Ross Williams, MSc
Ross obtained his MSc (2017) in Data Science from King's College London having previously obtained his BSc in Physics and Philosophy from the same institution. His thesis focused on predicting the change in diastolic blood pressure level for patients being treated for hypertension based upon demographics and pharmacological intervention, a particular focus of this was on external validation of the developed models.
His current focus is on methodological research into external validation of prediction models. Including but not limited too assessment metrics, transportability and recalibration. Accordingly he has contributed code to the PatientLevelPrediction R package along these lines. Further lines of interest include the creation of a prediction model library, implementation of Association Rule mining, temporal data analysis and methods for dealing with class imbalance.
- Assists Dr. Rijnbeek in the teaching of data science to students of the “Klinische Technology” Master of Science program. This course aims to provide students the fundamentals of machine learning in a medical context. The course includes practical exercises that focus on the development of clinical prediction models. Ideally, this course is further extended to a full curriculum on health data science to teach all medical students at the Erasmus MC the basics of this exciting multidisciplinary field.
- Teaches on the Patient-Level Prediction tutorial day. A day organised around the OHDSI Symposiums and at other times during the year which teaches students the why, what and how of running a clinical prediction model using the OHDSI tools.
Prediction Modelling Autumn School, King's College London, November 2017.
Population Health Management course Advanced Risk Stratification, Leiden UMC, May 2018.
- Young Researcher in the Spotlight, HealthySciencesDay, ErasmusMC, April 2019.
- "Predicting adverse events following total knee replacement", ISPE 2019, Philadelphia, August 2019
- "Predicting Heart Failure in PAtients newly initialising treatment for type 2 diabetes", OHDSI Symposium 2018, October 2018.
2019 Titan Award for Clinical Application, OHDSI Symposium, Bethesda, September 2019