1
|
Pontone GM, McDaniels B, Keener AM, Subramanian I. A Wellness Prescription for Parkinson's: Mid to Late-Stage Disease. Am J Geriatr Psychiatry 2023; 31:737-747. [PMID: 37005185 DOI: 10.1016/j.jagp.2023.02.049] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/29/2023] [Revised: 02/22/2023] [Accepted: 02/23/2023] [Indexed: 04/04/2023]
Abstract
The mid- to late-stages of Parkinson's disease (PD) bring increasing disability that may challenge independence and lower quality of life. Many people with PD struggle to remain hopeful and cope with an uncertain future due to the progression of the disease. Although disability in PD is due chiefly to motor impairment, nonmotor symptoms and psychosocial distress are also major contributors that are amenable to treatment. Interventions that address nonmotor symptoms and psychosocial distress can improve daily function and quality of life even as motor function worsens with disease progression. This manuscript proposes a patient-centered, proactive strategy to promote psychosocial adaptation to decrease the impact of motor, nonmotor, and psychosocial distress on quality of life and function in people with PD.
Collapse
Affiliation(s)
- Gregory M Pontone
- Department of Psychiatry and Neurology (GMP), Johns Hopkins University School of Medicine, Baltimore, MD.
| | - Bradley McDaniels
- Department of Rehabilitation and Health Services (BM), University of North Texas, Denton, TX
| | - Adrienne M Keener
- Department of Neurology (AMK, IS), David Geffen School of Medicine, UCLA, Los Angeles, CA; PADRECC (AMK, IS), West Los Angeles Veterans Administration, Los Angeles, CA
| | - Indu Subramanian
- Department of Neurology (AMK, IS), David Geffen School of Medicine, UCLA, Los Angeles, CA; PADRECC (AMK, IS), West Los Angeles Veterans Administration, Los Angeles, CA
| |
Collapse
|
2
|
Alfalahi H, Shehhi AA, Lamprou C, Ziogas I, Ganiti-Roumeliotou E, Khandoker AH, Hadjileontiadis LJ. Parkinsonian Tremor Detection with Compact Convolutional Transformer from Bispectrum Representation of tri-Axial Accelerometer Signals. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2023; 2023:1-5. [PMID: 38083408 DOI: 10.1109/embc40787.2023.10340646] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/18/2023]
Abstract
After the breakthroughs of Transformer networks in Natural Language Processing (NLP) tasks, they have led to exciting progress in visual tasks as well. Nonetheless, there has been a parallel growth in the number of parameters and the amount of training data, which led to the conclusion that Transformers are not suited for small datasets. This paper is the first to convey the feasibility of Compact Convolutional Transformers (CCT) for the prediction of Parkinsonian postural tremor based on the Bispectrum (BS) representation of IMU accelerometer time series. The dataset includes tri-axial accelerometer signals collected unobtrusively in-the-wild while subjects are on a phone call, and labelled by neurologists and signal processing experts. The BS is a noise-immune, higher-order representation that reflects a signal's deviation from Gaussianity and measures quadratic phase coupling. We performed comparative classification experiments using the CCT, pre-trained CNNs such as VGG-16 and ResNet-50, and the conventional Vision Transformer (ViT). Our model achieves competitive prediction accuracy and F1 score of 96% with only 1.016 M trainable parameters, compared to the ViT with 21.659 M trainable parameters, in a five-fold cross-validation scheme. Our model also outperforms pre-trained CNNs such as VGG-16 and ResNet-50. Furthermore, we show that the performance gains are maintained when training on a larger dataset of BS images. Our effort here is motivated by the hypothesis that data-efficient transformers outperform transfer learning using pre-trained CNNs, paving the way for promising deep learning architecture for small-scale, novel and noisy medical imaging datasets.Clinical relevance- Novel deep learning model for unobtrusive prediction of Parkinsonian Postural Tremor from Bispectrum image representation of tri-axial accelerometer signals collected in-the-wild.
