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
. 2023 Aug 3;13(15):2582.
doi: 10.3390/diagnostics13152582.

What Is Machine Learning, Artificial Neural Networks and Deep Learning?-Examples of Practical Applications in Medicine

Jakub Kufel  1 , Katarzyna Bargieł-Łączek  2 , Szymon Kocot  3 , Maciej Koźlik  4 , Wiktoria Bartnikowska  2 , Michał Janik  5 , Łukasz Czogalik  5 , Piotr Dudek  5 , Mikołaj Magiera  5 , Anna Lis  6 , Iga Paszkiewicz  5 , Zbigniew Nawrat  1 , Maciej Cebula  7 , Katarzyna Gruszczyńska  8
Affiliations
Review

What Is Machine Learning, Artificial Neural Networks and Deep Learning?-Examples of Practical Applications in Medicine

Jakub Kufel et al. Diagnostics (Basel). .

Abstract

Machine learning (ML), artificial neural networks (ANNs), and deep learning (DL) are all topics that fall under the heading of artificial intelligence (AI) and have gained popularity in recent years. ML involves the application of algorithms to automate decision-making processes using models that have not been manually programmed but have been trained on data. ANNs that are a part of ML aim to simulate the structure and function of the human brain. DL, on the other hand, uses multiple layers of interconnected neurons. This enables the processing and analysis of large and complex databases. In medicine, these techniques are being introduced to improve the speed and efficiency of disease diagnosis and treatment. Each of the AI techniques presented in the paper is supported with an example of a possible medical application. Given the rapid development of technology, the use of AI in medicine shows promising results in the context of patient care. It is particularly important to keep a close eye on this issue and conduct further research in order to fully explore the potential of ML, ANNs, and DL, and bring further applications into clinical use in the future.

Keywords: AI; AI in medicine; artificial intelligence; medicine.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 5
Figure 5
Diagram of the AdaBoost algorithm—different size circles stand for samples with more associated weights, various colors of the circles stand for different subsets of data [31].
Figure 1
Figure 1
k-nearest neighbour (kNN) example p—new data before and after kNN.
Figure 2
Figure 2
Linear regression example—ice cream sales versus average daily temperature—individual values on subsequent days are represented by brown circles. The red line stands for the linear regression plot created from this data.
Figure 3
Figure 3
A function graphically depicting the performance of a Naive Bayes classification algorithm.
Figure 4
Figure 4
A simplified example of the support vectors and samples of two classes.
Figure 6
Figure 6
A simplified diagram of a mathematical neuron. 1—signal inputs, 2—scales, 3—adder, 4—activator (activation function), and 5—signal output, respectively.
Figure 7
Figure 7
A simplified diagram of a human neuron. 1—dendrites, signal input site, 2—nucleus of the neuron, 3—zone of initiation (where the action potential of the neuron is formed), 4—axon, and 5—axon terminals (which form connections with other cells, and are the sites of signal output), respectively.
Figure 8
Figure 8
Simplified diagram of the neural network operation.
Figure 9
Figure 9
Graphical representation of an artificial neural network (ANN) and a deep neural network (DNN) [39].
Figure 10
Figure 10
Graphical representation of the auto-encoder [64]. The light blue colour indicates the input and output layers. The dark green colour together with the dark blue colour indicates the internal layers of the encoder and decoder. Red, on the other hand, stands for code.
Figure 11
Figure 11
Graphical representation of the transfer learning technique.
Figure 12
Figure 12
Simplified representation of the few-shot learning paradigm [72].
Figure 13
Figure 13
Graphical representation of deep reinforcement learning [73].
Figure 14
Figure 14
Simplified diagram of TNN operation [74].
Figure 15
Figure 15
Attention mechanism—simple diagram.
See this image and copyright information in PMC

References

    1. Ward T.M., Mascagni P., Madani A., Padoy N., Perretta S., Hashimoto D.A. Surgical Data Science and Artificial Intelligence for Surgical Education. J. Surg. Oncol. 2021;124:221–230. doi: 10.1002/jso.26496. - DOI - PubMed
    1. Mortani Barbosa E.J., Gefter W.B., Ghesu F.C., Liu S., Mailhe B., Mansoor A., Grbic S., Vogt S. Automated Detection and Quantification of COVID-19 Airspace Disease on Chest Radiographs: A Novel Approach Achieving Expert Radiologist-Level Performance Using a Deep Convolutional Neural Network Trained on Digital Reconstructed Radiographs from Computed Tomography-Derived Ground Truth. Investig. Radiol. 2021;56:471–479. doi: 10.1097/RLI.0000000000000763. - DOI - PubMed
    1. Gupta M. Introduction to Data in Machine Learning. GeeksforGeeks. [(accessed on 1 May 2023)]. Available online: https://www.geeksforgeeks.org/ml-introduction-data-machine-learning/
    1. Dorfman E. How Much Data Is Required for Machine Learning? Postindustria. [(accessed on 7 May 2023)]. Available online: https://postindustria.com/how-much-data-is-required-for-machine-learning/
    1. Patel H. Data-Centric Approach vs. Model-Centric Approach in Machine Learning. MLOps Blog 2023. [(accessed on 1 May 2023)]. Available online: https://neptune.ai/blog/data-centric-vs-model-centric-machine-learning.

LinkOut - more resources