Yazar "Mermer, Gülengül" seçeneğine göre listele
Listeleniyor 1 - 5 / 5
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Diabetes Risk Prediction with Machine Learning Models(2022) Özsezer, Gözde; Mermer, GülengülDiabetes mellitus (DM) is one of the most common chronic diseases worldwide, which is a major public health problem. The aim of this study is to predict DM risk with machine learning (ML) models using available data. In the analytical study, the “Diabetes Health Indicators Dataset” consisting of 253680 data and 21 variables collected annually by the CDC was used. The open access dataset was retrieved from Kaggle on March 5, 2022. Data analysis was done with Phyton 3.0 programming language using numpy, pandas, matplotlib, seaborn, sciktlearn, imblearn libraries. With data pre-processing, outliers and missing data were removed. KNN, Logistic regression, Decision tree, Random forest and Naive Bayes from ML algorithms were used in predictive modeling. The prediction rate of the algorithms was evaluated with accuracy, precision, recall and F1 Score. It did not require permission as the data was open access. KNN’s accuracy was 0.74, precision 0.31, recall 0.55, F1 score 0.39; Logistic regression’s accuracy was 0.72; precision 0.33, recall 0.74, F1 score 0.46; Decision tree’s was accuracy 0.84, precision 0.54 recall 0.15, F1 score 0.24; Random forest’s accuracy was 0.84, precision 0.56, recall 0.16, F1 score 0.25; Naive bayes's accuracy was 0.84, precision 0.52, recall 0.19, F1 score 0.28. In this study, ML algorithms were used for DM risk estimation. According to the experimental results, when the data set is divided into random training (80%) and testing (20%), the accuracy values of random forest and decision tree algorithms are very close to each other (RF: 0.848, DT: 0.847). Therefore, it can be said that the two best algorithms for diabetes risk estimation are random forest and decision tree.Öğe Feasibility Study for Using Artificial Intelligence Based GPT-3 in Public Health Nursing(Halk Sağlığı Hemşireliği Derneği, 2023) Özsezer, Gözde; Mermer, GülengülThe aim of this study is to create feasibility for the use of GPT-3, an artificial intelligence-based model, in public health nursing. Several GPT-3 models were tried for text generation and summarization in this feasibility study (text-ada-001, text-babbage-001, text-curie-001, text-davinci-003). The "text-davinci-003" model, which is also known as the most capable GPT-3 model provided in a free beta version by OpenAI in January 2023, was used in this study. In this study, text-davinci-003 was evaluated as a natural language generation model that allows users to interact with an artificial intelligence in a simple way. The "maximum length" parameter was changed to 2048 to reflect the capacity and detail required per response in the input query. Responses from GPT-3 were obtained on March 9, 2023. Prior to asking predetermined research questions for GPT-3, the method was analyzed. The relevant features of GPT-3 as a custom model developed by OpenAI were checked. Specifically, the GPT-3 citation used in this research was suggested by GPT-3 upon request. In this feasibility study, questions were asked and answers were provided by GPT-3 according to 6 purposes generated by GPT-3 regarding the contributions of GPT-3 to public health nursing. It can be stated that GPT-3 can contribute to public health nursing research as a team member by bringing together possible text blocks related to public health nursing. Human writers may need to follow scientific literature in addition to artificial intelligence, and a broad scientific discussion on the contributions of artificial intelligence to public health nursing may be necessaryÖğe Prediction of drinking water quality with machine learning models: A public health nursing approach(John Wiley and Sons Inc, 2024) Özsezer, Gözde; Mermer, GülengülObjective: The aim of this study is to use machine learning models to predict drinking water quality from a public health nursing approach. Design: Machine learning study. Sample: “Water Quality Dataset” was used in the study. The dataset contains physical and chemical measurements of water quality for 2400 different water bodies. The process consists of four stages: Data processing with Synthetic Minority Oversampling Technique, hyperparameter tuning with 10-fold cross-validation, modeling and comparative analysis. 