Yazar "Tunç, Zeynep" seçeneğine göre listele
Listeleniyor 1 - 15 / 15
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Analyzing and detecting risk factors for the diagnosis of angina pectoris with machine learning(2023) Özhan, Onural; Çiçek, İpek Balıkçı; Tunç, ZeynepAim: To classify angina pectoris (AP) in women by applying the Bagged CART approach, which is one of the machine learning (ML) methods, to the open-access AP dataset. Another aim is to reveal the risk factors associated with AP in women through modeling. Materials and Methods: In the current study, modeling was done with the Bagged CART technique utilizing an open-access data set containing the factors associated with AP. Model results were assessed with accuracy (ACC), sensitivity (Sen), balanced accu racy (BACC), positive predictive value (PPV), specificity (Spe), negative predictive value (NPV), and F1-score performance criteria. In addition, a 5-fold cross-validation approach was applied in the modeling phase. Finally, variable importance was derived with model ing. Results: ACC, BACC, Sen, Spe, PPV, NPV, and F1-score from Bagged CART modeling were 98.5%, 98.5%, 99.0%, 98.0%, 98.0%, 99.0%, and 98.5%, respectively. Depending on the variable importance values calculated for the input variables investigated in the current study, age, family history of myocardial infarction: yes, the average number of cigarettes smoked per day smoking status: current, family history of angina: yes, hypertensive condition: moderate, smoking status: ex, hypertensive condition: mild, family history of stroke: yes, whether the woman has diabetes: yes were obtained as the most important variables associated with AP. Conclusion: With the ML model used, the AP dataset was classified successfully, and the associated risk factors were revealed. ML models can be used as clinical decision support systems for early diagnosis and treatment.Öğe Classification of stroke with gradient boosting tree using smote-based oversampling method(2021) Yağın, Fatma Hilal; Cicek, Ipek Balikci; Tunç, ZeynepThe aim of this study is to classify the disease with the gradient increasing tree classification method in an open access dataset containing data from patients with and without stroke disease. In addition, it is aimed to compare the results by balancing the data with the oversampling method Synthetic Minority Over-sampling Technique (SMOTE) which is one of the data balancing methods in the study. In this study, a dataset containing information about patients with and without stroke disease obtained from the address "https://www.kaggle.com/asaumya/healthcare-problem-prediction-stroke-patients" was used. In the study, SMOTE was used as the data balancing method, and the gradient boosting tree method was used in the modeling. The performance of the model was evaluated by Specificity, sensitivity, accuracy, positive predictive value and negative predictive values. Specificity, sensitivity, accuracy, positive predictive value and negative predictive values were obtained as 0.0887, 0.9772, 0.9339, 0.9544 and 0.1679, respectively, according to the modeling result using the gardient boosting tree method using the original version of the dataset. Specificity, sensitivity, accuracy, positive predictive value and negative predictive values were obtained as 0.0887, 0.9772, 0.9339, 0.9544 and 0.1679, respectively, according to the modeling result using the gardient boosting tree method using the SMOTE applied version of the dataset. When the results obtained from the study were examined, the modeling results made with the SMOTE applied dataset were obtained more consistently and realistically. As a result, it is suggested that researchers use dataset balancing methods to acquire more accurate results whenever they come across an unbalanced dataset problem.