The proliferation of healthcare data has brought the opportunities of applying data-driven approaches, such as machine learning methods, to assist diagnosis. Recently, many deep learning methods have been shown with impressive successes in predicting disease status with raw input data. However, the "black-box" nature of deep learning and the highreliability requirement of biomedical applications have created new challenges regarding the existence of confounding factors. In this paper, with a brief argument that inappropriate handling of confounding factors will lead to models' sub-optimal performance in real-world applications, we present an efficient method that can remove the influences of confounding factors such as age or gender to improve the across-cohort prediction accuracy of neural networks. One distinct advantage of our method is that it only requires minimal changes of the baseline model's architecture so that it can be plugged into most of the existing neural networks. We conduct experiments across CT-scan, MRA, and EEG brain wave with convolutional neural networks and LSTM to verify the efficiency of our method.
Natural
extracellular matrix is formed by the assembly of small
molecules and macromolecules into a hydrogel-like network that can
mechanically support cells and involve in cellular processes. Here,
we developed a fluorescent supramolecular hydrogel based on a conjugated
oligomer OFBTCO2Na, which facilitated noncovalent assembly
through hydrophobic interactions and hydrogen bonds in a molecular
scale. The generated dense three-dimensional network endows the supramolecular
hydrogel with stretchability and stability. Furthermore, fluorescent
OFBTCO2Na in hydrogel acted as a donor, which can excite
the acceptor dyes on cells encapsulated in hydrogel via the Förster
resonance energy transfer (FRET) mechanism. Investigating the fluorescence
signal responsiveness of hydrogel to dynamic mechanical stretching
well reflected that enhanced stretching dictated the extent of connection
between the cell and matrix, which enables effective FRET at a molecular
level and allow spatiotemporally monitoring cell–matrix interactions
at the three-dimensional network. Importantly, cells can sense stretch
forces by their connection with a hydrogel matrix. The dynamic cell–matrix
interaction can be conveniently employed to formulate cell morphology.
Therefore, the fluorescent supramolecular hydrogel offers a suitable
culture platform not only to investigate cell interactions on interfaces
but also to regulate cell behavior at interfaces.
The proliferation of healthcare data has brought the opportunities of applying data-driven approaches, such as machine learning methods, to assist diagnosis. Recently, many deep learning methods have been shown with impressive successes in predicting disease status with raw input data. However, the "black-box" nature of deep learning and the high-reliability requirement of biomedical applications have created new challenges regarding the existence of confounding factors. In this paper, with a brief argument that inappropriate handling of confounding factors will lead to models' sub-optimal performance in real-world applications, we present an efficient method that can remove the influences of confounding factors such as age or gender to improve the across-cohort prediction accuracy of neural networks. One distinct advantage of our method is that it only requires minimal changes of the baseline model's architecture so that it can be plugged into most of the existing neural networks. We conduct experiments across CT-scan, MRA, and EEG brain wave with convolutional neural networks and LSTM to verify the efficiency of our method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.