National Technical University of Athens (NTUA)
Ανάπτυξη ευφυούς συστήματος υποστήριξης κλινικής απόφασης για την έγκαιρη διάγνωση και την εξατομικευμένη διαχείριση γυναικών που βρίσκονται σε κίνδυνο ανάπτυξης καρκίνου του μαστού
Abstract
dc:descriptionWomen population screening using mammography has dramatically reduced breast cancer rates worldwide. Nowadays, in many countries, the prevention of breast cancer policy is based on frequent and repeated mammographies, followed by breast ultrasound and, if necessary, by histological examination in the biological material of the biopsy. However, evaluating mammography findings is considered as a difficult process which can be properly performed only by a highly experienced and well-trained medical staff. Subsequently, the interpretation of the findings could be easily influenced by subjective factors and therefore can be prone to diagnostic errors as evidenced in the present study. Breast MRI (Magnetic Resonance Imaging), is a diagnostic practice indicated in cases of high breast density and at the same time, a high-cost examination for healthcare systems. Furthermore, genetic testing that is used to diagnose hereditary breast cancer, represents a small proportion of breast cancers and at the same time it is a high-cost specialized test. Even the most widely used biopsy, Fine Needle Aspirate (FNA), in some cases involves risks and produces false negative results. Considering the aforementioned facts, this study presents the development of AI (Artificial Intelligence) - based models and the creation of a Clinical Decision Support System (CDSS) for the early diagnosis and personalized management of women at risk of developing breast cancer. These models are based on non-invasive medical data collected during daily clinical practice at the Breast Center of the General Hospital "Elena Venizelou", as well as on data from women’s personal medical health records. Therefore, we demonstrate a tool, which, by combining the results of non-invasive and low-cost diagnostic tests and the medical health record, will be easy to use by clinicians on a daily basis and at the same time cost-effective for the health systems. Using feature selection techniques and machine learning tools, we found that the Random Forest (RF) classifier showed the highest values of accuracy (95.9%), sensitivity (96.5 %), NPV (95%), Youden’s index (0.92) και F1 score (0.97), proving to be an effective algorithm in the development of our innovative CDSS. The proposed CDSS aims to be a sustainable and cost-effective solution for national healthcare systems as it can contribute to a significant cost reduction in terms of personalized management of women at risk of developing breast cancer, while achieving a remarkable increase in the validity of diagnosis.
Degree
thesis:*- Grantor dc:publisher
- National Technical University of Athens (NTUA)
- Year dc:date
- 2022
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Tarousi, Marilena
- Ταρούση, Μαριλένα
Subjects
dc:subject × 25- Καρκίνος του μαστού
- Μαστογραφία
- Υπέρηχος μαστών
- Ατομικός ιατρικός φάκελος υγείας
- Εκτίμηση κινδύνου
- Συστήματα υποστήριξης κλινικής απόφασης
- Εξατομικευμένη ιατρική
- Μηχανική μάθηση
- Μπεϋζιανά δίκτυα
- Τυχαία δάση
- Breast cancer
- Mammography
- Breast ultrasound
- Medical health record
- Risk assessment
- Clinical decision support systems
- Personalized medicine
- Machine learning
- Bayesian networks
- Random forests
- Βιοϊατρική Μηχανική
- Επιστήμες Μηχανικού και Τεχνολογία
- Medical Engineering
- Engineering and Technology
- Biomedical Engineering
Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/52090