An ensemble approach for healthcare application and diagnosis using natural language processing

Abstract

Integration of healthcare records into a single application is still a challenging process There are additional issues when data becomes heterogeneous, and its application based on users does not appear to be the same. Hence, we propose an application called MEDSHARE which is a web-based application that integrates the data from various sources and helps the patient to access all their health records in a single point of source. Apart just from the collection of data, this portal enables the process of diagnosis using Natural language processing. The process is carried out by fuzzy logic ruleset which is generated by using NLP packages. The resulted information is given to the SVM classifier which helps in the prediction of diseases resulting in 89% of accuracy and standing the best compared to other classifiers. Finally, the observations resulted are sent to the front end application and the concerned user mobile through text message in their own native language for which translation package is been used.

An adaptive ml model for covid-19 diagnosis in a smart hospital environment

“…The Applications of machine learning in the healthcare sector have been very effective because it has more relevance than other applications or approaches due to their ability to reduce the burden of medical professionals in this kind of pandemic situation and help to control it in remote areas where medical facilities are least available [24]. A lot of research has been undertaken on the use of deep learning in the interpretation of the signs and symptoms of the Novel COVID-19.…”

“…Based on the enhancing predictive performance of the ensemble model in our healthcare sector, there have already been several attempts in recent years to incorporate the ensemble in all medical activities. According to [24], [35], the application of an ensemble model in the healthcare sector which in turn can be used to enhance the classi cation task can also be known as a method for varies in terms of how to split the training data and the ways to merge several learners to produce the nal prediction model since traditional database management system are inadequate [36]. Aside from all this, some researchers have also evaluated and compared the performance of their classi cation problems using different ensemble methods.…”

From Fragmented to Integrated: Transforming Emergency Healthcare Delivery through Digital Twin Technology

“…Furthermore, the prediction made by this Machine Learning technique also provides the probability of the ongoing action and states based on the measures mentioned in Table 2. One of the most significant advantages of Ensemble Modelling includes its optimization for specific situations critical from a Healthcare perspective (Alekhya & Sasikumar, 2022).…”

An Asymmetric Ensemble Method for Determining the Importance of Individual Factors of a Univariate Problem

“…In recent years, in both machine and statistical learning fields, good results have been achieved by using ensemble methods that can leverage good characteristics of both types of the aforementioned methods while mitigating their shortcomings and limitations [18,19]. Among the ensemble methods, the best results have been achieved through the application of stacking group methods, which use the aggregation of different algorithms to obtain better predictive models than could be obtained from any of the algorithms individually and are superior to most known methods [20,21].…”