Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 2 de 2
Filter
Add filters

Database
Main subject
Language
Document Type
Year range
1.
Comput Biol Med ; 162: 107053, 2023 Aug.
Article in English | MEDLINE | ID: covidwho-2328348

ABSTRACT

Raman spectroscopy (RS) optical technology promises non-destructive and fast application in medical disease diagnosis in a single step. However, achieving clinically relevant performance levels remains challenging due to the inability to search for significant Raman signals at different scales. Here we propose a multi-scale sequential feature selection method that can capture global sequential features and local peak features for disease classification using RS data. Specifically, we utilize the Long short-term memory network (LSTM) module to extract global sequential features in the Raman spectra, as it can capture long-term dependencies present in the Raman spectral sequences. Meanwhile, the attention mechanism is employed to select local peak features that were ignored before and are the key to distinguishing different diseases. Experimental results on three public and in-house datasets demonstrate the superiority of our model compared with state-of-the-art methods for RS classification. In particular, our model achieves an accuracy of 97.9 ± 0.2% on the COVID-19 dataset, 76.3 ± 0.4% on the H-IV dataset, and 96.8 ± 1.9% on the H-V dataset.


Subject(s)
COVID-19 , Humans , Spectrum Analysis, Raman
2.
J Inflamm Res ; 15: 4199-4215, 2022.
Article in English | MEDLINE | ID: covidwho-1968916

ABSTRACT

The coronavirus disease 2019 (COVID-19), induced by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), is a multi-organ and multi-system disease with high morbidity and mortality in severe cases due to respiratory failure and severe cardiovascular events. However, the various manifestations of neurological and psychiatric (N/P) systems of COVID-19 should not be neglected. Some clinical studies have reported a high risk of N/P disorders in COVID-19 and post-COVID-19 patients and that their outcomes were positively associated with the disease severity. These clinical manifestations could attribute to direct SARS-CoV-2 invasion into the central nervous system (CNS), which is often complicated by systemic hypoxia, the dysfunctional activity of the renin-angiotensin system and other relevant pathological changes. These changes may remain long term and may even lead to persistent post-COVID consequences on the CNS, such as memory, attention and focus issues, persistent headaches, lingering loss of smell and taste, enduring muscle aches and chronic fatigue. Mild confusion and coma are serious adverse outcomes of neuropathological manifestations in COVID-19 patients, which could be diversiform and vary at different stages of the clinical course. Although lab investigations and neuro-imaging findings may help quantify the disease's risk, progress and prognosis, large-scale and persistent multicenter clinical cohort studies are needed to evaluate the impact of COVID-19 on the N/P systems. However, we used "Boolean Operators" to search for relevant research articles, reviews and clinical trials from PubMed and the ClinicalTrials dataset for "COVID-19 sequelae of N/P systems during post-COVID periods" with the time frame from December 2019 to April 2022, only found 42 in 254,716 COVID-19-related articles and 2 of 7931 clinical trials involved N/P sequelae during post-COVID periods. Due to the increasing number of infected cases and the incessant mutation characteristics of this virus, diagnostic and therapeutic guidelines for N/P manifestations should be further refined.

SELECTION OF CITATIONS
SEARCH DETAIL