journal article·2024-03-04Open access

A Neural Modelling Tool for Non-Linear Influence Analyses and Perspectives of Applications in Medical Research

Antonello Pasini, Stefano Amendola

Applied Sciences· Volume 14· Issue 5

Abstract

Neural network models are often used to analyse non-linear systems; here, in cases of small datasets, we review our complementary approach to deep learning with the purpose of highlighting the importance and roles (linear, non-linear or threshold) of certain variables (assumed as causal) in determining the behaviour of a target variable; this also allows us to make predictions for future scenarios of these causal variables. We present a neural tool endowed with an ensemble strategy and its applications to influence analyses in terms of pruning, attribution and future predictions (free code issued). We describe some case studies on climatic applications which show reliable results and the potentialities of our method for medical studies. The discovery of the importance and role (linear, non-linear or threshold) of causal variables and the possibility of applying the relationships found to future scenarios could lead to very interesting applications in medical research and the study and treatment of cancer, which are proposed in this paper.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Machine Learning in Healthcare · Heart Rate Variability and Autonomic Control · Mental Health Research Topics

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

National Research Council, Institute of Atmospheric Pollution Research, Monterotondo Stazione, 00015 Rome, Italy

Italian Air Force Mountain Centre, 41029 Sestola, Italy

References (29)

Show source-provided references
1. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions10.1186/s40537-021-00444-8 ↗
2. Anderson, C. (2024, February 02). The End of Theory: The Data Deluge Makes the Scientific Method Obsolete. Wired. Available online: https://www.wired.com/2008/06/pb-theory/.
3. Egger, J., Gsaxner, C., Pepe, A., Pomykala, K.L., Jonske, F., Kurz, M., Li, J., and Kleesiek, J. (2022). Medical deep learning—A systematic meta-review. Comput. Methods Prog. Biomed., 221.10.1016/j.cmpb.2022.106874 ↗
4. A survey on deep learning in medicine: Why, how and when?10.1016/j.inffus.2020.09.006 ↗
5. Artificial neural networks for small dataset analysis
6. Attribution of recent temperature behaviour reassessed by a neural-network method10.1038/s41598-017-18011-8 ↗
7. Linear and nonlinear influences of climatic changes on migration flows: A case study for the ‘Mediterranean bridge’10.1088/2515-7620/ab0464 ↗
8. Is natural variability really natural? The case of Atlantic Multidecadal Oscillation investigated by a neural network model10.1007/s00704-022-04207-0 ↗
9. Lualdi, M., Cavalleri, A., Battaglia, L., Colombo, A., Garrone, G., Morelli, D., Pignoli, E., Sottotetti, E., and Leo, E. (2018). Early detection of colorectal adenocarcinoma: A clinical decision support tool based on plasma porphyrin accumulation and risk factors. BMC Cancer, 18.10.1186/s12885-018-4754-2 ↗
10. Detection of Dominant Intra-prostatic Lesions in Patients With Prostate Cancer Using an Artificial Neural Network and MR Multi-modal Radiomics Analysis10.3389/fonc.2019.01313 ↗
11. Imai, S., Takekuma, Y., Kashiwagi, H., Miyai, T., Kobayashi, M., Iseki, K., and Sugawara, M. (2020). Validation of the usefulness of artificial neural networks for risk prediction of adverse drug reactions used for individual patients in clinical practice. PLoS ONE, 15.10.1371/journal.pone.0236789 ↗
12. Hu, Z., Zhang, Q., Petoukhov, S., and He, M. (2021). Advances in Artificial Systems for Logistics Engineering, Springer.10.1007/978-3-030-80475-6 ↗
13. Sohn, J., Jung, I.-Y., Ku, Y., and Kim, Y. (2021). Machine-Learning-Based Rehabilitation Prognosis Predictionin Patients with Ischemic Stroke Using Brainstem Auditory Evoked Potential. Diagnostics, 11.10.3390/diagnostics11040673 ↗
14. Detecting of a Patient’s Condition From Clinical Narratives Using Natural Language Representation10.1109/OJEMB.2022.3209900 ↗
15. Detecting whether L1 or other lumbar levels would be excluded from DXA bone mineral density analysis during opportunistic CT screening for osteoporosis using machine learning10.1007/s11548-023-02910-5 ↗
16. Hertz, J., Krogh, A., and Palmer, R.G. (1991). Introduction to the Theory of Neural Computation, Addison-Wesley.10.1063/1.2810360 ↗
17. Bishop, C.M. (1995). Neural Networks for Pattern Recognition, Oxford University Press.10.1093/oso/9780198538493.001.0001 ↗
18. Approximation by superposition of a sigmoidal function10.1007/BF02551274 ↗
19. Multilayer feedforward networks are universal approximators10.1016/0893-6080(89)90020-8 ↗
20. Orr, G.B., and Müller, K.-R. (1998). Neural Networks: Tricks of the Trade, Springer.10.1007/3-540-49430-8 ↗
21. Beisbart, C., and Saam, N. (2019). Computer Simulation Validation. Simulation Foundations, Methods and Applications, Springer.10.1007/978-3-319-70766-2 ↗
22. The strategy of model building in climate science10.1007/s11229-020-02707-y ↗
23. Mitigation costs in a globalized world: Climate policy analysis with REMIND-R10.1007/s10666-009-9204-8 ↗
24. Prognosis and Treatment of Non–Small Cell Lung Cancer in the Age of Deep Learning10.1001/jamanetworkopen.2020.6368 ↗
25. Personalized chemotherapy selection for breast cancer using gene expression profiles10.1038/srep43294 ↗
26. Understanding the tumor immune microenvironment (TIME) for effective therapy10.1038/s41591-018-0014-x ↗
27. Discovering the anti-cancer potential of non-oncology drugs by systematic viability profiling10.1038/s43018-019-0018-6 ↗
28. The future of immune checkpoint therapy10.1126/science.aaa8172 ↗
29. Dermatologist-level classification of skin cancer with deep neural networks10.1038/nature21056 ↗