Using Deep Learning for Task and Tremor Type Classification in People with Parkinson’s Disease

Farhani, Ghazal; Zhou, Yue; Jenkins, Mary E.; Naish, Michael D.; Trejos, Ana Luisa

doi:10.3390/s22197322

Cited by 8 publications

(3 citation statements)

References 51 publications

(51 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Los estudios se han centrado en valorar diferentes manifestaciones de los TM, como el temblor [6][7][8][9] , la bradicinesia 10 , las discinesias 11 , la «congelación» al caminar 12 o la inestabilidad 13 . Se dispone también de estudios enfocados al diagnóstico precoz 14 y a la discriminación de los diferentes tipos de parkinsonismos 15 , entre otros usos.…”

Section: Análisis De Sensores Y Señalesunclassified

Inteligencia artificial en la enfermedad de Parkinson y otros trastornos del movimiento

Lapeña Motilva,

Sánchez-Ferro

2024

KRANION

View full text Add to dashboard Cite

La inteligencia artificial se ha ido abriendo paso de forma progresiva y los trastornos del movimiento no han sido una excepción a esta tendencia. La relativa facilidad de la recogida de datos hace que existan muchas iniciativas de inteligencia artificial para intentar diagnosticar o evaluar a los pacientes con trastornos del movimiento. Se han realizado estudios exitosos recogiendo datos de wearables u otros dispositivos, imágenes radiológicas, vídeos de los pacientes o señales neurofisiológicas. Los resultados en general son variables, pero la mayor parte de los estudios presentan una precisión por encima del 80%. Actualmente, la monitorización mediante wearables es la que se encuentra más avanzada, y esto se plasma en la aparición de dispositivos comerciales que ya se encuentran disponibles. Pese a toda la expectación que hay sobre estas nuevas tecnologías, quedan retos en cuanto a su validez, seguridad y responsabilidad que deben resolverse para llegar a una utilización generalizada en la práctica clínica diaria.

show abstract

Section: Análisis De Sensores Y Señalesunclassified

Inteligencia artificial en la enfermedad de Parkinson y otros trastornos del movimiento

Lapeña Motilva,

Sánchez-Ferro

2024

KRANION

View full text Add to dashboard Cite

show abstract

“…However, other types of sensors are also capable of identifying these symptoms. For instance, Farhani et al [16] used data from 15 patients wearing an EMG sensor to train a Bi-LSTM. They employed a regularized evolutionary algorithm to set the hyperparameters of the model instead of doing so manually.…”

Section: Related Workmentioning

confidence: 99%

InSEption: A Robust Mechanism for Predicting FoG Episodes in PD Patients

et al. 2023

View full text Add to dashboard Cite

The integration of IoT and deep learning provides the opportunity for continuous monitoring and evaluation of patients’ health status, leading to more personalized treatment and improved quality of life. This study explores the potential of deep learning to predict episodes of freezing of gait (FoG) in Parkinson’s disease (PD) patients. Initially, a literature review was conducted to determine the state of the art; then, two inception-based models, namely LN-Inception and InSEption, were introduced and tested using the Daphnet dataset and an additional novel medium-sized dataset collected from an IMU (inertial measuring unit) sensor. The results show that both models performed very well, outperforming or achieving performance comparable to the state-of-the-art. In particular, the InSEption network showed exceptional performance, achieving a 6% increase in macro F1 score compared to the inception-only-based counterpart on the Daphnet dataset. In a newly introduced IMU dataset, InSEption scored 97.2% and 98.6% in terms of F1 and AUC, respectively. This can be attributed to the added squeeze and excitation blocks and the domain-specific oversampling methods used for training. The benefits of using the Inception mechanism for signal data and its potential for integration into wearable IoT are validated.

show abstract

“…In the last decades, wearable technologies have been constantly gaining prominence, especially in health-related applications, where miniaturized devices (sensors and actuators) are placed on or near the body, aiming to minimize interference with the user's activities [1,2]. This is partially due to technological advances in microelectronics, which have allowed the development of miniaturized devices capable of collecting data with high quality in a compact space and with low energy consumption.…”

Section: Introductionmentioning

confidence: 99%

Towards a Modular Pathological Tremor Simulation System Based on the Stewart Platform

Fajardo,

Melo

2023

Sensors

View full text Add to dashboard Cite

Wearable technologies have aided in reducing pathological tremor symptoms through non-intrusive solutions that aim to identify patterns in involuntary movements and suppress them using actuators positioned at specific joints. However, during the development of these devices, tests were primarily conducted on patients due to the difficulty of faithfully simulating tremors using simulation equipment. Based on studies characterizing tremors in Parkinson’s disease, the development of a robotic manipulator based on the Stewart platform was initiated, with the goal of satisfactorily simulating resting tremor movements in the hands. In this work, a simulator was implemented in a computational environment using the multibody dynamics method. The platform structure was designed in a virtual environment using SOLIDWORKS® v2017 software and later exported to Matlab® R17a software using the Simulink environment and Simscape multibody library. The workspace was evaluated, and the Kalman filter was used to merge acceleration and angular velocity data and convert them into data related to the inclination and rotation of real patients’ wrists, which were subsequently executed in the simulator. The results show a high correlation and low dispersion between real and simulated signals, demonstrating that the simulated mechanism has the capacity to represent Parkinson’s disease resting tremors in all wrist movements. The system could contribute to conducting tremor tests in suppression devices without the need for the presence of the patient and aid in comparing suppression techniques, benefiting the development of new wearable devices.

show abstract

Using Deep Learning for Task and Tremor Type Classification in People with Parkinson’s Disease

Cited by 8 publications

References 51 publications

Inteligencia artificial en la enfermedad de Parkinson y otros trastornos del movimiento

Inteligencia artificial en la enfermedad de Parkinson y otros trastornos del movimiento

InSEption: A Robust Mechanism for Predicting FoG Episodes in PD Patients

Towards a Modular Pathological Tremor Simulation System Based on the Stewart Platform

Contact Info

Product

Resources

About