Öğe A clinical decision support system based on machine learning for the prediction of diabetes mellitus(2022) Evren, Bahri; Tunç, ZeynepAim: Early diagnosis of diabetes mellitus (DM), one of the most important health prob- lems worldwide, and taking necessary steps are very important. Therefore, it has become very important to develop models for the prediction of the disease. The aim of this study is to create a clinical decision support model with Stochastic Gradient Boosting, a machine learning model for DM prediction. Materials and Methods: In the study, modeling was done with the Stochastic Gradient Boosting method using an open access data set including the factors associated with DM. Model results were evaluated with accuracy, balanced accuracy, sensitivity, selectivity, positive predictive value, negative predictive value, and F1-score performance metrics. In addition, 5-fold cross-validation method was used in the modeling phase. Finally, variable importance values were obtained by modeling. Results: Accuracy, balanced accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score from by Stochastic Gradient Boosting modeling were 93.6%, 92.8%, 91.7%, 93.9%, 73.3%, 98.4%, and 81.5%, respectively. According to the variable importance values obtained for the input variables in the data set examined in this study, the most important variables are glucose, age, systolic BP, cholesterol, chol/HDL, BMI, height, waist/hip, HDL, waist, weight, diastolic BP, hip, and gender: male. Conclusion: In the current study, it was seen that the ML model applied with the results obtained can predict diabetes. Addition, according to the results of the relevant model, the most important risk factors for DM were determined and given in degrees of importance of the risk factors. With these results, necessary precautions can be taken for the disease at early levels.Öğe En küçük kareler ve temel bileşenler regresyon analizlerinin karşılaştırılması(İnönü Üniversitesi, 2018) Tunç, ZeynepAim: The aim of this study is to compare the results of Ordinary Least Squares (OLS) and Principal Components Regression (PCR) analyses when there is multicollinearity in the data. Material and Method: Two different data groups were simulated in order to examine the effect of the degree of multicollinearity and the sample size. The first data group consisted of 10 data sets with different multicollinearity degree and the second data group consisted of 10 data sets with the same correlation structure but with different sample sizes. All datasets had one dependent and three independent variables, and all the variables were derived from standard normal distribution. The presence of multicollinearity in the derived data was proven by commonly used measures. The least squares and principal components regression were applied to all datasets. Results: When generating multicollinearity, all relationships were defined as positive in data simulation. However, the sign of the regression coefficients for the second (X2) and third (X3) independent variables were obtained as reverse (negative) as one of the expected effects of multicollinearity in Least Squares analysis. In the analysis of the Principal Components Regression, the sign of coefficients was found to be in the right direction (positive). The sign of the coefficients obtained from OLS and PCR were different and they also differed in magnitude. In addition, the standard errors of the coefficients in PCR results were lower than OLS results. Conclusion: In the case of multiple linear regression analysis, the existence of multicollinearity must be examined and one of the methods that can handle this problem should be used. Otherwise, predictions may lead to incorrect results. Based on the results of this study that compares two methods when there is multicollinearity in data, it is recommended to use Principal Components Regression instead of Ordinary Least Squares. Key words: Multicollinearity, Linear regression, Ordinary least squares, Sample size, Principal components regression.