Data Implementation

Creating a digital twin from the earliest moment in the life course

This project combines data collection, storage, and analytics in a context-driven life course care platform. Our Digital Twin platform is valuable to people through supporting (non-)medical and lifestyle care and adopting health literacy and agency. The second objective is to investigate how to develop, implement and scale a sustainable ecosystem of the Digital Twin.

To this end, we selected a specific topic from the wide range of medical problems that may benefit from a Digital Twin: predicting the probability of hypertension-related complications around pregnancy. Hypertension is an underlying furtive process that can result in adverse health outcomes for both mother and child.

With this case study, we aim to:

  1. Establish individual (non-)medical and lifestyle care paths, create, implement, and evaluate the Digital Twin.
  2. Identify patient (care) values, protocols for design, implementation, business models, and scaling.


Data, as it were, forms the hardware of the participant’s Digital Twin. Through the personal joint lifestyle and medical care path on the platform, the participant receives targeted advice, monitoring, and coaching to improve their health based on their data. Doctors have direct insight into both the medical health status and context of their patients. Using artificial intelligence, researchers can use these extensive data to study diseases within a large patient population and better predict, treat, and even prevent future disease risks.

Current Projects

Pregnancy journey mining

This project aims to extract a typical pregnancy journey of hypertensive pregnant women from their online community posts. The women describe what’s happening to them to share with others. Important events from their posts can be longitudinally sorted as a pregnancy journey since they have posted time information.

This project applies data mining algorithms to identify a common pregnancy journey of hypertensive pregnant women automatically. This pregnancy journey will suggest what many of these women frequently experience and cover in the posts. It will also indicate the trajectory of significant events of hypertensive pregnant women that the digital twin needs to handle.

The effects of hypertension on pregnant women, the fetus, and the neonate

This study aims to early predict, treat, and prevent hypertension in (pre-)pregnant women using multiple data sources. Our question is twofold:

  • How do we optimally predict maternal, fetal, and neonatal adverse outcomes by online modelling of blood pressure measurements before and during pregnancy?
  • How does the risk of adverse outcomes change over time with new measurements regarding hypertension during pregnancy?

These predictions could monitor patient risk and partly remove the uncertainty for adverse outcomes in the mother and the fetus/neonate, which will guide treatment decisions. We will collaborate with the work packages Data CollectionData Storage and Data Analytics.

A product-service intervention for pregnant women with hypertension

This project aims to develop a product-service intervention that can motivate hypertensive pregnant women to avoid convenience food.

We will interview pregnant women online and analyze these interviews qualitatively. Our main goal is to identify themes and variables relating to convenience food consumption and intervention points on a pregnancy journey. We will design a service intervention prototype that addresses the findings in data analysis and test that intervention on a small group of pregnant women within the study population.