Publications by authors named "K N Ngan"
Multiple imputation (MI) models can be improved with auxiliary covariates (AC), but their performance in high-dimensional data remains unclear. We aimed to develop and compare high-dimensional MI (HDMI) methods using structured and natural language processing (NLP)-derived AC in studies with partially observed confounders. We conducted a plasmode simulation with acute kidney injury as outcome and simulated 100 cohorts with a null treatment effect, incorporating creatinine labs, atrial fibrillation (AFib), and other investigator-derived confounders in the outcome generation.
View Article and Find Full Text PDFThe FDA Sentinel Real World Evidence Data Enterprise (RWE-DE).
Pharmacoepidemiol Drug Saf
October 2024
Article Synopsis
- - The FDA's Sentinel Innovation Center created a quality-checked network using electronic health records (EHRs) and insurance claims data from over 10 million individuals to enhance regulatory decision-making with real-world data.
- - The resulting network, called the Real-World Evidence Data Enterprise (RWE-DE), includes data from two commercial sources covering 21 million lives and four academic partners covering 4.5 million lives.
- - The report details data completeness, patient populations, and a process for managing free-text notes, while also highlighting potential use cases for RWE-DE to address broader questions in healthcare regulation.
Objectives: There is currently no reliable tool for classifying dementia severity level based on administrative claims data. We aimed to develop a claims-based model to identify patients with severe dementia among a cohort of patients with dementia.
Design: Retrospective cohort study.
Deep Learning models such as Convolutional Neural Networks (CNNs) are very effective at extracting complex image features from medical X-rays. However, the limited interpretability of CNNs has hampered their deployment in medical settings as they failed to gain trust among clinicians. In this work, we propose an interactive framework to allow clinicians to ask what-if questions and intervene in the decisions of a CNN, with the aim of increasing trust in the system.
View Article and Find Full Text PDFArticle Synopsis
- Pancreatic intraductal oncocytic papillary neoplasms (IOPNs) are rare precursors to pancreatic cancer, often identified through imaging techniques like CT and MRI.
- A study involving 14 patients revealed that most were middle-aged men with average lesion sizes of 5.4 cm, commonly exhibiting enhancing mural nodules and thick internal septations.
- Histological analysis showed that 57% had high-grade dysplasia without invasive cancer, while 43% did have invasive carcinoma, with those cases generally being larger in size.