Uncertainty Handling in medical diagnosis using probabilistic ML
Keywords:
Probabilistic Machine Learning, Medical Diagnosis, Uncertainty Estimation, Bayesian Neural Networks, Gaussian Processes, Confidence Intervals, Clinical Decision Support, Explainable AIAbstract
In medical diagnosis, there is usually noisy, incomplete, or imprecise data that causes uncertainty in the decisions that are made. Powerful models Traditional machine learning models can be very powerful, but they tend to give deterministic predictions without considering the associated uncertainty. The given paper dwells upon the use of probabilistic machine learning (ML) methods to handle uncertainty in medical diagnostics. Probabilistic ML has advantages over modeling predictions as point estimates by providing interpretable measures of confidence to improve clinical trust, make risk-sensitive decisions, and improve the overall diagnostic accuracy. This work contains a comparative review of probabilistic techniques, such as Bayesian Neural Networks, Gaussian Processes, and Monte Carlo Dropout, on open health care data. The experiment results demonstrate that the inclusion of uncertainty estimation can already lead to a significant increase in performance and reliability which opens the door to safer AI-based medical systems.
Downloads
References
L. Huang, S. Ruan, Y. Xing, and M. Feng, “A review of uncertainty quantification in medical image analysis: Probabilistic and non-probabilistic methods,” Medical Image Analysis, vol. 97, p. 103223, Jun. 2024, doi: 10.1016/j.media.2024.103223.
M. Abdar et al., “A review of uncertainty quantification in deep learning: Techniques, applications and challenges,” Information Fusion, vol. 76, pp. 243–297, May 2021, doi: 10.1016/j.inffus.2021.05.008.
S. Seoni, V. Jahmunah, M. Salvi, P. D. Barua, F. Molinari, and U. R. Acharya, “Application of uncertainty quantification to artificial intelligence in healthcare: A review of last decade (2013–2023),” Computers in Biology and Medicine, vol. 165, p. 107441, Sep. 2023, doi: 10.1016/j.compbiomed.2023.107441.
E. Hüllermeier and W. Waegeman, “Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods,” Machine Learning, vol. 110, no. 3, pp. 457–506, Mar. 2021, doi: 10.1007/s10994-021-05946-3.
M. Barandas et al., “Evaluation of uncertainty quantification methods in multi-label classification: A case study with automatic diagnosis of electrocardiogram,” Information Fusion, vol. 101, p. 101978, Aug. 2023, doi: 10.1016/j.inffus.2023.101978.
R. Senge et al., “Reliable classification: Learning classifiers that distinguish aleatoric and epistemic uncertainty,” Information Sciences, vol. 255, pp. 16–29, Aug. 2013, doi: 10.1016/j.ins.2013.07.030.
M. S. Arif, A. Mukheimer, and D. Asif, “Enhancing the early detection of chronic kidney Disease: a robust machine learning model,” Big Data and Cognitive Computing, vol. 7, no. 3, p. 144, Aug. 2023, doi: 10.3390/bdcc7030144.
M. Barandas, D. Folgado, R. Santos, R. Simão, and H. Gamboa, “Uncertainty-Based rejection in Machine Learning: Implications for model development and Interpretability,” Electronics, vol. 11, no. 3, p. 396, Jan. 2022, doi: 10.3390/electronics11030396.
S. Asif et al., “Advancements and Prospects of Machine Learning in Medical Diagnostics: Unveiling the future of Diagnostic Precision,” Archives of Computational Methods in Engineering, Jun. 2024, doi: 10.1007/s11831-024-10148-w.
Z. Guo et al., “A survey on uncertainty reasoning and quantification in belief theory and its application to deep learning,” Information Fusion, vol. 101, p. 101987, Aug. 2023, doi: 10.1016/j.inffus.2023.101987.
B. X. Yong and A. Brintrup, “Bayesian autoencoders with uncertainty quantification: Towards trustworthy anomaly detection,” Expert Systems With Applications, vol. 209, p. 118196, Jul. 2022, doi: 10.1016/j.eswa.2022.118196.
H. Salem, M. Y. Shams, O. M. Elzeki, M. A. Elfattah, J. F. Al-Amri, and S. Elnazer, “Fine-Tuning fuzzy KNN classifier based on uncertainty membership for the medical diagnosis of diabetes,” Applied Sciences, vol. 12, no. 3, p. 950, Jan. 2022, doi: 10.3390/app12030950.
Thelen et al., “A comprehensive review of digital twin—part 2: roles of uncertainty quantification and optimization, a battery digital twin, and perspectives,” Structural and Multidisciplinary Optimization, vol. 66, no. 1, Dec. 2022, doi: 10.1007/s00158-022-03410-x.
W. V. Padula et al., “Machine Learning Methods in Health Economics and Outcomes Research—The PALISADE Checklist: A Good Practices Report of an ISPOR Task Force,” Value in Health, vol. 25, no. 7, pp. 1063–1080, Jun. 2022, doi: 10.1016/j.jval.2022.03.022.
D. Li, Z. Qi, Y. Zhou, and M. Elchalakani, “Machine Learning Applications in Building Energy Systems: Review and Prospects,” Buildings, vol. 15, no. 4, p. 648, Feb. 2025, doi: 10.3390/buildings15040648.
Ellouze, O. Kahouli, M. Ksantini, H. Alsaif, A. Aloui, and B. Kahouli, “Artificial Intelligence-Based Diabetes Diagnosis with Belief Functions Theory,” Symmetry, vol. 14, no. 10, p. 2197, Oct. 2022, doi: 10.3390/sym14102197.
M. A. Abd-Elrazek, A. A. Eltahawi, M. H. A. Elaziz, and M. N. Abd-Elwhab, “Predicting length of stay in hospitals intensive care unit using general admission features,” Ain Shams Engineering Journal, vol. 12, no. 4, pp. 3691–3702, Apr. 2021, doi: 10.1016/j.asej.2021.02.018
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
