Healthplus.ai: machine learning for medical decision support systems
11-30, 10:55–11:25 (Europe/Amsterdam), Planck

Healtphlus.ai is developping PERISCOPE© as a decision support system for surgical departments. With PERICOPE we train a machine learning model on data in the electronic health records. In this talk we will show you our mission, the design choices we have made and the resulting architecture as well as shed some light on some of the challenges we face.


"With PERISCOPE we predict the chance that a patient develops an infection after surgery. We aim to improve the care after surgery by allowing medical staff to closer monitor high risk patients, this way infections might be detected and treated earlier.
In 20 minutes we will try to show you what the medical IT field looks like and how we have choosen to develop a data driven application for it. To give you two spoilers: We had to develop a flexibale ETL mechanism to be able to read in data from different EHR vendors and in all kinds off different hospitals.
And we have trained an XGBoost model and setup an extensive model validation proces to check that the performance of our model is good for every hospital and every patient group."


Prior Knowledge Expected

No previous knowledge expected

Bart Steverink holds a bachelor's degree in aeronautical engineering and a master’s degree in engineering and policy analysis. Driven by a deep desire to better understand how the world works, Bart started his career as an independent contractor, developing simulation models for use in the transportation, healthcare and renewable energy domains. Writing code had always been a major aspect of the development of simulation models and ultimately led to a career switch towards information architecture and software development. Over the past decade Bart founded multiple software oriented startups and is currently engaged as CTO and co-owner at Healthplus.ai. Bart lives in the east of The Netherlands with his wife and two sons.

Laurens Schinkelshoek completed his bachelor in Physics and afterwards started working in IT. While working for the IT department in a hospital he got familiar with IT systems and data structures in healthcare. When he learned about machine learning he saw the huge potential this technology could offer to decrease the workload of healthcare practitioners and improve patient experience. At the same time the hurdles to get this new technology ready for use were huge. Now he works as a Data Scientist for Healthplus.ai on besting these hurdles and making machine learning based products available in the clinic.