University of Patras
Μεθοδολογία στατιστικής μάθησης για την πρόγνωση ασθενών με Β-χρόνια λεμφογενή λευχαιμία (Β-ΧΛΛ) με χρήση δεδομένων κυτταρομετρίας ροής
Abstract
dc:descriptionB-Chronic Lymphocytic Leukemia (B-CLL) is known to be the most common type of leukemia in the Western world. Its prognosis remains one of the most interesting decision problems in clinical research and practice. Various clinical and laboratory factors are known to be associated with the evolution of the disease. However, for the parameters obtained by flow cytometry analysis that are traditionally utilized as the cornerstone during the diagnosis procedure of the disease, whether they offer additional prognostic information is an open issue. In this dissertation, we propose a decision support system to the hematologists, that provides multiparametric B-CLL patients’ prognosis, combining the usage of diverse heterogeneous factors (clinical, laboratory and flow cytometry) associated with the disease. B-CLL diagnosis is primarily derived from the study of the antigenic phenotype of the patients’ blood cells, which is held with flow cytometry analysis. Despite the fact that the method of the analysis is well defined, the process traditionally followed by the laboratory experts is characterized by amounts of inexactness and subjectivity. As flow cytometry technology advances rapidly, the need for adequate automated (computer-assisted) analysis methodologies on the data it produces is accordingly increasing. In this context, we present a useful paradigm of automated analysis of flow cytometry data that does not require the direct supervision of the expert, for B-CLL patients’ diagnosis. The values of the flow cytometry characteristic parameters extracted by applying the proposed methodology are afterward incorporated to the prognostic system for B-CLL mentioned above. By reducing the B-CLL prognosis problem to an instance of the pattern classification problem, as well as by simulating each step of the B-CLL diagnosis procedure with an instance of the data classification problem, we proceeded with applying statistical learning techniques. We focused on Bayesian network methodologies and utilized the naïve-Bayes model for both cases, in its supervised and unsupervised version, respectively. The characteristics of the data (especially of the flow cytometry ones) generated by a pathological underlying mechanism, like the disease’s one, did not encourage the direct use of the above model. Therefore, we combined the naïve-Bayes model with a set of suitable heuristic algorithmic procedures to obtain better results, not only with respect to some commonly used algorithmic optimality metrics, but also by considering the experts’ opinion. Due to their ability of incorporating the expert knowledge as a priori initial information to their learning methods, Bayesian methodologies are considered as the most appropriate ones to make use of in such types of applications.
Degree
thesis:*- Grantor dc:publisher
- University of Patras
- Year dc:date
- 2010
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Lakoumentas, Ioannis
- Λακουμέντας, Ιωάννης
Subjects
dc:subject × 20- Β-χρόνια λεμφογενή λευχαιμία
- Κυτταρομετρία ροής
- Στατιστική μάθηση
- Δίκτυα πεποίθησης
- Εξόρυξη δεδομένων
- Κατηγοριοποίηση προτύπων
- Συσταδοποίηση δεδομένων
- Ενοποίηση βιοϊατρικών δεδομένων
- B-chronic lymphocytic leukemia
- Flow cytometry
- Statistical learning
- Bayesian networks
- Data mining
- Pattern classification
- Data clustering
- Biomedical data integration
- Ιατρική και Επιστήμες Υγείας
- Άλλες Ιατρικές Επιστήμες
- Medical and Health Sciences
- Other Medical Sciences
Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/26506