Ensemble Evolutionary Algorithm for Feature Selection and Classification in Healthcare Data Mining
In the field of primary and secondary healthcare, the widespread adoption of electronic health record (EHR) systems has resulted in the availability of a vast quantity of clinical data that is simple to access. From where we were before, this is a significant advancement in our situation.
Melanoma is a common skin cancer; nevertheless, despite the fact that it has a high death rate, medical professionals frequently make an incorrect diagnosis of it. It is essential to refer patients to arrive at an accurate prognosis from the beginning.
Within the scope of this investigation, we develop an ensemble evolutionary framework in order to classify cancer disorders through the utilization of electronic health information.
Electronic health record systems are responsible for this influence. The majority of this data originates from clinical reports that were either spoken or recorded by medical professionals. These reports were not arranged in any way.
The proposed method outperforms the other approaches in terms of the classification rate, as we discovered when we ran the simulation to evaluate how well the model functions.
This work can be recommended for developing a novel framework that uses deep learning algorithms to effectively optimize the provision of healthcare services and address these issues.
This work can be enhanced using several deep-learning algorithms for better accuracy and performance.
Back