intelligence in Medicine.pdf por zeeshan811731
Artificial Intelligence in Medicine.pdfArtificial Intelligence in Medicine.pdf
Artificial Intelligence in Medicine.pdf
zeeshan81173121 vistas
Data Science for (Health) Science: tales from a challenging front line, and h... por Paolo Missier
Data Science for (Health) Science:tales from a challenging front line, and h...Data Science for (Health) Science:tales from a challenging front line, and h...
Data Science for (Health) Science: tales from a challenging front line, and h...
Paolo Missier238 vistas
K-Nearest Neighbours based diagnosis of hyperglycemia por ijtsrd
K-Nearest Neighbours based diagnosis of hyperglycemiaK-Nearest Neighbours based diagnosis of hyperglycemia
K-Nearest Neighbours based diagnosis of hyperglycemia
ijtsrd66 vistas
AI in Healthcare por Paul Agapow
AI in HealthcareAI in Healthcare
AI in Healthcare
Paul Agapow151 vistas
Artificial intelligence in healthcare por Yamini Shah
Artificial intelligence in healthcareArtificial intelligence in healthcare
Artificial intelligence in healthcare
Yamini Shah3.4K vistas
5 Reasons Why Radiology Needs Artificial Intelligence por Simon Harris
5 Reasons Why Radiology Needs Artificial Intelligence5 Reasons Why Radiology Needs Artificial Intelligence
5 Reasons Why Radiology Needs Artificial Intelligence
Simon Harris3.9K vistas
IRJET - Digital Assistance: A New Impulse on Stroke Patient Health Care using... por IRJET Journal
IRJET - Digital Assistance: A New Impulse on Stroke Patient Health Care using...IRJET - Digital Assistance: A New Impulse on Stroke Patient Health Care using...
IRJET - Digital Assistance: A New Impulse on Stroke Patient Health Care using...
IRJET Journal10 vistas
Heart Failure Prediction using Different MachineLearning Techniques por IRJET Journal
Heart Failure Prediction using Different MachineLearning TechniquesHeart Failure Prediction using Different MachineLearning Techniques
Heart Failure Prediction using Different MachineLearning Techniques
IRJET Journal5 vistas

Más de JAI NAHAR, MD MBA

Augmenting Health care delivery in Generative AI era: Balancing the hope and ... por
Augmenting Health care delivery in Generative AI era: Balancing the hope and ...Augmenting Health care delivery in Generative AI era: Balancing the hope and ...
Augmenting Health care delivery in Generative AI era: Balancing the hope and ...JAI NAHAR, MD MBA
14 vistas27 diapositivas
A23017-ACC23-WCC-Presenentation Jai Nahar (2).pptx por
A23017-ACC23-WCC-Presenentation Jai Nahar (2).pptxA23017-ACC23-WCC-Presenentation Jai Nahar (2).pptx
A23017-ACC23-WCC-Presenentation Jai Nahar (2).pptxJAI NAHAR, MD MBA
15 vistas19 diapositivas
Jai_Nahar_HIT Lab symposium July 2023 (1).pptx por
Jai_Nahar_HIT Lab symposium July 2023 (1).pptxJai_Nahar_HIT Lab symposium July 2023 (1).pptx
Jai_Nahar_HIT Lab symposium July 2023 (1).pptxJAI NAHAR, MD MBA
11 vistas11 diapositivas
Chat GPT - Copy.pptx por
Chat GPT - Copy.pptxChat GPT - Copy.pptx
Chat GPT - Copy.pptxJAI NAHAR, MD MBA
27 vistas6 diapositivas
Rethinking Conversation in Medicine: Balancing the hype and hope of Generativ... por
Rethinking Conversation in Medicine: Balancing the hype and hope of Generativ...Rethinking Conversation in Medicine: Balancing the hype and hope of Generativ...
Rethinking Conversation in Medicine: Balancing the hype and hope of Generativ...JAI NAHAR, MD MBA
52 vistas20 diapositivas
Mayo AI CAI final.pptx por
Mayo AI CAI final.pptxMayo AI CAI final.pptx
Mayo AI CAI final.pptxJAI NAHAR, MD MBA
46 vistas26 diapositivas

Más de JAI NAHAR, MD MBA(18)

Augmenting Health care delivery in Generative AI era: Balancing the hope and ... por JAI NAHAR, MD MBA
Augmenting Health care delivery in Generative AI era: Balancing the hope and ...Augmenting Health care delivery in Generative AI era: Balancing the hope and ...
Augmenting Health care delivery in Generative AI era: Balancing the hope and ...
JAI NAHAR, MD MBA14 vistas
A23017-ACC23-WCC-Presenentation Jai Nahar (2).pptx por JAI NAHAR, MD MBA
A23017-ACC23-WCC-Presenentation Jai Nahar (2).pptxA23017-ACC23-WCC-Presenentation Jai Nahar (2).pptx
A23017-ACC23-WCC-Presenentation Jai Nahar (2).pptx
JAI NAHAR, MD MBA15 vistas
Jai_Nahar_HIT Lab symposium July 2023 (1).pptx por JAI NAHAR, MD MBA
Jai_Nahar_HIT Lab symposium July 2023 (1).pptxJai_Nahar_HIT Lab symposium July 2023 (1).pptx
Jai_Nahar_HIT Lab symposium July 2023 (1).pptx
JAI NAHAR, MD MBA11 vistas
Rethinking Conversation in Medicine: Balancing the hype and hope of Generativ... por JAI NAHAR, MD MBA
Rethinking Conversation in Medicine: Balancing the hype and hope of Generativ...Rethinking Conversation in Medicine: Balancing the hype and hope of Generativ...
Rethinking Conversation in Medicine: Balancing the hype and hope of Generativ...
JAI NAHAR, MD MBA52 vistas
Nlp in cardiology ai med clinician series june 2021 por JAI NAHAR, MD MBA
Nlp in cardiology ai med clinician series june 2021Nlp in cardiology ai med clinician series june 2021
Nlp in cardiology ai med clinician series june 2021
JAI NAHAR, MD MBA42 vistas
Role of Medical Intelligence in Augmenting The Virtual Health Care Delivery por JAI NAHAR, MD MBA
Role of Medical Intelligence in Augmenting The Virtual Health Care DeliveryRole of Medical Intelligence in Augmenting The Virtual Health Care Delivery
Role of Medical Intelligence in Augmenting The Virtual Health Care Delivery
JAI NAHAR, MD MBA35 vistas
Role of NLP, Conversational AI & Virtual Voice Assistants in Pediatrics por JAI NAHAR, MD MBA
Role of NLP, Conversational AI & Virtual Voice Assistants in PediatricsRole of NLP, Conversational AI & Virtual Voice Assistants in Pediatrics
Role of NLP, Conversational AI & Virtual Voice Assistants in Pediatrics
JAI NAHAR, MD MBA44 vistas
Role of Conversational AI and Virtual Voice Assistants in Cardiology: What is... por JAI NAHAR, MD MBA
Role of Conversational AI and Virtual Voice Assistants in Cardiology: What is...Role of Conversational AI and Virtual Voice Assistants in Cardiology: What is...
Role of Conversational AI and Virtual Voice Assistants in Cardiology: What is...
JAI NAHAR, MD MBA195 vistas
Emerging Frontier in Health Care delivery: Conversational AI & Virtual Voice ... por JAI NAHAR, MD MBA
Emerging Frontier in Health Care delivery: Conversational AI & Virtual Voice ...Emerging Frontier in Health Care delivery: Conversational AI & Virtual Voice ...
Emerging Frontier in Health Care delivery: Conversational AI & Virtual Voice ...
JAI NAHAR, MD MBA108 vistas
Cognitive personal digital assistant for physicians por JAI NAHAR, MD MBA
Cognitive personal digital assistant for physiciansCognitive personal digital assistant for physicians
Cognitive personal digital assistant for physicians
JAI NAHAR, MD MBA62 vistas
Emerging Frontier in Cardiovascular Care: Conversational AI & Virtual Voice A... por JAI NAHAR, MD MBA
Emerging Frontier in Cardiovascular Care: Conversational AI & Virtual Voice A...Emerging Frontier in Cardiovascular Care: Conversational AI & Virtual Voice A...
Emerging Frontier in Cardiovascular Care: Conversational AI & Virtual Voice A...
JAI NAHAR, MD MBA275 vistas
Rise of Intelligent Machines: The Potential of Artificial Intelligence in Car... por JAI NAHAR, MD MBA
Rise of Intelligent Machines: The Potential of Artificial Intelligence in Car...Rise of Intelligent Machines: The Potential of Artificial Intelligence in Car...
Rise of Intelligent Machines: The Potential of Artificial Intelligence in Car...
JAI NAHAR, MD MBA98 vistas
AUGMENTED CARDIOVASCULAR PRACTITIONER:GIVING DOCTORS AND PATIENTS A NEW VOICE por JAI NAHAR, MD MBA
AUGMENTED CARDIOVASCULAR  PRACTITIONER:GIVING DOCTORS AND PATIENTS A NEW VOICEAUGMENTED CARDIOVASCULAR  PRACTITIONER:GIVING DOCTORS AND PATIENTS A NEW VOICE
AUGMENTED CARDIOVASCULAR PRACTITIONER:GIVING DOCTORS AND PATIENTS A NEW VOICE
JAI NAHAR, MD MBA61 vistas

Último

ANIMALS USED IN EXPERIMENTAL PHARMACOLOGY.pptx por
ANIMALS USED IN EXPERIMENTAL PHARMACOLOGY.pptxANIMALS USED IN EXPERIMENTAL PHARMACOLOGY.pptx
ANIMALS USED IN EXPERIMENTAL PHARMACOLOGY.pptxThakurHarsh11
10 vistas12 diapositivas
Reeem assignment 4.pdf por
Reeem assignment 4.pdfReeem assignment 4.pdf
Reeem assignment 4.pdfد حاتم البيطار
6 vistas6 diapositivas
How Bluetooth Connectivity Is Revolutionizing Upper Arm Digital Blood Pressur... por
How Bluetooth Connectivity Is Revolutionizing Upper Arm Digital Blood Pressur...How Bluetooth Connectivity Is Revolutionizing Upper Arm Digital Blood Pressur...
How Bluetooth Connectivity Is Revolutionizing Upper Arm Digital Blood Pressur...Omron Healthcare Australia
8 vistas1 diapositiva
Gil Bashe FINN Partners: The Future of Digital Health – Nose Dive or Transfor... por
Gil Bashe FINN Partners: The Future of Digital Health – Nose Dive or Transfor...Gil Bashe FINN Partners: The Future of Digital Health – Nose Dive or Transfor...
Gil Bashe FINN Partners: The Future of Digital Health – Nose Dive or Transfor...Levi Shapiro
205 vistas21 diapositivas
2024 Medicare Physician Fee Schedule (MPFS) Final Rule Updates por
2024 Medicare Physician Fee Schedule (MPFS) Final Rule Updates2024 Medicare Physician Fee Schedule (MPFS) Final Rule Updates
2024 Medicare Physician Fee Schedule (MPFS) Final Rule UpdatesHealth Catalyst
216 vistas76 diapositivas
What's Next for OPPS: A Look at the 2024 Final Rule por
What's Next for OPPS: A Look at the 2024 Final RuleWhat's Next for OPPS: A Look at the 2024 Final Rule
What's Next for OPPS: A Look at the 2024 Final RuleHealth Catalyst
380 vistas72 diapositivas

Último(20)

ANIMALS USED IN EXPERIMENTAL PHARMACOLOGY.pptx por ThakurHarsh11
ANIMALS USED IN EXPERIMENTAL PHARMACOLOGY.pptxANIMALS USED IN EXPERIMENTAL PHARMACOLOGY.pptx
ANIMALS USED IN EXPERIMENTAL PHARMACOLOGY.pptx
ThakurHarsh1110 vistas
Gil Bashe FINN Partners: The Future of Digital Health – Nose Dive or Transfor... por Levi Shapiro
Gil Bashe FINN Partners: The Future of Digital Health – Nose Dive or Transfor...Gil Bashe FINN Partners: The Future of Digital Health – Nose Dive or Transfor...
Gil Bashe FINN Partners: The Future of Digital Health – Nose Dive or Transfor...
Levi Shapiro205 vistas
2024 Medicare Physician Fee Schedule (MPFS) Final Rule Updates por Health Catalyst
2024 Medicare Physician Fee Schedule (MPFS) Final Rule Updates2024 Medicare Physician Fee Schedule (MPFS) Final Rule Updates
2024 Medicare Physician Fee Schedule (MPFS) Final Rule Updates
Health Catalyst216 vistas
What's Next for OPPS: A Look at the 2024 Final Rule por Health Catalyst
What's Next for OPPS: A Look at the 2024 Final RuleWhat's Next for OPPS: A Look at the 2024 Final Rule
What's Next for OPPS: A Look at the 2024 Final Rule
Health Catalyst380 vistas
Automated Patient Reported Outcomes (PROs) for Hip & Knee Replacement por Health Catalyst
Automated Patient Reported Outcomes (PROs) for Hip & Knee ReplacementAutomated Patient Reported Outcomes (PROs) for Hip & Knee Replacement
Automated Patient Reported Outcomes (PROs) for Hip & Knee Replacement
Health Catalyst6 vistas
Best Hair Transplant in Delhi.pptx por Praful Wadhwa
Best Hair Transplant in Delhi.pptxBest Hair Transplant in Delhi.pptx
Best Hair Transplant in Delhi.pptx
Praful Wadhwa9 vistas
Oral presentaion slides.pptx por anwahiamna
Oral presentaion slides.pptxOral presentaion slides.pptx
Oral presentaion slides.pptx
anwahiamna6 vistas
5 safety tips keeping dogs healthy in autumn season por CanadaVetCare
5 safety tips keeping dogs healthy in autumn season5 safety tips keeping dogs healthy in autumn season
5 safety tips keeping dogs healthy in autumn season
CanadaVetCare6 vistas
Introduction to Sociology for physiotherapists.pptx por Mumux Mirani
Introduction to Sociology for physiotherapists.pptxIntroduction to Sociology for physiotherapists.pptx
Introduction to Sociology for physiotherapists.pptx
Mumux Mirani32 vistas
Low Vision Managment, Age Related Macular Degeneration ARMD por mahendra singh
Low Vision Managment, Age Related Macular Degeneration ARMDLow Vision Managment, Age Related Macular Degeneration ARMD
Low Vision Managment, Age Related Macular Degeneration ARMD
mahendra singh9 vistas
New Microsoft Word Document (2).docx por ElyaGhiasyan
New Microsoft Word Document (2).docxNew Microsoft Word Document (2).docx
New Microsoft Word Document (2).docx
ElyaGhiasyan11 vistas
vital signs...ILAYARAJA SAMPATH por S ILAYA RAJA
vital signs...ILAYARAJA SAMPATHvital signs...ILAYARAJA SAMPATH
vital signs...ILAYARAJA SAMPATH
S ILAYA RAJA401 vistas

Use of Artificial Intelligence in AAOCA

  • 1. Use of Artificial Intelligence in AAOCA Jai Nahar, MD, MBA Associate Professor of Pediatrics The GeorgeWashington University School of Medicine and Health Sciences Division of Cardiology Children’s National Medical Center Washington, DC Congenital Heart Surgeons Society Fall work weekend Nov. 2017,Toronto
  • 3. Agenda 1. AAOCA: Background, problem, questions to be addressed 2. Current Opportunity 3. Introduction to AI in medicine 4. PotentialApplication ofAI in AAOCA 5. Challenges 6. Future directions
  • 4. AAOCA: Background • Second leading cause of SCD in young athletes in USA • Care of these patients involve three important challenges 1. Diagnosis: incidental diagnosis, lack of symptoms, initial presentation may be SCD or sudden cardiac arrest 2. Risk Stratification: phenotypic heterogeneity 3. Ideal management Risk Stratification Diagnosis AAOCA Ideal Management
  • 5. AAOCA:What causes the Critical Lethal event? Critical Event : Coronary ischemia and lethal Ventricular Tachyarrhythmia Decreased coronary perfusion due to Mechanical factors, altered blood flow dynamics Electrically unstable myocardial substrate Unknown Factors ? • Acute angle take off and Kinking of coronary artery at its origin • Flap like closure of abnormal slit like coronary orifice • Compression of anomalous coronary artery between Aorta and Pulmonary artery during exercise • Spasm of anomalous coronary artery possibly secondary to endothelial injury Prior intermittent ischemia Patchy Myocardial Fibrosis • Local myocardial metabolic factors • Channelopathies • Genetic predisposition to arrhythmia Basso et al. (2000). Clinical profile of congenital coronary artery anomalies with origin from the wrong aortic sinus leading to sudden death in young competitive athletes. Journal of the American College of Cardiology, 35(6), 1493-1501.
