Neural Computation-Based Methods for the Early Diagnosis and Prognosis of Alzheimer's Disease Not Using Neuroimaging Biomarkers: A Systematic Review.

Background: The growing number of older adults in recent decades has led to more prevalent geriatric diseases, such as strokes and dementia. Therefore, Alzheimer's disease (AD), as the most common type of dementia, has become more frequent too. Background: Objective: The goals of this work are to present state-of-the-art studies focused on the automatic diagnosis and prognosis of AD and its early stages, mainly mild cognitive impairment, and predicting how the research on this topic may change in the future. Methods: Articles found in the existing literature needed to fulfill several selection criteria. Among others, their classification methods were based on artificial neural networks (ANNs), including deep learning, and data not from brain signals or neuroimaging techniques were used. Considering our selection criteria, 42 articles published in the last decade were finally selected. Results: The most medically significant results are shown. Similar quantities of articles based on shallow and deep ANNs were found. Recurrent neural networks and transformers were common with speech or in longitudinal studies. Convolutional neural networks (CNNs) were popular with gait or combined with others in modular approaches. Above one third of the cross-sectional studies utilized multimodal data. Non-public datasets were frequently used in cross-sectional studies, whereas the opposite in longitudinal ones. The most popular databases were indicated, which will be helpful for future researchers in this field. Conclusions: The introduction of CNNs in the last decade and their superb results with neuroimaging data did not negatively affect the usage of other modalities. In fact, new ones emerged.

Utility of a Pulmonary Oedema Score for Predicting the Need for Mechanical Ventilation in COVID-19 Patients in a General Hospital.

BACKGROUND: The Radiographic Assessment of Lung Edema (RALE) score has been used to estimate the extent of pulmonary damage in patients with acute respiratory distress syndrome and might be useful in patients with COVID-19. AIM OF THE STUDY: To examine factors associated with the need for mechanical ventilation in hospitalized patients with a clinical diagnosis of COVID-19, and to estimate the predictive value of the RALE score. METHODS: In a series of patients admitted between April 14 and August 28, 2020, with a clinical diagnosis of COVID-19, we assessed lung involvement on the chest radiograph using the RALE score. We examined factors associated with the need for mechanical ventilation in bivariate and multivariate analysis. The area under the receiver operating curve (AUC) indicated the predictive value of the RALE score for need for mechanical ventilation. RESULTS: Among 189 patients, 90 (48%) were judged to need mechanical ventilation, although only 60 were placed on a ventilator. The factors associated with the need for mechanical ventilation were a RALE score >6 points, age >50 years, and presence of chronic kidney disease. The AUC for the RALE score was 60.9% (95% CI 52.9-68.9), indicating it was an acceptable predictor of needing mechanical ventilation. CONCLUSIONS: A score for extent of pulmonary oedema on the plain chest radiograph was a useful predictor of the need for mechanical ventilation of hospitalized patients with COVID-19.

Recurrent Neural Network for Inertial Gait User Recognition in Smartphones.

In this article, a gait recognition algorithm is presented based on the information obtained from inertial sensors embedded in a smartphone, in particular, the accelerometers and gyroscopes typically embedded on them. The algorithm processes the signal by extracting gait cycles, which are then fed into a Recurrent Neural Network (RNN) to generate feature vectors. To optimize the accuracy of this algorithm, we apply a random grid hyperparameter selection process followed by a hand-tuning method to reach the final hyperparameter configuration. The different configurations are tested on a public database with 744 users and compared with other algorithms that were previously tested on the same database. After reaching the best-performing configuration for our algorithm, we obtain an equal error rate (EER) of 11.48% when training with only 20% of the users. Even better, when using 70% of the users for training, that value drops to 7.55%. The system manages to improve on state-of-the-art methods, but we believe the algorithm could reach a significantly better performance if it was trained with more visits per user. With a large enough database with several visits per user, the algorithm could improve substantially.

Time-resolved chemiluminescent analysis of hydralazine in pharmaceuticals.

A new analytical method is proposed for determination of hydralazine (HZ) in pharmaceuticals--measurement of the chemiluminescence (CL) emitted after reaction with phosphoric-acidified KMnO4. The novelty of this method is the recording of the whole CL-time profile. Such a recording is possible by use of a CL-detector operating in tandem which enables the reactants to be mixed in the measurement cell only and, therefore, the CL is reaction monitored from beginning. At the precise time the pump is stopped signal recording is triggered and so CL evolution is recorded completely. The optimum chemical conditions for the determination were 0.8 mol L(-1) formaldehyde, 0.3 mmol L(-1) KMnO4, 4.0 mol L(-1) H3PO4, and a total flow of 0.37 mL s(-1). Two calibration graphs were plotted, CL intensity and area under the profile curve against HZ concentration. Exhaustive statistical analysis provided very interesting results, for example, accordance with Clayton's theory, detection limit below 0.2 microg mL(-1), and linear calibration ranges from 0.2 to 5.0 microg mL(-1). This method was successfully applied to the determination of HZ in pharmaceuticals. Because they are usually formulated in association with diuretics and beta-blockers, the method was used for analysis of HZ in pharmaceuticals that contained either HZ only or HZ with other hypotensive substances. Obtained and nominal content were approximately the same and experimental Student t values indicated there were no significant differences between the values.

Fast kinetic determination of 1-naphthylacetic acid in commercial formulations, soils, and fruit samples using stopped-flow phosphorimetry.

A kinetic method has been developed for the determination of 1-naphthylacetic acid by means of micellar-stabilized room temperature phosphorescence (MSRTP) using the stopped-flow mixing technique. The main feature of this system is that it diminishes the time required for the deoxygenation of the micellar medium and for the phosphorescence development. Phosphorescence enhancers such thallium(I) nitrate, sodium dodecyl sulfate (SDS), and sodium sulfite were optimized to obtain maximum sensitivity. The pH was also optimized as it strongly affects the luminescent properties of 1-naphthylacetic acid. A pH of 6.6 was selected as adequate for the phosphorescence development. The kinetic curve of 1-naphthylacetic acid phosphorescence was scanned at lambda(ex) = 278 nm and lambda(em) = 490 nm, and the maximum rate of phosphorescence was taken as the analytical signal. This was obtained by calculating the maximum slope of the curve in an interval of 3.6 s as it provided a good noise-to-signal ratio. This method permitted the determination of 1-naphthylacetic acid throughout a concentration range of 100-1800 ng mL(-1) with high precision (relative standard error = 0.91% and relative standard deviation = 2.30%; 1-naphthylacetic acid concentration = 800 ng mL(-1)). According to the Clayton criterion, the detection limit was 45 ng mL(-1). The same limit resulted in 39.3 ng mL(-1) when the error propagation theory was applied. The applicability of the method was successfully demonstrated by determining 1-naphthylacetic acid in different kind of samples, such as phytosanitary products, soils, pears, and apples. Recovery values not significantly different from the nominal content or the spiked amount were found for these determinations.