Background:Logistic regression (LR) and linear discriminant analysis (LDA) are two popular statistical models for prediction of group membership. Although they are very similar, the LDA makes more assumptions about the data. When categorical and continuous variables used simultaneously, the optimal choice between the two models is questionable. In most studies, classification error (CE) is used to discriminate between subjects in several groups, but this index is not suitable to predict the accuracy of the outcome. The present study compared LR and LDA models using classification indices.Methods:This cross-sectional study selected 243 cancer patients. Sample sets of different sizes (n = 50, 100, 150, 200, 220) were randomly selected and the CE, B, and Q classification indices were calculated by the LR and LDA models.Results:CE revealed the a lack of superiority for one model over the other, but the results showed that LR performed better than LDA for the B and Q indices in all situations. No significant effect for sample size on CE was noted for selection of an optimal model. Assessment of the accuracy of prediction of real data indicated that the B and Q indices are appropriate for selection of an optimal model.Conclusion:The results of this study showed that LR performs better in some cases and LDA in others when based on CE. The CE index is not appropriate for classification, although the B and Q indices performed better and offered more efficient criteria for comparison and discrimination between groups.
Background:Cancer is one of the chronic diseases, which increases the risk of depression. The main causes of depression among these patients are pain due to metastasis, limited social activities and disability. Objectives: The aim of this research was to determine the prevalence of depression and relevant factors in patients with cancer referred to Shiraz Nemazee hospital for chemotherapy and radiotherapy. Patients and Methods: This was a cross-sectional study on 260 patients with cancer. To diagnose depression, the Beck questionnaire was used. To analyze data, logistic regression was more appropriate than the univariate analysis, because it simultaneously considers the effects of each of the predictors. Results: The prevalence of depression was 47.4%. There was a statistically significant association between depression and income (P < 0.001), family history of depression (P = 0.001), satisfaction with her or his condition (P < 0.001), disease duration (P < 0.001) and education (P = 0.025). Logistic regression revealed that the main effective factors were disease duration more than five years (OR = 5.9, P = 0.013), lack of satisfaction with her or his condition (OR = 19.6, P < 0.001) and family history of depression (OR = 2.4, P = 0.049). Conclusions: Consultation sessions are necessary to reduce depression of patients with cancer. Since depression may reduce quality of life and reaction to treatment, curing depression may relatively reduce side effects of disease for patients to have less pain and problems.
Purpose The triage and initial care of injured patients and a subsequent right level of care is paramount for an overall outcome after traumatic injury. Early recognition of patients is an important case of such decision-making with risk of worse prognosis. This article is to answer if clinical and paraclinical signs can predict the critical conditions of injured patients after traumatic injury resuscitation. Methods The study included 1107 trauma patients, 16 years and older. The patients were trauma victims of Levels I and II triage and admitted to the Rajaee (Emtiaz) Trauma Hospital, Shiraz, in 2014–2015. The cross-industry process for data mining methodology and modeling was used for assessing the best early clinical and paraclinical variables to predict the patients’ prognosis. Five modeling methods including the support vector machine, K-nearest neighbor algorithms, Bagging and Adaboost, and the neural network were compared by some evaluation criteria. Results Learning algorithms can predict the deterioration of injured patients by monitoring the Bagging and SVM models with 99% accuracy. The most-fitted variables were Glasgow Coma Scale score, base deficit, and diastolic blood pressure especially after initial resuscitation in the algorithms for overall outcome predictions. Conclusion Data mining could help in triage, initial treatment, and further decision-making for outcome measures in trauma patients. Clinical and paraclinical variables after resuscitation could predict short-term outcomes much better than variables on arrival. With artificial intelligence modeling system, diastolic blood pressure after resuscitation has a greater association with predicting early mortality rather than systolic blood pressure after resuscitation. Artificial intelligence monitoring may have a role in trauma care and should be further investigated.
Background. The lack of enough medical evidence about COVID-19 regarding optimal prevention, diagnosis, and treatment contributes negatively to the rapid increase in the number of cases globally. A chest computerized tomography (CT) scan has been introduced as the most sensitive diagnostic method. Therefore, this research aimed to examine and evaluate the chest CT scan as a screening measure of COVID-19 in trauma patients. Methods. This cross-sectional study was conducted in Rajaee Hospital in Shiraz from February to May 2020. All patients underwent unenhanced CT with a 16-slice CT scanner. The CT scans were evaluated in a blinded manner, and the main CT scan features were described and classified into four groups according to RSNA recommendation. Subsequently, the first two Radiological Society of North America (RSNA) categories with the highest probability of COVID-19 pneumonia (i.e., typical and indeterminate) were merged into the “positive CT scan group” and those with radiologic features with the least probability of COVID-19 pneumonia into “negative CT scan group.” Results. Chest CT scan had a sensitivity of 68%, specificity of 56%, positive predictive value of 34.8%, negative predictive value of 83.7%, and accuracy of 59.3% in detecting COVID-19 among trauma patients. Moreover, for the diagnosis of COVID-19 by CT scan in asymptomatic individuals, a sensitivity of 100%, specificity of 66.7%, and negative predictive value of 100% were obtained ( p value: 0.05). Conclusion. Findings of the study indicated that the CT scan’s sensitivity and specificity is less effective in diagnosing trauma patients with COVID-19 compared with nontraumatic people.
ObjectivesThe triage of trauma patients with potential COVID-19 remains a major challenge given that a significant number of patients may be asymptomatic or pre-symptomatic. This study aimed to compare the specificity and sensitivity of available triage systems for COVID-19 among trauma patients. Furthermore, it aimed to develop a novel triage system for SARS-CoV-2 detection among trauma patients in centers with limited resources.MethodsAll patients referred to our center from February to May 2020 were enrolled in this prospective study. We evaluated the SARS-CoV-2 triage protocols from the WHO, the Iranian Ministry of Health and Medical Education (MOHME), and the European Centre for Disease Control and Prevention (ECDC) for their effectiveness in finding COVID-19 infected individuals among trauma patients. We then used these data to design a stepwise triage protocol to detect COVID-19 positive patients among trauma patients.ResultsAccording to our findings, the WHO protocol showed 100% specificity and 13.3% sensitivity. The MOHME protocol had 99% specificity and 23.3% sensitivity. While the ECDC protocol showed 93.3% sensitivity and 89.5% specificity, it did not prioritize patients based on traumatic injuries and unstable conditions. Our stepwise triage protocol, which prioritizes traumatic injuries, had 93.3% sensitivity and 90.3% specificity.ConclusionOur study shows that the triage protocols from the WHO, MOHME and ECDC are not best equipped to diagnose SARS-CoV-2 infected individuals among trauma patients. In our proposed stepwise triage system, patients are triaged according to their hemodynamic conditions, COVID-19 related clinical states, and COVID-19 related laboratory findings. Our triage model can lead to more accurate and resource-effective management of trauma patients with potential COVID-19 infection.Level of evidenceLevel Ⅲ.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.