1,720,992 research outputs found
Hybrid data analysis methods and artificial neural network design in breast cancer diagnosis: IDEST experience
No full textThis paper presents a method for breast cancer diagnosis using a system based on an artificial neural network (ANN) trained using a particular version of the back propagation (BP) algorithm. The Wisconsin Breast Cancer Database (WBCD) was used in order to train and validate the ANN; WBCD is composed by 699 cases monitored by Doc. William H. Wolberg in the first '90s. The development of this system required an articulate phase of data analysis and preprocessing: various statistical tools like principal component analysis (PCA) and principal factor analysis (PFA), were used in order to find parameters more strictly correlated to the malignant/benignant nature of the cancer. Non linear data analysis techniques were employed to gain more knowledge about the internal structure of the database. A genetic algorithm was then set up to find the best topology of ANN. The analysis of results obtained by IDEST followed training and validation of the AN
Developing a Theoretical Framework for Optofluidic Device Designing for System Identification in Systems Biology: the EGFR Study Case
No full textIdentification of dynamics underlying biochemical pathways of interest in oncology is a primary goal in current systems biology. Understanding structures and interactions that govern the evolution of such systems is believed to be a cornerstone in this research. Systems theory and systems identification theory are primary resources for this task since they both provide a self consistent framework for modelling and manipulating models of dynamical systems that are best suited for the problem under investigation. We address herein the issue of obtaining an informative dataset ZN to be used as starting point for identification of EGFR pathway dynamics. In order to match experimental identifiability criteria we propose a theoretical framework for input stimulus design based on dynamical properties of the system under investigation. A feasible optofluidic design has been designed on the basis of the spectral properties of the driving inputs that maximize information content after the theoretical studies
Engineering and control of biological systems: A new way to tackle complex diseases.
No full textAbstractThe ongoing merge between engineering and biology has contributed to the emerging field of synthetic biology. The defining features of this new discipline are abstraction and standardisation of biological parts, decoupling between parts to prevent undesired cross-talking, and the application of quantitative modelling of synthetic genetic circuits in order to guide their design.Most of the efforts in the field of synthetic biology in the last decade have been devoted to the design and development of functional gene circuits in prokaryotes and unicellular eukaryotes. Researchers have used synthetic biology not only to engineer new functions in the cell, but also to build simpler models of endogenous gene regulatory networks to gain knowledge of the “rules” governing their wiring diagram.However, the need for innovative approaches to study and modify complex signalling and regulatory networks in mammalian cells and multicellular organisms has prompted advances of synthetic biology also in these species, thus contributing to develop innovative ways to tackle human diseases.In this work, we will review the latest progress in synthetic biology and the most significant developments achieved so far, both in unicellular and multicellular organisms, with emphasis on human health
Un approccio fuzzy per la pianificazione del rinnovo delle apparecchiature nelle strutture ospedaliere
No full textNegli ultimi anni in ambito sanitario si è assistito ad una rapida evoluzione dal punto di vista tecnologico non sempre
accompagnata da altrettanti progressi dal punto di vista gestionale. In una struttura ospedaliera sono presenti numerose
apparecchiature mediche la cui gestione, molto onerosa sia in termini di tempo sia di denaro, rende indispensabile
l’introduzione di innovazioni soprattutto nelle attività di manutenzione.
Al fine di ridurre in modo significativo i costi operativi ed incrementare la qualità del servizio erogato è necessaria una
gestione efficace degli interventi di manutenzione e una corretta definizione di piani per la sostituzione del parco
macchine.
Nel presente lavoro, si presenta un modello inferenziale fuzzy in grado di individuare le attrezzature da sostituire,
rispettando i principali obiettivi di riduzione della spesa in una struttura ospedaliera e di incremento del grado di
soddisfazione dei pazienti e del personale medico. Il modello considera parametri quantitativi e qualitativi, stimati in
modo oggettivo, al fine di comprendere i fattori che effettivamente influenzano le decisioni di sostituzione con un
approccio unico per il contesto sanitario.
