Publications by authors named "M Ketenci"
Study Question: Do recent changes in European Society of Human Reproduction and Embryology (ESHRE) clinical guidelines result in more comprehensive diagnosis of women with endometriosis?
Summary Answer: The latest shift in clinical guidelines results in diagnosis of more women with endometriosis but current ESHRE diagnostic criteria do not capture a sizable percentage of women with the disease.
What Is Known Already: Historically, laparoscopy was the gold standard for diagnosing endometriosis, a complex gynecological condition marked by a heterogeneous set of symptoms that vary widely among women. More recently, changes in clinical guidelines have shifted to incorporate imaging-based approaches such as transvaginal sonography and magnetic resonance imaging.
Maximum Likelihood Estimation of Flexible Survival Densities with Importance Sampling.
Proc Mach Learn Res
August 2023
Article Synopsis
- Survival analysis is used to study time-to-event data, especially when some data points are censored, and new methods have been developed that work well with large datasets and less strict assumptions than traditional models.
- These new models require careful tuning of hyperparameters, like bin sizes and cluster assignments, which can significantly impact their performance.
- The authors present a new survival analysis approach that eliminates the need for hyperparameter tuning, making it easier for practitioners, and they demonstrate that this approach performs as well or better than existing methods on real-world datasets.
One of the major complications of diabetes mellitus is diabetic cardiomyopathy. One of the mechanisms that initiates the irreversible deterioration of cardiac function in diabetic cardiomyopathy is mitochondrial dysfunction. Functionally impaired mitochondria result in greater levels of oxidative stress and lipotoxicity, both of which exacerbate mitochondrial damage.
View Article and Find Full Text PDFArticle Synopsis
- The text introduces Latent Meaning Cells (LMC), a new deep learning model designed to create contextualized word representations by integrating local word context with metadata like section types and document IDs.
- The model is particularly useful in the clinical field, where the text is often semi-structured and covers a wide range of topics.
- In tests for zero-shot clinical acronym expansion on three datasets, the LMC outperformed various baseline models while requiring less pre-training, showcasing the importance of both metadata and the LMC's inference algorithm.
Background And Study Aims: Percutaneous endoscopic gastrostomy (PEG) is a procedure that provides long term enteral nutrition. To investigate the predictors of PEG-related complications and 30-day mortality rates and evaluate the indicators for deciding whether to recommend elective PEG insertions, we sought to determine the complications and early mortality rates of patients who underwent PEG.
Patients And Methods: We performed a retrospective analysis of consecutive adult patients who had undergone PEG for the first time between October 2016 and January 2019.