Cryptococcus neoformans is an opportunistic fungal pathogen with significant medical importance, especially in immunosuppressed patients. It is the causative agent of cryptococcosis. An estimated 220,000 annual cases of cryptococcal meningitis (CM) occur among people with HIV/AIDS globally, resulting in nearly 181,000 deaths. The gold standards for the diagnosis are either direct microscopic identification or fungal cultures. However, these diagnostic methods need special types of equipment and clinical expertise, and relatively low sensitivities have also been reported. This study aims to produce and implement a deep-learning approach to detect C. neoformans in patient samples. Therefore, we adopted the state-of-the-art VGG16 model, which determines the output information from a single image. Images that contain C. neoformans are designated positive, while others are designated negative throughout this section. Model training, validation, testing, and evaluation were conducted using frameworks and libraries. The state-of-the-art VGG16 model produced an accuracy and loss of 86.88% and 0.36203, respectively. Results prove that the deep learning framework VGG16 can be helpful as an alternative diagnostic method for the rapid and accurate identification of the C. neoformans, leading to early diagnosis and subsequent treatment. Further studies should include more and higher quality images to eliminate the limitations of the adopted deep learning model.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is responsible for the current pandemics of coronavirus disease. This virus is able to attack the cells of the airway epithelium by binding to the transmembrane angiotensin I converting enzyme 2 (ACE2). In the current study, we experimented a food supplement containing alpha-cyclodextrin and hydroxytyrosol as active compounds for the improvement of the defenses against the SARS-CoV-2. Hydroxytyrosol has anti-viral properties and is able to reduce the serum lipids in mice fed with high-cholesterol diet, and α-cyclodextrin has the ability to deplete sphingolipids and phospholipids from the cellular membranes. The aim of the present preliminary open non-controlled interventional study was to evaluate the efficacy of alpha-cyclodextrin and hydroxytyrosol in improving defenses against SARS-CoV-2. Fifty healthy volunteers at a higher risk of SARS-CoV-2 infection from Northern Cyprus and six positive individuals for SARS-CoV-2 by RT-qPCR assay were enrolled in this study. The in silico prediction analysis was performed using the bioinformatic tool D3DOCKING to evaluate the interactions of hydroxytyrosol and alpha-cyclodextrin with proteins involved in the biological cycle of SARS-CoV-2 in the humans. The 50 volunteers did not become positive in 15 days for SARS-CoV-2 RT-qPCR assay after the administration of the compound for two weeks, despite they were at higher risk of infection than the general population. Interestingly, in the cohort of six positive patients, two patients were administered with the spray and became negative after five days of spray administration, despite the viral load was higher in the treated subjects than the patients that did not take the compound and that became negative after ten days. In addition, we have identified the presence of possible direct interactions among hydroxytyrosol and alpha-cyclodextrin with the viral protein Spike and the human proteins ACE2 and TMPRSS2. We preliminary reported on the results of the possible role of alpha-cyclodextrin and hydroxytyrosol in improving defenses against SARS-CoV-2. The next step would be the administration of the compound on a larger cohort in a controlled study and see whether there is a reduced infection rate of SARS-CoV-2 in the treated subjects than in the non-treated individuals. (www.actabiomedica.it)

A substantial proportion of coronavirus disease 2019 (COVID-19) survivors continue to suffer from long-COVID-19 (LC) symptoms. Our study aimed to determine the risk factors for LC by using a patient population from Northern Cyprus. Subjects who were diagnosed with severe acute respiratory syndrome-2 (SARS-CoV-2) infection in our university hospital were invited and asked to fill in an online questionnaire. Data from 296 survivors who had recovered from COVID-19 infection at least 28 days prior the study was used in the statistical analysis. For determination of risk factors for “ongoing symptomatic COVID-19 (OSC)” and “Post-COVID-19 (PSC)” syndromes, the patient population was further divided into group 1 (Gr1) and group 2 (Gr2), that included survivors who were diagnosed with COVID-19 within 4-12 weeks and at least three months prior the study, respectively. The number of people with post-vaccination SARS-CoV-2 infection was 266 (89.9%). B.1.617.2 (Delta) (41.9%) was the most common SARS-CoV-2 variant responsible for the infections, followed by BA.1 (Omicron) (34.8%), B.1.1.7 (Alpha) (15.5%), and wild-type SARS-CoV-2 (7.8%). One-hundred-and-nineteen volunteers (40.2%) stated an increased frequency of COVID-19-related symptoms and experienced the symptoms in the week prior to the study. Of those, 81 (38.8%) and 38 (43.7%) were from Gr1 and Gr2 groups, respectively. Female gender, chronic illness, and symptomatic status at PCR testing were identified as risk factors for developing OSC syndrome, while only the latter showed a similar association with PSC symptoms. Our results also suggested that ongoing and persistent COVID-19-related symptoms are not influenced by the initial viral cycle threshold (Ct) values of the SARS-CoV-2, SARS-CoV-2 variant as well as vaccination status and type prior to COVID-19. Therefore, strategies other than vaccination are needed to combat the long-term effect of COVID-19, especially after symptomatic SARS-CoV-2 infection, and their possible economic burden on healthcare settings.

