Cong enjoys working with our partners on projects such as the Simulacrum. He says working with our partner companies is “Fantastic, and remarkably educational. Always delighted to see them.” He enjoys the collaborative spirit of “…working through problems together from down at the data/code level to operational questions like IG assessment to project questions like analysis design”
Cong Chen
Principal Data Scientist (Epidemiology)
Dr Cong Chen is an HDI stalwart who led the work on the Simulacrum project and the Patient Pathway tool.
Cong studied Mathematics at Trinity College Cambridge before completing his PhD in Mathematical Logic at the University of Leeds. His current work at HDI involves applying statistics, algorithms and data architecture to design and develop the Simulacrum dataset and Patient Pathway work. He likes algorithm optimisation, problem solving, long baths with a good book and fruit salad.
Education and awards:
University of Leeds
– Oct 2014: Degree of Doctor of Philosophy in Mathematics, Thesis: Diamond-free Partial Orders
University of Cambridge
– July 2010: Degree of Master of Mathematics
– July 2009: Degree of Bachelor of Arts (Honours 1st Class) in Mathematics
Publications and Posters:
- Identification of Patient Prescribing Predicting Cancer Diagnosis Using Boosted Decision Trees. AIME 2019: 328-333 Josephine French, Cong Chen, Katherine Henson, Brian Shand, Patrick Ferris, Josh Pencheon, Sally Vernon, Meena Rafiq, David Howe, Georgios Lyratzopoulos, Jem Rashbass
- Creating the Best Risk-Utility Profile: The Synthetic Data Challenge Joint UNECE/Eurostat Work Session on Statistical Data Confidentiality
Jennifer Taub, Mark Elliot, Gillian Raab, Anne-Sophie Charest, Cong Chen, Christine M. O’Keefe, Michelle Pistner Nixon, Joshua Snoke, Aleksandra Slavković - Assessing the impact of loss-to-follow-up on cancer survival estimates: a simulation study
Ayako Okuyama, Matthew Barclay, Cong Chen, Takahiro Higashi
BMJ Open 2020;10:e033510. doi: 10.1136/bmjopen-2019-033510
Projects:
Syndasera
Reducing the rate of post-colonoscopy colorectal cancers (PCCRC) in England
Data Extraction Automation
The Simulacrum
