1
|
Huang J, Lin L, Yu F, He X, Song W, Lin J, Tang Z, Yuan K, Li Y, Huang H, Pei Z, Xian W, Yu-Chian Chen C. Parkinson's severity diagnosis explainable model based on 3D multi-head attention residual network. Comput Biol Med 2024; 170:107959. [PMID: 38215619 DOI: 10.1016/j.compbiomed.2024.107959] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2023] [Revised: 12/31/2023] [Accepted: 01/01/2024] [Indexed: 01/14/2024]
Abstract
The severity evaluation of Parkinson's disease (PD) is of great significance for the treatment of PD. However, existing methods either have limitations based on prior knowledge or are invasive methods. To propose a more generalized severity evaluation model, this paper proposes an explainable 3D multi-head attention residual convolution network. First, we introduce the 3D attention-based convolution layer to extract video features. Second, features will be fed into LSTM and residual backbone networks, which can be used to capture the contextual information of the video. Finally, we design a feature compression module to condense the learned contextual features. We develop some interpretable experiments to better explain this black-box model so that it can be better generalized. Experiments show that our model can achieve state-of-the-art diagnosis performance. The proposed lightweight but effective model is expected to serve as a suitable end-to-end deep learning baseline in future research on PD video-based severity evaluation and has the potential for large-scale application in PD telemedicine. The source code is available at https://github.com/JackAILab/MARNet.
Collapse
Affiliation(s)
- Jiehui Huang
- Artificial Intelligence Medical Research Center, School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, Guangdong 518107, China
| | - Lishan Lin
- Department of Neurology, The First Affiliated Hospital, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Diagnosis and Treatment of Major Neurological Diseases, National Key Clinical Department and Key Discipline of Neurology, 510080, China
| | - Fengcheng Yu
- Artificial Intelligence Medical Research Center, School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, Guangdong 518107, China
| | - Xuedong He
- School of Computer Science and Technology, Zhejiang Normal University, Jinhua, 321004, Zhejiang, China
| | - Wenhui Song
- Artificial Intelligence Medical Research Center, School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, Guangdong 518107, China
| | - Jiaying Lin
- Artificial Intelligence Medical Research Center, School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, Guangdong 518107, China
| | - Zhenchao Tang
- Artificial Intelligence Medical Research Center, School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, Guangdong 518107, China
| | - Kang Yuan
- Department of Neurology, The First Affiliated Hospital, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Diagnosis and Treatment of Major Neurological Diseases, National Key Clinical Department and Key Discipline of Neurology, 510080, China
| | - Yucheng Li
- Department of Neurology, The First Affiliated Hospital, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Diagnosis and Treatment of Major Neurological Diseases, National Key Clinical Department and Key Discipline of Neurology, 510080, China
| | - Haofan Huang
- Polytechnic Institute, Zhejiang University, Hangzhou 310058, China
| | - Zhong Pei
- Department of Neurology, The First Affiliated Hospital, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Diagnosis and Treatment of Major Neurological Diseases, National Key Clinical Department and Key Discipline of Neurology, 510080, China.
| | - Wenbiao Xian
- Department of Neurology, The First Affiliated Hospital, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Diagnosis and Treatment of Major Neurological Diseases, National Key Clinical Department and Key Discipline of Neurology, 510080, China.
| | - Calvin Yu-Chian Chen
- Artificial Intelligence Medical Research Center, School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, Guangdong 518107, China; AI for Science (AI4S)-Preferred Program, Peking University Shenzhen Graduate School, Shenzhen, 518055, Guangdong, China; School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, 518055, Guangdong, China; Department of Medical Research, China Medical University Hospital, Taichung, 40447, Taiwan; Department of Bioinformatics and Medical Engineering, Asia University, Taichung, 41354, Taiwan.
