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 team

Julian Hong, MD, MS

Principal Investigator

Anthony Lin, MD

Resident

 

Collaborators

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

Felix Feng, MD (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)

Donna Niedzwiecki, PhD (Biostatistics and Bioinformatics, Duke University)

Kyle Lafata, PhD (Radiation Oncology, Duke University)

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

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 a prospective randomized study (results are pending).

 

 

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, 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).

 

 

 

Positions

Join us!

Our group is always interested in finding new lab members and collaborators to contribute in either or both of 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

Officially posting soon. Contact us for more details.

Undergraduate and post-baccalaureate opportunities

Officially posting soon. Contact us for more details.

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.

 

 

Contact us

 

UCSF Mission Hall

550 16th St

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