RESUMO
The speedy development of intelligent technologies and gadgets has led to a drastic increment of dimensions within the datasets in recent years. Dimension reduction algorithms, such as feature selection methods, are crucial to resolving this obstacle. Currently, metaheuristic algorithms have been extensively used in feature selection tasks due to their acceptable computational cost and performance. In this article, a binary-modified version of aphid-ant mutualism (AAM) called binary aphid-ant mutualism (BAAM) is introduced to solve the feature selection problems. Like AAM, in BAAM, the intensification and diversification mechanisms are modeled via the intercommunication of aphids with other colonies' members, including aphids and ants. However, unlike AAM, the number of colonies' members can change in each iteration based on the attraction power of their leaders. Moreover, the second- and third-best individuals can take the place of the ringleader and lead the pioneer colony. Also, to maintain the population diversity, prevent premature convergence, and facilitate information sharing between individuals of colonies including aphids and ants, a random cross-over operator is utilized in BAAM. The proposed BAAM is compared with five other feature selection algorithms using several evaluation metrics. Twelve medical and nine non-medical benchmark datasets with different numbers of features, instances, and classes from the University of California, Irvine and Arizona State University repositories are considered for all the experiments. Moreover, a coronavirus disease (COVID-19) dataset is used to validate the effectiveness of the BAAM in real-world applications. Based on the acquired outcomes, the proposed BAAM outperformed other comparative methods in terms of classification accuracy using various classifiers, including K nearest neighbor, kernel-based extreme learning machine, and multi-class support vector machine, choosing the most informative features, the best and mean fitness values and convergence speed in most cases. As an instance, in the COVID-19 dataset, BAAM achieved 96.53% average accuracy and selected the most informative feature subset.
RESUMO
Introduction: The present study examines clinical features of patients infected with the 2019 sever acute respiratory syndrome coronavirus 2(SARS-Cov-2) leading to the coronavirus disease 2019 (covid-2019) in Rasool Akram hospital, Tehran, Iran. Material(s) and Method(s): This was a retrospective case report performed at Rasool Akram hospital, Tehran, Iran. A total of 77 patients referred to the hospital with SARS-Covid-2 infection. Data of the present study has been collected from March 5th to April 5th 2020. Result(s): Intensive care unit (ICU) has admitted 20 patients out of 77 patients. Among this sample, 23 patients were infected with acute respiratory syndrome and the other 18 remaining passed away. The calculated mean age of the patients admitted to the ICU was 60.8, 18 out of whom had deceased. In our results, male patients outnumber female patients where male patients account for 62.33% and female patients account for 37.66% of the whole study population. The most frequent and usual sings of this disease first reported as respirational distress or dyspnea (54.54%), coughs (54.54%) and myalgia (25.97). Only 3.89% of the patients had chest pain or chest discomfort. The most common comorbidities among those patients taken in the ICU and or deceased were diabetes, cardiovascular problems, hypertension and endocrine system problems. Out of 18 deaths, 11 (61.11%) cased had comorbidities. Among radiography and CT-scan results, 62.79% of the patients had involvement on chest radiography and 98.15% of the patients showed consolidation with ground glass opacities and 83.33% showed pleural effusion on their scan results. Conclusion(s): Having as much thorough information as possible about the characteristics of the patients infected with this virus helps us make better and sooner judgmental calls and more accurate diagnosis.Copyright © 2020 Ubiquity Press. All rights reserved.
RESUMO
Objective: Healthcare teams often forget the possibility of pregnancy when fecund women present for non-obstetric problems. In this patient group, routine pregnancy tests are often omitted and related documentation is missing. This patient safety issue was further highlighted by an anecdotal story when a surgical procedure was performed and mid surgery a pregnancy was identified. Prior to our intervention, simple point of care testing was limited to the emergency department. At ward level, pregnancy tests could only be performed using blood serum. Also, the admission forms did not specifically ask to exclude a pregnancy. Design: We reviewed whether all female surgical admissions of childbearing age underwent pregnancy testing. A baseline audit highlighted the need to introduce point of care pregnancy kits on the surgical ward. The initial audit was presented to surgical and anaesthetic departments. In collaboration with management, funding was secured to provide pregnancy kits for the surgical wards and the admission protocol was changed accordingly. Method: The project was completed over a period of 19 months (delayed by Covid). The base-line data collection was from November to December 2019 with presentation of the results in December 2020. Introduction of pregnancy kits in April 2021 and follow-up data collection in May to June 2021. A total of 159 case notes were reviewed using the hospital patient information system named 'Portal'. In the baseline survey, 86 case notes were screened for pregnancy tests and whether the findings were documented. After the introduction of pregnancy kits, the survey was repeated involving 73 women. The mean age was 32 with a range from 17 to 52 years of age. Results: Results were obtained retrospectively using the Portal system to screen for pregnancy tests (urine/serum β-HCG), any radiation exposure and surgical intervention. In 2021, prior to intervention, 75% of fecund patients were exposed to radiation and 95% underwent surgery without pregnancy testing. In 2021 the rates dropped to 32% for radiation exposure and surgery without pregnancy testing to 27%. Overall pregnancy testing in fecund women for surgical admission improved to 60%. Conclusions: Omitting pregnancy tests and subsequent documentation could be due to time pressures in particular during same day admissions. The remaining 40% could be captured by using a computer-based admission protocol which prompts the health care staff to undertake a pregnancy test, but adds more complexity to an already busy surgical admission ward.
RESUMO
Background: Close contact tracing is an essential measure that countries are applying to combat the epidemic of COVID-19. The purpose of contact tracing is to rapidly identify potentially infected individuals and prevent further spread of the disease. In this study, based on the factors affecting the COVID-19 transmission, a scoring protocol is provided for close contact tracing. Methods: First, the factors affecting the COVID-19 transmission in close contacts were identified by a rapid review of the literature. Data were gathered by searching the Embase, PubMed, Google Scholar, and Scopus databases. Then, by formulating and scoring the identified factors with two sessions of the expert panel, close contact transmission risk score determined, and a protocol for contacts tracing was designed. Results: Close contact transmission risk depends on the contact environment characteristics, the infectivity (virus shedding) of the sentinel case, and contact characteristics. Based on these factors, the close contact transmission risk score and contact tracing protocol were prepared. Conclusion: The close contact transmission risk scores will provide the ability to contact classifications and developing specific tracing strategies for them. Given that there are not any specific treatments for COVID-19 and lack of universal vaccination, applying nonpharmaceutical measures such as contact tracing along with physical distancing is very crucial. Therefore, we recommended this model to the evaluation of exposure risk and contact tracing. © 2021 Yazdani et al.
RESUMO
Exposing medical students to real-world situations and clinical practice experiences during their education years can help them build their professional value frameworks. The COVID-19 pandemic is one of the most challenging conditions that medical students have experienced;however, this pandemic have provided value-rich opportunities assisting in development and enhancement of their professional identity. This commentary aimed to emphasize the importance of medical students' exposure to clinical practice during the pandemic and the potential that such encounters provide for internalizing values.