Dataset Information

Prediction of larynx function using multichannel surface EMG classification.

ABSTRACT: Total laryngectomy (TL) affects critical functions such as swallowing, coughing and speaking. An artificial, bio-engineered larynx (ABL), operated via myoelectric signals, may improve quality of life for TL patients. To evaluate the efficacy of using surface electromyography (sEMG) as a control signal to predict instances of swallowing, coughing and speaking, sEMG was recorded from submental, intercostal and diaphragm muscles. The cohort included TL and control participants. Swallowing, coughing, speaking and movement actions were recorded, and a range of classifiers were investigated for prediction of these actions. Our algorithm achieved F1-scores of 76.0 ± 4.4 % (swallows), 93.8 ± 2.8 % (coughs) and 70.5 ± 5.4 % (speech) for controls, and 67.7 ± 4.4 % (swallows), 71.0 ± 9.1 % (coughs) and 78.0 ± 3.8 % (speech) for TLs, using a random forest (RF) classifier. 75.1 ± 6.9 % of swallows were detected within 500 ms of onset in the controls, and 63.1 ± 6.1 % in TLs. sEMG can be used to predict critical larynx movements, although a viable ABL requires improvements. Results are particularly encouraging as they encompass a TL cohort. An ABL could alleviate many challenges faced by laryngectomees. This study represents a promising step toward realising such a device.

SUBMITTER: McNulty J

PROVIDER: S-EPMC7612081 | biostudies-literature | 2021 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction of larynx function using multichannel surface EMG classification.

McNulty Johnny J de Jager Kylie K Lancashire Henry T HT Graveston James J Birchall Martin M Vanhoestenberghe Anne A

IEEE transactions on medical robotics and bionics 20211026 4

Total laryngectomy (TL) affects critical functions such as swallowing, coughing and speaking. An artificial, bio-engineered larynx (ABL), operated via myoelectric signals, may improve quality of life for TL patients. To evaluate the efficacy of using surface electromyography (sEMG) as a control signal to predict instances of swallowing, coughing and speaking, sEMG was recorded from submental, intercostal and diaphragm muscles. The cohort included TL and control participants. Swallowing, coughing ...[more]

PMID: 34901764

Similar Datasets

Project description:Intervertebral disc degeneration is one of the most common reasons for chronic low back pain and sensomotoric deficits, often treated by lumbar sequestrectomy. Nevertheless, the prognostic factors relevant for time and quality of recovery, of the surgical procedure, relative to conservative treatment, remain controversial and require further investigation. Surface electrical stimulation (SES) may be an influential intervention, already showing positive impact on motor and sensory recovery in different patient groups. Since mechanisms of SES still remain unclear, further inquiry is needed.This is a prospective, monocentric, randomized, controlled clinical trial. A total of 80 adult patients suffering from a lumbar disc herniation (LDH; 40 treated surgically, 40 conservatively) are allocated in a ratio of 1:1. Patients in the treatment group will receive surface electromyography (EMG)-triggered electrical stimulation for eight weeks, whereas patients in the control group will not obtain any additional treatment. The primary outcome parameter is defined as the cold detection threshold (CDT), determined by quantitative sensory testing (QST), 24 months after intervention. Secondary outcome parameters include the inquiry of sensory nerve function by two-point discrimination and QST, the assessment of motor nerve function by manual muscle testing, and validated scales and scores. These include: the Oswestry Disability Index (ODI) and the Core Outcome Measures Index (COMI) assessing the domains pain, back-specific function, work disability, and patient satisfaction; the EQ-5D investigating the patient's generic health status; the painDETECT questionnaire (PD-Q) to identify neuropathic pain components; and the Beck Depression Inventory (BDI) to assess severity of depression. Moreover, neurological status, pain medication usage, and blood samples (CRP, TNF?, IL-1?, IL-6) will be evaluated. Study data generation (study site) and data storage, processing, and statistical analysis are clearly separated.The results of the RECO study will detect the effect of EMG-triggered multichannel SES on the improvement of mechanical and thermal sensitivity and the effect on motor recovery and pain, associated with clinical and laboratory parameters. Furthermore, data comparing surgical and conservative treatment can be collected. This will hopefully allow treatment recommendations for patients with LDH accompanied by a sensomotoric deficit.ISRCTN, ISRCTN12741173 . Registered on 15 January 2017.

Project description:BackgroundOntologies and catalogs of gene functions, such as the Gene Ontology (GO) and MIPS-FUN, assume that functional classes are organized hierarchically, that is, general functions include more specific ones. This has recently motivated the development of several machine learning algorithms for gene function prediction that leverages on this hierarchical organization where instances may belong to multiple classes. In addition, it is possible to exploit relationships among examples, since it is plausible that related genes tend to share functional annotations. Although these relationships have been identified and extensively studied in the area of protein-protein interaction (PPI) networks, they have not received much attention in hierarchical and multi-class gene function prediction. Relations between genes introduce autocorrelation in functional annotations and violate the assumption that instances are independently and identically distributed (i.i.d.), which underlines most machine learning algorithms. Although the explicit consideration of these relations brings additional complexity to the learning process, we expect substantial benefits in predictive accuracy of learned classifiers.ResultsThis article demonstrates the benefits (in terms of predictive accuracy) of considering autocorrelation in multi-class gene function prediction. We develop a tree-based algorithm for considering network autocorrelation in the setting of Hierarchical Multi-label Classification (HMC). We empirically evaluate the proposed algorithm, called NHMC (Network Hierarchical Multi-label Classification), on 12 yeast datasets using each of the MIPS-FUN and GO annotation schemes and exploiting 2 different PPI networks. The results clearly show that taking autocorrelation into account improves the predictive performance of the learned models for predicting gene function.ConclusionsOur newly developed method for HMC takes into account network information in the learning phase: When used for gene function prediction in the context of PPI networks, the explicit consideration of network autocorrelation increases the predictive performance of the learned models. Overall, we found that this holds for different gene features/ descriptions, functional annotation schemes, and PPI networks: Best results are achieved when the PPI network is dense and contains a large proportion of function-relevant interactions.

Dataset Information

Prediction of larynx function using multichannel surface EMG classification.

Publications

Prediction of larynx function using multichannel surface EMG classification.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets