Subscription or Fee Access
Differential diagnosis of hemorrhagic fevers using ARTMAP and an Artificial Immune System
The differential diagnosis of endemic hemorrhagic fevers in tropical countries is by no means an easy task for medical practitioners. Several diseases often overlap with others in terms of signs and symptoms, thus making this diagnosis a difficult, error-prone process. Machine Learning algorithms possess some useful qualities to tackle this kind of pattern recognition problems. In this paper, a neural-network-based approach to the differential diagnosis of Dengue Fever, Leptospirosis and Malaria, using the Adaptive Resonance Theory Map (ARTMAP) family is discussed. The use of an Artificial Immune System (CLONALG) led to the identification of a subset of symptoms that enhanced the performance of the classifiers considered. Training, validation and testing phases were conducted using a dataset consisting of medical charts from patients treated in the last 10 years at Napole´on Franco Pareja Children Hospital in Cartagena, Colombia. Results obtained on the test set are promising, and support the feasibility of this approach.
Machine Learning, Neural Networks, ARTMAP, Hemorrhagic Fever, Dengue, Leptospirosis, Malaria, Differential Diagnosis.
Disclaimer/Regarding indexing issue:
We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.