Artificial intelligence approach towards assessment of condition of COVID-19 patients - Identification of predictive biomarkers associated with severity of clinical condition and disease progression.

BACKGROUND AND OBJECTIVES: Although ML has been studied for different epidemiological and clinical issues as well as for survival prediction of COVID-19, there is a noticeable shortage of literature dealing with ML usage in prediction of disease severity changes through the course of the disease. In that way, predicting disease progression from mild towards moderate, severe and critical condition, would help not only to respond in a timely manner to prevent lethal results, but also to minimize the number of patients in hospitals where this is not necessary. METHODS: We present a methodology for the classification of patients into 4 distinct categories of the clinical condition of COVID-19 disease. Classification of patients is based on the values of blood biomarkers that were assessed by Gradient boosting regressor and which were selected as biomarkers that have the greatest influence in the classification of patients with COVID-19. RESULTS: The results show that among several tested algorithms, XGBoost classifier achieved best results with an average accuracy of 94% and an average F1-score of 94.3%. We have also extracted 10 best features from blood analysis that are strongly associated with patient condition and based on those features we can predict the severity of the clinical condition. CONCLUSIONS: The main advantage of our system is that it is a decision tree-based algorithm which is easier to interpret, instead of the use of black box models, which are not appealing in medical practice.

Giant liver hemangioma in patient with ileal gastrointestinal stromal tumor.

INTRODUCTION: Gastrointestinal stromal tumors are the most common mesenchymal neoplasms of the gastrointestinal tract. These tumors represent more than 80% of all mesenchymal tumors found in the gastrointestinal tract, though they account for only approximately 3% of all gastrointestinal malignancies. Literature offers case reports, which describe symptomatic gastrointestinal stromal tumors and they generally represent patients with larger tumors. CASE REPORT: We present the case of a small gastrointestinal stromal tumor in a 40-year-old man, with associated giant liver hemangioma and fever, and with history of abdominal discomfort and fever. Clinical examination revealed hepatosplenomegaly, palpable mass in the right lower abdomen, and signs of neurofibromatosis type 1 (Morbus von Recklinghausen). Computed tomography revealed a giant tumor in the right lobe of the liver. Magnetic resonance showed abscess in the hemangioma of the liver. An intestinal tumor was incidentally found and excised during surgical laparotomy. An intestinal gastrointestinal stromal tumor was revealed by histopathology and confirmed by immunohistochemistry. Although a multidisciplinary team proposed surgical removal of the liver tumor mass, the surgeons decided to follow up the patient because of a high risk of new intervention. CONCLUSION: According to the available data, this is a very rare case of small intestinal gastrointestinal stromal tumor, with symptoms of fever and giant abscess in the liver hemangioma.