Date: December 14, 2023
Time: 3:00 pm - 4:00 pm
Location: VU NU Building - 3B07

Time: arrival & drinks from 14:30
Talks from 15:00 – 16:00

We are looking forward to seeing you at our next AI4Health meetup, with the following very interesting speakers:

Caroline Jagtenberg (VU, Operations Analytics)
How should volunteers be dispatched to out-of-hospital cardiac arrests?

Survival for out-of-hospital cardiac arrest (OHCA) can be significantly improved through bystander efforts. To shorten the time to good-quality cardiopulmonary resuscitation, some emergency call centers use mobile phone technology to rapidly locate and alert nearby trained volunteers. A number of such community first responder (CFR) systems are active worldwide, for example HartslagNu in the Netherlands and GoodSAM in the UK, Australia and New Zealand.

GoodSAM sends so-called phased alerts: they notify increasingly many volunteers with built-in time delays. The policy that defines these delays affects (1) response times – which have a direct relation to survival – (2) CFR workload and (3) the number of redundant CFR arrivals. We start by comparing policies through Monte Carlo Simulation, in which we use bootstrapped values from historical GoodSAM responses, estimating the three KPIs above. CFR app managers can use those results to identify a policy that displays a desirable trade-off between the performance measures.

We continue by using machine learning to predict the best policy to use, given where the volunteers are observed in relation to the patient. We do this by formulating the problem as a multiclass classification problem, for which we train a tree on the results from the simulations above. We compare the performance of the tree against a policy designed by dynamic programming. Finally, we look into optimal decision trees which go beyond the heuristic nature of machine learning algorithms.

Charlotte van Westerhuis & Marwan El Morabet (HvA, Center of Expertise Urban Vitality & Amsterdam UMC, Physiotherapy)
Data-Driven Recovery after Oncology Surgery: An Exploration of Machine Learning Applications

In the pursuit of enhancing post-oncology surgery recovery, the OPRAH project provides a unique bridge between traditional care and modern technology. Research shows that increasing protein intake and maintaining physical activity after hospital release is crucial in improving recovery. The Oprah project equips patients with wearables for tracking physical activity and an app to log protein intake. This data is then communicated to a physiotherapist and dietitian who together guide the patient towards recovery.

The data generated in this study, however, is a valuable asset from which we can start to think about personalizing this care, fueled by machine learning algorithms. During this presentation we will explain our combined physical activity and nutrition intervention, supported by eHealth, and we will present use cases about static recovery risk predictions, as well as continuous risk predictions. Bringing us one step closer to a future where personalized recovery is the norm.