| |
Collapse
|
2
|
Yang YY, Ho MY, Tai CH, Wu RM, Kuo MC, Tseng YJ. FastEval Parkinsonism: an instant deep learning-assisted video-based online system for Parkinsonian motor symptom evaluation. NPJ Digit Med 2024; 7:31. [PMID: 38332372 PMCID: PMC10853559 DOI: 10.1038/s41746-024-01022-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2023] [Accepted: 01/18/2024] [Indexed: 02/10/2024] Open
Abstract
The Motor Disorder Society's Unified Parkinson's Disease Rating Scale (MDS-UPDRS) is designed to assess bradykinesia, the cardinal symptoms of Parkinson's disease (PD). However, it cannot capture the all-day variability of bradykinesia outside the clinical environment. Here, we introduce FastEval Parkinsonism ( https://fastevalp.cmdm.tw/ ), a deep learning-driven video-based system, providing users to capture keypoints, estimate the severity, and summarize in a report. Leveraging 840 finger-tapping videos from 186 individuals (103 patients with Parkinson's disease (PD), 24 participants with atypical parkinsonism (APD), 12 elderly with mild parkinsonism signs (MPS), and 47 healthy controls (HCs)), we employ a dilated convolution neural network with two data augmentation techniques. Our model achieves acceptable accuracies (AAC) of 88.0% and 81.5%. The frequency-intensity (FI) value of thumb-index finger distance was indicated as a pivotal hand parameter to quantify the performance. Our model also shows the usability for multi-angle videos, tested in an external database enrolling over 300 PD patients.
Collapse
Affiliation(s)
- Yu-Yuan Yang
- Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, No. 1 Roosevelt Rd. Sec. 4, Taipei, 10617, Taiwan, ROC
| | - Ming-Yang Ho
- Department of Computer Science and Information Engineering, National Taiwan University, No. 1 Roosevelt Rd. Sec. 4, Taipei, 10617, Taiwan, ROC
| | - Chung-Hwei Tai
- Department of Neurology, National Taiwan University Hospital, No. 1 Changde St., Zhongzheng Dist., Taipei City, 100229, Taiwan, ROC
| | - Ruey-Meei Wu
- Department of Medicine, National Taiwan University Cancer Center, No. 57, Lane 155, Sec. 3, Keelung Rd., Da'an Dist., Taipei City, 106, Taiwan, ROC
| | - Ming-Che Kuo
- Department of Neurology, National Taiwan University Hospital, No. 1 Changde St., Zhongzheng Dist., Taipei City, 100229, Taiwan, ROC.
- Department of Medicine, National Taiwan University Cancer Center, No. 57, Lane 155, Sec. 3, Keelung Rd., Da'an Dist., Taipei City, 106, Taiwan, ROC.
| | - Yufeng Jane Tseng
- Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, No. 1 Roosevelt Rd. Sec. 4, Taipei, 10617, Taiwan, ROC.
- Department of Computer Science and Information Engineering, National Taiwan University, No. 1 Roosevelt Rd. Sec. 4, Taipei, 10617, Taiwan, ROC.
| |
Collapse
|
3
|
Elshourbagy A, Eltaras MM, Abdalshafy H, Javed S, Sadaney AO, Harrigan TP, Mills KA, Hernandez ME, Brašić JR. Feasibility of virtual low-cost quantitative continuous measurement of movements in the extremities of people with Parkinson's disease. MethodsX 2023; 11:102230. [PMID: 37383624 PMCID: PMC10293722 DOI: 10.1016/j.mex.2023.102230] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/02/2023] [Accepted: 05/25/2023] [Indexed: 06/30/2023] Open
Abstract
A low-cost quantitative continuous measurement of movements in the extremities of people with Parkinson's disease, a structured motor assessment administered by a trained examiner to a patient physically present in the same room, utilizes sensors to generate output to facilitate the evaluation of the patient. However, motor assessments with the patient and the examiner in the same room may not be feasible due to distances between the patient and the examiner and the risk of transmission of infections between the patient and the examiner. Therefore, we propose a protocol for the remote assessment by examiners in different locations of both (A) videos of patients recorded during in-person motor assessments and (B) live virtual assessments of patients in different locations from examiners. The proposed procedure provides a framework for providers, investigators, and patients in vastly diverse locations to conduct optimal motor assessments required to develop treatment plans utilizing precision medicine tailored to the specific needs of each individual patient. The proposed protocol generates the foundation for providers to remotely perform structured motor assessments necessary for optimal diagnosis and treatment of people with Parkinson's disease and related conditions.
