Search

Background: Brucellosis, as a serious zoonotic infectious disease, has been recognized as a re-emerging disease in the developing countries worldwide. In china, the incidence of brucellosis is increasing each year, seriously threatening the health of humans as well as animal populations. Despite a quite number of diagnostic methods currently being used for brucellosis, innovative technologies are still needed for its rapid and accurate diagnosis, especially in area where traditional diagnostic is unavailable. Methodology/Principal findings: In this study, a total of 22 B cell linear epitopes were predicted from five Brucella outer membrane proteins (OMPs) using an immunoinformatic approach. These epitopes were then chemically synthesized, and with the method of indirect ELISA (iELISA), each of them displayed a certain degree of capability in identifying human brucellosis positive sera. Subsequently, a fusion protein consisting of the 22 predicted epitopes was prokaryotically expressed and used as diagnostic antigen in a newly established brucellosis testing method, nano-ZnO modified paper-based ELISA (nano-p-ELISA). According to the verifying test using a collection of sera collected from brucellosis and non-brucellosis patients, the sensitivity and specificity of multiepitope based nano-p-ELISA were 92.38% and 98.35% respectively. The positive predictive value was 98.26% and the negative predictive value was 91.67%. The multiepitope based fusion protein also displayed significantly higher specificity than Brucella lipopolysaccharide (LPS) antigen. Conclusions: B cell epitopes are important candidates for serologically testing brucellosis. Multiepitope fusion protein based nano-p-ELISA displayed significantly sensitivity and specificity compared to Brucella LPS antigen. The strategy applied in this study will be helpful to develop rapid and accurate diagnostic method for brucellosis in human as well as animal populations. Author summary: Brucellosis is one of the most important zoonosis in the world and has caused tremendous economic losses in agriculture and animal husbandry in many countries. Developing rapid, sensitive and specific diagnostic methods is very important for early detection and treatment of brucellosis patients. In this study, a novel diagnostic technique, nano-ZnO modified paper ELISA, was established. The antigen used in this technique was a fusion protein containing multiple B cell epitopes, which were predicted from Brucella major outer membrane proteins such as Bp26, Omp31, Omp16, Omp2b and Omp25. Comparing to traditional LPS antigen, this multiepitope based antigen displayed considerably higher sensitivity and higher specificity in laboratory. With the strategy described in this paper, more efficient epitopes and protein antigen can be identified in the future. Currently, LPS antigen is only prepared from live Brucella, while protein antigen can be produced in large quantities in prokaryotic expression system. In addition to nano-p-ELISA, this protein antigen can also be used for development other methods such as fluorescent polarization assay (FPA) and immunochromatographic assay (ICA) to meet the varied demand for brucellosis testing. [ABSTRACT FROM AUTHOR]

Cardiovascular diseases (CVD) also known as heart disease are now the leading cause of death in the world. This paper presents research for the design and creation of a fuzzy logic-based expert system for the prognosis and diagnosis of heart disease that is precise, economical, and effective. This system entails a fuzzification module, knowledge base, inference engine, and defuzzification module where seven attributes such as chest pain type, HbA1c (Haemoglobin A1c), HDL (high-density lipoprotein), LDL (low-density lipoprotein), heart rate, age, and blood pressure are considered as input to the system. With the aid of the available literature and extensive consultation with medical experts in this field, an enriched knowledge database has been created with a sufficient number of IF-THEN rules for the diagnosis of heart disease. The inference engine then activates the appropriate IF-THEN rule from the knowledge base and determines the output value using the appropriate defuzzification technique after the fuzzification module fuzzifies each input depending on the appropriate membership function. Moreover, the fusion of web-based technology makes it suitable and cost-effective for the prognosis of heart disease for a patient and then he can take his decision for addressing the problem based on the status of his heart. On the other hand, it can also assist a medical practitioner to reach a more accurate conclusion regarding the treatment of heart disease for a patient. The Mamdani inference method has been used to evaluate the results. The system is tested with the Cleveland dataset and cross-checked with the in-field dataset. Compared with the other existing expert systems, the proposed method performs 98.08% accurately and can make accurate decisions for diagnosing heart diseases. [ABSTRACT FROM AUTHOR]