  • 6. Problem There are knowledge gaps/unknown variables which need to be filled/uncovered to refine our risk stratification for AAOCA patients who are at highest risk of sudden death • Asymptomatic (hidden) • Gray zone (symptoms of ? significance)
  • 7. Task: Making the invisible, visible AAOCA: Myocardial ischemia, malignant Ventricular arrhythmia, sudden death Unknown/Invisible? • Genetic make up • Channelopathies • Local myocardial/metabolic factors • Etc ??????
  • 8. Questions 1. How can we uncover currently unknown phenotypes (cluster of variables with non linear relation) which indicate high risk of sudden cardiac death? 2. How to develop good predictive models for risk stratification and prompt detection of high risk AAOCA ?
  • 9. Call for Action:Two step approach Uncover unknown high risk groups Develop refined risk stratification models Deep Phenotyping
  • 10. Agenda 1. Define the problem, and questions to be addressed 2. Current Opportunity 3. Introduction to AI in medicine 4. Potential Application of AI to AAOCA 5. Challenges 6. Future directions
  • 11. Current Opportunity : make the invisible, visible • Data: CHSS AAOCA registry • Artificial Intelligence Methods Power of Data Leverage AI Refined risk stratification and patient management
  • 12. Dawn of New Era of Augmented Intelligence Physician and AI ( Human/Machine) synergy for facilitating better • Diagnosis • Disease management • Clinical Decisions Physicians Machines Platform for Precision Medicine
  • 13. Agenda 1. Define the problem, and questions to be addressed 2. Current Opportunity 3. Introduction to AI in medicine 4. Potential Application of AI to AAOCA 5. Challenges 6. Future directions
  • 14. Medical Intelligence: AI in Medicine Big Data and Artificial Intelligence in Pediatric Cardiology Anthony C. Chang, MD, MBA, MPH
  • 16. Machine Learning Andrew Ng “Is the Science of getting computers to learn, without being explicitly programmed” Full spectrum application in CV medicine Machine Learning Diagnosis/Risk stratification Treatment Prevention Research
  • 17. Machine Learning types 1. Supervised 2. Unsupervised 3. Reinforcement
  • 18. Supervised Learning • Goal is to predict a known output orTarget • Algorithm is taught with right answers (labels) for examples used in training data set. • Can be categorized as:  Classification problem: predicting categories, discrete value output (0,1 etc.)  Regression problem: predict continuous values  Anomaly detection problem: predict unusual pattern
  • 19. Supervised Learning Applications • Document classification • Pattern recognition: Automated interpretation of EKG • Image Analysis in CV imaging • Predicting Risk
  • 20. Supervised Learning Algorithms • Artificial Neural Network (ANN) • SupportVector Machine • DecisionTree • Random Forests • Naive Bayes classifier • Fuzzy Logic • K-Nearest Neighbor (KNN)
  • 21. Unsupervised Learning • Goal is to learn the intrinsic structure within data. • No outputs to predict • Task is to find hidden pattern/structure in data, without human feedback Cluster2 Cluster3 Cluster 1
  • 22. Unsupervised Learning Application Identify novel disease mechanisms, genotypes, phenotypes: Filling the knowledge gaps Identify Novel Disease Mechanisms New paths/approach to therapy Precision Medicine initiative
  • 23. Unsupervised Learning Algorithms • Clustering algorithms: K-Means, Hierarchical clustering  Used to cluster unlabeled data into different groups  Used when no obvious natural grouping • Association rule- learning algorithm:  Help to uncover relationships between seemingly unrelated data items • PrincipalComponent Analysis • Sparse Coding
  • 25. K-Means clustering Algorithms (left) K-means in 2d. (right) K-means in 3d. You have to imagine k-means in 4d. http://stanford.edu/~cpiech/cs221/handouts/kmeans.html
  • 26. Reinforcement learning Reinforcement learning led to AlphaGo’s stunning victory over a human Go champion https://www.technologyreview.com/s/603501/10-breakthrough-technologies-2017-reinforcement- learning/ Reinforcement learning is learning by trial-and-error, solely from rewards or punishments. https://deepmind.com/blog/deep-reinforcement- learning/ Can be viewed as hybrid of supervised and unsupervised learning
