Pattern analysis of peripheral-vestibular deficits with machine learning using hierarchical clustering

A Comparative Study Using Vestibular Mapping in Sudden Sensorineural Hearing Loss With and Without Vertigo

OBJECTIVE

To investigate the impairment patterns in peripheral vestibular organs in sudden sensorineural hearing loss (SSNHL) with and without vertigo.

STUDY DESIGN

Retrospective study.

SETTING

Single tertiary medical center.

METHODS

Data from 165 SSNHL patients in a tertiary referral center from January 2017 to December 2022 were retrospectively analyzed. All patients underwent a video head impulse test, vestibular evoked myogenic potential test, and pure-tone audiometry. Hierarchical cluster analysis was performed to investigate vestibular impairment patterns. The prognosis of the hearing was determined using American Academy of Otolaryngology-Head and Neck Surgery recommendations.

RESULTS

After excluding patients with vestibular schwannoma and Meniere's disease, 152 patients were included in this study. A total of 73 of 152 patients were categorized as SSNHL with vertigo (SSNHL_V) and showed an independent merge of the posterior semicircular canal (PSCC) in cluster analysis. A total of 79 of 152 patients were categorized as SSNHL without vertigo (SSNHL_N) and showed an independent merge of saccule in cluster analysis. The PSCC (56.2%) and saccule (20.3%) were the most frequently impaired vestibular organs in SSNHL_V and SSNHL_N, respectively. In terms of prognosis, 106 of 152 patients had partial/no recovery and showed an independent merge of the PSCC in cluster analysis. A total of 46 of 152 patients had a complete recovery and showed an independent merge of the saccule in cluster analysis.

CONCLUSION

A tendency of isolated PSCC dysfunction was seen in SSNHL_V and partial/no recovery. A tendency of isolated saccular dysfunction was seen in SSNHL_N and complete recovery. Different treatments might be needed in SSNHL depending on the presence of vertigo.

Machine learning applications for multi-source data of edible crops: A review of current trends and future prospects

The quality and safety of edible crops are key links inseparable from human health and nutrition. In the era of rapid development of artificial intelligence, using it to mine multi-source information on edible crops provides new opportunities for industrial development and market supervision of edible crops. This review comprehensively summarized the applications of multi-source data combined with machine learning in the quality evaluation of edible crops. Multi-source data can provide more comprehensive and rich information from a single data source, as it can integrate different data information. Supervised and unsupervised machine learning is applied to data analysis to achieve different requirements for the quality evaluation of edible crops. Emphasized the advantages and disadvantages of techniques and analysis methods, the problems that need to be overcome, and promising development directions were proposed. To monitor the market in real-time, the quality evaluation methods of edible crops must be innovated.

EEG-based driver states discrimination by noise fraction analysis and novel clustering algorithm

Driver states are reported as one of the principal factors in driving safety. Distinguishing the driving driver state based on the artifact-free electroencephalogram (EEG) signal is an effective means, but redundant information and noise will inevitably reduce the signal-to-noise ratio of the EEG signal. This study proposes a method to automatically remove electrooculography (EOG) artifacts by noise fraction analysis. Specifically, multi-channel EEG recordings are collected after the driver experiences a long time driving and after a certain period of rest respectively. Noise fraction analysis is then applied to remove EOG artifacts by separating the multichannel EEG into components by optimizing the signal-to-noise quotient. The representation of data characteristics of the EEG after denoising is found in the Fisher ratio space. Additionally, a novel clustering algorithm is designed to identify denoising EEG by combining cluster ensemble and probability mixture model (CEPM). The EEG mapping plot is used to illustrate the effectiveness and efficiency of noise fraction analysis on the denoising of EEG signals. Adjusted rand index (ARI) and accuracy (ACC) are used to demonstrate clustering performance and precision. The results showed that the noise artifacts in the EEG were removed and the clustering accuracy of all participants was above 90%, resulting in a high driver fatigue recognition rate.

Environmental risk assessment associated with acidic volcanics in Egypt

The present work aims to study gamma rays emitted by radionuclides such as ²³⁸U, ²³²Th and ⁴⁰K from acidic Monqul volcanics. The studied volcanics are represented by a thick stratified lava flows interbanded with their pyroclastics. They are composed of thick lava flows of andesite and, to a lesser extent of basalt, and acidic volcanics including rhyolite and dacite. The average values of ²³⁸U, ²³²Th and ⁴⁰K are (46 ± 24 Bq kg^-1), (62 ± 11 Bq kg^-1) and (1227 ± 318 Bq kg^-1) in the rhyolite-dacite samples are greater than the worldwide average. The variation of radioactive bearing minerals observed inside granite faults produced the great amounts of radioactivity perceived in the samples. Calculating radiological risks is used to assess the public's radioactive risk from radionuclides revealed in the studied Rhyolite-dacite samples. The acceptable limit for excess lifetime cancer (ELCR) evaluations has been exceeded. As a result, Rhyolite-dacite are inappropriate for apply in building materials.