Dataset Information

A Convenient Non-harm Cervical Spondylosis Intelligent Identity method based on Machine Learning.

ABSTRACT: Cervical spondylosis (CS), a most common orthopedic diseases, is mainly identified by the doctor's judgment from the clinical symptoms and cervical change provided by expensive instruments in hospital. Owing to the development of the surface electromyography (sEMG) technique and artificial intelligence, we proposed a convenient non-harm CS intelligent identify method EasiCNCSII, including the sEMG data acquisition and the CS identification. Faced with the limit testable muscles, the data acquisition method are proposed to conveniently and effectively collect data based on the tendons theory and CS etiology. Faced with high-dimension and the weak availability of the data, the 3-tier model EasiAI is developed to intelligently identify CS. The common features and new features are extracted from raw sEMG data in first tier. The EasiRF is proposed in second tier to further reduce the data dimension, improving the performance. A classification model based on gradient boosted regression tree is developed in third tier to identify CS. Compared with 4 common machine learning classification models, the EasiCNCSII achieves best performance of 91.02% in mean accuracy, 97.14% in mean sensitivity, 81.43% in mean specificity, 0.95 in mean AUC.

SUBMITTER: Wang N

PROVIDER: S-EPMC6258664 | biostudies-literature | 2018 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Convenient Non-harm Cervical Spondylosis Intelligent Identity method based on Machine Learning.

Wang Nana N Huang Xi X Rao Yi Y Xiao Jing J Lu Jiahui J Wang Nian N Cui Li L

Scientific reports 20181127 1

Cervical spondylosis (CS), a most common orthopedic diseases, is mainly identified by the doctor's judgment from the clinical symptoms and cervical change provided by expensive instruments in hospital. Owing to the development of the surface electromyography (sEMG) technique and artificial intelligence, we proposed a convenient non-harm CS intelligent identify method EasiCNCSII, including the sEMG data acquisition and the CS identification. Faced with the limit testable muscles, the data acquisi ...[more]

PMID: 30479349

Similar Datasets

Project description:BackgroundElectroacupuncture (EA) has been commonly used for the management of neck pain caused by cervical spondylosis (NPCS); however, current electrical instruments have limitations on intelligence, digitalization, and visualization. The intelligent electronic stimulator (CX-DZ-II) is a digital device with an evidence-based diagnosis and treatment system. This study aimed to investigate the efficacy and safety of the CX-DZ-II intelligent EA instrument for NPCS.Materials and methodsA total of 164 patients with NPCS [mean age (SD), 49.48 (13.47) years] were randomly assigned to receive 8 sessions (over 2 weeks) EA of the intelligent electronic stimulator (CX-DZ-II) or the regular electronic stimulator (SDZ-II). The primary outcome was the change of the visual analog scale (VAS) from baseline to 2 weeks of treatment. Secondary outcomes included mean scores of the VAS after each treatment in 1 week, responder rate, drug-usage rate of non-steroidal antipyretic analgesics (NSAAs), the occurrence rate of adverse events (AEs), proportions of apparatus with defect during treatment, and excellent rate of apparatus.ResultsThe intelligent electronic stimulator (CX-DZ-II) was non-inferior to the regular electronic stimulator (SDZ-II) for changes from baseline in the VAS [3.36 vs. 3.23, with a difference of 0.17 (95% CI, -0.36 to 0.69), P < 0.025 for non-inferiority]. No between-group differences were found in outcomes of VAS in 1 week, overall responders, and drug-usage rate of NSAAs. The defect rate and excellent rate of the instrument were similar in the CX-DZ-II and SDZ-II groups. Adverse events occurred in 9 (10.84%) patients in the CX-DZ-II group and 4 (5.00%) patients in the SDZ-II group.ConclusionThe intelligent electronic stimulator (CX-DZ-II) was non-inferior to the regular electronic stimulator (SDZ-II) in relieving neck pain. The intelligent electronic stimulator (CX-DZ-II) is a promising non-inferior alternative instrument for NPCS.Clinical trial registration[https://clinicaltrials.gov/], identifier [NCT030 05301].

Dataset Information

A Convenient Non-harm Cervical Spondylosis Intelligent Identity method based on Machine Learning.

Publications

A Convenient Non-harm Cervical Spondylosis Intelligent Identity method based on Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets