Assistant Professor
Department of Mathematics and Computer Science
Emory University

Contact

: joyce.c.ho AT emory.edu
: (404)-727-5605, Fax: (404) 727-5611
: Mathematics and Science Center, W414
: 400 Dowman Dr, Atlanta, GA 30322
Picture

Short Bio

I'm an assistant professor in the Department of Mathematics and Computer Science at Emory University. I received my Ph.D. from the Electrical and Computer Engineering Department at UT-Austin, co-advised by Dr. Joydeep Ghosh (Intelligent Data Analysis Exploration Lab) and Dr. Sriram Vishwanath (Laboratory for Informatics, Networks, and Communications). I'm also a co-founder and the chief data scientist of Accordion Health. We are a healthcare data analytics startup that provides targeted guidance using predictive analytics.

Prior to UT, I graduated from MIT with a B.S and M.Eng degree from the Electrical Engineering and Computer Science Department. After graduation, I worked at Lawrence Livermore National Laboratory on various projects before returning to graduate school. For more details, view my CV.

Recent News

2017 Distinguished Clinical Research Informatics Paper Award
Emory
CIKM 2017
Short Research Paper Chair for CIKM 2017
Joining Emory University's Mathematics and Computer Science Department as assistant professor
  • I'm looking for students! Apply to our program by January 3rd.
Emory
2015 Healthcare Symposium
KDD 2014 Student Travel Award Winner
KDD2014
Datapalooza
Accordion Health wins 2014 Health Datapalooza Award
  • Listen to Dr. Alvi, our Chief Medical Officer, talk about the company on NPR
  • Watch the award ceremony
  • Read the US Department of Health and Human Services press release
Accordion Health is awarded a Phase I NSF SBIR
NSF

Research Interests

My research interests encompass the intersection of data mining / machine learning and healthcare analytics. My work focuses on missing data, disease-specific risk prediction, temporal analysis, and dimensionality reduction. Read more details about my research projects here.

Selected Publications

For the full publication list, see the publications page.

  1. Marble: High-throughput phenotyping from electronic health records via sparse nonnegative tensor factorization. KDD 2014.
  2. Limestone: High-throughput candidate phenotype generation via tensor factorization. Journal of Biomedical Informatics 2014.
  3. Septic shock prediction for patients with missing data. ACM Transactions on Management Information Systems 2014.
  4. DYNACARE: Dynamic cardiac arrest risk estimation. AISTATS 2013.
  5. Risk prediction of a multiple sclerosis diagnosis. ICHI 2013.

Service