Abstract | ||
---|---|---|
Precocious diagnosis increases the survival time and patient quality of life. It is a binary classification, exhaustively studied in the literature. This paper innovates proposing the application of genetic programming to obtain a discriminate function. This function contains the disease dynamics used to classify the patients with as little false negative diagnosis as possible. If its value is greater than zero then it means that the patient is ill, otherwise healthy. A graphical representation is proposed to show the influence of each dataset attribute in the discriminate function. The experiment deals with Breast Cancer and Thrombosis & Collagen diseases diagnosis. The main conclusion is that the discriminate function is able to classify the patient using numerical clinical data, and the graphical representation displays patterns that allow understanding of the model. |
Year | Venue | Keywords |
---|---|---|
2003 | EuroGP | patient quality,false negative diagnosis,graphical representation,graphical representation displays pattern,discriminate function,breast cancer,disease modeling,precocious diagnosis,dataset attribute,binary classification,collagen diseases diagnosis,quality of life,discriminant function,genetic programming |
Field | DocType | Volume |
Disease,Receiver operating characteristic,Binary classification,Computer science,Genetic programming,Artificial intelligence,Genetic algorithm,Discriminant function analysis,Machine learning | Conference | 2610 |
ISSN | ISBN | Citations |
0302-9743 | 3-540-00971-X | 0 |
PageRank | References | Authors |
0.34 | 9 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
James Cunha Werner | 1 | 3 | 0.93 |
Tatiana Kalganova | 2 | 195 | 15.96 |