Converting data into personalized cancer care.

Integrating clinical knowledge and data science

We integrate knowledge of the underlying details of clinical data with machine learning expertise to guide algorithmic development.

Uncovering insights from real world data

We apply computational methods for real world data-driven clinical knowledge discovery and hypothesis generation.

Crossing multiple data streams

We extract and combine information from multi-modal data sources to generate insights and predictions.

Bringing personalized and actionable decision making to patient care

We work from end-to-end through development, validation, and prospective evaluation with the goal of precision cancer care.




The Hong Lab is part of the Department of Radiation Oncology and Bakar Computational Health Sciences Institute at the University of California, San Francisco (UCSF).



Our research

Bringing machine learning to the clinic

The primary goal of our lab is to develop computational analyses and tools that reach patient care to improve  outcomes. The convergence of machine learning and expansive routine clinical data enable the development of automated predictive models which can be integrated into the clinical workflow to personalize care.

We have developed predictive tools with a range of complexity, including identifying favorable characteristics in patients with oligometastatic cancers (Hong, PLOS ONE 2018) and predicting testosterone recovery following androgen deprivation (Spiegel, Int J Radiat Oncol Biol Phys 2019). Among these, we developed an electronic health record-based machine learning algorithm to predict acute care visits during outpatient cancer therapy (Hong, JCO Clin Cancer Inform 2018). This tool was recently evaluated in one of the first prospective randomized studies of clinical machine learning, demonstrating that its use directed clincial management to reduce rates of acute care during cancer therapy (Hong, J Clin Oncol 2020).



Learning from real world data

Real world data offers insights into practice patterns and may generate knowledge where prospective trials are not feasible or do not sufficiently generalize to patients. We analyze data from electronic health records, national databases, institutional experiences, claims data, and payor data to both learn from prior experiences and characterize data limitations.

We have evaluated practice patterns in a range of cancers including lung (Hong, J Natl Compr Canc Netw 2019), prostate, and gynecologic malignancies. Among these studies, we have used Medicare provider data to identify disparities in access to specialized therapies for prostate and gynecologic malignancies (Hong, Brachytherapy 2018).



Synthesizing multi-modal data

Routine clinical practice generates multi-modal complementary data, including imaging, pathology slides, laboratory time series, and -omics. We apply methods to generate quantitative features from this complementary data to generate new analyses.

Imaging can be converted into quantitative features which can complement other sources of data. Additionally, it may offer a proxy for other forms of clinical data. We have applied quantitative imaging approaches to a number of oncologic questions, including prediction of outcomes by PET/CT during treatment of anal (Hong, Int J Radiat Oncol Biol Phys 2018) and esophageal (Tandberg, Int J Radiat Oncol Biol Phys 2018) cancers, as well as other clinical applications such as the approximation of pulmonary function tests based on CT (Lafata, Sci Rep 2019).



Unlocking unstructured clinical data

Large amounts of data are captured in free-text clinical notes, which can pose challenges to clinical study. Extracting this unstructured information can both inform clinical research and facilitate deployable computational tools.

We have adapted clinical natural language processing pipelines to extract patient outcomes during cancer therapy from routine clinical documentation. Our studies indicate high variability even among human experts, which may motivate the use of systematic computational approaches (Fairchild, Int J Radiat Oncol Biol Phys 2020).


Our team

Julian Hong, MD, MS

Principal Investigator

William Chen, MD

Resident Physician

UCSF Radiation Oncology

Andrew Fairchild, MD, MA

Resident Physician

Duke Radiation Oncology

Meera Garriga, BA

Medical Student


Havish Kantheti, MS

Medical Student

Texas A&M College of Medicine

Anthony Lin, MD

Resident Physician

UCSF Internal Medicine

Kevin Miao


UC Berkeley Data Science

Divya Natesan, MD

Resident Physician

Duke Radiation Oncology

Shawn Patel


UC Berkeley Electrical Engineering and Computer Science

Sumi Sinha, MD

Resident Physician

UCSF Radiation Oncology

Saira Somnay


UC Berkeley Molecular and Cellular Biology

Clark Wang


UC Berkeley Computer Science

Jon Wang, MS

Medical Student


Eric Xu


Stanford University Economics

Sasha Yousefi


UC Berkeley Data Science



Atul Butte, MD, PhD (Bakar Computational Health Sciences Institute, UCSF)