With the spread of SARS-CoV-2 variants with higher transmissibility and disease severity, rapid detection and isolation of patients remains a critical step in the control of the pandemic. RT-PCR is the recommended diagnostic test for the diagnosis of COVID-19. The current study aims to develop an artificial intelligence (AI)-driven COVID-19 RT-PCR detection system for rapid and reliable diagnosis, facilitating the heavy burden of healthcare workers. A multi-input deep convolutional neural network (DCNN) is proposed. A MobileNetV2 DCNN architecture was used to predict the possible diagnostic result of RT-PCR fluorescence data from patient nasopharyngeal sample analyses. Amplification curves in FAM (ORF1ab and N genes, SARS-CoV-2) and HEX (human RNAse P gene, internal control) channels of 400 samples were categorized as positive, weak-positive, negative or re-run (unspecific fluorescence). During the network training, HEX and FAM channel images for each sample were simultaneously presented to the DCNN. The obtained DCNN model was verified using another 160 new test samples. The proposed DCNN classified RT-PCR amplification curves correctly for all COVID-19 diagnostic categories with an accuracy, sensitivity, specificity, $F_1$-score, and AUC of the model reported to be 1. Furthermore, the performance of other pre-trained well-known DCNN models was also compared with the MobileNetV2 model using 5-fold cross-validation, and the results showed that there were no significant differences between the other models at the 5% significance level; however, the MobileNetV2 model outperformed others dramatically in terms of the training speed and fast convergence. The developed model can help rapidly diagnose COVID-19 patients and would be beneficial in tackling future pandemics.

Antibody tests, widely used as a complementary approach to reverse transcriptase–polymerase chain reaction testing in identifying COVID-19 cases, are used to measure antibodies developed for COVID-19. This study aimed to evaluate the different parameters of the FDA-authorized SARS-CoV-2 IgM antibody tests and to rank them according to their performance levels. In the study, we involved 27 antibody tests, and the analyzes were performed using the fuzzy preference ranking organization method for the enrichment evaluation model, a multi-criteria decision-making model. While criteria such as analytical sensitivity, specificity, positive predictive value, and negative predictive value were evaluated in the study, the ranking was reported by determining the importance levels of the criteria. According to our evaluation, Innovita 2019-nCoV Ab Test (colloidal gold) was at the top of the ranking. While Cellex qSARS-CoV-2 IgG/IgM Rapid Test and Assure COVID-19 IgG/IgM Rapid Tester ranked second and third on the list, the InBios-SCoV 2 Detect Ig M ELISA Rapid Test Kit was determined as the least preferable. The fuzzy preference ranking organization method for enrichment evaluation, which has been applied to many fields, can help decision-makers choose the appropriate antibody test for managing COVID-19 in controlling the global pandemic.

Accurate diagnosis of urinary tract infections (UTIs) is important as early diagnosis increases treatment rates, reduces the risk of infection and disease spread, and prevents deaths. This study aims to evaluate various parameters of existing and developing techniques for the diagnosis of UTIs, the majority of which are approved by the FDA, and rank them according to their performance levels. The study includes 16 UTI tests, and the fuzzy preference ranking organization method was used to analyze the parameters such as analytical efficiency, result time, specificity, sensitivity, positive predictive value, and negative predictive value. Our findings show that the biosensor test was the most indicative of expected test performance for UTIs, with a net flow of 0.0063. This was followed by real-time microscopy systems, catalase, and combined LE and nitrite, which were ranked second, third, and fourth with net flows of 0.003, 0.0026, and 0.0025, respectively. Sequence-based diagnostics was the least favourable alternative with a net flow of −0.0048. The F–PROMETHEE method can aid decision makers in making decisions on the most suitable UTI tests to support the outcomes of each country or patient based on specific conditions and priorities.