A recent study has shown promising results for the use of digital phenotyping in the management of myasthenia gravis (MG), a rare autoimmune disorder that affects the muscles and leads to weakness and fatigue. The study utilized a smartphone-based research platform to collect real-world, patient-reported data on MG symptoms and exacerbations.
The study involved 82 patients who completed a 3-month period of data collection. Participants were categorized into five groups based on their medication regimens. They were required to submit daily check-ins through the research platform, reporting and rating their MG symptoms using a standardized scale. The most common MG phenotype reported among the participants was severe MG, with 84% of them experiencing several exacerbations each year.
The data collected from over 4000 data points showed that 98% of participants had days without exacerbations, while 55% reported days with exacerbations, and 73% were unsure if they had any exacerbations. On average, participants experienced 6.3 exacerbations during the study period. The study also found that MG-ADL scores were significantly higher during reported exacerbation periods compared to nonexacerbation periods.
In addition to symptom data, the study looked at other factors such as step counts and comorbidities. It found that fewer steps were taken on days with exacerbations, and there was a weak correlation between daily step count and MG-ADL score. Symptoms commonly reported on exacerbation days included difficulty swallowing and impaired speech, while nonexacerbation days had higher rates of drooping eyelids and weakness in the legs and arms.
The study concluded that the use of digital phenotyping, which involves collecting data more frequently and passively through smartphones and wearable devices, holds promise for improving the understanding and management of MG. By gathering real-time patient-reported data, healthcare providers may be able to predict and prevent exacerbations more effectively.
However, the study acknowledged some limitations, including the lack of diversity in the study population and the potential exclusion of those with lower levels of digital literacy. Further research is needed to validate these findings and explore the potential benefits of digital phenotyping in a broader population of MG patients.
Overall, this study highlights the potential of digital phenotyping in improving the lives of patients living with MG. By harnessing the power of smartphones and wearable devices, healthcare providers may be able to gain a more comprehensive understanding of the disease and develop personalized treatment strategies to minimize the impact of exacerbations.
– Help Build an A.I. Model to Predict Myasthenia Gravis Symptom Patterns and Flares. NCT04590716.
– Steyaert S, Lootus M, Sarabu C, et al. A decentralized, prospective, observational study to collect real-world data from patients with myasthenia gravis using smartphones. Front Neurol. 2023;14:1144183. doi:10.3389/fneur.2023.1144183.