Lauren Boreta, MD (Radiation Oncology, UCSF)

Steve Braunstein, MD, PhD (Radiation Oncology, UCSF)

Felix Feng, MD (Radiation Oncology, UCSF)

Osama Mohamad, MD, PhD (Radiation Oncology, UCSF)

Olivier Morin, PhD (Radiation Oncology, UCSF)

Catherine Park, MD (Radiation Oncology, UCSF)

Manisha Palta, MD (Radiation Oncology, Duke University)

Jessie Tenenbaum, PhD (North Carolina Department of Health and Human Services; Biostatistics and Bioinformatics, Duke University)

Daphna Spiegel, MD, MS (Radiation Oncology, Beth Israel Deaconess Medical Center; Harvard Medical School)


Nishali Naik, BA - Aon


Join us!

Our group is always interested in finding new lab members and collaborators to contribute with clinical domain knowledge or computational expertise. Join our multidisciplinary team of clinicians and scientists in the Department of Radiation Oncology and the Bakar Computational Health Sciences Institute. Lab members are also be encouraged to take advantage of other training and learning opportunities within the UCSF Helen Diller Family Comprehensive Cancer Center, the Bakar Computational Health Sciences Institute, and other related entities at UCSF.

If you are interested in joining the lab or collaborating on research in a role not listed below, please contact us.

Post-doctoral opportunities

We are recruiting highly motivated investigators to develop algorithms and analyses with multi-modal clinical data to guide personalized oncology care. Projects will be tailored to the individual's prior experience and interests but will center on the utilization of computational techniques to drive clinical prediction or discover new clinical insights using routine clinical data (including electronic health records, imaging, digital pathology, and genomic data).

Ideal candidates will have an MD and/or PhD with a strong background in bioinformatics or related computational science and demonstrated publication record. Strong problem-solving skills, creative thinking, and programming ability are required. Applicants must possess good communication skills and be fluent in both spoken and written English. Prior experience in machine learning, natural language processing, network analysis, and computer vision are a plus.

The post-doctoral fellow will join a multidisciplinary team of clinicians and scientists in the Department of Radiation Oncology and the Bakar Computational Health Sciences Institute.

Interested candidates may send their CV, a brief statement of research interests, and contact information for three references to julian [dot] hong [at] ucsf [dot] edu.

Undergraduate and post-baccalaureate opportunities

Our lab welcomes undergraduates and recent graduates with an interest in medicine and informatics to join us. We hope that this experience will provide preparation for future opportunities in medicine and informatics. Clinical shadowing opportunities are available to those interested.

UC Berkeley students can apply through the Undergraduate Research Apprentice Program.

We are recruiting for a Data Science Research Specialist, application available on UCSF Recruit.

Clinical trainee opportunities

Our lab welcomes medical students, residents, and fellows from all backgrounds to join us. Projects can be tailored based on the trainee's areas of interest and computational experience (not required).

UCSF medical students and trainees can apply at UCSF LabSpot.



Selected publications


System for High-Intensity Evaluation During Radiation Therapy (SHIELD-RT): A Prospective Randomized Study of Machine Learning–Directed Clinical Evaluations During Radiation and Chemoradiation. Hong JC, Eclov NCW, Dalal NH, Thomas SM, Stephens SJ, Malicki M, Shields S, Cobb A, Mowery YM, Niedzwiecki D, Tenenbaum JD, Palta M. J Clin Oncol. 2020 Sep 4:JCO2001688. doi: 10.1200/JCO.20.01688. PMID: 32886536 

Closing the Gap Between Machine Learning and Clinical Cancer Care-First Steps Into a Larger World. Kang J, Morin O, Hong JC. JAMA Oncol. 2020 Sep 24.doi: 10.1001/jamaoncol.2020.4314. doi: 10.1001/jamaoncol.2020.4314. PMID: 32970129.

Inter-rater reliability in toxicity identification: Limitations of current standards. Fairchild AT, Tanksley JP, Tenenbaum JD, Palta M, Hong JC. Int J Radiat Oncol Biol Phys. 2020 May 1. pii: S0360-3016(20)31084-1. doi: 10.1016/j.ijrobp.2020.04.040. PMID: 32371073.


