Redirigiendo al acceso original de articulo en 16 segundos...
Inicio  /  Information  /  Vol: 14 Par: 10 (2023)  /  Artículo
ARTÍCULO
TITULO

Innovative Visualization Approach for Biomechanical Time Series in Stroke Diagnosis Using Explainable Machine Learning Methods: A Proof-of-Concept Study

Kyriakos Apostolidis    
Christos Kokkotis    
Evangelos Karakasis    
Evangeli Karampina    
Serafeim Moustakidis    
Dimitrios Menychtas    
Georgios Giarmatzis    
Dimitrios Tsiptsios    
Konstantinos Vadikolias and Nikolaos Aggelousis    

Resumen

Stroke remains a predominant cause of mortality and disability worldwide. The endeavor to diagnose stroke through biomechanical time-series data coupled with Artificial Intelligence (AI) poses a formidable challenge, especially amidst constrained participant numbers. The challenge escalates when dealing with small datasets, a common scenario in preliminary medical research. While recent advances have ushered in few-shot learning algorithms adept at handling sparse data, this paper pioneers a distinctive methodology involving a visualization-centric approach to navigating the small-data challenge in diagnosing stroke survivors based on gait-analysis-derived biomechanical data. Employing Siamese neural networks (SNNs), our method transforms a biomechanical time series into visually intuitive images, facilitating a unique analytical lens. The kinematic data encapsulated comprise a spectrum of gait metrics, including movements of the ankle, knee, hip, and center of mass in three dimensions for both paretic and non-paretic legs. Following the visual transformation, the SNN serves as a potent feature extractor, mapping the data into a high-dimensional feature space conducive to classification. The extracted features are subsequently fed into various machine learning (ML) models like support vector machines (SVMs), Random Forest (RF), or neural networks (NN) for classification. In pursuit of heightened interpretability, a cornerstone in medical AI applications, we employ the Grad-CAM (Class Activation Map) tool to visually highlight the critical regions influencing the model?s decision. Our methodology, though exploratory, showcases a promising avenue for leveraging visualized biomechanical data in stroke diagnosis, achieving a perfect classification rate in our preliminary dataset. The visual inspection of generated images elucidates a clear separation of classes (100%), underscoring the potential of this visualization-driven approach in the realm of small data. This proof-of-concept study accentuates the novelty of visual data transformation in enhancing both interpretability and performance in stroke diagnosis using limited data, laying a robust foundation for future research in larger-scale evaluations.

 Artículos similares

       
 
Igor Ilin, Anastasia Levina, Konstantin Frolov, Alexandra Borremans, Alyona Ershova, Andrea Tick and Mariia Averina    
The active digitalization of the healthcare system has given impetus to the emergence of a new type of enterprise?high-tech medical organizations (HMO). Their main distinguishing feature is the use of innovative high-tech medical equipment. However, the ... ver más

 
Liliana Di Brigida, Alessandro Naddeo, Nicola Cappetti, Antonio Borri and Antonio Cortese    
Orthognathic surgery allows broad-spectrum deformity correction involving both aesthetic and functional aspects on the TMJ (temporo-mandibular joint) and on the facial skull district. The combination of Reverse Engineering (RE), Virtual Surgery Planning ... ver más
Revista: Applied Sciences

 
Xiaodong Yu, Hongsheng Yu, Wei Zhang, Luigi T. DeLuca and Ruiqi Shen    
3D printing manufacturing is used to manufacture hybrid rocket fuel grains featuring a special grid-like structure in order to control combustion performance. An innovative penetrative combustion mechanism, capable of affecting regression rate, was notic... ver más
Revista: Aerospace

 
Oleksandr Nesterenko,Igor Netesin,Valery Polischuk,Oleksandr Trofymchuk     Pág. 33 - 43
Improving the decision-making efficiency in defense planning based on the capabilities of military forces and means for performing purposeful tasks requires new methodological approaches and their implementation in the form of software information-analyt... ver más

 
Doupadi Bandara, Michael Woodward, Christopher Chin and Danchi Jiang    
This paper considers the feasibility of using augmented reality (AR) as a tool for enhancing visualization in maritime operations to avoid collision in different environmental conditions. According to the International Maritime Organization (IMO 2010), 9... ver más