Powered by OpenAIRE graph
Found an issue? Give us feedback
addClaim

Biossensores E-Tongue/E-Nose para deteção de analitos em fluídos humanos

Authors: Lemos, Armando Flávio Carneiro;

Biossensores E-Tongue/E-Nose para deteção de analitos em fluídos humanos

Abstract

Os métodos convencionais atuais, no tratamento de certas doenças, como doenças ginecológicas e do trato urinário, são particularmente dispendiosos e demorados, o que não facilita o processo de diagnóstico precoce da doença, podendo originar efeitos colaterais mais graves e recuperações mais demoradas. As doenças ginecológicas, afetam uma grande parte da população feminina tornando-se um problema grave da sociedade e as do trato urinário são generalizadas. Normalmente, estas patologias não são fatais, podendo, no entanto, causar desconforto. Geralmente, o organismo humano apresenta uma grande quantidade de micro-organismos comensais que, dependendo do estado de imunidade do paciente, podem se tornar infeciosas. O presente trabalho, tem como objetivo a criação/utilização de sistemas, eletronic nose (E-Nose) e eletronic tongue (E-Tongue), que consiga detetar e distinguir patologias do foro ginecológico e urinário, de forma efeciente, rápida, não invasiva, com baixo custo e potencial para aplicar num dispositivo home care. Os dados recolhidos da intereção do sistema misto, com os analitos alvo, serão analisados através dos métodos: análise dos componentes principais (PCA) e técnicas de Artificial Neural Networks (ANN), aferindo-se uma “impressão digital” do biomarcador e calibrar os sistemas para que se possam aplicar ao diagnóstico de patologias associadas. Os resultados obtidos, demonstraram que embora não seja difícil distinguir os biomarcadores através da técnica PCA, obtiveram-se bons indicadores com a criação de ANN, num biomarcador específico (tiramina), com uma probabilidade de 95% de acerto num teste cego.

Current conventional methods for the treatment of certain diseases, such as gynaecological and urinary tract diseases, are particularly expensive and time-consuming, which does not facilitate the process of early diagnosis of the disease, and may lead to more serious side effects and longer recovery. Gynaecological diseases affect a large part of the female population, becoming a serious problem for society, while those of the urinary tract are widespread. Normally, these pathologies are not fatal, but they may cause discomfort. Generally, the human organism presents a large quantity of commensal microorganisms which, depending on the patient's state of immunity, may become infectious. This work aims to create/use systems, electronic nose (E-Nose) and electronic tongue (E-Tongue), that can detect and distinguish gynaecological and urinary pathologies, in an effective, fast, non-invasive, low cost and potential to be applied in a home care device. The data collected from the interaction of the mixed system, with the target analytes, will be analysed using the methods: principal component analysis (PCA) and techniques of Artificial Neural Networks (ANN), assessing a "fingerprint" of the biomarker and calibrate the systems so that they can be applied to the diagnosis of associated pathologies. The results obtained, demonstrated that although it is not difficult to distinguish the biomarkers through the PCA technique, good indicators were obtained with the creation of ANN, in a specific biomarker (tyramine), with a 95% probability of accuracy in a blind test.

Mestrado em Engenharia Biomédica

Country
Portugal
Related Organizations
Keywords

E-Nose, PCA, Artificial neural networks, E-Tongue, Patologias ginecológicas e do trato urinário

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!