An Exploratory Radiomics Approach to Quantifying Pulmonary Function in CT Images. Lafata KJ, Zhou Z, Liu JG, Hong J, Kelsey CR, Yin FF. Sci Rep. 2019 Aug 8;9(1):11509. doi: 10.1038/s41598-019-48023-5. PMID: 31395937.

A Nomogram for Testosterone Recovery After Combined Androgen Deprivation and Radiation Therapy for Prostate Cancer. Spiegel DY, Hong JC, Oyekunle T, Waters L, Lee WR, Salama JK, Koontz BF. Int J Radiat Oncol Biol Phys. 2019 Mar 15;103(4):834-842. doi: 10.1016/j.ijrobp.2018.11.007. Epub 2018 Nov 10. PMID: 30419308.

Increasing PET Use in Small Cell Lung Cancer: Survival Improvement and Stage Migration in the VA Central Cancer Registry. Hong JC, Boyer MJ, Spiegel DY, Williams CD, Tong BC, Shofer SL, Moravan MJ, Kelley MJ, Salama JK. J Natl Compr Canc Netw. 2019 Feb;17(2):127-139. doi: 10.6004/jnccn.2018.7090. PMID: 30787126.

Radiotherapy Treatment Planning in the Age of AI: Are We Ready Yet? Zheng D, Hong JC, Wang C, Zhu X. Technol Cancer Res Treat. 2019 Jan-Dec;18:1533033819894577. doi: 10.1177/1533033819894577. PMID: 31858890.

Artificial Intelligence in Radiotherapy Treatment Planning: Present and Future. Wang C, Zhu X, Hong JC, Zheng D. Technol Cancer Res Treat. 2019 Jan 1;18:1533033819873922. doi: 10.1177/1533033819873922. PMID: 31495281.


Predicting Emergency Visits and Hospital Admissions During Radiation and Chemoradiation: An Internally Validated Pretreatment Machine Learning Algorithm. Hong JC, Niedzwiecki D, Palta M, Tenenbaum JD. JCO Clin Cancer Inform. 2018 Dec;2:1-11. doi: 10.1200/CCI.18.00037. PMID: 30652595.

High-volume providers and brachytherapy practice: A Medicare provider utilization and payment analysis. Hong JC, Spiegel DY, Havrilesky LJ, Chino JP. Brachytherapy. 2018 Nov-Dec;17(6):906-911. doi: 10.1016/j.brachy.2018.07.007. Epub 2018 Jul 26. PMID: 30057292.

Intratreatment Response Assessment With 18F-FDG PET: Correlation of Semiquantitative PET Features With Pathologic Response of Esophageal Cancer to Neoadjuvant Chemoradiotherapy. Tandberg DJ, Cui Y, Rushing CN, Hong JC, Ackerson BG, Marin D, Zhang X, Czito BG, Willett CW, Palta M. Int J Radiat Oncol Biol Phys. 2018 Nov 15;102(4):1002-1007. doi: 10.1016/j.ijrobp.2018.07.187. Epub 2018 Jul 25. PMID: 30055238.

Association of Interim FDG-PET Imaging During Chemoradiation for Squamous Anal Canal Carcinoma With Recurrence. Hong JC, Cui Y, Patel BN, Rushing CN, Faught AM, Eng JS, Higgins K, Yin FF, Das S, Czito BG, Willett CG, Palta M. Int J Radiat Oncol Biol Phys. 2018 Nov 15;102(4):1046-1051. doi: 10.1016/j.ijrobp.2018.04.062. Epub 2018 May 4. PMID: 29891206.

Classification for long-term survival in oligometastatic patients treated with ablative radiotherapy: A multi-institutional pooled analysis. Hong JC, Ayala-Peacock DN, Lee J, Blackstock AW, Okunieff P, Sung MW, Weichselbaum RR, Kao J, Urbanic JJ, Milano MT, Chmura SJ, Salama JK. PLoS One. 2018 Apr 12;13(4):e0195149. doi: 10.1371/journal.pone.0195149. PMID: 29649281.

Contact us


UCSF Bakar Computational Health Sciences Institute

Box 0110

480 16th St, Floor 2

San Francisco, CA 94158

julian [dot] hong [at] ucsf [dot] edu

UCSF Precision Cancer Medicine Building

1825 4th St, Suite L1101

San Francisco, CA 94158

Back to top