ASA LiDS webinar: dynamic prediction methods with Alessandro Gasparini

We're excited to announce that Alessandro Gasparini, then Principal Statistical Methodologist at Red Door Analytics, will be teaching a webinar on dynamic prediction methods as part of the American Statistical Association Lifetime Data Section's webinar series. This will be a two-hour tour of dynamic prediction methods, with a longer version of this course coming later in the year.

Prediction models in clinical settings are routinely developed using traditional, prospective study designs that define a baseline at which predictors are measured and from which to predict future risk. However, the increased availability and use of electronic health records and data registers provide a large wealth of dynamic information collected over time, information that is directly related to disease status, progression, cure, and relapse. Such information can be used to inform and individualise predictions based on a dynamic assessment of a patient's characteristics.

Several estimators have been proposed for the task of dynamic prediction, mainly from two approaches: joint modelling and landmarking. The workshop introduces both approaches for dynamic prediction, including clear definitions of risk estimators, various modelling strategies, and performance metrics, illustrated in practice using openly available observational data on heart function after surgery.