Project Description: DETECT-ME/CFS | Münchner Chronische Fatigue Centrum für junge Menschen (MCFC)

Myalgic encephalomyelitis /chronic fatigue syndrome (ME/CFS) is a chronic multisystem disorder that typically leads to a substantial reduction in social participation and quality of life. Its cardinal symptoms include profound fatigue and post-exertional malaise (PEM), a worsening of symptoms following even minor exertion. These symptoms are commonly accompanied by sleep disturbances, pain, and cognitive impairment, including difficulties with concentration and memory. Circulatory dysfunction and flu-like symptoms are also frequently reported. ME/CFS is a serious and common sequela of infectious diseases, including coronavirus disease 2019 (COVID-19). Its prevalence has increased significantly during and after the COVID-19 pandemic, with adolescent girls and young women being particularly affected. The pathogenesis of ME/CFS is not yet fully understood, and reliable biomarkers as well as treatment remain largely symptom-based and are often complex.

The DETECT-ME/CFS project, coordinated in Braunschweig, Germany, aims to improve the screening and diagnosis of ME/CFS in order to reduce the burden on specialized clinics with limited resources and to enable timely and appropriate patient care. To achieve this, the project is developing an innovative Clinical Decision Support System (CDSS) that integrates clinical expertise and diagnostic decision-making processes into computer-based algorithms. Two additional knowledge layers are intended to further enhance diagnostic accuracy and efficiency. First, artificial intelligence (AI)-based analyses of a patient databases will identify patterns and novel diagnostic features to support the differentiation and exclusion of differential diagnoses. Second, a symptom–disease association model based on automated literature mining of ME/CFS and related differential diagnoses will be developed to strengthen diagnostic capabilities. The system will undergo a multi-phase real-world evaluation and incorporates closed-loop learning mechanisms for continuous optimization. The resulting AI-based CDSS has the potential to substantially improve the diagnosis of ME/CFS in routine clinical practice. Furthermore, it may serve as a model for the diagnosis of other complex diseases and thereby represent a significant advancement in healthcare delivery.