ABSTRACT
The pandemic of COVID-19 is continuously spreading, becoming a worldwide emergency. Early and fast identification of subjects with a current or past infection must be achieved to slow down the epidemiological widening. Here we report a Raman-based approach for the analysis of saliva, able to significantly discriminate the signal of patients with a current infection by COVID-19 from healthy subjects and/or subjects with a past infection. Our results demonstrated the differences in saliva biochemical composition of the three experimental groups, with modifications grouped in specific attributable spectral regions. The Raman-based classification model was able to discriminate the signal collected from COVID-19 patients with accuracy, precision, sensitivity and specificity of more than 95%. In order to translate this discrimination from the signal-level to the patient-level, we developed a Deep Learning model obtaining accuracy in the range 89-92%. These findings have implications for the creation of a potential Raman-based diagnostic tool, using saliva as minimal invasive and highly informative biofluid, demonstrating the efficacy of the classification model.
Subject(s)
COVID-19/diagnosis , Saliva/chemistry , Spectrum Analysis, Raman/methods , Aged , Aged, 80 and over , Antibodies, Viral/analysis , Comorbidity , Computational Biology , Deep Learning , Female , Humans , Male , Middle Aged , Normal Distribution , Reproducibility of Results , Sensitivity and SpecificityABSTRACT
Amyotrophic Lateral Sclerosis (ALS) is a neurodegenerative disease leading to progressive and irreversible muscle atrophy. The diagnosis of ALS is time-consuming and complex, with the clinical and neurophysiological evaluation accompanied by monitoring of progression and a long procedure for the discrimination of similar neurodegenerative diseases. The delayed diagnosis strongly slows the potential development of adequate therapies and the time frame for a prompt intervention. The discovery of new biomarkers could improve the disease diagnosis, as well as the therapeutic and rehabilitative effectiveness and monitoring of the pathological progression. In this work saliva collected from 19 patients with ALS, 10 affected by Parkinson's disease, 10 affected by Alzheimer's disease and 10 healthy subjects, was analysed using Raman spectroscopy, optimizing the parameters for detailed and reproducible spectra. The statistical multivariate analysis of the data revealed a significant difference between the groups, allowing the discrimination of the disease onset. Correlation of Raman data revealed a direct relationship with paraclinical scores, identifying multifactorial biochemical modifications related to the pathology. The proposed approach showed a promising accuracy in ALS onset discrimination, using a fast and sensitive procedure that can make more efficient the diagnostic procedure and the monitoring of therapeutic and rehabilitative processes in ALS.
Subject(s)
Amyotrophic Lateral Sclerosis/diagnosis , Biomarkers/metabolism , Saliva/metabolism , Aged , Aged, 80 and over , Alzheimer Disease/diagnosis , Alzheimer Disease/metabolism , Amyotrophic Lateral Sclerosis/metabolism , Disease Progression , Humans , Male , Middle Aged , Parkinson Disease/diagnosis , Parkinson Disease/metabolismABSTRACT
BACKGROUND: Kyphoscoliosis is a skeletal condition involving the hyperflexion of the thoracic spine. It is characterized by reduced chest wall compliance and impaired respiratory mechanisms leading to progressive hypo-ventilation. We evaluated the effectiveness and the safety of non-invasive ventilation (NIV) in patients after an episode of acute respiratory failure (ARF). METHODS: Eighteen patients with severe kyphoscoliosis who had been hospitalized for an episode of ARF were followed for 4 years. NIV was applied via mouthpiece (MPV) during the daytime and via mask during the night. The primary outcomes were changes in physiological and functional parameters as well as quality of life. Secondary outcomes were considered re-hospitalization and mortality rate after discharge. A set of control subjects was used for comparison. RESULTS: All patients showed a significant improvement in several clinical, physiological, functional and quality of life parameters. Four of them (22.2%) died during the four year follow-up period. In the uni-variate analysis patients who died had higher cardiac co-morbidity, lower MIP and SNIP, higher paCO2, and oxygen desaturation index at initial admission. CONCLUSIONS: Diurnal MPV associated with nocturnal NIV had significantly improved lung function, clinical outcomes and quality of life. It should be considered as a safe alternative to traditional administering of NIV.