Early evaluation and diagnosis can significantly reduce the life-threatening nature of lung diseases. Computer-aided diagnostic systems (CADs) can help radiologists make more precise diagnoses and reduce misinterpretations in lung disease diagnosis. Existing literature indicates that more research is needed to correctly classify lung diseases in the presence of multiple classes for different radiographic imaging datasets. As a result, this paper proposes RVCNet, a hybrid deep neural network framework for predicting lung diseases from an X-ray dataset of multiple classes. This framework is developed based on the ideas of three deep learning techniques: ResNet101V2, VGG19, and a basic CNN model. In the feature extraction phase of this new hybrid architecture, hyperparameter fine-tuning is used. Additional layers, such as batch normalization, dropout, and a few dense layers, are applied in the classification phase. The proposed method is applied to a dataset of COVID-19, non-COVID lung infections, viral pneumonia, and normal patients' X-ray images. The experiments take into account 2262 training and 252 testing images. Results show that with the Nadam optimizer, the proposed algorithm has an overall classification accuracy, AUC, precision, recall, and F1-score of 91.27%, 92.31%, 90.48%, 98.30%, and 94.23%, respectively. Finally, these results are compared with some recent deep-learning models. For this four-class dataset, the proposed RVCNet has a classification accuracy of 91.27%, which is better than ResNet101V2, VGG19, VGG19 over CNN, and other stand-alone models. Finally, the application of the GRAD-CAM approach clearly interprets the classification of images by the RVCNet framework. [ABSTRACT FROM AUTHOR]

Reference 1 Yin D, Bai Q, Wu X, Li H, Shao J, Sun M, et al. (2021) Paper-based ELISA diagnosis technology for human brucellosis based on a multiepitope fusion protein. The last author's name is spelled incorrectly. [Extracted from the article]

Background: In the process of medical diagnosis, a large amount of uncertain and inconsistent information is inevitably involved. There have been many fruitful results were investigated for medical diagnosis by utilizing different traditional uncertainty mathematical tools. It is found that there is limited study on measuring reliability of the information involved are rare, moreover, the existed methods cannot give the measuring reliability of every judgment to all symptoms in details. Objectives: It is quite essential to recognize the impact on the reliability of the fuzzy information provided under inadequate experience, lack of knowledge and so on. In this paper, the notion of the Z-numbers soft set is proposed to handle the reliability of every judgment to all symptoms in details. The study in this paper is an interdisciplinary approach towards rapid and efficient medical diagnosis. Methods: An approach based on Z-numbers soft set (ZnSS)to medical diagnosis has been developed and is used to estimate whether two patterns or images are identical or approximately. The notion of Z-numbers soft set is proposed by combing the theory of soft set and Z-numbers theory. The basic properties of subset, equal, intersection, union and complement operations on the Z-numbers soft sets are defined and the similarity measure of two Z-numbers soft sets are also discussed in this paper. Results: An illustrative example similar to existing studies is showed to verify the effectiveness and feasibility, which can highlight the proposed method and demonstrate the solution characteristics. Conclusion: Diagnosing diseases by uncertainty symptoms is not a direct and simple task at all. The approach based on ZnSS presented in this paper can not only measure reliability of the information involved, but also give the measuring reliability of every judgment to all symptoms in details. [ABSTRACT FROM AUTHOR]

The purpose of this study was to determine the diagnostic efficacy of Xpert MTB/RIF assay for rapid diagnosis of Tuberculosis (TB) and detection of rifampicin (RIF) resistance in patients suspected of having EPTB, assessing it against traditional culture and drug susceptibility test (DST) by proportional method, and the ability to predict multidrug resistance TB by Xpert MTB/RIF assay. In this study, the Xpert MTB/RIF assay was applied to 1,614 extrapulmonary specimens. Compared with TB culture and Composite Reference Standard (CRS), the Xpert MTB/RIF assay had a high sensitivity and specificity for detection of EPTB. Depending on the culture method or CRS as the standard, sensitivity of the Xpert MTB/RIF assay for detection of MTB in pleural effusion, cerebrospinal fluid, thoracic drainage fluid and throat swabs specimens were lower than that of other specimens. According to the experimental results, we have reason to believe that Xpert MTB/RIF assay is a rapid and simple technique with high sensitivity and specificity for diagnosing EPTB and detecting drug resistance in variety of specimens. Xpert MTB/RIF assay combined with DST maybe identify more cases of multi-drug resistant tuberculosis (MDR-TB). Author summary: Tuberculosis (TB) is the second most deadly infectious disease after COVID-19. Improving the accessibility of WHO recommended rapid molecular diagnostic tests to achieve earlier and more accurate diagnosis of TB is an important part of strengthening TB laboratory work in the strategy of ending the epidemic of tuberculosis. Extrapulmonary tuberculosis (EPTB) accounts for 15% of all tuberculosis cases. Due to the unique biological samples of different classified EPTB and the occult nature of their onset, their diagnosis is more challenging. Smear microscopy is often insensitive and culture methods are prolonged. With the introduction of Xpert MTB/RIF assay (Cepheid Inc.), this has changed TB diagnostics by providing a rapid accessible platform to diagnose TB and identify rifampicin(RIF) resistance within 2h. Xpert MTB/RIF assay is a suite of semi-nested real-time fluorescent quantitative PCR in vitro diagnostic technologies with good detection efficiency. In recent years, WHO has limited recommended Xpert MTB/RIF assay to detect various types of samples other than sputum for preliminary diagnosis of EPTB. The purpose of this paper is to systematically evaluate the practical application effect of Xpert MTB/RIF assay in the clinical diagnosis of EPTB, and provide scientific guidance for clinicians.ű [ABSTRACT FROM AUTHOR]