80% of the dataset is allocated as training data and 20% as test data. ML models logistic regression, K-nearest neighbor, support vector machine, random forest, XGBoost, AdaBoost Classifier, Decision Tree algorithms were used for water quality prediction. Accuracy, precision, recall, F1 score and AUC performance metrics of ML models were compared. To evaluate the performance of the models, 10-fold cross-validation was used and a comparative analysis was performed. The p-values of the models were also compared. Results: N this study, where drinking water quality was predicted with seven different ML algorithms, it can be said that XGBoost and Random Forest are the best classification models in all performance metrics. There is a significant difference in all ML algorithms according to the p-value. The H0 hypothesis is accepted for these algorithms. According to the H0 hypothesis, there is no difference between actual values and predicted values. Conclusion: In conclusion, the use of ML models in the prediction of drinking water quality can help nurses greatly improve access to clean water, a human right, be more knowledgeable about water quality, and protect the health of individuals.Öğe Sağlık Hizmetlerinde Çığır Açan Uygulamalar: İnsan Dijital İkizi ile Geleceğe Yolculuk(Bandırma Onyedi Eylül Üniversitesi, 2024) Özsezer, Gözde; Mermer, GülengülDijital ikiz, “yaşam döngüsü boyunca bir ürün veya sistemin sanal bir kopyası” olarak tanımlanmaktadır. Sağlık paradigmasının dijital ikizi etkileşimlidir ve insanların anlaması için basittir. Bireyler, kendilerini daha sağlıklı bir yaşam sürmeye motive eden dijital ikize sahip olabilmektedir. Sağlık verilerini değerlendirmek için dijital ikiz kullanmak, şeffaflığı artırmakta ve tedavi boyunca güven oluşturmaktadır. Dijital ikiz ile araştırmacılar gerçek zamanlı verilere, simülasyon sonuçlarına ve çözümlere erişebilmekte ve yüzlerce operasyonel görevi uzun mesafeden verimli bir şekilde gerçekleştirebilmektedir. Sağlık hizmetlerinde çeşitli dijital ikiz teknolojileri kullanılmaktadır. Hastanın sağlığı, tedavisi ve bakımı ile ilgili hizmet maliyetlerinde azalma, kalitatif hizmetler, toplumsal aksaklıklarla ilgili konular vb. açısından hizmetlerde kullanılmaktadır. Bu hizmetler, hızlı iyileşme sağlamak için tedavi boyunca hastanın bakımındaki iyileşmeyi daha iyi yansıtmaktadır. Bu çalışmada “sağlık hizmetlerinde insanlar için dijital ikiz kullanılabilir mi? sorusuna yanıt aranmaktadır. Ayrıca bu çalışmanın amacı literatür ışığında dijital ikiz, insan dijital ikizi kavramının model ve özelliklerini vurgulamak, sağlık hizmetlerindeki geleceğe yön veren son araştırmaları sunmaktırÖğe Using Artificial Intelligence in the COVID-19 Pandemic: A Systematic Review(Medical Sciences University of Teheran, 2022) Özsezer, Gözde; Mermer, GülengülArtificial intelligence applications are known to facilitate the diagnosis and treatment of COVID-19 infection. This research was conducted to investigate and systematically review the studies published on the use of artificial intelligence in the COVID-19 pandemic. The study was conducted between April 25 and May 6, 2020 by scanning national and international studies accessed in "Web of Science, Google Scholar, Pubmed, and Scopus" databases with the keywords ("Coronavirus" or "COVID-19") and ("artificial intelligence" or "deep learning" or "machine learning"). As a result of the scanning process, 1495 (Google Scholar: 1400, Pubmed: 58, Scopus: 30, WOS: 7) studies were accessed. The studies were first examined according to their titles, and 1385 studies, which were not related to the research topic, were not included in the scope of the research. 50 articles, which did not meet the inclusion criteria, were excluded. The abstract and complete texts of the remaining 60 studies were scanned for the study's inclusion and exclusion criteria. A total of 10 studies, consisting of reviews, letters to the editor, meta-analysis studies, animal studies, conference presentations, studies not related to COVID-19, and incomplete studying protocols, were excluded. There were 50 studies left. 9 articles with duplication were identified and excluded. The remaining 41 studies were examined in detail. A total of 26 studies were found to meet the criteria for the systematic review study. In this systematic review, AI applications were found to be effective in COVID-19 diagnosis, classification, epidemiological estimates, mode of transmission, distribution, the density of lesions, case increase estimation, mortality/mortality risk, and early scans. © 2022 Tehran University of Medical Sciences. All rights reserved.
