Development of neural network models for prediction of the outcome of COVID-19 hospitalized patients based on initial laboratory findings, demographics, and comorbidities.

Background: During the process of the treatment of COVID-19 hospitalized patients, physicians still face a lot of unknowns and problems. Despite the application of the treatment protocol, it is still unknown why the medical status of a certain number of patients worsens and ends with death. Many factors were analyzed for the prediction of the clinical outcome of the patients using different methods. The aim of this paper was to develop a prediction model based on initial laboratory blood test results, accompanying comorbidities, and demographics to help physicians to better understand the medical state of patients with respect to possible clinical outcomes using neural networks, hypothesis testing, and confidence intervals. Methods: The research had retrospective-prospective, descriptive, and analytical character. As inputs for this research, 12 components of laboratory blood test results, six accompanying comorbidities, and demographics (age and gender) data were collected from hospital information system in Sarajevo for each patient from a sample of 634 hospitalized patients. Clinical outcome of the hospitalized patients, survival or death, was recorded 30 days after admission to the hospital. The prediction model was designed using a neural network. In addition, formal hypothesis tests were performed to investigate whether there were significant differences in laboratory blood test results and age between patients who died and those who survived, including the construction of 95% confidence intervals. Results: In this paper, 11 neural networks were developed with different threshold values to determine the optimal neural network with the highest prediction performance. The performances of the neural networks were evaluated by accuracy, precision, sensitivity, and specificity. Optimal neural network model evaluation metrics are: accuracy = 87.78%, precision = 96.37%, sensitivity = 90.07%, and specificity = 62.16%. Significantly higher values (P < 0.05) of blood laboratory result components and age were detected in patients who died. Conclusion: Optimal neural network model, results of hypothesis tests, and confidence intervals could help to predict, analyze, and better understand the medical state of COVID-19 hospitalized patients and thus reduce the mortality rate.

Arterial Hypertension in Patients with COVID-19 - Neural Network Model.

Background: Angiotensin-converting enzyme 2 (ACE2) is not only an enzyme but also a functional receptor on cell surfaces through which Severe acute respiratory syndrome coronavirus 2 (SARS-CoV2). The exact mechanism by which arterial hypertension (particularly regulated) could affect the presentation and outcome of Coronavirus disease-19 (COVID-19) has not been fully elucidated. Objective: The aim of this study was to analyze the parameters of patients with verified COVID-19 and existing arterial hypertension at the time of hospital admission and to develop neural network model. Methods: The research had a cross-sectional descriptive and analytical character, and included patients (n=634) who were hospitalized in the General Hospital "Prim. dr. Abdulah Nakas" in Sarajevo, Bosnia and Herzegovina, in the period from 01 Sep 2020 to 01 May 2021. From the hospital information system, which is used in everyday clinical work, laboratory parameters at admission were verified, along with demographic data, the comorbidities, while the outcome (recovery, death) was recorded thirty days after the admission. Results: Out of the total number, in 314 patients (200 males), arterial hypertension was verified, out of which, 56 (17.83%) patients died. Patients were divided into two groups, according to outcome, i.e., whether they survived COVID-19 infection or not. A significant difference in age (p = 0.00), erythrocyte count (p = 0.03), haemoglobin (p = 0.05), hematocrit (p = 0.03), platelets count (p = 0.00), leukocytes (p = 0.01), neutrophils (p = 0.00), lymphocytes (p = 0.00), monocytes (p = 0.00), basophils (p = 0.00), eosinophils (p = 0.00), C-reactive protein (p = 0.00) and D-dimer (p = 0.01) was noted. When patients who died and had hypertension were compared with those who died and did not have hypertension (n = 15), out of alll the analyzed parameters, the only significant difference was established in the patient's age (p = 0.00). In case when patients with hypertension who died were compared to patients with hypertension and diabetes mellitus who died no significant differences were found between features. Conclusion: Patients with hypertension and COVID-19 who died were older, had higher values of erythrocytes, hemoglobin, hematocrit, leukocytes, neutrophils, CRP and D-dimer, and lower values of platelets, lymphocytes, monocytes, basophils and eosinophils count at admission. Compared to deaths without hypertension, the only difference that was established was that patients with hypertension were older.

Rare giant female adnexal tumor of probable Wolffian origin: a case report.

Female adnexal tumors of probable Wolffian origin (FATWOs) are extremely rare tumors, with only around 100 cases published worldwide. FATWOs are most frequently found in the broad ligament, but these can also appear in the mesosalpinx, Fallopian tube, ovary, paravaginal region or peritoneum. We present a case of a 68-year-old female with a history of painless abdominal distension and frequent urination, with palpable big abdominal mass. Initial diagnosis was made using ultrasound and computed tomography scan that showed 22 × 21-cm tumor with solid and cystic components. Blood test showed elevated serum levels of CA 125, HE4 and Roma index. Intraoperatively, a large abdominopelvic encapsulated mass, fixated to surrounding tissue, was found. Our patient underwent hysterectomy 12 years ago. Total tumor resection, including bilateral adnexectomy, was performed. At 6 months of following, there was no evidence of disease. Here, we report extremely rare abdominal tumors and one of the biggest FATWOs reported so far.

Challenges of Surgical Treatment of Atypical Giant Choledochal Cyst with the Absence of Gallbladder in Adult Patient.

Choledochal cysts (CCs) are rare congenital anomalies in the form of cystic dilatation of any part of the biliary tree, and they rarely reach the size over 10 cm. We present a case of a 51-year-old female with a one-year history of abdominal pain and palpable mass in the epigastrium and right upper abdomen. Diagnosis of giant CC was made using magnetic resonance cholangiopancreatography. Intraoperatively, a large CC without gallbladder (no previous cholecystectomy was performed) was found under the liver pushing the surrounding structures, extending into the intrapancreatic portion of bile ducts and leading to the destruction of the backside of the pancreas head. Complete excision of CC and biliopancreatic reconstruction was achieved by Roux-en-Y pancreaticojejunostomy and hepaticojejunostomy. This case report describes an extremely rare association between an atypical giant choledochal cyst and gallbladder agenesis.