Background: Neglected tropical diseases (NTDs) primarily affect the poorest populations, often living in remote, rural areas, urban slums or conflict zones. Arboviruses are a significant NTD category spread by mosquitoes. Dengue, Chikungunya, and Zika are three arboviruses that affect a large proportion of the population in Latin and South America. The clinical diagnosis of these arboviral diseases is a difficult task due to the concurrent circulation of several arboviruses which present similar symptoms, inaccurate serologic tests resulting from cross-reaction and co-infection with other arboviruses. Objective: The goal of this paper is to present evidence on the state of the art of studies investigating the automatic classification of arboviral diseases to support clinical diagnosis based on Machine Learning (ML) and Deep Learning (DL) models. Method: We carried out a Systematic Literature Review (SLR) in which Google Scholar was searched to identify key papers on the topic. From an initial 963 records (956 from string-based search and seven from a single backward snowballing procedure), only 15 relevant papers were identified. Results: Results show that current research is focused on the binary classification of Dengue, primarily using tree-based ML algorithms. Only one paper was identified using DL. Five papers presented solutions for multi-class problems, covering Dengue (and its variants) and Chikungunya. No papers were identified that investigated models to differentiate between Dengue, Chikungunya, and Zika. Conclusions: The use of an efficient clinical decision support system for arboviral diseases can improve the quality of the entire clinical process, thus increasing the accuracy of the diagnosis and the associated treatment. It should help physicians in their decision-making process and, consequently, improve the use of resources and the patient's quality of life. Author summary: Neglected tropical diseases (NTDs) primarily affect the poorest populations, often living in remote, rural areas, urban slums or conflict zones. Arboviruses are a significant NTD category spread by mosquitoes. Dengue, Chikungunya, and Zika are three arboviruses that affect a large proportion of the population in Latin and South America. The clinical diagnosis of these arboviral diseases is a difficult task due to the concurrent circulation of several arboviruses which present similar symptoms and, sometimes, inaccurate test results. In this paper, we present the state of the art of studies investigating the automatic classification of arboviral diseases based on Machine Learning (ML) and Deep Learning (DL) models. Results show that current research is focused on the classification of Dengue, primarily using tree-based ML algorithms. The use of an efficient clinical decision support system for arboviral diseases can improve the quality of the entire clinical process, thus increasing the accuracy of the diagnosis and the associated treatment. It should help physicians in their decision-making process and, consequently, improve the use of resources and the patient's quality of life. [ABSTRACT FROM AUTHOR]

An unbiased, widely accepted estimate of the rate of occurrence of new cases of autism over time would facilitate progress in understanding the causes of autism. The same may also apply to other disorders. While incidence is a widely used measure of occurrence, birth prevalence—the proportion of each birth year cohort with the disorder—is the appropriate measure for disorders and diseases of early childhood. Studies of autism epidemiology commonly speculate that estimates showing strong increases in rate of autism cases result from an increase in diagnosis rates rather than a true increase in cases. Unfortunately, current methods are not sufficient to provide a definitive resolution to this controversy. Prominent experts have written that it is virtually impossible to solve. This paper presents a novel method, time-to-event birth prevalence estimation (TTEPE), to provide accurate estimates of birth prevalence properly adjusted for changing diagnostic factors. It addresses the shortcomings of prior methods. TTEPE is based on well-known time-to-event (survival) analysis techniques. A discrete survival process models the rates of incident diagnoses by birth year and age. Diagnostic factors drive the probability of diagnosis as a function of the year of diagnosis. TTEPE models changes in diagnostic criteria, which can modify the effective birth prevalence when new criteria take effect. TTEPE incorporates the development of diagnosable symptoms with age. General-purpose optimization software estimates all parameters, forming a non-linear regression. The paper specifies all assumptions underlying the analysis and explores potential deviations from assumptions and optional additional analyses. A simulation study shows that TTEPE produces accurate parameter estimates, including trends in both birth prevalence and the probability of diagnosis in the presence of sampling effects from finite populations. TTEPE provides high power to resolve small differences in parameter values by utilizing all available data points. [ABSTRACT FROM AUTHOR]

