Application of Artificial Intelligence in Support of NAFLD Diagnosis
Source abstract
Abstract
A comprehensive system for automated medical data analysis and diagnosis of non-alcoholic fatty liver disease using artificial intelligence has been developed. The system consists of several modules: medical data aggregation, AI model training using advanced machine learning algorithms, Explainable AI generating reports, and patient diagnosis by ensemble model. Those models have achieved diagnostic accuracy higher than 95%, and the system is designed for continuous improvement by aggregating more data and automatically retraining models. It is a modern, flexible, and scalable tool designed to support medical diagnosis. It can make doctors’ work easier and faster, and the discovered biomarkers of a disease can increase the quality of its diagnosis. The ensemble model generating diagnoses achieved nearly perfect quality and, using explainable artificial intelligence, it was possible to determine attributes and their values that constitute non-alcoholic-fatty-liver-disease (NAFLD) biomarkers.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Liver Disease Diagnosis and Treatment · Cardiovascular Disease and Adiposity · Artificial Intelligence in Healthcare
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Electronics and Information Technology, Warsaw University of Technology, 00-665 Warsaw, Poland
References (16)
Show source-provided references
1. The global nafld epidemic10.1038/nrgastro.2013.171 ↗
2. Rzadkiewicz, M., Haugan, G., and Włodarczyk, D. (2022). Mature adults at the gp: Length of visit and patient satisfaction associations with patient, doctor, and facility characteristics. Medicina, 58.10.3390/medicina58020159 ↗
3. Baniecki, H., Kretowicz, W., Piatyszek, P., Wisniewski, J., and Biecek, P. (2021). Dalex: Responsible machine learning with interactive explainability and fairness in python. arXiv.
4. Evolution of nafld and its management10.1002/ncp.10449 ↗
5. Management of nafld: A stage-based approach10.1038/nrgastro.2016.3 ↗
6. Singh, C., Gaba, N.S., Kaur, M., and Kaur, B. (2019, January 10–11). Comparison of different ci/cd tools integrated with cloud platform. Proceedings of the 2019 9th International Conference on Cloud Computing, Data Science & Engineering (Confluence), Noida, India.10.1109/CONFLUENCE.2019.8776985 ↗
7. The use of the multi-model ensemble in probabilistic climate projections10.1098/rsta.2007.2076 ↗
8. Dwivedi, R., Kumar, R., Chopra, D., Kothari, P., and Singh, M. (2023). An efficient ensemble explainable ai (xai) approach for morphed face detection. arXiv.10.1016/j.patrec.2024.06.014 ↗
9. Regression imputation in the functional linear model with missing values in the response10.1016/j.jspi.2018.12.004 ↗
10. Calzolari, N., Huang, C.-R., Kim, H., Pustejovsky, J., Wanner, L., Choi, K.-S., Ryu, P.-M., Chen, H.-H., Donatelli, L., and Ji, H. (2022, January 12–17). SHAP-based explanation methods: A review for NLP interpretability. Proceedings of the 29th International Conference on Computational Linguistics, Gyeongju, Republic of Korea. Available online: https://aclanthology.org/2022.coling-1.406.
11. Płudowski, J., and Mulawka, J. (2022). Machine learning in recognition of basic pulmonary pathologies. Appl. Sci., 12.10.3390/app12168086 ↗
12. Ai-driven deep cnn approach for multi-label pathology classification using chest x-rays10.7717/peerj-cs.495 ↗
13. A comprehensive review of deep neural networks for medical image processing: Recent developments and future opportunities10.1016/j.health.2023.100216 ↗
14. Vision transformers in medical computer vision—A contemplative retrospection10.1016/j.engappai.2023.106126 ↗
15. A survey of transformers10.1016/j.aiopen.2022.10.001 ↗
16. Xgboost, a novel explainable ai technique, in the prediction of myocardial infarction: A uk biobank cohort study10.1177/11795468221133611 ↗