Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2021 Mar 22;22(2):1543-1559.
doi: 10.1093/bib/bbaa237.

Deep learning in systems medicine

Haiying Wang  1 , Estelle Pujos-Guillot  2 , Blandine Comte  3 , Joao Luis de Miranda  4 , Vojtech Spiwok  5 , Ivan Chorbev  6 , Filippo Castiglione  7 , Paolo Tieri  8 , Steven Watterson  9 , Roisin McAllister  10 , Tiago de Melo Malaquias  11 , Massimiliano Zanin  12 , Taranjit Singh Rai  13 , Huiru Zheng  14
Affiliations
Review

Deep learning in systems medicine

Haiying Wang et al. Brief Bioinform. .

Abstract

Systems medicine (SM) has emerged as a powerful tool for studying the human body at the systems level with the aim of improving our understanding, prevention and treatment of complex diseases. Being able to automatically extract relevant features needed for a given task from high-dimensional, heterogeneous data, deep learning (DL) holds great promise in this endeavour. This review paper addresses the main developments of DL algorithms and a set of general topics where DL is decisive, namely, within the SM landscape. It discusses how DL can be applied to SM with an emphasis on the applications to predictive, preventive and precision medicine. Several key challenges have been highlighted including delivering clinical impact and improving interpretability. We used some prototypical examples to highlight the relevance and significance of the adoption of DL in SM, one of them is involving the creation of a model for personalized Parkinson's disease. The review offers valuable insights and informs the research in DL and SM.

Keywords: biomarker discovery; data integration; deep learning (DL); disease classification; systems medicine (SM).

PubMed Disclaimer

Figures

Figure 1
Figure 1
Illustration of the layer-by-layer processing in DL consisting of an input layer, multiple hidden layers and an output layer.
Figure 2
Figure 2
Illustration of a basic building block in a DNN.
Figure 3
Figure 3
An illustration of the basic structure of an unfolded RNN with an input unit formula image, a hidden unit formula image, and an output unit formula image at a sequence index t. The weight matrices formula image representing input connection, output connection and recurrent connection, respectively, are shared across the sequence dimension.
Figure 4
Figure 4
A typical architecture of CNNs which includes four main operations, i.e. convolution, ReLU, pooling and classification with convolutional layers, and pooling layers arranged in an alternating fashion.
Figure 5
Figure 5
Main steps of the GAF image construction. Starting from an originating time series (A), its ordinate is first scaled to fit the interval [−1, 1] (B), and then translated into polar coordinates (C), and finally to the GAF image (D).
Figure 6
Figure 6
DL for integrative biomarker identification. Abbreviations: Seq-Sequencing, GWAS: Genome wide association.
See this image and copyright information in PMC

References

    1. Federoff HJ, Gostin LO. Evolving from reductionism to holism: is there a future for systems medicine. JAMA 2009;302(9):994–6. - PubMed
    1. Apweiler R, Beissbarth T, Berthold M, et al. . Whither systems medicine? Exp Mol Med 2018;50:e453. - PMC - PubMed
    1. Zanin M, Chorbev I, Stres B, et al. . Community effort endorsing multiscale modelling, multiscale data science and multiscale computing for systems medicine. Brief Bioinform 2019;20(3):1057–62. - PMC - PubMed
    1. Capobianco E. Systems and precision medicine approaches to diabetes heterogeneity: a big data perspective. Clin Transl Med 2017;6(1):23. - PMC - PubMed
    1. Zhou Z, Feng J. Deep forest: towards an alternative to deep neural networks. In: Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017, pp. 3553–9.

Publication types