Segmentation of retinal vessels is important for doctors to diagnose some diseases. The segmentation accuracy of retinal vessels can be effectively improved by using deep learning methods. However, most of the existing methods are incomplete for shallow feature extraction, and some superficial features are lost, resulting in blurred vessel boundaries and inaccurate segmentation of capillaries in the segmentation results. At the same time, the "layer-by-layer" information fusion between encoder and decoder makes the feature information extracted from the shallow layer of the network cannot be smoothly transferred to the deep layer of the network, resulting in noise in the segmentation features. In this paper, we propose the MFI-Net (Multi-resolution fusion input network) network model to alleviate the above problem to a certain extent. The multi-resolution input module in MFI-Net avoids the loss of coarse-grained feature information in the shallow layer by extracting local and global feature information in different resolutions. We have reconsidered the information fusion method between the encoder and the decoder, and used the information aggregation method to alleviate the information isolation between the shallow and deep layers of the network. MFI-Net is verified on three datasets, DRIVE, CHASE_DB1 and STARE. The experimental results show that our network is at a high level in several metrics, with F1 higher than U-Net by 2.42%, 2.46% and 1.61%, higher than R2U-Net by 1.47%, 2.22% and 0.08%, respectively. Finally, this paper proves the robustness of MFI-Net through experiments and discussions on the stability and generalization ability of MFI-Net. [ABSTRACT FROM AUTHOR]

The microscopic agglutination test (MAT) is the standard serological reference test for the diagnosis of leptospirosis, despite being a technically demanding and laborious procedure. The use of a locally optimised MAT panel is considered essential for proper performance and interpretation of results. This paper describes the procedure of selecting such an optimised panel for Sri Lanka, a country hyper-endemic for leptospirosis. MAT was performed using 24 strains on 1132 serum samples collected from patients presenting with acute undifferentiated fever. Of 24 strains, 15 were selected as the optimised panel, while only 11% of serum samples showed positivity. A geographical variation in predominantly reactive serovars was observed, whereas reactivity was low with the saprophytic strain Patoc. Testing with paired sera yielded a higher sensitivity but provided only a retrospective diagnosis. Serological tests based on ELISA with complimentary molecular diagnosis using PCR are a feasible and robust alternative approach to diagnose leptospirosis in countries having a higher burden of the disease. Author summary: Microscopic agglutination test is the most commonly used serological test in the diagnosis of leptospirosis. The test uses a live panel of Leptospira representing main serogroups and for proper performance of the test, an optimised panel which react well with patient samples need to be selected. This paper describes the procedure of selecting such an optimised panel for Sri Lanka which is a country hyper-endemic for leptospirosis. The test was done on serum samples collected from patients presented with acute undifferentiated fever with 24 panel of serogroups and 15 were selected as the optimised panel. The test was found to have a low sensitivity in the acute stage and ELISA based serological tests with molecular diagnosis using PCR assays would be a better way for diagnosis of leptospirosis. [ABSTRACT FROM AUTHOR]

Mild traumatic brain injury (mTBI or concussion) is receiving increased attention due to the incidence in contact sports and limitations with subjective (pen and paper) diagnostic approaches. If an mTBI is undiagnosed and the athlete prematurely returns to play, it can result in serious short-term and/or long-term health complications. This demonstrates the importance of providing more reliable mTBI diagnostic tools to mitigate misdiagnosis. Accordingly, there is a need to develop reliable and efficient objective approaches with computationally robust diagnostic methods. Here in this pilot study, we propose the extraction of Mel Frequency Cepstral Coefficient (MFCC) features from audio recordings of speech that were collected from athletes engaging in rugby union who were diagnosed with an mTBI or not. These features were trained on our novel particle swarm optimised (PSO) bidirectional long short-term memory attention (Bi-LSTM-A) deep learning model. Little-to-no overfitting occurred during the training process, indicating strong reliability of the approach regarding the current test dataset classification results and future test data. Sensitivity and specificity to distinguish those with an mTBI were 94.7% and 86.2%, respectively, with an AUROC score of 0.904. This indicates a strong potential for the deep learning approach, with future improvements in classification results relying on more participant data and further innovations to the Bi-LSTM-A model to fully establish this approach as a pragmatic mTBI diagnostic tool. [ABSTRACT FROM AUTHOR]

