Predicting postpartum depression

Predicting Postpartum Depression Using Early Warning Signals [PhD Project]

Postpartum depression (PPD), defined as an episode of depression up to one year after giving birth, can have devastating effects on mothers and their families. Research has shown that PPD is highly heterogeneous: Every mother experiences her own form of PPD, caused by her own set of causes (a different network of symptoms and risk factors). This heterogeneity calls for a personalized approach: Who should retrieve prevention, and when?

The aim of this project is to identify causal predictors for postpartum depression and use them to create a deep-learning algorithm for personalized prevention that uses early warning signals to predict an episode before it even occurs. This project is part of the Personalized Prevention and Care theme.

To identify important symptoms and risk factors, existing cross-sectional data from the Brabant study will be analyzed using state-of-the-art machine learning techniques. After validating identified symptoms and risk factors using semi-structured interviews with mothers and experts, they will be used as input for a large ESM study where we will intensively monitor (pregnant) mothers. In the analysis of these data, we will rely on the Network Approach to Psychopathology and construct individual networks of interacting PPD symptoms and possible causes for each mother separately. This allows a) the identification of unique symptom-symptom interactions and b) tailoring prevention strategies to a mother’s situation and own network (like e.g., treating the central symptom in her symptom network). Finally, we will use the obtained data to train a deep-learning algorithm that, based on early warning signals, can predict if a mother is moving from a mentally healthy to a more depressed state. In a second ESM study, this algorithm will be validated, where regular expert meetings will facilitate clinical interpretation.


This project is a collaboration between researchers affiliated with the departments Methodology and Statistics, Cognitive Neuropsychology, and Tranzo as well as researchers involved in the Brabant study. To facilitate clinical implementation, we will also work together closely with health professionals, practitioners and (expecting) mothers.


Cross-cutting themes

The Herbert Simon Research Institute for Health, Well-being, and Adaptiveness is a research center devoted to carrying out excellent, state of the art research in order to contribute to healthy and resilient people. We have selected three themes, which involve the collaboration between various Departments  and address actual themes in need of both fundamental and applied research.