Öğe Evaluation of clinical and laboratory results of patients diagnosed urinary calculi in emergency department(2023) Atila, Abdullah Ahmet; Sarıhan, Mehmet Ediz; Tunç, Zeynep; Güngör, HasanAim: In this study, we examined the factors affecting the rate of urine culture positivity and the rate of urine culture positivity in patients who were found to have kidney stones in the emergency department and were followed up by the Urology outpatient clinic. We evaluated the examinations and treatments of these patients with the results of the urology outpatient clinic until the urine culture results were obtained. We think that our study will provide useful information to emergency service workers in the evaluation of patients with urinary system stones. Materials and Methods: In this study, patients who applied to Emergency Medicine Department of İnönü University Faculty of Medicine between January 1st, 2016 and November 1st, 2022, who were diagnosed with urinary calculi by imaging and who were followed up in the Urology outpatient clinic, were retrospectively analyzed. The age and gender of the patients, as laboratory tests, complete blood count, urinalysis, serology and urine culture results were examined. Multiple logistic regression analysis was performed with all the parameters obtained from our study and the analysis was statistically significant according to the Hosmer&Lemeshow test. Results: In our study, there were a total of 349 patients, 99 (28.37%) female and 250 (71.63%) male, and a pathogenic microorganism growth was observed in the urine culture of 40 (11.7%) of the patients. The first two microorganisms most frequently encountered in urine culture were Escherichia Coli (24/40) and Klebsiella spp. (5/40). In the logistic regression model, nitrite positivity increased 48.8%, urinary white blood cells increased 0.2%, bacteria presence in urine 3.06%, and increased patient age increased the probability of culture positivity by 2.6%. Each 1 unit increase in hemoglobin value decreased the probability of positive urine culture by 27.8%. Conclusion: The leukocyte count, bacteria presence, nitrite positivity, low blood hemoglobin and advancing advanced age in the complete expulsion examination of a patient with urinary system stone are the prediction of a positive ejection result. These data should be considered in the decision to take the culture of dissemination at the time of death of patients with urinary tract stones or the management of care during the time until they reach the respiratory tract.Öğe Evaluation of Vaccine Hesitancy, Anti-Vaccination, and Anxiety Levels for Medical Secretaries During COVID-19 Pandemic(2022) Akbulut, Ahmet Sami; Işıklı, Ayşe Gökçe; Boz, Gülseda; Tunç, Zeynep; Sarıtaş, Hasan; Unsal, Selver; AliObjective: This study aimed to evaluate the vaccine hesitancy, anti-vaccination, and anxiety levels of medical secretaries during the pandemic. Methods: This cross-sectional study was conducted on 161 medical secretaries working at the time of the Study. Sociodemographic characteristics form, Coronavirus Anxiety Scale (CAS), Vaccine Hesitancy Scale (VHS) adapted to the pandemic, and Anti-vaccination Scale (AVS) were used in the questionnaire form used to collect the data of the study. Results: Median (IQR) CAS, VHS, and AVS scores of the participants were 2 (IQR=3), 32 (IQR=10), and 58 (IQR=16), respectively. 35.4 % of the participants were exposed to the COVID-19, and 87% were vaccinated against COVID-19. Participants' hesitations about the childhood and COVID-19 vaccines were 15.5 % and 49.1%, respectively. A significant relationship was found between the presence of Coronavirus anxiety and educational status (p=0.035), hesitancy against childhood vaccine (p=0.016), and working in COVID-19 Units (p=0.044). A statistically significant relationship was found between VHS scores and hesitancy against childhood vaccine (p=0.001), hesitancy against COVID-19 vaccine (p<0.001), vaccination against COVID-19 (p=0.014), belief that the COVID-19 vaccine is protective (p<0.001), and make COVID-19 vaccination mandatory (p<0.001). A significant relationship was found between AVS scores and vaccination against COVID-19 (p=0.002), hesitancy against COVID-19 vaccine (p<0.001), and belief that the COVID-19 vaccine is protective (p<0.001), making COVID-19 vaccination mandatory (p<0.001). Conclusion: The concern about their parents’ exposure to COVID-19 is high among secretaries. COVID 19 vaccine hesitancy is high among secretaries. During the pandemic, higher rates of anxiety were detected in secretaries and those working in COVID-19 units and lower in the high school education.