  • 27. Artificial Neural Network (ANN) ANN are modeled after human neurons • Nodes are like neurons • Input layer: input data/ predictor variables/ features • Hidden layer: processing of input • Output layer:Target (prediction of class or value) Lee, J.-G., Jun, S., Cho, Y.-W., Lee, H., Kim, G. B., Seo, J. B., & Kim, N. (2017). Deep Learning in Medical Imaging: General Overview. Korean Journal of Radiology, 18(4), 570–584. http://doi.org/10.3348/kjr.2017.18.4.570
  • 28. Deep Learning • Part of Machine Learning • Uses multiple layers of ANN • Mimics the working of human brain Lee, J.-G., Jun, S., Cho, Y.-W., Lee, H., Kim, G. B., Seo, J. B., & Kim, N. (2017). Deep Learning in Medical Imaging: General Overview. Korean Journal of Radiology, 18(4), 570–584. http://doi.org/10.3348/kjr.2017.18.4.570
  • 29. Deep Learning Three types of Network: 1. Deep Neural Networks: Google’s Deep mind Alpha Go 2. Recurrent Neural Networks (RNN): natural language processing, handwriting and speech recognition 3. Convolutional Neural Networks (CNN): Computer vision, image recognition, CV imaging
  • 30. Cognitive Computing Systems mimicking human cognition, help replicate human capabilities across the spectrum of sensory perception, deduction, reasoning, learning and knowledge.
  • 31. Upcoming inWorld of AI • Quantum Computing: accelerate the data processing speed • Neuromorphic chips • Partnership with other technologies  AI and AR  AI and Robotics
  • 32. Agenda 1. AAOCA: Background, problem, questions to be addressed 2. Current Opportunity 3. Introduction to AI in medicine 4. Potential Application of AI in AAOCA 5. Challenges 6. Future directions
  • 33. First : A Machine Learning overview Machine Learning in Medicine Rahul C. Deo Circulation. 2015;132:1920-1930, originally published November 16, 2015 https://doi.org/10.1161/CIRCULATIONAHA.115.001593 A: Matrix representation of the supervised and unsupervised learning problem. B: Decision trees map features to outcome (Supervised Learning) C: Neural networks predict outcome based on transformed representations of features. (Supervised Learning) D:The k-nearest neighbor algorithm assigns class based on the values of the most similar training examples. (Supervised Learning)
  • 34. Phenomapping Use of unsupervised machine learning in Phenotypic classification of a heterogeneous clinical syndrome into discrete phenogroups PG1 PG2 PG3 PG4 PG5 Phenomapping
  • 35. Phenotypic classification (Phenomapping) A: Phenotype heat map of HFpEF. B: BIC analysis for the identification of the optimal number of phenotypic clusters (pheno groups). C: Kaplan–Meier curves Survival free of cardiovascular (CV) hospitalization or death stratified by pheno groups. Machine Learning in Medicine Rahul C. Deo Circulation. 2015;132:1920-1930
  • 36. Stepwise approach for AAOCA Detection of High Risk Cases Develop Supervised model for disease prediction Novel phenogroup selection using Unsupervised learning
  • 37. Proposed Framework for AAOCA Demographic Data Stress lab/Nuclear Medicine Data EP data Surgical data Cath data Imaging data Clinical Data Unsupervised learning based Pheno-groups identification Supervised Learning based Model for Risk stratification High Medium Low Expert Knowledge
  • 38. Challenges • Deep learning:  Problem of model overfitting  Need for large data sets, multi Institutional collaboration  Setting a neural network is time consuming • Need for sharing of machine learning expertise • Need for Novel informative features to build improved models • Need for refined biomarkers to access myocardial status
  • 39. Future Directions Seamless data collaboration across institutions, and enhanced Computer- Human synergy lead Augmented intelligence will refine the path of precisionCardiovascular Medicine. Precision Medicine Big Data Collaboration Augmented Intelligence (Human/Machine Partnership)
  • 40. Conclusion To optimally harness the power of Big Data and AI in Medicine we need Multi Institutional collaboration between Physicians, Data Scientists and Machine Learning Experts.
