Analysis of Missing Health Care Data by Effective Adaptive DASO Based Naive Bayesian Model

Abstract

Inevitably, researchers in the field of medicine must deal with the issue of missing data. Imputation is frequently employed as a solution to this issue. Unfortunately, the perfect would overfit the experiential data distribution due to the uncertainty introduced by imputation, which would have a negative effect on the replica's generalisation presentation. It is unclear how machine learning (ML) approaches are applied in medical research despite claims that they can work around lacking data. We hope to learn if and how machine learning prediction model research discuss how they deal with missing data. Information contained in EHRs is evaluated to ensure it is accurate and comprehensive. The missing information is imputed from the recognised EHR record. The Predictive Modelling approach is used for this, and the Naive Bayesian (NB) model is then used to assess the results in terms of performance metrics related to imputation. An adaptive optimisation technique, called the Adaptive Dolphin Atom Search Optimisation (Adaptive DASO) procedure, is used to teach the NB. The created Adaptive DASO method syndicates the DASO procedure with the adaptive idea. Dolphin Echolocation (DE) and Atom Search Optimisation (ASO) come together to form DASO. This indicator of performance metrics verifies imputation's fullness.

Ähnliche Arbeiten