Machine learning applied to healthcare: a conceptual review

Gomes, Myller Augusto Santos; Kovaleski, João Luiz; Pagani, Regina; Silva, Vander Luiz da

doi:10.1080/03091902.2022.2080885

Cited by 7 publications

(4 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Supervised machine learning is a process of using samples of known categories to adjust the parameters of the classifier to achieve target performance. Unsupervised machine learning mainly involves discovering methods to solve various problems concerning pattern recognition from unknowns [ 83 ]. The field of application of machine learning is very broad.…”

Section: Resultsmentioning

confidence: 99%

The Application of Wearable Sensors and Machine Learning Algorithms in Rehabilitation Training: A Systematic Review

Wei,

2023

Sensors

View full text Add to dashboard Cite

The integration of wearable sensor technology and machine learning algorithms has significantly transformed the field of intelligent medical rehabilitation. These innovative technologies enable the collection of valuable movement, muscle, or nerve data during the rehabilitation process, empowering medical professionals to evaluate patient recovery and predict disease development more efficiently. This systematic review aims to study the application of wearable sensor technology and machine learning algorithms in different disease rehabilitation training programs, obtain the best sensors and algorithms that meet different disease rehabilitation conditions, and provide ideas for future research and development. A total of 1490 studies were retrieved from two databases, the Web of Science and IEEE Xplore, and finally 32 articles were selected. In this review, the selected papers employ different wearable sensors and machine learning algorithms to address different disease rehabilitation problems. Our analysis focuses on the types of wearable sensors employed, the application of machine learning algorithms, and the approach to rehabilitation training for different medical conditions. It summarizes the usage of different sensors and compares different machine learning algorithms. It can be observed that the combination of these two technologies can optimize the disease rehabilitation process and provide more possibilities for future home rehabilitation scenarios. Finally, the present limitations and suggestions for future developments are presented in the study.

show abstract

Section: Resultsmentioning

confidence: 99%

The Application of Wearable Sensors and Machine Learning Algorithms in Rehabilitation Training: A Systematic Review

Wei,

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Machine learning algorithm has many advantages compared with the traditional method of generating signal analysis, such as relatively high computational e ciency, the use of samples to determine the optimal solution of the model, etc. [31]. It should be noted that as common machine learning algorithms, WGCNA and RF analysis have been widely used in biomedical research.…”

Section: Discussionmentioning

confidence: 99%

Comprehensive analysis based on machine learning algorithm: Hspb1 and Lgals3 in neurons after spinal cord injury are closely related to autophagy

Yan

et al. 2023

Preprint

View full text Add to dashboard Cite

Spinal cord injury (SCI) refers to the dysfunction of sensorimotor and autonomic nerves caused by extensive and permanent loss of neurons after different degrees of damage to the spinal cord or cauda equina. The mechanism of spinal cord neuron injury after SCI has not been fully elucidated so far, although some opinions have been put forward. In this study, we extracted primary spinal neurons from neonatal rats, constructed a neuron injury model using glutamate stimulation, and performed full transcriptome sequencing analysis. We used machine learning algorithm (WGCNA, RF, and LASSO) to comprehensively and in-depth explore the important genes of spinal cord neuron injury and screen out the key genes Anxa2, Ccng1, Hspb1, Lgals3, Timp1 and S100a10, which are accompanied by the up-regulation of six expression levels of spinal cord neuron injury. Importantly, Hspb1 and Lgals3 are closely related to autophagy. To improve the reliability of our results, we downloaded the corresponding expression levels of six key genes of GSE2599, GSE20907, GSE45006, and GSE174549 to make ROC curve for verification, and then conducted RT-PCR verification of six key genes in vitro and in vivo, respectively. These findings will help us to further understand the pathogenesis of SCI, and may contribute to the screening of key targets for future clinical treatment.

show abstract

“…To delve deeper into the characterization of key genes implicated in spinal cord neuron excitotoxicity and investigate potential correlations, we undertook an additional analysis of the sequencing data using a machine learning algorithm. In comparison to conventional signal processing methods, machine learning algorithms offer numerous advantages, including enhanced computational efficiency and the capacity to derive optimal model solutions using sample data [59]. Notably, well-established machine learning algorithms such as WGCNA and RF have been extensively applied in biomedical research.…”

Section: Plos Onementioning

confidence: 99%

Hspb1 and Lgals3 in spinal neurons are closely associated with autophagy following excitotoxicity based on machine learning algorithms

Yan,

Li,

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Excitotoxicity represents the primary cause of neuronal death following spinal cord injury (SCI). While autophagy plays a critical and intricate role in SCI, the specific mechanism underlying the relationship between excitotoxicity and autophagy in SCI has been largely overlooked. In this study, we isolated primary spinal cord neurons from neonatal rats and induced excitotoxic neuronal injury by high concentrations of glutamic acid, mimicking an excitotoxic injury model. Subsequently, we performed transcriptome sequencing. Leveraging machine learning algorithms, including weighted correlation network analysis (WGCNA), random forest analysis (RF), and least absolute shrinkage and selection operator analysis (LASSO), we conducted a comprehensive investigation into key genes associated with spinal cord neuron injury. We also utilized protein-protein interaction network (PPI) analysis to identify pivotal proteins regulating key gene expression and analyzed key genes from public datasets (GSE2599, GSE20907, GSE45006, and GSE174549). Our findings revealed that six genes—Anxa2, S100a10, Ccng1, Timp1, Hspb1, and Lgals3—were significantly upregulated not only in vitro in neurons subjected to excitotoxic injury but also in rats with subacute SCI. Furthermore, Hspb1 and Lgals3 were closely linked to neuronal autophagy induced by excitotoxicity. Our findings contribute to a better understanding of excitotoxicity and autophagy, offering potential targets and a theoretical foundation for SCI diagnosis and treatment.

show abstract

Machine learning applied to healthcare: a conceptual review

Cited by 7 publications

References 59 publications

The Application of Wearable Sensors and Machine Learning Algorithms in Rehabilitation Training: A Systematic Review

The Application of Wearable Sensors and Machine Learning Algorithms in Rehabilitation Training: A Systematic Review

Comprehensive analysis based on machine learning algorithm: Hspb1 and Lgals3 in neurons after spinal cord injury are closely related to autophagy

Hspb1 and Lgals3 in spinal neurons are closely associated with autophagy following excitotoxicity based on machine learning algorithms

Contact Info

Product

Resources

About