Collapse
|
3
|
ZhuParris A, de Goede AA, Yocarini IE, Kraaij W, Groeneveld GJ, Doll RJ. Machine Learning Techniques for Developing Remotely Monitored Central Nervous System Biomarkers Using Wearable Sensors: A Narrative Literature Review. SENSORS (BASEL, SWITZERLAND) 2023; 23:s23115243. [PMID: 37299969 DOI: 10.3390/s23115243] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/04/2023] [Revised: 05/23/2023] [Accepted: 05/26/2023] [Indexed: 06/12/2023]
Abstract
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.
Collapse
Affiliation(s)
- Ahnjili ZhuParris
- Centre for Human Drug Research (CHDR), Zernikedreef 8, 2333 CL Leiden, The Netherlands
- Leiden Institute of Advanced Computer Science (LIACS), Snellius Gebouw, Niels Bohrweg 1, 2333 CA Leiden, The Netherlands
- Leiden University Medical Center (LUMC), Albinusdreef 2, 2333 ZA Leiden, The Netherlands
| | - Annika A de Goede
- Centre for Human Drug Research (CHDR), Zernikedreef 8, 2333 CL Leiden, The Netherlands
| | - Iris E Yocarini
- Leiden Institute of Advanced Computer Science (LIACS), Snellius Gebouw, Niels Bohrweg 1, 2333 CA Leiden, The Netherlands
| | - Wessel Kraaij
- Leiden Institute of Advanced Computer Science (LIACS), Snellius Gebouw, Niels Bohrweg 1, 2333 CA Leiden, The Netherlands
- The Netherlands Organisation for Applied Scientific Research (TNO), Anna van Buerenplein 1, 2595 DA, Den Haag, The Netherlands
| | - Geert Jan Groeneveld
- Centre for Human Drug Research (CHDR), Zernikedreef 8, 2333 CL Leiden, The Netherlands
- Leiden Institute of Advanced Computer Science (LIACS), Snellius Gebouw, Niels Bohrweg 1, 2333 CA Leiden, The Netherlands
| | - Robert Jan Doll
- Centre for Human Drug Research (CHDR), Zernikedreef 8, 2333 CL Leiden, The Netherlands
| |
Collapse
|
4
|
Karni L, Jusufi I, Nyholm D, Klein GO, Memedi M. Toward Improved Treatment and Empowerment of Individuals With Parkinson Disease: Design and Evaluation of an Internet of Things System. JMIR Form Res 2022; 6:e31485. [PMID: 35679097 PMCID: PMC9227793 DOI: 10.2196/31485] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2021] [Revised: 03/08/2022] [Accepted: 03/18/2022] [Indexed: 11/13/2022] Open
Abstract
Background
Parkinson disease (PD) is a chronic degenerative disorder that causes progressive neurological deterioration with profound effects on the affected individual’s quality of life. Therefore, there is an urgent need to improve patient empowerment and clinical decision support in PD care. Home-based disease monitoring is an emerging information technology with the potential to transform the care of patients with chronic illnesses. Its acceptance and role in PD care need to be elucidated both among patients and caregivers.
Objective
Our main objective was to develop a novel home-based monitoring system (named EMPARK) with patient and clinician interface to improve patient empowerment and clinical care in PD.
Methods
We used elements of design science research and user-centered design for requirement elicitation and subsequent information and communications technology (ICT) development. Functionalities of the interfaces were the subject of user-centric multistep evaluation complemented by semantic analysis of the recorded end-user reactions. The ICT structure of EMPARK was evaluated using the ICT for patient empowerment model.
Results
Software and hardware system architecture for the collection and calculation of relevant parameters of disease management via home monitoring were established. Here, we describe the patient interface and the functional characteristics and evaluation of a novel clinician interface. In accordance with our previous findings with regard to the patient interface, our current results indicate an overall high utility and user acceptance of the clinician interface. Special characteristics of EMPARK in key areas of interest emerged from end-user evaluations, with clear potential for future system development and deployment in daily clinical practice. Evaluation through the principles of ICT for patient empowerment model, along with prior findings from patient interface evaluation, suggests that EMPARK has the potential to empower patients with PD.
Conclusions
The EMPARK system is a novel home monitoring system for providing patients with PD and the care team with feedback on longitudinal disease activities. User-centric development and evaluation of the system indicated high user acceptance and usability. The EMPARK infrastructure would empower patients and could be used for future applications in daily care and research.
