CALM-QE

CALM-QE is a project focused on addressing the challenges posed by Chronic Obstructive Pulmonary Disease (COPD) and bronchial asthma (BA), two prevalent non-communicable pulmonary diseases with significant socio-economic implications. These conditions are influenced by intricate interactions between genes and the environment, resulting in diverse phenotypes and endotypes that can overlap between COPD and BA. To support the emerging concept of precision medicine, which involves tailoring treatments to individual patients, CALM-QE aims to develop, train, and test predictive models using multidimensional real-world datasets from COPD and BA patients across different healthcare sectors.

The project seeks to overcome the primary obstacle in the field of COPD and BA, which is translating the treatable trait approach to personalized patient care. To achieve this, CALM-QE will incorporate various data sources into their models, including the established clinical core dataset, as well as additional information such as lung function, medication, chest imaging, local climate and air pollutant data, and biosignals obtained from wearable devices. By harnessing these diverse datasets, the project aims to identify and categorize disease trajectories to enhance understanding and treatment planning.

CALM-QE also plans to integrate research study data, including longitudinal information from the German COPD cohort, as a proof of concept. Since COPD and BA have origins in early life, the project will model trajectories spanning childhood to adulthood. Importantly, as patients with these conditions are often seen in private practices, CALM-QE brings together cross-sectorial healthcare providers ranging from private practices to university hospitals. The project’s collaborative approach involves an interdisciplinary team of experts from pediatric and adult medicine, epidemiology, and medical informatics. Leveraging existing local infrastructures, such as data integration centers, the team aims to build novel predictive models that utilize large, multi-dimensional datasets to predict clinically relevant outcomes.

In conclusion, CALM-QE’s ambitious goal is to develop and validate predictive models that leverage extensive real-world datasets for COPD and BA patients. By adhering to the principles of personalized, participatory, predictive, and preventive (4P) medicine, these models have the potential to advance precision medicine in the treatment of pulmonary diseases.