  • 42. References 1. Basso, C., Maron, B. J., Corrado, D., & Thiene, G. (2000). Clinical profile of congenital coronary artery anomalies with origin from the wrong aortic sinus leading to sudden death in young competitive athletes. Journal of the American College of Cardiology, 35(6), 1493-1501. 2. Betancur, J., Otaki, Y., Motwani, M., Fish, M. B., Lemley, M., Dey, D., . . . Sharir, T. (2017). Prognostic value of combined clinical and myocardial perfusion imaging data using machine learning. JACC: Cardiovascular Imaging, 3. Brothers, J. A. (2017). Introduction to anomalous aortic origin of a coronary artery. Congenital Heart Disease, 12(5), 600-602. doi:10.1111/chd.12497 4. Chang, A. C. (2016). Big data in medicine: The upcoming artificial intelligence. Progress in Pediatric Cardiology, 43, 91-94. 5. Chang, A. P., & Musen, M. (2012). Artificial Intelligence in Pediatric Cardiology: An Innovative Transformation in Patient Care, Clinical Research, and Medical Education. Congenital Cardiology, 10, 1-9 6. Deo, R. C. (2015). Machine learning in medicine. Circulation, 132(20), 1920-1930. doi:10.1161/CIRCULATIONAHA.115.001593 [doi] 7. Krittanawong, C., Zhang, H., Wang, Z., Aydar, M., & Kitai, T. (2017). Artificial intelligence in precision cardiovascular medicine. Journal of the American College of Cardiology, 69(21), 2657-2664. 8. Lee, J., Jun, S., Cho, Y., Lee, H., Kim, G. B., Seo, J. B., & Kim, N. (2017). Deep learning in medical imaging: General overview. Korean Journal of Radiology, 18(4), 570-584. 9. Maron, B. J., Doerer, J. J., Haas, T. S., Tierney, D. M., & Mueller, F. O. (2009). Sudden deaths in young competitive athletes: Analysis of 1866 deaths in the united states, 1980-2006. Circulation, 119(8), 1085-1092. doi:10.1161/CIRCULATIONAHA.108.804617 [doi] 10. Shah, S. J., Katz, D. H., Selvaraj, S., Burke, M. A., Yancy, C. W., Gheorghiade, M., . . . Deo, R. C. (2015). Phenomapping for novel classification of heart failure with preserved ejection fraction. Circulation, 131(3), 269-279. doi:10.1161/CIRCULATIONAHA.114.010637 [doi] 11. Van Hare, G. F., Ackerman, M. J., Evangelista, J. A., Kovacs, R. J., Myerburg, R. J., Shafer, K. M., . . . American Heart Association Electrocardiography and Arrhythmias Committee of Council on Clinical Cardiology, Council on Cardiovascular Disease in Young, Council on Cardiovascular and Stroke Nursing, Council on Functional Genomics and Translational Biology, and American College of Cardiology. (2015). Eligibility and disqualification recommendations for competitive athletes with cardiovascular abnormalities: Task force 4: Congenital heart disease: A scientific statement from the american heart association and american college of cardiology. Circulation, 132(22), e281-91. doi:10.1161/CIR.0000000000000240 [doi]

Notas del editor

  1. Two step approach Using unsupervised learning, uncover unknown high risk patterns, groups within the data Evaluate their performance in subsequent supervised learning tasks (how useful these new patterns are to AAOCA). This can help in developing refined risk stratification models, facilitating precision medicine
  2. Krittanawong, C., Zhang, H., Wang, Z., Aydar, M., & Kitai, T. (2017). Artificial intelligence in precision cardiovascular medicine. Journal of the American College of Cardiology, 69(21), 2657-2664.
