Predicting Patient Outcomes During and After Hospitalization Using - - PowerPoint PPT Presentation

▶

Nov 04, 2023 573 likes •680 views

Predicting Patient Outcomes During and After Hospitalization Using AI Aziz Nazha, MD Director, Center for Clinical Artificial Intelligence Associate Medical Director, Enterprise Analytics Assistant Professor of Medicine Lerner College of

SLIDE 1

Predicting Patient Outcomes During and After Hospitalization Using AI

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

SLIDE 2

216,221

46,864,534,945

Google Brain

SLIDE 3

Google Brain

SLIDE 4

Model Building

Algorithm Variable Importance Final Model ü 1 ü 2 EMR Data using NLP

SLIDE 5

Outcomes During Hospitalization (CCAI)

Between 1/2011- 5/2018

Abbreviations: ROC = Receiver Operating Characteristic, AUC= Area Under the Curve, RMSE = Root mean squared error

1,485,880 Hospitalization 708,089 Unique patients

SLIDE 6

Our Model Explainability for 30-days Hospital Readmissions

SLIDE 7

Our Model Explainability for Gender

SLIDE 8

Personalized Explanation of the Model Output

SLIDE 9

Conclusions

ü We build a personalized prediction model for hospital

utcomes

ü We used AI algorithm to learn something new

SLIDE 10

Cleveland Clinic

Every Life Deserves World Class Care.

E-mail: nazhaa@ccf.org