Movement Disorders and Smart Wrist Devices: A Comprehensive Study

Sensors, Journal Year: 2025, Volume and Issue: 25(1), P. 266 - 266

Published: Jan. 5, 2025

In the medical field, there are several very different movement disorders, such as tremors, Parkinson’s disease, or Huntington’s disease. A wide range of motor and non-motor symptoms characterizes them. It is evident that in modern era, use smart wrist devices, smartwatches, wristbands, bracelets spreading among all categories people. This diffusion justified by limited costs, ease use, less invasiveness (and consequently greater acceptability) than other types sensors used for health status monitoring. systematic review aims to synthesize research studies using devices a specific class disorders. Following PRISMA-S guidelines, 130 were selected analyzed. For each study, information provided relating smartwatch/wristband/bracelet model (whether it commercial not), number end-users involved experimentation stage, finally characteristics benchmark dataset possibly testing. Moreover, some articles also reported type raw data extracted from device, implemented designed algorithmic pipeline, classification methodology. turned out most have been published last ten years, showing growing interest scientific community. The mainly investigate relationship between Epilepsy seizure detection topics interest, while few papers analyzing gait Disease, ataxia, Tourette Syndrome. However, results this highlight difficulties still present identified despite advantages these technologies could bring dissemination low-cost solutions usable directly within living environments without need caregivers personnel.

Language: Английский

---

Translational gaps and opportunities for medical wearables in digital health

Science Translational Medicine, Journal Year: 2022, Volume and Issue: 14(666)

Published: Oct. 12, 2022

A confluence of advances in biosensor technologies, enhancements health care delivery mechanisms, and improvements machine learning, together with an increased awareness remote patient monitoring, has accelerated the impact digital across nearly every medical discipline. Medical grade wearables—noninvasive, on-body sensors operating clinical accuracy—will play increasingly central role medicine by providing continuous, cost-effective measurement interpretation physiological data relevant to status disease trajectory, both inside outside established settings. Here, we review current technologies highlight critical gaps translation adoption.

Language: Английский

---

Seizure occurrence is linked to multiday cycles in diverse physiological signals

Epilepsia, Journal Year: 2023, Volume and Issue: 64(6), P. 1627 - 1639

Published: April 15, 2023

The factors that influence seizure timing are poorly understood, and unpredictability remains a major cause of disability. Work in chronobiology has shown cyclical physiological phenomena ubiquitous, with daily multiday cycles evident immune, endocrine, metabolic, neurological, cardiovascular function. Additionally, work chronic brain recordings identified risk is linked to activity. Here, we provide the first characterization relationships between modulation diverse set signals, activity, timing.In this cohort study, 14 subjects underwent ambulatory monitoring multimodal wrist-worn sensor (recording heart rate, accelerometry, electrodermal temperature) an implanted responsive neurostimulation system interictal epileptiform abnormalities electrographic seizures). Wavelet filter-Hilbert spectral analyses characterized circadian wearable recordings. Circular statistics assessed physiology.Ten met inclusion criteria. mean recording duration was 232 days. Seven had reliable electroencephalographic detections (mean = 76 Multiday were present all device signals across subjects. Seizure phase locked five (temperature), four (heart phasic activity), three (accelerometry, rate variability, tonic activity) Notably, after regression behavioral covariates from six seven locking residual signal.Seizure associated multiple processes. Chronic can situate rare paroxysmal events, like seizures, within broader context individual. Wearable devices may advance understanding enable personalized time-varying approaches epilepsy care.

Language: Английский

---

Wearable Digital Health Technology for Epilepsy

New England Journal of Medicine, Journal Year: 2024, Volume and Issue: 390(8), P. 736 - 745

Published: Feb. 21, 2024

One third of people with epilepsy have seizures despite medical treatment. The authors examine wearable digital health devices that can detect and how these affect care.

Language: Английский

---

Seizure forecasting using minimally invasive, ultra‐long‐term subcutaneous electroencephalography: Individualized intrapatient models

Epilepsia, Journal Year: 2022, Volume and Issue: 64(S4)

Published: April 8, 2022

One of the most disabling aspects living with chronic epilepsy is unpredictability seizures. Cumulative research in past decades has advanced our understanding dynamics seizure risk. Technological advances have recently made it possible to record pertinent biological signals, including electroencephalogram (EEG), continuously. We aimed assess whether patient-specific forecasting using remote, minimally invasive ultra-long-term subcutaneous EEG.

