Publications by authors named "Kartikeya M Menon"

Purpose: To investigate if combination therapy with immune checkpoint inhibitor (ICI) and yttrium-90 (Y) radioembolization results in superior outcomes than those yielded by tyrosine kinase inhibitor (TKI) therapy and Y for the treatment of intermediate- to advanced-stage hepatocellular carcinoma (HCC).

Methods: A retrospective review of patients presented at an institutional multidisciplinary liver tumor board between January 1, 2012 and August 1, 2023 was conducted. In total, 44 patients with HCC who underwent Y 4 weeks within initiation of ICI or TKI therapy were included.

View Article and Find Full Text PDF

Kidney disease affects 50% of all diabetic patients; however, prediction of disease progression has been challenging due to inherent disease heterogeneity. We use deep learning to identify novel genetic signatures prognostically associated with outcomes. Using autoencoders and unsupervised clustering of electronic health record data on 1,372 diabetic kidney disease patients, we establish two clusters with differential prevalence of end-stage kidney disease.

View Article and Find Full Text PDF

We developed and tested a novel template matching approach for signal quality assessment on electrocardiogram (ECG) data. A computational method was developed that uses a sinusoidal approximation to the QRS complex to generate a correlation value at every point of an ECG. The strength of this correlation can be numerically adapted into a 'score' for each segment of an ECG, which can be used to stratify signal quality.

View Article and Find Full Text PDF
Article Synopsis
  • Clinical EHR data is diverse and complex, which makes it difficult for machine learning models to accurately predict outcomes due to high variability within the same category.
  • To improve prediction accuracy, a new supervised pre-training model using an embedded k-nearest-neighbor positive sampling strategy is proposed.
  • This approach demonstrates strong performance, achieving an AUROC score of 0.872 in predicting patient mortality from COVID-19 data, outperforming existing methods, especially in cases with limited training data.
View Article and Find Full Text PDF

Unlabelled: Proteins containing polyglutamine (polyQ) regions are found in almost all eukaryotes, albeit with various frequencies. In humans, proteins such as huntingtin (Htt) with abnormally expanded polyQ regions cause neurodegenerative diseases such as Huntington's disease (HD). To study how the presence of endogenous polyQ aggregation modulates polyQ aggregation and toxicity, we expressed polyQ expanded Htt fragments (polyQ Htt) in Schizosaccharomyces pombe In stark contrast to other unicellular fungi, such as Saccharomyces cerevisiae, S.

View Article and Find Full Text PDF