Objectives:

Multidimensional models are to be developed using statistical methods and machine learning approaches in order to predict the risk for important clinical endpoints. In the data integration centers (DIZ) of the Medical Informatics Initiative (MII), healthcare data will be made available for medical research in accordance with data protection regulations.

In Module 3 of the MII, eight clinical use cases and three method platforms are funded- including CALM-QE!

In the clinical use cases (e.g. CALM-QE), the added value of sharing health-related data beyond the boundaries of the consortia in research and healthcare will be tested using medically relevant use cases.

The first objective is to make healthcare data available for research.

The pandemic triggered by the SARS-CoV-2 pathogen has shown how important it is to obtain a comprehensive picture of the extent, severity, treatment successes (or failures), the impact of preventive measures including vaccination and the associated side effects in a timely manner.

This knowledge creates the basis for correct, balanced and informed decisions.

Asthma and COPD are the most common chronic lung diseases. “Every patient is different and also special in terms of their clinical picture”, as both terms encompass complex disease patterns with different phenotypes and underlying pathologies that differ in their response to certain medications and therapies as well as in the long-term course of the disease.

What makes this project extraordinary: the use of data from patient care, so-called “real-world” data, with which the reality of care can be depicted. By looking at a large patient collective, generating patient data from various care structures – from inpatient care to data from outpatient clinics at university hospitals to data from patient care in outpatient practices – and continuously collecting data via wearables, it is possible to create a comprehensive picture that is as close to reality as possible. Correspondingly, extensive data sets are necessary in order to map disease progression due to the variety of influencing factors and phenotypes, to be able to highlight patterns and to develop multidimensional models using statistical methods and machine learning techniques that enable individual risk stratification to support therapy.

And finally: the range of influencing factors and parameters taken into account is very broad: in addition to patient data on disease, progression and therapy, data from the environment (air pollution, climate) is also included, as well as data such as oxygen saturation and pulse rate, which is recorded via smartwatches for a smaller number of patients. Individualized, personalized medicine is an important building block for the active participation of patients. This participation should begin at the research stage. CALM-QE explicitly includes patients as partners. Representatives of patient organizations will contribute the views and priorities of patients to the project.

IMPORTANT TO KNOW: CALM-QE combines the expertise of adult and paediatric pneumologists, experts in chronic inflammation, statistics and modelling, artificial intelligence and patients as experts on the literal experience of the disease.

The goal is to contribute to better control of the disease and long-term prognosis and ultimately to an improved quality of life by providing a more accurate picture of individual patients through more tailored therapy, better identification of individual risk factors and appropriate countermeasures