1 code implementation • 6 Nov 2023 • Arina Odnoblyudova, Çağlar Hızlı, ST John, Andrea Cognolato, Anne Juuti, Simo Särkkä, Kirsi Pietiläinen, Pekka Marttinen
By differentiating treatment components, incorporating their dosages, and sharing statistical information across patients via a hierarchical multi-output Gaussian process, our method improves prediction accuracy over existing approaches, and allows us to interpret the different effects of carbohydrates and fat on the overall glucose response.
no code implementations • 9 Sep 2022 • Çağlar Hızlı, ST John, Anne Juuti, Tuure Saarinen, Kirsi Pietiläinen, Pekka Marttinen
Our model enables the estimation of a treatment policy from observational sequences of treatments and outcomes, and it can predict the interventional and counterfactual progression of the outcome after an intervention on the treatment policy (in contrast with the causal effect of a single treatment).
1 code implementation • 10 Jun 2019 • Guangyi Zhang, Reza Ashrafi, Anne Juuti, Kirsi Pietiläinen, Pekka Marttinen
Estimating the effect of a treatment on a given outcome, conditioned on a vector of covariates, is central in many applications.