Tremor assessment using smartphone sensor data and fuzzy reasoning

Tips and tricks in tremor treatment

Tremor, whether arising from neurological diseases, other conditions, or medication side effects, significantly impacts patients' lives. Treatment complexities necessitate clear algorithms and strategies. Levodopa remains pivotal for Parkinson's tremor, though response variability exists. Some dopamine agonists offer notable tremor reduction targeting D2 receptors. Propranolol effectively manages essential tremor and essential tremor plus (ET/ET +), sometimes with primidone for added benefits, albeit dose-dependent side effects. As reserve medications anticholinergics and clozapine are used for treatment of parkinsonian tremor, 1-Octanol and certain anticonvulsant drugs for tremor of other orign, especially ET. Therapies such as invasive deep brain stimulation and lesional focused ultrasound serve for resistant cases. A medication review is crucial for all forms of tremor, but it is particularly important if medication may have triggered the tremor. Sensor-based detection and non-drug interventions like wristbands and physical therapy broaden diagnostic and therapeutic horizons, promising future tremor care enhancements. Understanding treatment nuances is a key for tailored tremor management respecting patient needs and tolerability. Successful strategies integrate pharmacological, non-invasive, and technological modalities, aiming for optimal symptom control and improved quality of life.

Upper limb intention tremor assessment: opportunities and challenges in wearable technology

BACKGROUND

Tremors are involuntary rhythmic movements commonly present in neurological diseases such as Parkinson's disease, essential tremor, and multiple sclerosis. Intention tremor is a subtype associated with lesions in the cerebellum and its connected pathways, and it is a common symptom in diseases associated with cerebellar pathology. While clinicians traditionally use tests to identify tremor type and severity, recent advancements in wearable technology have provided quantifiable ways to measure movement and tremor using motion capture systems, app-based tasks and tools, and physiology-based measurements. However, quantifying intention tremor remains challenging due to its changing nature.

METHODOLOGY & RESULTS

This review examines the current state of upper limb tremor assessment technology and discusses potential directions to further develop new and existing algorithms and sensors to better quantify tremor, specifically intention tremor. A comprehensive search using PubMed and Scopus was performed using keywords related to technologies for tremor assessment. Afterward, screened results were filtered for relevance and eligibility and further classified into technology type. A total of 243 publications were selected for this review and classified according to their type: body function level: movement-based, activity level: task and tool-based, and physiology-based. Furthermore, each publication's methods, purpose, and technology are summarized in the appendix table.

CONCLUSIONS

Our survey suggests a need for more targeted tasks to evaluate intention tremors, including digitized tasks related to intentional movements, neurological and physiological measurements targeting the cerebellum and its pathways, and signal processing techniques that differentiate voluntary from involuntary movement in motion capture systems.

Machine Learning Techniques for Developing Remotely Monitored Central Nervous System Biomarkers Using Wearable Sensors: A Narrative Literature Review

BACKGROUND

Central nervous system (CNS) disorders benefit from ongoing monitoring to assess disease progression and treatment efficacy. Mobile health (mHealth) technologies offer a means for the remote and continuous symptom monitoring of patients. Machine Learning (ML) techniques can process and engineer mHealth data into a precise and multidimensional biomarker of disease activity.

OBJECTIVE

This narrative literature review aims to provide an overview of the current landscape of biomarker development using mHealth technologies and ML. Additionally, it proposes recommendations to ensure the accuracy, reliability, and interpretability of these biomarkers.

METHODS

This review extracted relevant publications from databases such as PubMed, IEEE, and CTTI. The ML methods employed across the selected publications were then extracted, aggregated, and reviewed.

RESULTS

This review synthesized and presented the diverse approaches of 66 publications that address creating mHealth-based biomarkers using ML. The reviewed publications provide a foundation for effective biomarker development and offer recommendations for creating representative, reproducible, and interpretable biomarkers for future clinical trials.

CONCLUSION

mHealth-based and ML-derived biomarkers have great potential for the remote monitoring of CNS disorders. However, further research and standardization of study designs are needed to advance this field. With continued innovation, mHealth-based biomarkers hold promise for improving the monitoring of CNS disorders.