Toward crises prediction and enhancing patient care in myasthenia gravis using telemonitoring and wearable-based data

• Applicant: Dr. Maike Stein
• Subject Area: Clinical Neurology; Neurosurgery and Neuroradiology
• Term: since 2024
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 553539684

This project aims to address the challenges faced by individuals with Myasthenia gravis (MG), a chronic neurological autoimmune disease characterized by exercise-dependent muscle weakness. The disease has a highly variable course of symptoms that require continuous monitoring and timely medical decisions, which is often hindered by limited access to specialists and long waiting times for appointments. Symptoms can increase until respiratory insufficiency within days, which can lead to myasthenic crisis requiring intensive care. Current methods for assessing the disease’s clinical course have limitations with lack of objectivity and no reliable predictors for myasthenic crises available yet. To overcome these challenges, we developed a telemedical platform called "MyaLink" that consists of an app for patients and a web-based platform for physicians, enabling remote monitoring and communication. It facilitates the exchange of health data and allows physicians to track patients’ progress and adjust therapy remotely when necessary. With this we are introducing a new and concrete concept in the field of neuromuscular diseases, that uses longitudinal remote assessment as a tool to improve time-critical needs-based care for MG patients. Continuous data from remote monitoring and patient-physician interaction can provide real-time insights into disease conditions and therefore enable earlier detection for non-responses to treatment. A first randomized-controlled pilot study was conducted at the integrated myasthenia center (iMZ) at Charité Berlin comparing standard of care with and without additional telemedical treatment with MyaLink involving continuous symptom monitoring and collection of vital parameters. The here proposed project aims at conducting a statistical in-depth analysis of this pilot dataset to assess whether the use of MyaLink reduces the severity of the disease and improves the quality of life of MG patients. Furthermore, it aims to analyze patient-physician communication patterns to gain insights into telemedical interventions. Lastly, the proposed work focuses on developing first machine learning-based models for early identification of myasthenic crises, enhancing our ability to predict and prevent these critical events and enabling timely and personalized support for MG patients (digital biomarkers/phenotyping).

• DFG Programme: WBP Fellowship
• International Connection: USA
• Host: Professorin Dr. Pushpa Narayanaswami