Publications by authors named "Y H Tay"
Background Acute appendicitis remains a common surgical pathology, with the accepted standard of care being appendectomy. However, in cases of acute appendicitis complicated by an inflammatory phlegmon, a dilemma remains regarding the best management options. The aim of our study was to examine the outcomes for patients with an appendiceal phlegmon, comparing emergency appendectomy with those who had initial conservative management followed by subsequent interval appendectomy.
View Article and Find Full Text PDFDystonia is one of the most prevalent movement disorders, characterized by significant clinical and etiological heterogeneity. Despite considerable heritability (~25%) and the identification of several disease-linked genes, the etiology in most patients remains elusive. Moreover, understanding the correlations between clinical manifestation and genetic variants has become increasingly complex.
View Article and Find Full Text PDFImportance: This diagnostic study describes the merger of domain knowledge (Kramer principle of dermal advancement of icterus) with current machine learning (ML) techniques to create a novel tool for screening of neonatal jaundice (NNJ), which affects 60% of term and 80% of preterm infants.
Objective: This study aimed to develop and validate a smartphone-based ML app to predict bilirubin (SpB) levels in multiethnic neonates using skin color analysis.
Design, Setting, And Participants: This diagnostic study was conducted between June 2022 and June 2024 at a tertiary hospital and 4 primary-care clinics in Singapore with a consecutive sample of neonates born at 35 or more weeks' gestation and within 21 days of birth.
Article Synopsis
- Several new therapies, including biologics and JAK inhibitors, have been approved for treating atopic dermatitis (AD) in Singapore since 2016, leading to an update of treatment guidelines for moderate-to-severe cases.
- A modified Delphi panel with 12 dermatologists conducted surveys to reach consensus on treatment statements, resulting in agreement on 43 statements across different treatment categories.
- The study highlights dupilumab and JAK inhibitors as potential first-line treatments for certain patients with moderate-to-severe AD, and indicates that further updates to the guidelines may be necessary as new information emerges.
Article Synopsis
- Copy Number Variations (CNVs) are crucial in understanding complex diseases and vary across different populations, necessitating large sample studies for accurate analysis.
- The CNV-Finder pipeline utilizes deep learning, specifically Long Short-Term Memory (LSTM) networks, to streamline the identification of CNVs in specific genomic areas, making subsequent analyses like genome sequencing more efficient.
- The tool has been validated with data from various cohorts, focusing on genes related to neurological diseases, and includes an interactive web application for researchers to visualize and refine their findings based on model predictions.