Google's Med-PaLM 2: The Future of AI-Driven Medical Answers
Blog

Google’s Med-PaLM 2: The Future of AI-Driven Medical Answers

Google Health recently announced updates about its latest health initiatives and partnerships, which include tools for building health apps, AI-assisted ultrasounds, and cancer treatments. However, what created a buzz is the second version of its medical large language model called Med-PaLM 2.

What is Med-PaLM 2?

Med-PaLM 2 is an AI system that is designed to provide high-quality responses to medical questions. Its first iteration was launched last year, and it received a passing score of over 60% on multiple-choice style questions. The latest version of the technology consistently performs at an “expert” level on medical exam questions and has achieved an accuracy rate of over 85%, scoring 18% higher than its earlier version.

Dr. Alan Karthikesalingam, a research lead at Google Health, highlighted that the company is evaluating Med-PaLM 2’s answers against responses from real doctors and clinicians. The responses are evaluated for factual accuracy, bias, and potential for harm. In some cases, Med-PaLM 2’s answers were on par, and even more detailed, than the answers provided by clinicians. However, in other cases, the responses were not as accurate.

While the potential of Med-PaLM 2 is tremendous, Karthikesalingam emphasized the importance of responsible innovation in a controlled environment, given the sensitive nature of medical information. Thus, it could take some time before this technology becomes available to the average consumer.

Read Also: Google releases new AI features in its productivity apps

Final Words

Google plans to continue working with experts and researchers on Med-PaLM, and will share more updates in the future. With its remarkable accuracy, Med-PaLM 2 has the potential to transform the way people access and receive medical information. However, it’s essential to explore its real-world applications in an ethical and responsible manner.

What is your reaction?

Excited
0
Happy
0
In Love
0
Not Sure
0
Silly
0
Emily Davis
Emily is a machine learning engineer. She is dedicated to using AI to make a positive impact in the world. When she's not working, she enjoys reading and trying new recipes in the kitchen.

You may also like

More in:Blog