The kick-off meeting on February 2, 2023, marked the launch of DFG AI Research Group 5347, “Lifespan AI: From Longitudinal Health Data to Lifespan Inference.”
At the official launch of the collaborative project, the research project’s objectives were discussed, and organizational frameworks were addressed. Particular emphasis was placed on defining the next steps and coordinating work packages as the project progresses. Additionally, the meeting provided participants with an opportunity for networking, professional exchange, and strengthening collaboration. The new Lifespan AI members introduced themselves, were welcomed into the group, and were able to establish initial contacts. We are very much looking forward to a fruitful collaboration in the coming years.
Lifespan AI – These Are the Goals
The Lifespan AI work program consists of six projects organized into three thematic areas that pursue the Lifespan AI vision from different perspectives: Data and Methods (D), Models and Interpretation (M), and Inference and Causality (C). D1 will further develop DL strategies to investigate and process long-term temporal changes based on the integration of high-dimensional data from various sources; D2 will combine neural networks and mixed-effects models to predict individual health trajectories across the life course; M1 will develop “normalizing flow” methods to derive joint distributions and conditional densities for health data; M2 will create a cognitive digital twin from everyday human activities to predict changes across age groups; C1 will develop time-adaptive, explainable AI methods for recurrent neural networks and event times; and C2 will derive a framework for causality inference in longitudinal studies that combines different datasets and accounts for nonlinearities.