Health Recommender System for Cervical Cancer Prognosis in Women
Madhusree Kuanr, Puspanjali Mohapatra, Jayshree Piri · 2021
The large amount of digital data of patients are available for health domain to be used successfully for extracting information and aid disease prediction. Therefore, the available digital information for patient-oriented decision-making substantially expanded. Recommender systems may offer more laymen-friendly knowledge to patients in this sense, helping to better understand their clinical status as reflected by their reports. Health Recommender Systems (HRSs) are a viable solution when it comes to offering resources to support clinicians in the diagnosis of illnesses, as well as supporting people with guidance on how to preserve their health. This study has proposed a Health Recommender System using a feature selection method based on the Multi Objective Genetic Algorithm (MOGA) to help women by providing information on the features responsible for prognosis of Cervical Cancer in women. It also recommends some prediction models for Cervical Cancer prediction with high accuracy. It has used Cervical Cancer Risk Classification dataset for implementation and accuracy as the evaluation parameter.