Robust and scalable manifold learning via landmark diffusion for long-term medical signal processing

Abstract

Motivated by analyzing long-term physiological time series, like 24 hours electrocardiogram, we design a computationally efficient spectral embedding algorithm that is suitable to handle "big data". We measure the affinity between any pair of two points via a set of landmarks, which is composed of a small number of points, and "diffuse" on the dataset via the landmark set to achieve a spectral embedding. We coined the algorithm RObust and Scalable Embedding via LANdmark Diffusion (ROSELAND). The algorithm is applied to study the arterial blood pressure waveform dynamics during a liver transplant operation lasting for 12 hours long. The proposed Roseland could help researchers handle big datasets or long-term physiological signals if the spectral embedding is considered, and the landmark idea beyond Roseland could be applied to speed up other algorithms.

Innovative applications of artificial intelligence in zoonotic disease management

“…The emergence and re-emergence of zoonotic diseases, such as coronavirus disease 2019 (COVID-19), Ebola virus disease (EVD), and monkeypox, highlight the need for innovative approaches to enhance disease prevention, early diagnosis, and effective treatment [ 2 , 3 ]. In recent years, artificial intelligence (AI) has emerged as a powerful tool in the field of healthcare and has shown great potential in addressing these challenges [ [4] , [5] , [6] ].…”