Julian Hong
julianhong.bsky.social
Julian Hong
@julianhong.bsky.social
Radiation oncologist • Director of #radonc #informatics @UCSFCancer.bsky.social • Computational scientist @ucsf-bchsi.bsky.social @ucjointcph.bsky.social

Data and AI -> cancer care

clone wars historian • LEGO collector • BBQ amateur

honglab.ucsf.edu
Reposted by Julian Hong
Join our special Oct. UCSF AI Seminar Series, 10/31! Costumes Encouraged/Refreshments served (or Zoom)! We'll honor Atul Butte's enduring legacy showcasing projects built on the computational ecosystem he created @ucsanfrancisco.bsky.social @julianhong.bsky.social calendar.ucsf.edu/event/semina...
October 16, 2025 at 7:51 PM
Reposted by Julian Hong
I heard this morning that my informatics colleague Dr. Atul Butte passed after a battle with cancer. He was a giant in the field & inspired many of us over his distinguished career. He was a passionate champion of the power of big data & his impact on our field is immeasurable. RIP Atul & thanks.
June 14, 2025 at 1:20 PM
Reposted by Julian Hong
"All the data in the world will not make a difference, unless there are people ready to use it."

— Atul Butte, MD, PHD, FACMI
2024 Morris F. Collen Award Winner
November 16, 2024 at 1:58 AM
Reposted by Julian Hong
So…about AI’s energy use…

“…to create a five-second video, a newer AI model uses ‘about 3.4 million joules, more than 700 times the energy required to generate a high-quality image’. That's the equivalent of running a microwave for over an hour.”
Report: Creating a 5-second AI video is like running a microwave for an hour
That's a long time in the microwave.
mashable.com
May 22, 2025 at 5:04 PM
Reposted by Julian Hong
Frontiers in Computational Health conference - Marianna Elia at poster externally validating model
Predicting ER visits & hospitalizations during #radonc treatments @ucsanfrancisco.bsky.social @julianhong.bsky.social @ucsfcancer.bsky.social @UCJointCPH.bsky.social ascopubs.org/doi/10.1200/JC…
April 29, 2025 at 7:34 PM
Reposted by Julian Hong
From @julianhong.bsky.social lab led by Chichi Chang - used natural language processing to evaluate symptoms experienced by >28k patients w/ cancer prior to emergency visits and hospitalizations @ucsfcancer.bsky.social @ucsanfrancisco.bsky.social JAMA Network Open: jamanetwork.com/journals/jam...
April 24, 2025 at 5:51 PM
Reposted by Julian Hong
Editorial:
Identifying the appropriate target for an #AI intervention in a health care system is of utmost importance... socioeconomic, behavioral, and systemic issues [are] not easily navigable with technology as it stands

@julianhong.bsky.social
@jama.com
Considerations in Translating AI to Improve Care
The potential impact of artificial intelligence (AI) on personalized medicine, clinical decision support, clinical workflow optimization, and health care management has attracted the attention of pati...
jamanetwork.com
April 23, 2025 at 12:59 PM
Excited to share our latest paper in @jmirpub.bsky.social led by Dr. Daphna Spiegel of @bidmc-cancercenter.bsky.social #radonc

Social media conversations are important resources for patients making decisions in breast cancer treatment. We applied #AI #NLP to characterize these conversations #bcsm
Exploring the Social Media Discussion of Breast Cancer Treatment Choices: Quantitative Natural Language Processing Study
Background: Early-stage breast cancer has the complex challenge of carrying a favorable prognosis with multiple treatment options, including breast conserving surgery (BCS) or mastectomy. Social media...
cancer.jmir.org
January 31, 2025 at 6:41 PM
Reposted by Julian Hong
New in #JCOOP: “Toxicity in phase III oncology clinical trials is often incompletely reported and is frequently minimized in its interpretation. Industry-sponsored trials more comprehensively report toxicity than do cooperative group–sponsored trials.” ascopubs.org/doi/10.1200/...
#JCOJournals
Incomplete Toxicity Reporting and Use of Toxicity-Minimizing Language in Phase III Oncology Trials | JCO Oncology Practice
PURPOSEThis study aimed to determine complete toxicity reporting (CTR), and the use of subjective toxicity-minimizing language (TML) among phase III oncology trials.METHODSTwo-arm superiority-design p...
ascopubs.org
January 9, 2025 at 12:02 PM
Reposted by Julian Hong
It is with great sadness that we mourn our cherished friend and colleague Felix Feng, MD. Felix was a distinguished physician-scientist and beloved at @ucsfhealth.bsky.social. His vision, dedication, and commitment inspired colleagues, peers everywhere, and patients. cancer.ucsf.edu/in-memoriam-...
December 14, 2024 at 12:00 AM
Reposted by Julian Hong
Heartbroken💔we lost Dr. Felix Feng— close friend, selfless collaborator, brilliant scientist. We miss you--too early my friend.

To all: please consider supporting this ACS/ASTRO award in Felix name:

donate.cancer.org/g/tjjfqwdnrxrl…?
I just helped save a life
You can save one, too. Donate now.
https://donate.cancer.org/g/tjjfqwdnrxrl…
December 12, 2024 at 10:48 PM
Excited to share our latest paper evaluating large language models in assessing oncology radiology reports. Led by superstars Travis Zack and CPH student Li-Cheng Chen!
@atulbutte.bsky.social

Annotated reports included

@ucsf-bcshi.bsky.social @ucsfcancer.bsky.social

ascopubs.org/doi/10.1200/...
Assessing Large Language Models for Oncology Data Inference From Radiology Reports | JCO Clinical Cancer Informatics
PURPOSEWe examined the effectiveness of proprietary and open large language models (LLMs) in detecting disease presence, location, and treatment response in pancreatic cancer from radiology reports.ME...
ascopubs.org
December 11, 2024 at 10:18 PM
Reposted by Julian Hong
The next offering of the AMIA-OHSU introductory course in biomedical and health informatics begins next week! More information and registration at: www.amia.org/education-ev...
AMIA 10x10 with Oregon Health & Science University
Introduction to Biomedical and Health Informat
www.amia.org
November 27, 2024 at 5:22 PM
Happy Thanksgiving!
November 28, 2024 at 5:20 PM
One of the main goals of healthcare #AI has been to reduce burnout.

Interesting study showing radiology AI use correlated with burnout (interacting with workload+acceptance). Good accompanying commentary too!

Burnout is complex, workflows/human factors matter.

jamanetwork.com/journals/jam...
Artificial Intelligence and Radiologist Burnout
This cross-sectional study investigates whether there is an association between artificial intelligence (AI) use in radiology and radiologist burnout in China.
jamanetwork.com
November 25, 2024 at 4:13 PM
Reposted by Julian Hong
🎨 In case anyone need…

The NIH BioArt Source is an awesome library of *free* professionally drawn illustrations for scientific presentations or figures. Downloadable in HD. Thank you NIH for this invaluable tool 🙏!

Check it out 👇
bioart.niaid.nih.gov
November 23, 2024 at 3:50 PM
Reposted by Julian Hong
How it started: "AI is going to replace randomized clinical trials"

How it is going:
ai.nejm.org/doi/10.1056/...
We Need More Randomized Clinical Trials of AI
In the first prospective clinical trial of artificial intelligence (AI) assistance in stress echocardiography, there was no difference in diagnostic accuracy between AI assistance and standard-of-c...
ai.nejm.org
November 20, 2024 at 5:08 PM