scholarly journals A markerless 2D video of facial features recognition based artificial intelligence model to assist Parkinson’s disease screening (Preprint)

10.2196/29554 ◽  
2021 ◽  
Author(s):  
Xinyao Hou ◽  
Yanping Wang ◽  
Xinyi Wang ◽  
Jiahao Zhao ◽  
Xiaobo Zhu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Disease Screening ◽  
Facial Features

A markerless 2D video of facial features recognition based artificial intelligence model to assist Parkinson’s disease diagnosis (Preprint)

2021 ◽  
Author(s):  
Yu Zhang
Keyword(s):  
Artificial Intelligence ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Diagnostic Performance ◽  
Feature Recognition ◽  
Texture Features ◽  
Facial Feature ◽  
Disease Diagnosis ◽  
Facial Features ◽  
Geometric Features

UNSTRUCTURED Background: Mask face is a characteristic clinical manifestation of Parkinson's disease (PD), but subjective evaluations from different clinicians often show low consistency owing to lacking accurate detection technology. With the objective of making monitoring easier and more accessible, we developed a markerless 2D video of facial features recognition based artificial intelligence (AI) model to assess facial features of PD patients and aimed to investigate how AI could help neurologists improve PD early diagnostic performance. Methods: We collected 140 videos of facial expressions of 70 PD patients and 70 healthy controls from three hospitals. We developed and tested the AI model that performs mask face recognition of PD patients based on the acquisition and evaluation of facial features including geometric features and texture features, using a single 2D video camera. The diagnostic performance of AI model was compared with 5 neurologists. Results: Experimental results show that our AI models can achieve feasible and effective facial feature recognition ability to assist PD diagnosis. The precision and F1 values of PD diagnosis can reach 83% and 86%, using geometric features and texture features, respectively. When these two features are combined, a F1 value of 88% can be reached. Further, the facial features of patients with PD were not affected by the motor and non-motor symptoms of PD. Conclusions: PD patients commonly exhibit facial features. Video of facial features recognition based AI model can provide a valuable tool to assist PD diagnosis and potential of realizing remote monitoring on patients’ condition especially on the COVID-19 pandemic.

scholarly journals Will Artificial Intelligence Replace the Movement Disorders Specialist for Diagnosing and Managing Parkinson’s Disease?

2021 ◽  
pp. 1-6
Author(s):  
Matt Landers ◽  
Suchi Saria ◽  
Alberto J. Espay
Keyword(s):  
Artificial Intelligence ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Precision Medicine ◽  
Movement Disorders ◽  
Living Environment ◽  
Patient Status ◽  
Patient Symptom ◽  
Molecular Therapies ◽  
Improve Patient

The use of artificial intelligence (AI) to help diagnose and manage disease is of increasing interest to researchers and clinicians. Volumes of health data are generated from smartphones and ubiquitous inexpensive sensors. By using these data, AI can offer otherwise unobtainable insights about disease burden and patient status in a free-living environment. Moreover, from clinical datasets AI can improve patient symptom monitoring and global epidemiologic efforts. While these applications are exciting, it is necessary to examine both the utility and limitations of these novel analytic methods. The most promising uses of AI remain aspirational. For example, defining the molecular subtypes of Parkinson’s disease will be assisted by future applications of AI to relevant datasets. This will allow clinicians to match patients to molecular therapies and will thus help launch precision medicine. Until AI proves its potential in pushing the frontier of precision medicine, its utility will primarily remain in individualized monitoring, complementing but not replacing movement disorders specialists.

Identifying drugs with disease‐modifying potential in Parkinson's disease using artificial intelligence and pharmacoepidemiology

2020 ◽  
Vol 29 (8) ◽  
pp. 864-872
Author(s):  
Laura C. Maclagan ◽  
Naomi P. Visanji ◽  
Yi Cheng ◽  
Mina Tadrous ◽  
Alix M. B. Lacoste ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Disease Modifying

scholarly journals WHAT’S OLD IS NEW: USING ARTIFICIAL INTELLIGENCE TO ACCELERATE DISCOVERY OF NEW TREATMENTS

2019 ◽  
Vol 3 (Supplement_1) ◽  
pp. S16-S17
Author(s):  
Connie Marras ◽  
Laura C Maclagan ◽  
Yi Cheng ◽  
Naomi Visanji ◽  
Mina Tadrous ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Conditional Logistic Regression ◽  
Disease Diagnosis ◽  
Success Rates ◽  
Disease Modifying Drugs ◽  
Logistic Regression Models ◽  
Intelligence System ◽  
Disease Modifying

