Natural Language Processing in Medical Applications

Abstract

Medical applications of machine learning are very new, and there are still several obstacles that limit their widespread use. There is still a need to address issues like high dimensionality data and a lack of a standard data schema. An intriguing way to explore the possibilities of machine learning in healthcare is to apply it to the difficult problem of cardiovascular disease diagnosis. At the present day, cardiovascular disorders account for the majority of deaths worldwide. It is often too late to adopt appropriate treatment for many of them because they progress for a long time without showing any symptoms. Because of this, it's crucial to get checked up on routinely so that any developing diseases can be caught early. If the sickness is caught early enough, effective therapy can be put into place to stop the progression of the illness. This is done with the intention of analysing data from many sources and making use of NLP to overcome data heterogeneity. This paper evaluates the usefulness of several machine learning methods (such as the Naive Bayes (NB), Transductive Neuro-Fuzzy Inference, and Terminated Ramp-Support Vector Machine (TR-SVM)) for healthcare applications and suggests using Natural Language Processing (NLP) to address issues of data heterogeneity and the transformation of plain text. The implementation, testing, comparison of performance and analysis of the parameters of the algorithms used for diagnosis have simplified the process of selecting an algorithm better suited to a certain instance. TWNFI is particularly effective on larger datasets, while Terminated Ramp-Support Vector Machine is well suited to lesser datasets with a lower number of magnitudes due to performance difficulties.

Ähnliche Arbeiten