Artificial Intelligence in Healthcare The Cleveland Clinic Way Aziz - - PowerPoint PPT Presentation
Artificial Intelligence in Healthcare The Cleveland Clinic Way Aziz Nazha, MD Director, Center for Clinical Artificial Intelligence Associate Medical Director, Enterprise Analytics Assistant Professor of Medicine Lerner College of
Aziz Nazha, MD
Director, Center for Clinical Artificial Intelligence Associate Medical Director, Enterprise Analytics Assistant Professor of Medicine Lerner College of Medicine / CWRU Taussig Cancer Institute Cleveland Clinic
@AzizNazhaMD
Artificial Intelligence Machine Learning
Supervised Learning Unsupervised Learning
Deep Learning
Input Output
Variables Image Text Classification Regression Algorithm
Stage Diagnosis Treatment
Higher Risk Lower Risk
ü Transplant ü Azacitdine (6 months) ü Decitabine (6 months) ü Supportive care ü Growth factors ü Others
Stage Diagnosis Treatment
ü Subjective ü 30-40% is changed ü Dysplasia not enough to call it MDS ü Predicted outcome = Actual outcome ü Significant difference Uncertainty in predicting response or resistance
A Esteva et al. Nature 1–4 (2017) doi:10.1038/nature21056
Normal MDS AML Normal MDS AML
+
Algorithm Variable Importance Final Model ü 1 ü 2 Clinical + Mutational
Survival
IPSS-R
Demographic Clinical Genomics
Random Survival Forest Data Important Variables
Training CC + MLL
X
Validation Moffitt
Final Model
Azacitidine Decitabine
FDA approved Response Rate Treatment duration
Association Rules (Recommender System)
Mentor 1 Mentor 2
? ?
?
Association Rules (Recommender System)
Mentor 1 Mentor 2
Patient 1 Patient 2
Response (HMA)
ASXL1 TET2 RUNX1 TP53 RCOR SRSF2
Resistance (HMA)
Association Rules (Recommender System)
Association Rules (Resistance) ASXL1, NF1 ASXL1, EZH2, TET2 ASXL1, EZH2, RUNX1 EZH2, SRSF2, TET2 ASXL1, EZH2, SRSF2 ASXL1, RUNX1, SRSF2 ASXL1, TET2, SRSF2 ASXL1, BCOR, RUNX1
Rules Validation
Accuracy: 93% in the Validation cohort
29% pts > 3 mutations/sample
Association Rules
CRISPR/cas9 Multiplex CRISPR/cas9
1 2 3 4 5 6 0 .0 0 .5 1 .0 D e cita b in e , µ M V iability T E T 2 M T T E T 2 M T /S R S F 2 M T /R U N X 1 M T
In the Lab
To harness the power of AI to advance medicine and transform healthcare Become the world’s largest and most collaborative center for innovation and advancement of AI in healthcare
Cancer
Diagnosis
q Project 1 q Project 2 q Project 3
Prognosis
q Project 5 q Project 6 q Project 7 q Project 8
Predicting Response to Therapy
q Project 9 q Project 10 q Project 11 q Project 12
Medicine
Hospital Operation
q Project 13 q Project 14 q Project 15 q Project 16
Respiratory
ICU
q Project 17 q Project 18
Asthma
q Project 19
Pediatric
q Project 20 q Project 21
Others
Omics
q Project 22
Liver/GI
q Project 23
Cardiology
q Project 24
AI for healthcare providers course Cleveland Clinic June 10-26 Medical School AI track Lerner college of medicine Computer Science School Healthcare course Case Western Reserve University
continuous improvement of candles”
Cleveland Clinic
Mikkael Sekeres, MD, MS Jaroslaw Maciejewski, MD, PhD Brian Bolwell, MD Matt Kalaycio, MD Anjali Advani, MD Sudipto Mukherjee, MD, PhD Aaron Gerds, MD, MS Hetty Carrawy, MD, MBA Betty Hamilton, MD Ronald Sobecks, MD Navneet Majhail, MD Maciejewski’s lab Babl Jha’s Lab Leukemia nurses and staff
Moffitt Cancer Center
Alan List, MD Rami Komrokji, MD Eric Padron, MD David Sallman, MD Johns Hopkins Amy DeZern, MD
Cornell
Gail Roboz, MD
Dana Farber
David Steensma, MD Benjamin Ebert, MD Coleman Lindsley, MD, PhD University of Florence Valeria Santini, MD
France
Eric Solary, MD Rafael Itzykson, MD, PhD
All Patients!!!
MLL
Torsten Haferlach, MD Claudia Haferlach, MD Manja Megendorfer, MBA Wencke Walter, PhD Stephan Hutter, PhD
Guillermo Garcia-Manero, MD Hagop Kantarjian, MD
MD Anderson
K12
Nazha Lab
Orkun Balglo, MD Ping Chao, MD Jacob Shreve, MD Amin Moein, MD Cameron B Hilton Nathan Radakovich Rachel Shirly, PhD Yazan Rouphail Stephen Kemura
Every Life Deserves World Class Care.