Öğe Investigation of Usability of Artificial Intelligence Semantic Video Processing Methods in Medicine(2022) Ucuzal, Hasan; Tunç, Zeynep; Güldoğan, EmekAim: The goal of this study is to produce user-friendly software for healthcare professionals with various approaches such as detection, identification, classification, and tracking of polyps contained in endoscopic images utilizing appropriate video/image processing techniques and CNN architecture. Material and Method: There were 345 photos in total in the study. These photographs are images depicting anatomical milestones, clinical findings, or gastrointestinal procedures in the digestive tract that have been documented and validated by medical specialists (skilled endoscopists). Each class has hundreds of images. The photos were downloaded from https://datasets.simula.no/kvasir, which is a free source for educational and research purposes. In the modeling phase, CNN and the Max-Margin object detection technique (MMOD), one of the deep neural network designs in the Dlib package, were employed. The data set was separated as 80% training and 20% test dataset using the simple cross-validation method (hold-out). Precision, recall, F1-score, average precision (AP), mean average precision (mAP), ideal localization recall precision (oLRP), mean optimal LRP (moLRP), and intersection over union (IoU) were used to evaluate model performance. Results: When the previously described steps were performed on the open-access video image dataset of endoscopic polyps in the current study, all performance metrics examined in the training dataset received a value of 1, whereas, in the test dataset precision, sensitivity, F1-score, AP, mAP, oLRP, and moLRP were 98%, 90%, 94%, 89%, 89%, 48%, and 48% respectively. Conclusion: The proposed approach was found to make accurate predictions in the diagnosis of gastrointestinal polyps based on the values of the calculated performance criteria.Öğe MACHINE LEARNING-BASED CLASSIFICATION OF HBV AND HCV-RELATED HEPATOCELLULAR CARCINOMA USING GENOMIC BIOMARKERS(2022) Akbulut, Ahmet Sami; Tunç, Zeynep; Çolak, CemilObjective: It is crucial to know the underlying causes of hepatocellular carcinoma (HCC) for optimal management. This study aims to classify open access gene expression data of HCC patients who have an HBV or HCV infection using the XGboost method. Material and Methods: This case-control study considered the open-access gene expression data of patients with HBV-related HCC and HCV-related HCC. For this purpose, data from 17 patients with HBV+HCC and 17 patients with HCV+HCC were included. XGboost was constructed for the classification via tenfold cross-validation. Accuracy, balanced accuracy, sensitivity, specificity, the positive predictive value, the negative predictive value, and F1 score performance metrics were evaluated for a model performance. Results: With the feature selection approach, 17 genes were chosen, and modeling was done using these input variables. Accuracy, balanced accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and the F1 score obtained from the XGboost model were 97.1%, 97.1%, 94.1%, 100%, 100%, 94.4%, and 97%, respectively. Based on the variable importance findings from the XGboost, the ALDOC, GLUD2, TRAPPC10, FLJ12998, RPL39, KDELR2, and KIAA0446 genes can be employed as potential biomarkers for HBV-related HCC. Conclusion: As a result of the study, two different etiological factors (HBV and HCV) causing HCC were classified using a machine learning-based prediction approach, and genes that could be biomarkers for HBV-related HCC were identified. After the resulting genes have been clinically validated in subsequent research, therapeutic procedures based on these genes can be established and their utility in clinical practice documented.