Language: Английский

---

Artificial intelligence‐enhanced epileptic seizure detection by wearables

Epilepsia, Journal Year: 2023, Volume and Issue: 64(12), P. 3213 - 3226

Published: Sept. 16, 2023

Wrist- or ankle-worn devices are less intrusive than the widely used electroencephalographic (EEG) systems for monitoring epileptic seizures. Using custom-developed deep-learning seizure detection models, we demonstrate of a broad range types by wearable signals.Patients admitted to epilepsy unit were enrolled and asked wear sensors on either wrists ankles. We collected patients' electrodermal activity, accelerometry (ACC), photoplethysmography, from which blood volume pulse (BVP) is derived. Board-certified epileptologists determined onset, offset, using video EEG recordings per International League Against Epilepsy 2017 classification. applied three neural network models-a convolutional (CNN) CNN-long short-term memory (LSTM)-based generalized model an autoencoder-based personalized model-to raw time-series sensor data detect seizures utilized performance measures, including sensitivity, false positive rate (the number alarms divided total nonseizure segments), day, delay. 10-fold patientwise cross-validation scheme multisignal biosensor evaluated 28 types.We analyzed 166 patients (47.6% female, median age = 10.0 years) 900 (13 254 h data) types. With CNN-LSTM-based model, ACC, BVP, their fusion performed better chance; ACC BVP reached best 83.9% sensitivity 35.3% rate. Nineteen could be detected at least one modality with area under receiver operating characteristic curve > .8 performance.Results this in-hospital study contribute paradigm shift in care that entails noninvasive detection, provides time-sensitive accurate additional clinical types, proposes novel combination out-of-the-box algorithm individualized person-oriented approach.

Language: Английский

---

Machine Learning and Artificial Intelligence Applications to Epilepsy: a Review for the Practicing Epileptologist

Current Neurology and Neuroscience Reports, Journal Year: 2023, Volume and Issue: 23(12), P. 869 - 879

Published: Dec. 1, 2023

Language: Английский

---

Advancements in Wearable Digital Health Technology: A Review of Epilepsy Management

Cureus, Journal Year: 2024, Volume and Issue: unknown

Published: March 27, 2024

This review explores recent advancements in wearable digital health technology specifically designed to manage epilepsy. Epilepsy presents unique challenges monitoring and management due the unpredictable nature of seizures. Wearable devices offer continuous real-time data collection, providing insights into seizure patterns trends. is important epilepsy because it enables early detection, prediction, personalized intervention, empowering patients healthcare providers. Key findings highlight potential improve detection accuracy, enhance patient empowerment through monitoring, facilitate data-driven decision-making clinical practice. However, further research needed validate accuracy reliability these across diverse populations settings. Collaborative efforts between researchers, clinicians, developers, are essential drive innovation for management, ultimately improving outcomes quality life individuals with this neurological condition.

Language: Английский

---

Prospective validation of a seizure diary forecasting falls short

Epilepsia, Journal Year: 2024, Volume and Issue: 65(6), P. 1730 - 1736

Published: April 12, 2024

Recently, a deep learning artificial intelligence (AI) model forecasted seizure risk using retrospective diaries with higher accuracy than random forecasts. The present study sought to prospectively evaluate the same algorithm.

Language: Английский

---

Seizure forecasting: Bifurcations in the long and winding road

Epilepsia, Journal Year: 2022, Volume and Issue: 64(S4)

Published: May 23, 2022

To date, the unpredictability of seizures remains a source suffering for people with epilepsy, motivating decades research into methods to forecast seizures. Originally, only few scientists and neurologists ventured this niche endeavor, which, given difficulty task, soon turned long winding road. Over past decade, however, our narrow field has seen major acceleration, trials chronic electroencephalographic devices subsequent discovery cyclical patterns in occurrence Now, burgeoning science seizure timing is emerging, which turn informs best forecasting strategies upcoming clinical trials. Although finish line might be view, many challenges remain make reality. This review covers most recent scientific, technical, medical developments, discusses methodology detail, sets number goals future studies.

Language: Английский

---