Abstract Given the high cost of drug development and low success rates, repurposing drugs already proven safe provides a promising avenue for identifying effective therapies with additional indications. The IBM Watson artificial intelligence system was used to search 1.3 million Medline abstracts to prioritize medications that may be potentially disease-modifying in Parkinson’s disease. We assessed patterns of use of the top 50 Watson-ranked drugs among 14,866 adults with Parkinson’s disease aged 70 and older who were matched to persons without Parkinson’s disease on age, sex, and comorbidity. Sociodemographic characteristics, chronic conditions, and use of other medications were compared using standardized differences. Patterns of potentially disease-modifying drug use were examined prior to and following ascertainment of Parkinson’s disease. Preliminary findings from multivariable conditional logistic regression models on the association between previous exposure to potentially disease-modifying drugs and Parkinson’s disease diagnosis will be presented.

Using Polar Expression Features and Nonlinear Machine Learning Classifier for Automated Parkinson’s Disease Screening

2020 ◽  
Vol 20 (1) ◽  
pp. 501-514 ◽  
Author(s):  
Tsung-Lung Yang ◽  
Ping-Ju Kan ◽  
Chia-Hung Lin ◽  
Hsin-Yu Lin ◽  
Wei-Ling Chen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Disease Screening ◽  
Learning Classifier

scholarly journals Artificial intelligence applications and robotic systems in Parkinson's disease (Review)

2021 ◽  
Vol 23 (2) ◽  
Author(s):  
Lacramioara Perju‑dumbrava ◽  
Maria Barsan ◽  
Daniel Leucuta ◽  
Luminita C. Popa ◽  
Cristina Pop ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Robotic Systems

scholarly journals Remote Evaluation of Parkinson's Disease Using a Conventional Webcam and Artificial Intelligence

2021 ◽  
Vol 12 ◽  
Author(s):  
Mariana H. G. Monje ◽  
Sergio Domínguez ◽  
Javier Vera-Olmos ◽  
Angelo Antonini ◽  
Tiago A. Mestre ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Upper Limb ◽  
Rating Scale ◽  
Hand Movement ◽  
Movement Speed ◽  
Clinical Scales ◽  
Video Frames ◽  
Disease Rating

Objective: This study aimed to prove the concept of a new optical video-based system to measure Parkinson's disease (PD) remotely using an accessible standard webcam.Methods: We consecutively enrolled a cohort of 42 patients with PD and healthy subjects (HSs). The participants were recorded performing MDS-UPDRS III bradykinesia upper limb tasks with a computer webcam. The video frames were processed using the artificial intelligence algorithms tracking the movements of the hands. The video extracted features were correlated with clinical rating using the Movement Disorder Society revision of the Unified Parkinson's Disease Rating Scale and inertial measurement units (IMUs). The developed classifiers were validated on an independent dataset.Results: We found significant differences in the motor performance of the patients with PD and HSs in all the bradykinesia upper limb motor tasks. The best performing classifiers were unilateral finger tapping and hand movement speed. The model correlated both with the IMUs for quantitative assessment of motor function and the clinical scales, hence demonstrating concurrent validity with the existing methods.Conclusions: We present here the proof-of-concept of a novel webcam-based technology to remotely detect the parkinsonian features using artificial intelligence. This method has preliminarily achieved a very high diagnostic accuracy and could be easily expanded to other disease manifestations to support PD management.

scholarly journals A novel artificial intelligence protocol to investigate potential leads for Parkinson's disease

RSC Advances ◽  
2020 ◽  
Vol 10 (39) ◽  
pp. 22939-22958
Author(s):  
Zhi-Dong Chen ◽  
Lu Zhao ◽  
Hsin-Yi Chen ◽  
Jia-Ning Gong ◽  
Xu Chen ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Parkinson’S Disease ◽  
Parkinson's Disease

Three candicates gained by a novel artificial intelligence protocol for Parkinson's disease (PD).

Sign in / Sign up

Export Citation Format

Share Document