  3. This algorithm consist of a target / outcome variable (or dependent variable) which is to be predicted from a given set of predictors (independent variables). Using these set of variables, we generate a function that map inputs to desired outputs. The training process continues until the model achieves a desired level of accuracy on the training data. Examples of Supervised Learning: Regression, Decision Tree, Random Forest, KNN, Logistic Regression etc. Supervised learning is so named because the data scientist acts as a guide to teach the algorithm what conclusions it should come up with. It’s similar to the way a child might learn arithmetic from a teacher. Supervised learning requires that the algorithm’s possible outputs are already known and that the data used to train the algorithm is already labeled with correct answers. For example, a classification algorithm will learn to identify animals after being trained on a dataset of images that are properly labeled with the species of the animal and some identifying characteristics.
  4. Su[prevised learning algorithms have been applied to problems in prediction, diagnosis and treatment of CVD Prediction accuracy depends on: Algorithm used Dataset hypothesis
  5. K means clustering: Data is clustered in K classes by K-Means Algorithm Hierarchical clustering: can be two types Agglomerative approach: Bottom up approach Divisive: Top down approach https://www.youtube.com/watch?v=RD0nNK51Fp8 (Stanford site)
  6. An ANN is comprised of a network of artificial neurons (also known as "nodes"). These nodes are connected to each other, and the strength of their connections to one another is assigned a value based on their strength: inhibition (maximum being -1.0) or excitation (maximum being +1.0). If the value of the connection is high, then it indicates that there is a strong connection. Within each node's design, a transfer function is built in. There are three types of neurons in an ANN, input nodes, hidden nodes, and output nodes
  7. Three types of deep learning
  8. http://researcher.watson.ibm.com/researcher/view_group.php?id=4384 Medical Sieve is an ambitious long-term exploratory grand challenge project to build a next generation cognitive  assistant with advanced multimodal analytics, clinical knowledge and reasoning capabilities that is qualified to assist in clinical decision making in radiology and cardiology. It will exhibit a deep understanding of diseases and their interpretation in multiple modalities (X-ray, Ultrasound, CT, MRI, PET, Clinical text) covering various radiology and cardiology specialties. The project aims at producing a sieve that filters essential clinical and diagnostic imaging information to form anomaly-driven summaries and recommendations that tremendously reduce the viewing load of clinicians without negatively impacting diagnosis.
  9. http://circ.ahajournals.org/content/132/20/1920.short Machine learning overview. A, Matrix representation of the supervised and unsupervised learning problem. We are interested in developing a model for predicting myocardial infarction (MI). For training data, we have patients, each characterized by an outcome (positive or negative training examples), denoted by the circle in the right-hand column, and by values of predictive features, as well, denoted by blue to red coloring of squares. We seek to build a model to predict outcome by using some combination of features. Multiple types of functions can be used for mapping features to outcome (B through D). Machine learning algorithms are used to find optimal values of free parameters in the model to minimize training error as judged by the difference between predicted values from our model and actual values. In the unsupervised learning problem, we are ignoring the outcome column and grouping together patients based on similarities in the values of their features. B, Decision trees map features to outcome. At each node or branch point, training examples are partitioned based on the value of a particular feature. Additional branches are introduced with the goal of completely separating positive and negative training examples. C, Neural networks predict outcome based on transformed representations of features. A hidden layer of nodes integrates the value of multiple input nodes (raw features) to derive transformed features. The output node then uses values of these transformed features in a model to predict outcome. D, The k-nearest neighbor algorithm assigns class based on the values of the most similar training examples. The distance between patients is computed based on comparing multidimensional vectors of feature values. In this case, where there are only 2 features, if we consider the outcome class of the 3 nearest neighbors, the unknown data instance would be assigned a “no MI” class. LDL indicates low-density lipoprotein; and MI, myocardial infarction.
  10. Application of unsupervised learning to HFpEF. A, Phenotype heat map of HFpEF. Columns represent individual study participants; rows represent individual features. B, Bayesian information criterion analysis for the identification of the optimal number of phenotypic clusters (pheno groups). C, Survival free of cardiovascular (CV) hospitalization or death stratified by phenotypic cluster. Kaplan–Meier curves for the combined outcome of heart failure hospitalization, cardiovascular hospitalization, or death stratified by phenotypic cluster
  11. AAOCA Data: Multidimensional with Phenotypic Heterogeneity