Research

Due diligence research:

Pre-FDA 510k process analysis
Data set definition, size, preparation, vendor and reference assessment
Data labelling process assessment
Algorithm training, testing and validation assessment
Quality Assurance and Feedback Mechanism
Industry landscape and competitive evaluation
Radiology and medical use case analysis

There are over 10,000 conditions and findings I look for each day.

There are 67 FDA approved AI algorithms for radiology.

There is a gap to be filled with start ups.

Recent Presentations:

Predicting Disease with AI – Panel Session

Udacity AI for Healthcare: Virtual Conference, May 2020 Link

Artificial Intelligence And The Future Of Medicine

NAMDRC, Phoenix, AZ, March 2020 Link

Integrating AI into Medical Imaging Workflow

ICRM, Riyadh, Saudi Arabia, February 2020 Link

2019 YEAR IN REVIEW: MACHINE LEARNING IN HEALTHCARE

Link

American Medical Association Physician Innovation Network Spotlight

July 2019 Link

Who I’ve helped

A RADIOLOGIST’S INTRODUCTION TO AI AND MACHINE LEARNING

Leigh and I wrote this book to help radiologists.

With all of the news of artificial intelligence and machine learning it can be daunting to find a place to start.

You will need no computer background to read this book.

Program directors or professors may use this a tool to introduce AI and ML to trainees.

The book will present the difference between artificial intelligence, machine learning and neural networks. You will learn that a neural network is similar to human brains and ‘layers’ are similar to synapses.

Just like the first few years of medical school presented new vocabulary, ML and AI have some particular words that are described simply.

There are some similarities between residency training and ‘training an algorithm’ which will be explained.

After reading this book, you will be prepared to read radiology journal articles that showcase AI and ML applications.

Available On Amazon