Collapse
Affiliation(s)
- Liran Karni
- Centre for Empirical Research on Information Systems, Örebro University School of Business, Örebro, Sweden
| | - Ilir Jusufi
- Department of Computer Science and Media Technology, Linnaeus University, Växjö, Sweden
| | - Dag Nyholm
- Department of Medical Sciences, Neurology, Uppsala University, Uppsala, Sweden
| | - Gunnar Oskar Klein
- Centre for Empirical Research on Information Systems, Örebro University School of Business, Örebro, Sweden
| | - Mevludin Memedi
- Centre for Empirical Research on Information Systems, Örebro University School of Business, Örebro, Sweden
| |
Collapse
|
5
|
Mari Z, Mestre TA. The Disease Modification Conundrum in Parkinson’s Disease: Failures and Hopes. Front Aging Neurosci 2022; 14:810860. [PMID: 35296034 PMCID: PMC8920063 DOI: 10.3389/fnagi.2022.810860] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/08/2021] [Accepted: 01/03/2022] [Indexed: 12/11/2022] Open
Abstract
In the last half-century, Parkinson’s disease (PD) has played a historical role in demonstrating our ability to translate preclinical scientific advances in pathology and pharmacology into highly effective clinical therapies. Yet, as highly efficacious symptomatic treatments were successfully developed and adopted in clinical practice, PD remained a progressive disease without a cure. In contrast with the success story of symptomatic therapies, the lack of translation of disease-modifying interventions effective in preclinical models into clinical success has continued to accumulate failures in the past two decades. The ability to stop, prevent or mitigate progression in PD remains the “holy grail” in PD science at the present time. The large number of high-quality disease modification clinical trials in the past two decades with its lessons learned, as well as the growing knowledge of PD molecular pathology should enable us to have a deeper understanding of the reasons for past failures and what we need to do to reach better outcomes. Periodic reviews and mini-reviews of the unsolved disease modification conundrum in PD are important, considering how this field is rapidly evolving along with our views and understanding of the possible explanations.
Collapse
Affiliation(s)
- Zoltan Mari
- Parkinson’s and Movement Disorders Program, Cleveland Clinic Lou Ruvo Center for Brain Health, Las Vegas, NV, United States
- *Correspondence: Zoltan Mari,
| | - Tiago A. Mestre
- Division of Neurology, Department of Medicine, Parkinson’s Disease and Movement Disorders Center, The Ottawa Hospital Research Institute, University of Ottawa, Ottawa, ON, Canada
| |
Collapse
|
6
|
Remote measurement and home monitoring of tremor. J Neurol Sci 2022; 435:120201. [DOI: 10.1016/j.jns.2022.120201] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/22/2021] [Revised: 11/21/2021] [Accepted: 02/17/2022] [Indexed: 11/15/2022]
|
7
|
Objective vowel sound characteristics and their relationship with motor dysfunction in Asian Parkinson's disease patients. J Neurol Sci 2021; 426:117487. [PMID: 34004464 DOI: 10.1016/j.jns.2021.117487] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2020] [Revised: 05/05/2021] [Accepted: 05/10/2021] [Indexed: 11/23/2022]
Abstract
BACKGROUND Speech impairments are very common in patients with Parkinson's disease (PD). However, knowledge of their objective characteristics and relationship to other motor symptoms amongst Asian PD patients is limited. OBJECTIVES To identify objective vowel sound characteristics in Thai PD patients and correlate with disease severity, as determined by UPDRS and various sub-scores. METHOD We evaluated 100 Thai PD patients, with a mean age of 66.56 years (±7.52) and HY of 2.7 (±1.08), and 101 age-matched controls. Phonatory evaluation, comprising of 15 objective parameters, was conducted using the Multi-Dimensional Voice Programme with a sustained /a/ phonation. RESULTS PD patients exhibited significantly higher values of all dimensions of the phonatory parameters evaluated compared to controls (All, p < 0.001) except for duration of sustained phonation, which was significantly shorter in PD patients. When early- and advanced-stage patients were compared, significantly different parameters were limited to frequency perturbation parameters (Jitt, p = 0.01; RAP, p = 0.013; PPQ, p = 0.01; sPPQ, p = 0.001; vF0, p = 0.011), and NHR (p = 0.028). Several significant and moderate correlations were observed between both STD and frequency perturbation parameters and UPDRS-III, bradykinesia sub-score, and gait and postural instability sub-score. Both vF0, and STD significantly correlated with UPDRS-III and sub-scores in advanced stage patients. CONCLUSION Our study provides objective evidence of phonatory dysfunction in Asian PD patients with certain characteristics correlated with advanced stage or different motor dysfunction. Sustained vowel phonation is a promising digital outcome for global phenotyping a large number of PD patients.
