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.

While antibiotic resistance is becoming increasingly serious today, there is almost no doubt that more challenging times await us in the future. Resistant microorganisms have increased in the past decades leading to limited treatment options, along with higher morbidity and mortality. Klebsiella pneumoniae is one of the significant microorganisms causing major public health problems by acquiring resistance to antibiotics and acting as an opportunistic pathogen of healthcare-associated infections. The production of extended spectrum beta-lactamases (ESBL) is one of the resistance mechanisms of K. pneumoniae against antibiotics. In this study, the future clinical situation of ESBL-producing K. pneumoniae was investigated in order to reflect the future scenarios to understand the severity of the issue and to determine critical points to prevent the spread of the ESBL-producing strain. For evaluation purposes, SIS-type mathematical modeling was used with retrospective medical data from the period from 2016 to 2019. Stability of the disease-free equilibrium and basic reproduction ratios were calculated. Numerical simulation of the SIS model was conducted to describe the dynamics of non-ESBL and ESBL-producing K. pneumoniae. In order to determine the most impactful parameter on the basic reproduction ratio, sensitivity analysis was performed. A study on mathematical modeling using data on ESBL-producing K. pneumoniae strains has not previously been performed in any health institution in Northern Cyprus, and the efficiency of the parameters determining the spread of the relevant strains has not been investigated. Through this study, the spread of ESBL-producing K. pneumoniae in a hospital environment was evaluated using a different approach. According to the study, in approximately seventy months, ESBL-producing K. pneumoniae strains will exceed non-ESBL K. pneumoniae strains. As a result, the analyses showed that hospital admissions and people infected with non-ESBL or ESBL-producing K. pneumoniae have the highest rate of spreading the infections. In addition, it was observed that the use of antibiotics plays a major role in the spread of ESBL-producing K. pneumoniae compared to other risk factors such as in-hospital transmissions. As a matter of course, recoveries from Klebsiella infections were seen to be the most effective way of limiting the spread. It can be concluded from the results that although the use of antibiotics is one of the most effective factors in the development of the increasing ESBL-producing K. pneumoniae,

No abstract