Öğe Machine learning-based ovarian cancer prediction with XGboost and stochastic gradient boosting models(2023) Özhan, Onural; Tunç, Zeynep; Çiçek, İpek BalıkçıOvarian cancer is one of the most common types of gynecological malignancies with its high mortality rate, silent and occult tumor growth, late onset of symptoms and diagnosis in advanced stages. Therefore, the need to develop new diagnostic techniques to predict the course of the disease and the prognosis of this malignancy has increased. In this study, ovarian cancer and benign ovarian tumor samples will be classified to create an accurate diagnostic predictive model using the machine learning method XGBoost and Stochastic Gradient Boosting and disease-related risk factors will be determined. This current study considered the open- access ovarian cancer and benign ovarian tumor samples data set. For this purpose, data from 349 patients were included. The data set was divided as 80:20 as a training and test dataset. XGBoost and Stochastic Gradient Boosting were constructed for the classification via five-fold cross-validation. Accuracy, balanced accuracy, sensitivity, specificity, positive predictive value, and negative predictive value performance metrics were evaluated for model performance. Among the performance criteria in the test stage obtained from the XGBoost model that has the best classification result; accuracy, balanced accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score were obtained as 89.5%, 88.7%, 85.7%, 91.7%, 85.7%, 91.7%, and 85.7%, respectively. According to the variable importance obtained as a result of the model, the variables most associated with the diagnosis were CA72-4, HE4, LYM%, ALB, EO%, BUN, RBC, NEU, and MCV, respectively. The applied machine learning model successfully classified ovarian cancer and created a highly accurate diagnostic prediction model. The results from the study revealed effective parameters that can diagnose ovarian cancer with high accuracy. With the parameters determined as a result of the modeling, the clinician will be able to simplify and facilitate the decision-making process for the diagnosis of ovarian cancer.Öğe Normal Dağılıma Uygunluğu Değerlendirmek için Açık Kaynak Web Tabanlı Yazılım: Normal Dağılımı İnceleme Yazılımı(2020) Arslan, Ahmet Kadir; Tunç, Zeynep; Çolak, CemilÖz: Amaç: Bu araştırmada tek ve çok değişkenli normal dağılıma uygunluğu kolay bir şekilde test edebilecek ve kullanıcıların yapacakları çalışmalarında daha doğru sonuçlar elde etmesini sağlayacak yeni kullanıcı dostu web tabanlı yazılım geliştirmek amaçlanmıştır.Gereç ve Yöntem: Açık kaynak kodlu bir R paketi olan Shiny, önerilen web yazılımını geliştirmek için kullanıldı. Geliştirilen yazılımda tek değiş-kenli normal dağılıma uygunluk için Shapiro-Wilk ve Anderson-Darling testleri, çok değişkenli normal dağılıma uygunluk için ise Mardia’nın çarpık-lık-basıklık, Henze-Zirkler ve Doornik-Hansen testleri kullanıldı. Normal dağılıma uygunluk için verilen çıktılarda test istatistiklerine ilaveten grafik-sel yöntemler de sunulmuştur. Örnek uygulama olarak simulasyon ile türetilen iki değişkenli, her bir değişkenin standart normal dağılıma sahip oldu-ğu ve 1000 gözlemli veri seti için normal dağılıma uygunluk test edilerek bulgular değerlendirilmiştir.Bulgular: Türetilen veri setinde her bir değişken Anderson-Darling ve Shapiro-Wilk testlerine göre normal dağılmıştır (sırasıyla x1ve x2değişkenleri için p =0.91 ve p =0.707; p =0.756 ve p =0.573). Ayrıca türetilen veri seti Mardia’nın çarpıklık-basıklık, Henze-Zirkler ve Doornik-Hansen testlerine göre iki değişkenli normal dağılım göstermiştir (respectively p =0.826, p =0.831 and p =0.868).Sonuç: Geliştirilen yazılım tek değişkenli ve çok değişkenli normal dağılıma uygunluk analizlerini kolayca yapabilen ve kullanıcıların yapacakları çalışmalarında daha doğru sonuçlar elde etmesini sağlayan yeni kullanıcı dostu bir web tabanlı yazılımdır. İlerleyen çalışmalarda, en iyi yönteme karar vermede kullanılan ölçütlerden Tip I ve Tip II hata türlerinin yazılıma eklenmesi planlanmaktadır.