Collapse
|
8
|
Bhidayasiri R. Will Artificial Intelligence Outperform the Clinical Neurologist in the Near Future? Yes. Mov Disord Clin Pract 2021; 8:525-528. [PMID: 33981785 DOI: 10.1002/mdc3.13202] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2021] [Revised: 02/28/2021] [Accepted: 03/10/2021] [Indexed: 12/11/2022] Open
Affiliation(s)
- Roongroj Bhidayasiri
- Chulalongkorn Centre of Excellence for Parkinson's Disease & Related Disorders, Department of Medicine, Faculty of Medicine Chulalongkorn University and King Chulalongkorn Memorial Hospital Bangkok Thailand.,The Academy of Science The Royal Society of Thailand Bangkok Thailand
| |
Collapse
|
9
|
Shivkumar V, Subramanian T, Agarwal P, Mari Z, Mestre TA. Uptake of telehealth in Parkinson's disease clinical care and research during the COVID-19 pandemic. Parkinsonism Relat Disord 2021; 86:97-100. [PMID: 33895540 DOI: 10.1016/j.parkreldis.2021.03.032] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/17/2021] [Revised: 03/24/2021] [Accepted: 03/27/2021] [Indexed: 12/11/2022]
Abstract
INTRODUCTION Traditionally, medical care and research in Parkinson's disease (PD) have been conducted with in-person encounters. The recent COVID-19 pandemic has profoundly impacted the delivery of in-person clinical care and clinical research. We conducted an online survey of active clinician members of the Parkinson Study Group (PSG) to evaluate the adoption of various non-face-to-face methods in clinical practice and research in PD during the COVID-19 pandemic. METHODS We conducted a survey using the open-access online SurveyMonkey tool (http://www.surveymonkey.com). The survey had 27 items and was designed to elucidate clinical/research care before and during the COVID-19 pandemic. The survey was sent to 414 active PSG members with weekly reminders and it remained accessible for 30 days from May 2020. RESULTS We received 142 responses, of which 133 (93.7%) provided demographic data. The clinical use of virtual visits via synchronous video conferencing increased from 39.5% pre-COVID-19 to 94.6% during the COVID-19 pandemic. Lack of access for patients (68.2%) and patient resistance (51.4%) were the top barriers for its use. Approximately 70% respondents stated that 75-100% of their research activities were suspended during the COVID-19 pandemic. Many sites had to fill out protocol deviations (38.2%), protocol exceptions (25.5%) or change their research profile due to layoffs (16.8%). The overall use of video conferencing increased from 30.3% to 64.1%. CONCLUSION The current results suggest a need for flexibility in conducting office visits and clinical trials in PD patients. Technology has the potential to enhance patient care and convenience, when in-person visits can be challenging.
Collapse
Affiliation(s)
- Vikram Shivkumar
- Department of Neurology, Marshall University School of Medicine, Huntington, WV, USA
| | - Thyagarajan Subramanian
- Department of Neurology and Neural and Behavioral Sciences, Penn State University College of Medicine, Hershey, PA, USA
| | - Pinky Agarwal
- Booth Gardner Parkinson's Center, Evergreen Health, Kirkland, WA, USA
| | - Zoltan Mari
- Cleveland Clinic Lou Ruvo Center for Brain Health, Las Vegas, NV, USA
| | - Tiago A Mestre
- Parkinson Disease and Movement Disorders Centre, Division of Neurology, Department of Medicine, The Ottawa Hospital Research Institute, University of Ottawa Brain and Mind Research Institute, Ottawa, ON, Canada.
| | | |
Collapse
|