L'approccio fuzzy al problema delle decisioni riguardanti la pianificazione degli interventi di sostituzione è incoraggiato
dai risultati ottenuti da una sperimentazione effettuata presso l'ospedale "Casa Sollievo della Sofferenza - S. Giovanni
Rotondo
Un approccio fuzzy per la pianificazione del rinnovo delle apparecchiature nelle strutture ospedaliere
No full textNegli ultimi anni in ambito sanitario si è assistito ad una rapida evoluzione dal punto di vista tecnologico non sempre
accompagnata da altrettanti progressi dal punto di vista gestionale. In una struttura ospedaliera sono presenti numerose
apparecchiature mediche la cui gestione, molto onerosa sia in termini di tempo sia di denaro, rende indispensabile
l’introduzione di innovazioni soprattutto nelle attività di manutenzione.
Al fine di ridurre in modo significativo i costi operativi ed incrementare la qualità del servizio erogato è necessaria una
gestione efficace degli interventi di manutenzione e una corretta definizione di piani per la sostituzione del parco
macchine.
Nel presente lavoro, si presenta un modello inferenziale fuzzy in grado di individuare le attrezzature da sostituire,
rispettando i principali obiettivi di riduzione della spesa in una struttura ospedaliera e di incremento del grado di
soddisfazione dei pazienti e del personale medico. Il modello considera parametri quantitativi e qualitativi, stimati in
modo oggettivo, al fine di comprendere i fattori che effettivamente influenzano le decisioni di sostituzione con un
approccio unico per il contesto sanitario.
L'approccio fuzzy al problema delle decisioni riguardanti la pianificazione degli interventi di sostituzione è incoraggiato
dai risultati ottenuti da una sperimentazione effettuata presso l'ospedale "Casa Sollievo della Sofferenza - S. Giovanni
Rotondo
A Novel Multi-Objective Genetic Algorithm Approach to Artificial Neural Network Topology Optimisation: The Breast Cancer Classification Problem
No full textThis paper presents a novel approach to Artificial Neural Network (ANN) topology optimisation that uses Multi-Objective Genetic Algorithm in order to find the best network configuration for the Wisconsin Breast Cancer Database (WBCD) classification problem. The WBCD [1][2][3] is a publicly available database composed by 699 cases, each of which is defined by 11 parameters. The former first 10 values of each record account for geometrical features of cells extracted with FNA biopsy. The last parameter represents the nature of the tumour; two classes of tumour are considered in this database: benignant and malignant tumours. An Intelligent System, IDEST, was designed and implemented. At the core of this system there's an Artificial Neural Network that is able to classify cases. The design of such an ANN is a non trivial task and choices incoherent with the problem could lead to instability of the network. For these reasons a fixed topology Genetic Algorithm (GA) approach was used to find an optimal topology for the given problem. In a second step a Multi-Objective GA (MOGA) was developed and employed in order to refine the search in the "topology space". Results shown by the IDEST demonstrate the great potentialities of similar approache
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Genetic Algorithm and Neural Network Based Classification in Microarray Data Analysis with Biological Validity Assessment
No full textMicroarrays allow biologists to better understand the interactions between diverse pathologic states at the gene level. However, the amount of data generated by these tools becomes problematic. New techniques are then needed in order to extract valuable information about gene activity in sensitive processes like tumor cells proliferation and metastasis activity. Recent tools that analyze microarray expression data have exploited correlation-based approach such as clustering analysis. Here we describe a novel GA/ANN based method for assessing the importance of genes for sample classification based on expression data. Several different approaches have been exploited and a com-parison has been given. The developed system has been employed in the classification of ER+/- metastasis recurrence of breast cancer tumours and results were validated using a real life database. Further validation has been carried out using Gene Ontology based tools. Results proved the valuable potentialities and robustness of similar systems
Improving female breast cancer prognosis by means of fuzzy rule induction with artificial immune systems
No full textBreast cancer is the second most common cause of deaths from cancer among women in the United States. Even if significant steps have been made in the field of cancer treatment there’s still room for investigation when it comes to the modeling of metastatic behavior of tumors. In particular over-treatment avoidance of patient is currently a challenging area of research due to the positive effects it can have patients’ quality of life and clinical costs management. In this paper we propose a novel approach to gene signature finding aimed at improving prediction accuracy of the tumor recurrence. Our approach lays on a novel computational paradigm, namely Artificial Immune Systems (AIS). Based on AIS, our algorithm, IFRAIS (Induction of Fuzzy Rules with Artificial Immune Systems) mines the high density array data in order to extract useful knowledge, in the form of “IF-THEN” rules, easily interpretable by physicians and able to improve prediction accuracy for tumor recurrence
- …