Öğe Performance Comparison of Some Imputation Methods Used in Missing Value(s) Analysis: A Simulation Study(2019) Arslan, Ahmet Kadir; Tunç, Zeynep; Güldoğan, Emek; Çolak, CemilAbstract: Objective: In a research, it is not desirable that the dataset to be used contains missing value (s) and researchers try to cope with this situation. The main purpose of this research is to develop new user-friendly web-based software that uses various techniques to handle missing value(s). Material and Methods: In this study, to assess the performance of the software, various scenarios were tested: 5 variables were normally distributed, different sample sizes (n=1000, 1500, 2000 and 2500), high (r <-0.70 or r> 0.70) and low correlations (-0.30Öğe Prognostic value of neutrophil/lymphocyte, platelet/lymphocyte and MPV in patients diagnosed with pulmonary embolism(2022) Demirkaya, Alper; Sarıhan, Mehmet Ediz; Tunç, ZeynepAim: Pulmonary Embolism (PE) is an obstructive illness of the pulmonary artery system that occurs in varying degrees and locations and is caused by embolization of thrombus or non-thrombotic substances that originate in the deep veins of the lower limbs. Pulmonary embolism is a preventable disease that has a high probability of recurrence, high mortality, and morbidity. The differential diagnosis and clinical treatment of pulmonary embolism have a very important place in emergency service applications. The purpose of the present study was to retrospectively examine the patients who applied to Inonu University Turgut Ozal Medical Center Emergency Service between 2014 and 2019 and were diagnosed with PE. Materials and Methods: In the present study, the data were collected retrospectively from a total of 144 patients including 80 female and 64 male patients who applied to Turgut Ozal Medical Center (TOMC) Emergency Department with the complaints of sweating, chest pain, cough, hemoptysis, and syncope between January 2014 and August 2019 and diagnosed with PE with the I-26 diagnostic code according to the ICD 10 coding system. The quantitative data obtained from the patients were summarized as mean and standard deviation or median, as well as minimum and maximum, and the qualitative data were summarized as numbers and percentages. The compatibility of the data with the normal distribution was evaluated with the Kolmogorov Smirnov test and the homogeneity of the variances was examined with the Levene test. The Independent Samples t-test and Mann Whitney U test were used to analyze the data. The IBM SPSS Statistics version 26.0 for Windows package program was used in the analyses. A P<0.05 value was taken as statistically significant. Results: No significant differences were detected in terms of systolic arterial blood pressure, diastolic arterial blood pressure, and laboratory variables of leukocyte, lymphocyte, neutrophil, neutrophil/lymphocyte, and platelet/lymphocyte ratios between the PE patients with and without right ventricular dilatation on ECHO. Statistically significant differences were detected for platelet, MPV, and CRP between the patients with and without right ventricular dilatation in ECHO. Conclusion: It is considered that these findings will provide data on the prognosis and general condition of patients and will help the clinician to make an earlier and easier prediction about the clinical prognosis of patients.