AI-based longitudinal analyses and predictive models
Intelligent fusion and multimodal analysis of medical data allow diseases to be better understood and correlations in the human body to be interpreted more precisely. For example, linking a person's heart rate with movement parameters and medical history data provides a significantly better overall picture of performance and health status.
These most commonly measured medical biosignals include:
- Blood pressure
- Heart rate and ECG data
- Metabolic parameters, such as glucose
- Medical history data, such as weight or perceived condition
- Laboratory findings
Particularly in the case of patients with chronic diseases, medical data is recorded regularly and comprehensive information on the course of the disease and therapy is available.
If one analyzes these various data over a longer period of time, one obtains a meaningful overall picture of the patient's state of health. Using AI-based analysis of this longitudinal data, it is possible to identify correlations more quickly and predict potential disease outcomes.
The models can be visualized to the physician, who can work with the patient to identify, for example, drug effects or lifestyle adjustments on the course of therapy.