Background: Mycetoma is an important neglected tropical disease associated with debilitation, disfigurement and death if not diagnosed and treated adequately. In Pakistan, mycetoma cases have frequently been diagnosed in histopathology and microbiology laboratories. However, there is scarcity of published data from this country. Therefore, the objectives of this study were to evaluate the frequency and type of mycetoma reported in skin and soft tissue biopsies from a single center over 10 years and review of published literature from Pakistan. Method: This descriptive observational retrospective study was conducted at the Aga Khan University Hospital laboratory, Karachi, Pakistan. Laboratory data from 2009–2018 of skin and soft tissue biopsies with positive findings of mycetoma were retrieved from hospital information system. The variables for statistical analysis were age and gender of patient, anatomical site of lesion, residence of patient (geographical location) in the country, etiologic agents of mycetoma and significant gross and microscopic histopathological findings. The data was entered, and descriptive epidemiologic assessment was carried out using MS excel 2013. Geographical information system was used for mapping the location. Literature review of mycetoma cases reported from Pakistan was done on PubMed, Google search and PakMediNet from 1980 till April 2019. Result: During ten years of study period, 89 skin and soft tissue biopsies were reported as mycetoma, majority were eumycetoma [n = 66/89 (74%)] followed by actinomycetoma [n = 23/89 (26%)]. Involvement of lower limb was predominantly observed [n = 74/89 (83%)] in which foot had significant contribution [n = 65/74 (88%)]. Only 18 specimens were submitted for microbiological assessment and six grew agents of mycetoma, with Madurella mycetomatis reported in only three. Well-formed granuloma formation was observed in only 26%[n = 23/89] of cases. Specific geographical location was not identified, and cases were reported from across the country. From Pakistan, only two original papers and 7 case reports were available in published literature. Conclusion: This single center study reports a handful of cases of mycetoma from Pakistan. We conclude that the index of suspicion should remain high among treating surgeons and physicians and clinical laboratories should improve their diagnostic capacity and skills. This will have a great impact on disease outcome and patient's life. Author summary: World Health Organization (WHO) has included Mycetoma in the neglected tropical diseases. Epidemiological data of mycetoma cases from Pakistan is not available. Although physicians and surgeons frequently see cases of mycetoma in their clinical practice, but poor socioeconomic conditions of patients restrict laboratory diagnosis such as histopathological and microbiological confirmation of disease. This leads to disability, disfigurement and at times limb loss or mortality. Through this study we are documenting the diagnosed cases of mycetoma from specimens submitted to our laboratory. The diagnosis was mainly made by histopathological examination of samples. It is disappointing to note that mycetoma was not included in the differential diagnosis list of clinicians. Probably, that is the reason that very few samples were submitted to the microbiology laboratory for the culture to find out etiologic agents of eumycetoma and actinomycetoma. Overall, this study has highlighted the gaps in the clinical as well as laboratory diagnosis of this disease and case management. [ABSTRACT FROM AUTHOR]

To reorient food systems to ensure they deliver healthy diets that protect against multiple forms of malnutrition and diet-related disease and safeguard the environment, ecosystems, and natural resources, there is a need for better governance and accountability. However, decision-makers are often in the dark on how to navigate their food systems to achieve these multiple outcomes. Even where there is sufficient data to describe various elements, drivers, and outcomes of food systems, there is a lack of tools to assess how food systems are performing. This paper presents a diagnostic methodology for 39 indicators representing food supply, food environments, nutrition outcomes, and environmental outcomes that offer cutoffs to assess performance of national food systems. For each indicator, thresholds are presented for unlikely, potential, or likely challenge areas. This information can be used to generate actions and decisions on where and how to intervene in food systems to improve human and planetary health. A global assessment and two country case studies—Greece and Tanzania—illustrate how the diagnostics could spur decision options available to countries. [ABSTRACT FROM AUTHOR]

