Workflow for Medical Data Classification and Analysis

An approach for automated knowledge extraction and decision-making from medical images through a workflow for preprocessing of incoming X-ray images, analysis, classification and evaluation of the results is presented in this paper. The designed algorithm for analysis of medical X-rays images is based on machine learning and consists of three main phases: preprocessing of training and validation datasets, medical images classification utilizing Logistic Regression, Naive Bayes, SVM methods, evaluation of the model. A workflow was developed to process and analyze datasets of lung X-ray images containing four classes, and determine classification accuracy by examining performance evaluation parameters. © 2022 IEEE.

Efficacy and safety of emergency ureteroscopy as first-line treatment for patients with renal colic due to ureteral stones in the COVID-19 pandemic

Introduction & Objectives: Acute renal colic due to ureteral stones is a common emergency, which can be treated with conservative management, drainage of the kidney and delayed treatment, or emergency intervention. With the outbreak of COVID-19 infection and postponement of elective surgeries, emergency ureteroscopy became a valuable treatment option for acute renal colic in a single-stage setting. The objective of this study is to evaluate the efficacy and safety of emergency ureteroscopy as first-line treatment for patients with acute renal colic due to ureteral stones during the COVID-19 pandemic. Materials & Methods: A prospectively collected database of 120 patients with acute renal colic due to ureteral stone who underwent emergency ureteroscopy within 24 hours from hospitalization between March 2020 and December 2021, was reviewed. Data on patients’ preoperative characteristics, stone-free rates and complication rates was analyzed. Results: Patients’ mean age was 51.4±15.2 years. Male-to-female ratio was 73.3%/26.7%. Mean preoperative serum creatinine values were 120.1±64.1 umol/l. 33 patients (2.5%) had a solitary functioning kidney. Stone location was proximal ureter in 3 patients (27.5%), mid-ureter – in 12 (10%), distal ureter – in 73 (60.8%), distal and proximal ureter – in 2 cases (1.6%). Mean stone size was 8.1±3.3 mm. Stone-free rate after a single procedure was 95% and mean operative time – 25.1±11.5 min. Postoperative drainage was stent JJ in 34 (28.3%) and ureteral catheter for 12h – in 22 (18.3%) patients. 21 patients (17.5%) had a narrow ureter, necessitating the use of smaller caliber ureteroscope (6 Fr). In 2 patients (1.7%) the ureter could not be accessed and a stent JJ was inserted. Intraoperative complications were present in 5 cases – 1 ureteral perforation (0.8%) and 4 cases of upward stone migration (3.3%). Postoperative complications were fever in 2 patients (1.7%) and postoperative renal colic pain - in 7 (5.8%). Conclusions: The results of this prospective study suggest that emergency ureteroscopy is a safe and effective first-line treatment for acute renal colic due to ureteral stones. It offers a one-stage management, without the potential complications of obstruction and loss of renal function due to delayed treatment during the COVID-19 pandemic.

Application of a memristive neural network for classification of covid-19 patients

The global pandemic of COVID-19 has affected the lives of millions around the globe. We learn new facts about this corona virus every day. A contribution to this knowledge is described in the paper and it is related to employment of memristor neural networks and algorithms that help us analyze patients’ data and determine what patients are at increased risk for developing severe medical conditions once infected with the COVID-19. An efficient separation of potential patients in ill and healthy sub-groups is conducted using software and hardware neural networks, machine learning and unsupervised clustering. In the recent years, many works are related to reducing of neural chips area for the hardware realization of neural networks. For this purpose, a partial replacement of CMOS transistors in neural networks by memristors is made. Some of the main memristor advantages are its lower power consumption, nano-scale sizes, sound memory effect and a good compatibility to CMOS technology. In this reason, the main purpose of this paper is application of a memristor-based neural network with tantalum oxide memristor synapses for COVID-19 analysis. Additional experiments with data clustering are conducted. Experiments show that in fact patients with specific underlying health conditions and indicators are more predisposed to develop severe COVID-19 illness. This research is helpful for engineers and scientists to easier identifying patients that would need medical help. © 2021, North Atlantic University Union NAUN. All rights reserved.