New #AI initiative ASCO: Check out the first meeting of the #AI Community of Practice ( #CoP ) this Friday #ASCO24 ! We're gathering a community of clinicians, researchers, implementers, & educators looking to integrate AI responsibly in #oncology practice. conferences.asco.org/am/communities…

Artificial intelligence use in prostate cancer encompasses 4 main areas including diagnostic imaging, prediction of outcomes, histopathology, and treatment planning. #pcsm | James Yu
Julian Hong

cancernetwork.com/view/ai-use-in…

Peter Szolovits, PhD, discusses the capabilities and incomprehensibility of large language models (LLMs) and their use in medicine. Read the Perspective “Large Language Models Seem Miraculous, but Science Abhors Miracles”: nejm.ai/4aqBIqe

CancerNetwork® Ibrahim Halil SAHIN, MD Written with Julian Hong. Check out the super intense AI generated illustration prompted by @cancernetwrk team that accompanies the article

Artificial intelligence use in prostate cancer encompasses 4 main areas including diagnostic imaging, prediction of outcomes, histopathology, and treatment planning. #pcsm #radonc | James Yu Julian Hong

cancernetwork.com/view/ai-use-in…

Congratulations to all the winners including our very own Ali Sabbagh, MD from UCSF Helen Diller Family Comprehensive Cancer Ctr #radonc UCSF Bakar Computational Health Sciences Institute UC Joint Computational Precision Health Program (and incoming Memorial Sloan Kettering Cancer Center resident)!

The 2024 ROI Publication Excellence Awards call for nominations is now open! Early career #RadOnc researchers can apply to win $1,500💵and be honored🏆at #ASTRO24 . Visit bit.ly/ROI_Publicatio… for more information!

ARRO ASTRO ACROresident SWRO

Discovery, yes. But also analysis of cost reduction through ML use: Julian Hong and colleagues recognized for their groundbreaking work in NEJM AI . ai.nejm.org/doi/full/10.10… #ML

Identifying a high-risk group using ML associated with decreased costs in an RCT (secondary analysis) NEJM AI ai.nejm.org/doi/full/10.10… We need more studies like these if we expect healthcare to pay for ML. #AI

In a single-institution, randomized controlled study, electronic health record–based machine learning accurately identified patients at high risk for acute care during radiotherapy and targeted them for supplemental clinical evaluations. Full results: nejm.ai/3wNDiEj

Original Article: Health Care Cost Reductions with Machine Learning–Directed Evaluations during Radiation Therapy — An Economic Analysis of a Randomized Controlled Study nejm.ai/3wNDiEj

Are medical studies being written with ChatGPT?

Well, we all know ChatGPT overuses the word 'delve'.

Look below at how often the word 'delve' is used in papers on PubMed (2023 was the first full year of ChatGPT).

A machine learning approach with daily step counts from wearable devices from three prospective trials to predict unplanned hospitalization of patients undergoing chemoradiation was developed and validated in this study. ja.ma/4ax3WA1

Gohlke

Too busy to work in the rule changes by Kaggle to participate this year but here are some up-front #marchmadness probabilities anyway!

Saving money and improving care: RCT by @Julian_Hong and colleagues in NEJM AI shows how machine learning can reduce costs and acute care incidents for patients receiving radiation therapy. UCSF Bakar Computational Health Sciences Institute UCSF Helen Diller Family Comprehensive Cancer Ctr buff.ly/3wUDa5Z

Come by Ji Hyun Chang’s poster looking at patient portal (MyChart) messages at UCSF Helen Diller Family Comprehensive Cancer Ctr! Ji Hyun Chang applied #NLP approaches to identify common topics to hopefully improve triage (and reduce physician burnout)!

#is24

UCSF Bakar Computational Health Sciences Institute UC Joint Computational Precision Health Program