Öğe Propofol İnfüzyonu Sonrası İdrarın Yeşil Renk Değişikliği: Bir Olgu Sunumu(2020) Miniksar, Ökkeş Hakan; Yücel, Aytaç; Tunç, Zeynep; Kaya, Füsun; Togal, TürkanPropofol infüzyonu sonrası idrarda yeşil renk değişikliği geri dönüşümlü ve nadir karşılaşılanbir klinik durumdur. Yoğun bakım hastasında idrarda yeşil renk değişikliği ile karşılaşan klinisyen en başta endişe duymaktadır. Birçok klinisyen bu ender duruma yabancıdır. Burada,HELLP Sendromu ile takip edilen, postoperatif yoğun bakımda devamlı propofol infüzyonuuygulaması başladıktan 40 saat sonra idrarda yeşil renk değişikliği olan ve propofol kesildikten 6 saat sonra kendiliğinden normale dönen olgu sunulmuştur. Yaygın kullanılan propofolebağlı böyle bir geri dönüşümlü ve ender görülen klinik durumu bilmek gereksiz endişeyi azaltacak, gereksiz antibiyotik kullanımını ve laboratuvar testlerini önleyecektirÖğe Veri Dönüşümü İçin Açık Kaynak Erişimli Web Tabanlı Yazılım: Veri Dönüşüm Yazılımı(2019) Arslan, Ahmet Kadir; Tunç, Zeynep; Çolak, CemilÖz: Amaç: Bu çalışmada parametrik test koşulları varsayımlarını sağlamayan veri setlerini çeşitli matematiksel dönüşümler uygulayarak bu varsayımları sağlayabilen veri setlerine dönüştürebilmek için yeni kullanıcı dostu bir web tabanlı yazılım geliştirmek amaçlanmıştır. Gereç ve Yöntem: Bu web tabanlı yazılımı geliştirmek için açık kaynaklı bir R paketi olan Shiny, kullanıldı. Geliştirilen web tabanlı yazılımda arcsinh(x), Box-Cox, Üstel, Lambert W (h tipi), Lambert W (s tipi), Logaritmik, Karekök, Yeo-Johnson veri dönüşüm yöntemleri kullanılmıştır. Ayrıca yazılım dönüşüme tabi tutulacak veri seti için kullanılan yöntemler içinde en iyi yönteme karar vermemizi sağlayacak olan Pearson P test istatistiğini hesaplayarak en iyi dönüşüme karar vermemizi sağlar. Bu işlemi en küçük Pearson P istatistiğine sahip dönüşümü seçerek yapmaktadır. Bulgular: Yazılımın çıktılarını değerlendirebilmek adına üç değişkenden oluşan her bir değişkenin sırasıyla üstel, gamma ve Cauchy dağılımları ile elde edildiği ve değişkenlerin 1000 gözlem içerdiği bir veri seti kullanılmıştır. Sonuç: Geliştirilen yazılım kullanıcıların yapacakları çalışmalarında daha doğru sonuçlar elde etmesini sağlayan ve daha güçlü testler olarak bilinen parametrik test varsayımlarını elde etmeyi sağlayan veri dönüşümü yöntemlerini içeren yeni kullanıcı dostu bir web tabanlı yazılımdır.Öğe Yoğun Bakım ve Palyatif Bakım Ünitelerinde Çalışanların Palyatif Bakıma İlişkin Bilgi ve Görüşlerinin Belirlenmesi: Anket Çalışması(2020) Miniksar, Ökkeş Hakan; Korkmaz Dişli, Zeliha; Tunç, Zeynep; Acun Delen, Leman; Honca, MehtapÖz: Amaç: Yoğun bakım (YB) ve palyatif bakım (PB) üniteleri yaşam sonu bakımın uygulandığı kliniklerdir. PB hizmetlerinin optimal düzeyde verilebilmesi için bu ünitelerde çalışanların PB hakkında yeterli düzeyde bilgi sahibi olması gerekmektedir. Bu çalışmanın amacı, YB ve PB ünitelerinde çalışan doktor ve hemşirelerin PB’ye ilişkin bilgi ve görüşlerinin belirlenmesi ve karşılaştırılmasıdır. Gereç ve Yöntemler: Çalışma; Malatya Eğitim ve Araştırma Hastanesi Reanimasyon YB, Dahiliye YB ve PB ünitelerinde çalışan hekim ve hemşireler ile yüz yüze görüşme yöntemi ile yapılmıştır. Çalışmada veriler, sosyodemografik özellikler formu ve literatür bilgileri doğrultusunda hazırlanan, çalışanların PB’ye yönelik mevcut bilgi ve görüşlerini belirleyici anket formu kullanılarak elde edilmiştir. Bulgular: Çalışmaya katılanların (68 hemşire, 12 doktor) yaş ortalaması 34 olup, çoğunluğunu lisans mezunu kadınlar oluşturmaktaydı. Katılımcıların %80’i eğitimleri sırasında PB eğitimi almadıklarını ve %76,3’ü yapılacak eğitim programlarına ihtiyaç duyduklarını belirtti. YB çalışanlarının %37,5’i, PB çalışanlarının %20’si hospis tanımını bilmediklerini ifade etti. PB çalışanlarının çoğu (%85,1) tedavisi biten hastaların taburculuğunda zorlandıklarını ve %85,5’i PB’de tükenmişlik yaşadıklarını belirtti. YB hemşirelerinin %63,8’i “YB”de PB hizmeti verilmelidir, ifadesine katılmadıklarını ve bu konu hakkında bilgi sahibi olmadıklarını belirtti. Çalışanların tamamına yakını, PB temel eğitiminin üniversite eğitim programlarında zorunlu olması gerektiğini belirtti. Sonuç: YB ve PB ünitesinde çalışan sağlık personelinin “Palyatif bakım ve hospis” kavramları konusunda yeterli bilgiye sahip olmadıkları, bilgi düzeylerinde farklılıklar olduğu ve bu konuda yapılacak eğitim programlarına ihtiyaç duydukları belirlenmiştir. Bu durumun temel lisans eğitimindeki eksikliklerden kaynaklandığı, eğitim müfredatında zorunlu PB eğitim dersinin yer alması ve sertifikalı eğitim programlarının yaygınlaşması gerektiği düşünülmektedir.
