Machine-Learning Methods

Advancing machine-learning methods to benchmark health care expenditure profiles and technology adoption to inform health care policy and practice

In collaboration with: Monash University, Australia

Supported by: German Exchange DAAD / Bundesministerium für Bildung und Forschung 

Duration : 2020-2021

Abstract

Innovation in technologies for cardiovascular disease has been an ever-growing field due to disease chronicity, intervention complexity and global clinical burden. Variation in innovation capacity due to underlying regional environments, however, gives rise to clustering of regional innovation systems that determine the patterns of innovation and diffusion. In this project, we identify regional innovation systems of cardiovascular devices in Europe and examine their determinants by using bibliometric data of the largest biomedical database worldwide.

 

Working Paper of Project Results: 

Sriubaite I, Harris A, Jones AM, Gabbe B. Economic Consequences of Road Traffic InjuriesApplication of the Super Learner algorithm [Internet]. Health, Econometrics and Data Group (HEDG) Working Papers. HEDG, c/o Department of Economics, University of York; 2020 Nov [cited 2022 Aug 3]. (Health, Econometrics and Data Group (HEDG) Working Papers). Report No.: 20/20. Available from: https://ideas.repec.org/p/yor/hectdg/20-20.html 

Avdic D, Blankart KE. Do soft cost-control measures change productivity? - Preferred statin prescribing in Germany. Proceedings. 2021 Aug 1;2021(1):13060.