Collapse
Affiliation(s)
- Abdelwahab Elshourbagy
- Misr University for Science and Technology, Al Motamayez District-6th of October, Giza Governorate 3236101, Egypt
| | | | - Hassan Abdalshafy
- Faculty of Medicine, Cairo University, Giza Governorate 12613, Egypt
| | - Samrah Javed
- Jinnah Sindh Medical University, Karachi, Sindh 75510, Pakistan
| | | | - Timothy Patrick Harrigan
- Research and Exploratory Development, Applied Physics Laboratory, The Johns Hopkins University, Laurel, MD 20723, United States
| | - Kelly Alexander Mills
- Department of Neurology, The Johns Hopkins University School of Medicine, Baltimore, MD 21205, United States
| | - Manuel Enrique Hernandez
- Carle Health College of Medicine, University of Illinois at Urbana-Champaign, Urbana, IL 61801, United States
| | - James Robert Brašić
- Section of High-Resolution Brain Positron Emission Tomography Imaging, Division of Nuclear Medicine and Molecular Imaging, The Russell H. Morgan Department of Radiology and Radiological Science, The Johns Hopkins University School of Medicine, Baltimore, MD 21205, United States
| |
Collapse
|
4
|
Yu T, Park KW, McKeown MJ, Wang ZJ. Clinically Informed Automated Assessment of Finger Tapping Videos in Parkinson's Disease. SENSORS (BASEL, SWITZERLAND) 2023; 23:9149. [PMID: 38005535 PMCID: PMC10674854 DOI: 10.3390/s23229149] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/19/2023] [Revised: 10/30/2023] [Accepted: 11/10/2023] [Indexed: 11/26/2023]
Abstract
The utilization of Artificial Intelligence (AI) for assessing motor performance in Parkinson's Disease (PD) offers substantial potential, particularly if the results can be integrated into clinical decision-making processes. However, the precise quantification of PD symptoms remains a persistent challenge. The current standard Unified Parkinson's Disease Rating Scale (UPDRS) and its variations serve as the primary clinical tools for evaluating motor symptoms in PD, but are time-intensive and prone to inter-rater variability. Recent work has applied data-driven machine learning techniques to analyze videos of PD patients performing motor tasks, such as finger tapping, a UPDRS task to assess bradykinesia. However, these methods often use abstract features that are not closely related to clinical experience. In this paper, we introduce a customized machine learning approach for the automated scoring of UPDRS bradykinesia using single-view RGB videos of finger tapping, based on the extraction of detailed features that rigorously conform to the established UPDRS guidelines. We applied the method to 75 videos from 50 PD patients collected in both a laboratory and a realistic clinic environment. The classification performance agreed well with expert assessors, and the features selected by the Decision Tree aligned with clinical knowledge. Our proposed framework was designed to remain relevant amid ongoing patient recruitment and technological progress. The proposed approach incorporates features that closely resonate with clinical reasoning and shows promise for clinical implementation in the foreseeable future.
Collapse
Affiliation(s)
- Tianze Yu
- Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC V6T 1Z4, Canada;
| | - Kye Won Park
- Pacific Parkinson Research Centre, University of British Columbia, Vancouver, BC V6T 1Z4, Canada; (K.W.P.); (M.J.M.)
| | - Martin J. McKeown
- Pacific Parkinson Research Centre, University of British Columbia, Vancouver, BC V6T 1Z4, Canada; (K.W.P.); (M.J.M.)
- Department of Neurology, Faculty of Medicine, University of British Columbia, Vancouver, BC V6T 1Z4, Canada
| | - Z. Jane Wang
- Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC V6T 1Z4, Canada;
| |
Collapse
|
5
|
Wang Q, Lyu W, Zhou J, Yu C. Sleep condition detection and assessment with optical fiber interferometer based on machine learning. iScience 2023; 26:107244. [PMID: 37496677 PMCID: PMC10366502 DOI: 10.1016/j.isci.2023.107244] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/02/2023] [Revised: 05/21/2023] [Accepted: 06/26/2023] [Indexed: 07/28/2023] Open
Abstract
The prevalence of sleep disorders has increased because of the fast-paced and stressful modern lifestyle, negatively impacting the quality of human life and work efficiency. It is crucial to address sleep problems. However, the current practice of diagnosing sleep disorders using polysomnography (PSG) has limitations such as complexity, large equipment, and low portability, hindering its practicality for daily use. To overcome these challenges, in this article an optical fiber sensor is proposed as a viable solution for sleep monitoring. This device offers benefits like low power consumption, non-invasiveness, absence of interference, and real-time health monitoring. We introduce the sensor with an optical fiber interferometer to capture ballistocardiography (BCG) and electrocardiogram (ECG) signals from the human body. Furthermore, a new machine learning method is proposed for sleep condition detection. Experimental results demonstrate the superior performance of this architecture and the proposed model in monitoring and assessing sleep quality.
Collapse
Affiliation(s)
- Qing Wang
- Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong
| | - Weimin Lyu
- Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong
| | - Jing Zhou
- Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong
| | - Changyuan Yu
- Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong
- Shenzhen Research Institute, The Hong Kong Polytechnic University, Shenzhen 518057, China
| |
Collapse
|