Kütahya Health Sciences University Research Information System
Not a member yet
19078 research outputs found
Sort by
KALÇA CERRAHİSİNDE DEVAMLI FASYA İLİAKA KOMPARTMAN BLOĞUNUN POSTOPERATİF AĞRI ÜZERİNE ETKİSİ : KLİNİK DENEYİMLERE DAYANAN BİR OLGU SERİSİ
No full text
Türkiye’de Hemşirelik Alanında Çocuklarla Yürütülen Sanal Gerçeklik Çalışmaları: Lisansüstü Tez İncelemesi
No full textConvolutional neural networks can diagnose schizophrenia
No full textSchizophrenia is a severe mental disorder that affects how individuals think, perceive, and behave, often making accurate and timely diagnosis a significant challenge for clinicians. Traditional diagnostic approaches, such as interviews and psychological tests, have limitations in capturing the complex neurological underpinnings of the condition. In recent years, machine learning and deep learning techniques have shown promise in improving diagnostic accuracy across a variety of medical domains. However, relatively few studies have applied these methods to schizophrenia diagnosis, despite their potential. In this study, we investigate whether convolutional neural networks can effectively diagnose schizophrenia using publicly available EEG data. We achieved classification accuracies of 98.26% in subject-independent settings and 91.21% in subject-dependent settings on the test data, using a fully connected layer based on a Multi-Layer Perceptron classifier. These results appear promising when compared to the current state of the art.</p
The Effectiveness of CURB-65 and PSI Scores in Predicting Hospital Length of Stay in Patients Diagnosed with Community-Acquired Pneumonia in the Emergency Department
No full textIntroduction: Community-acquired pneumonia (CAP) is a major cause of infectious disease mortality and a burden on healthcare systems. CURB-65 and Pneumonia Severity Index (PSI) scores assess disease severity and guide hospitalization decisions, but their role in predicting hospital stay remains unclear. This study evaluates the effectiveness of CURB-65 and PSI scores in predicting hospital stay and their utility in forecasting ICU admission and mortality. Materials and Methods: This retrospective study included adult CAP patients admitted to the Pulmonology Department via the Emergency Department between September 2021 and September 2022. CURB-65 and PSI scores were calculated, and their correlations with hospital stay, ICU admission, and mortality were analyzed using SPSS 20.0. Results: A total of 82 patients (median age 67.69 years) were included. Patients hospitalized ≤7 days had a median CURB-65 score of 1 and PSI score of 83, while those >7 days had a CURB-65 score of 2 and PSI score of 115. CURB-65 scores ≥2 were linked to prolonged stays (>7 days) in 70% of patients, compared to 41% in those ≤7 days. PSI scores also differed significantly between groups (p < 0.01). Moderate positive correlations were observed between hospital stay and both CURB-65 (r = 0.411) and PSI scores (r = 0.472). ROC analysis showed an AUC of 0.754 for PSI, with 84.8% sensitivity and 46.9% specificity. Conclusion: CURB-65 and PSI scores effectively predict hospital length of stay in CAP patients, aiding clinical decision-making and resource allocation