Near Infrared Spectroscopy (NIRS) has been applied in epidemiological surveillance studies of insect vectors of parasitic diseases, such as the Dengue's mosquitoes. However, regarding mollusks, vectors of important worldwide helminth diseases such as schistosomiasis, fascioliasis and angiostrongyliasis, NIRS studies are rare. This work proposes to establish and standardize the procedure of data collection and analysis using NIRS applied to medical malacology, i.e., to mollusk vectors identifications. Biomphalaria shells and live snails were analyzed regarding several operational aspects, such as: moisture, shell side and position of the live animal for acquisition of NIR spectra. Representative spectra of Biomphalaria shells and live snails were collected using an average of 50 scans per sample and resolution of 16 cm-1. For shells, the sample should first be dried for a minimum of 15 days at an average temperature of 26±1°C, and then placed directly in the equipment measurement window with its left side facing the light beam. Live animals should be dried with absorbent paper; placed into a glass jar, and analyzed similarly to the shells. Once standardized, the technique was applied aiming at two objectives: identification of Biomphalaria using only the shells and parasitological diagnosis for Schistosoma mansoni infection. The discrimination of the three Biomphalaria species intermediate hosts of S. mansoni only by shell has technical limit due to the scarcity of organic material. Nevertheless, it was possible to differentiate B. straminea from B. tenagophila and B. glabrata with 96% accuracy. As for the parasitological diagnosis, it was possible to differentiate infected mollusks shedding S. mansoni cercariae from the non-infected ones with 82, 5% accuracy. In conclusion, the Near Infrared Spectroscopy (NIR's) technique has proven to be an innovative and sound tool to detect infection by S. mansoni in the different species of Biomphalaria intermediate hosts. [ABSTRACT FROM AUTHOR]

This paper focuses on the application of deep learning (DL) in the diagnosis of coronavirus disease (COVID-19). The novelty of this work is in the introduction of optimized InceptionResNetV2 for COVID-19 (CO-IRv2) method. A part of the CO-IRv2 scheme is derived from the concepts of InceptionNet and ResNet with hyperparameter tuning, while the remaining part is a new architecture consisting of a global average pooling layer, batch normalization, dense layers, and dropout layers. The proposed CO-IRv2 is applied to a new dataset of 2481 computed tomography (CT) images formed by collecting two independent datasets. Data resizing and normalization are performed, and the evaluation is run up to 25 epochs. Various performance metrics, including precision, recall, accuracy, F1-score, area under the receiver operating characteristics (AUC) curve are used as performance metrics. The effectiveness of three optimizers known as Adam, Nadam and RMSProp are evaluated in classifying suspected COVID-19 patients and normal people. Results show that for CO-IRv2 and for CT images, the obtained accuracies of Adam, Nadam and RMSProp optimizers are 94.97%, 96.18% and 96.18%, respectively. Furthermore, it is shown here that for the case of CT images, CO-IRv2 with Nadam optimizer has better performance than existing DL algorithms in the diagnosis of COVID-19 patients. Finally, CO-IRv2 is applied to an X-ray dataset of 1662 images resulting in a classification accuracy of 99.40%. [ABSTRACT FROM AUTHOR]

This paper analyses COVID-19 patients' dynamics during the first wave in the region of Castilla y León (Spain) with around 2.4 million inhabitants using multi-state competing risk survival models. From the date registered as the start of the clinical process, it is assumed that a patient can progress through three intermediate states until reaching an absorbing state of recovery or death. Demographic characteristics, epidemiological factors such as the time of infection and previous vaccinations, clinical history, complications during the course of the disease and drug therapy for hospitalised patients are considered as candidate predictors. Regarding risk factors associated with mortality and severity, consistent results with many other studies have been found, such as older age, being male, and chronic diseases. Specifically, the hospitalisation (death) rate for those over 69 is 27.2% (19.8%) versus 5.3% (0.7%) for those under 70, and for males is 14.5%(7%) versus 8.3%(4.6%)for females. Among patients with chronic diseases the highest rates of hospitalisation are 26.1% for diabetes and 26.3% for kidney disease, while the highest death rate is 21.9% for cerebrovascular disease. Moreover, specific predictors for different transitions are given, and estimates of the probability of recovery and death for each patient are provided by the model. Some interesting results obtained are that for patients infected at the end of the period the hazard of transition from hospitalisation to ICU is significatively lower (p < 0.001) and the hazard of transition from hospitalisation to recovery is higher (p < 0.001). For patients previously vaccinated against pneumococcus the hazard of transition to recovery is higher (p < 0.001). Finally, internal validation and calibration of the model are also performed. [ABSTRACT FROM AUTHOR]