BE PART OF THE REVOLUTION TRANSFORMING HEALTHCARE WITH AI - PowerPoint PPT Presentation

BE PART OF THE REVOLUTION TRANSFORMING HEALTHCARE WITH AI CALIFORNIA — THE RITZ-CARLTON, LAGUNA NIGUEL 11–14 DECEMBER 2019 1000 ATTENDEES 80 SPEAKERS 10 WORKSHOPS www.aimed.events/northamerica-2019/ 2 SOCIAL EVENTS #AIMed19 1 AIMed19

AIMed NORTH AMERICA, CALIFORNIA 11–14 DECEMBER 2019 Role of Precision Medicine in the Management of Congenital Heart Disease Sanjeet Hegde, MD, PhD Co-Director of Research, Heart Institute Program Director of 3D Innovation Lab Medical Director of Advanced Cardiac Imaging Rady Children’s Hospital San Diego/ UCSD

Disclosures: None

Integrative Approaches to Biomedical Science 20 th Century 21 st Century Biomedical Biomedical Science Science Reductionism Integration Molecular biology Comp Modeling Genomics Simulation parts Proteomics Bioengineering catalog Structural biology Courtesy: Prof. Andrew McCulloch

Big Data in Congenital Heart Disease ? Non-invasive B I O E N G I N E E R I N G imaging R A D I O L O G Y Registration and Structural/ characterization Functional Data modeling Acquisition M A T H E M A T I C S Better Dimension diagnosis reduction Statistical analysis “I can see it Analysis much more clearly now – C O M P U T E R S C I E N C E but I already M E D I C I N E knew that” Patient Pattern Software Diagnosis recognition Development Fonseca et al. Bioinformatics 27(16): 2288–2295; 2011

Computational cardiac atlas integrates huge amounts of otherwise disconnected information to discover the patterns that represent their internal logic or relationships

Prof. Alistair Young

You can tell by the shape… Mauger C et al 2019

What we set out to do …. Apply this approach to Population based Congenital Heart Disease cardiac modeling Model based cardiac MRI analysis Computer-aided cardiovascular diagnosis Personalized cardiac biomechanics

Ca Cardiac c Atlas of of Congeni Congenital He Hear art D t Dis iseas ase > 1000 patients CHD -Cardiac Atlas Project- Collaborative Project RCHSD,UC San Diego & University of Auckland (NIH funded-RO1)

Surgical repair in tetralogy of Fallot (ToF) Repaired Tetralogy of Fallot Transannular Patch VSD Patch Recruiting 1500 patients Suleiman, T. et al. Frontiers in (2015) ToF is the fastest growing population among patients with congenital heart disease

https://shaunwhite.com/

Cardiac MRI for Congenital Heart Disease Courtesy: Dr. Albert Hsiao

Stages of Pre-Surgical Modeling Computational Medical Imaging Image Processing Virtual Surgery Analysis Implement Optimal Surgical Option

STATISTICAL DISCOVERY PATIENT DATA SHAPE MODEL ATLAS Principal component Regression & CMR image data Guide-point modeling analysis clustering

Population based Cardiac Modeling Me Mean n LV end nd-dia diastolic olic sha hape e for or the fi five most ab abnorm rmal al modes re relative to the contro rol atlas Atlas-based analysis has the potential to reveal new measures of geometry and function, which may provide novel insights into the remodeling processes of disease

Model based Cardiac MRI analysis LV CIM, Auckland, New Zealand- Prof. Young Multicenter Study, UK- Bhuva et al

Biventricular Atlas Generation Biventricular Cardiac Image Modeler (CIM) Patient-Specific Model (3D+Time) Model Accumulation From Several Patients Shape Modes PCA

The most abnormal modes of systolic wall motion are detrimental to global LV function Predicted net effect on Mode of SWM Mean z-score LV EF (% pts.) 5 2.85 -9.61 2 1.68 -7.93 3 -2.11 -6.95 10 1.99 -1.60 18 -1.78 -1.23 4 1.29 -0.91 7 0.96 -0.81 13 -3.01 -0.80 9 0.35 -0.26 20 -0.29 -0.18 16 0.38 -0.17 19 1.16 -0.08 17 -0.27 -0.07 8 0.62 -0.05 11 0.33 -0.05 12 -0.06 0.00 14 -1.23 0.03 15 0.47 0.16 6 0.48 0.36 1 0.28 0.65 * p < 0.00125 for 2-sample t-test + p < 0.00125 for F-test of equal variance

ToF Atlas: Mode 1 (22.1%) Legend Wireframe ED Solid Mesh ES LV Endocardium Green RV Endocardium Blue Epicardium Red

Computer-aided Cardiovascular Diagnosis

Computer-aided Cardiovascular Diagnosis End-Diastolic Shape Patient 1 Patient 2 Patient 3 Patient 4 Patient 24 Patient 26 -0.7 1.7 Mode 1 -0.9 1.6 -0.7 2.2 2.9 0.8 Mode 2 0.6 3.1 1.6 -0.2 -0.7 2.3 Mode 3 1.3 1.4 -6.6 0.5 -3.5 -0.6 Mode 4 -1.5 -3.1 -1.6 0.1 Patient 1 Patient 3 Patient 24 Restrictive Valve Ventricular septal Moderately dilated • • • Motion defect Mild Hypertrophy Elongated and • • Mild Dilation curved LV shape • Patient 2 Patient 26 Mild Hypertrophy Low Function • •

Personalized Cardiac Biomechanics

Where are we going with this…. Machine-learning will enable discovery of imaging biomarkers related to: • Shape • Wall motion For earlier prediction of : • Heart remodeling • Clinical outcomes • Functional response to therapy “Personalized to Patients”

It of course takes a village…. Prof. Andrew McCulloch Prof. Alistair Young Prof. Jeff Omens Prof. James Perry AHA Precision Medicine Platform Grant Charlene Mauger Pau Medrano-Garcia Kathleen Gilbert Avan Suinesiaputra Dr. Hari Narayan Justin Ryan Sachin Govil Nick Forsch

Thank You