A novel optimization algorithm for the missing data in HCC based on multiple imputation and genetic algorithm

Hepatocellular carcinoma (HCC) is a threat to the
liver, which is considered one of the diseases devastating to
human health that leads to death. Therefore, discovering HCC
early is essential, this will not begin without complete, adequate,
and reliable data. Hence, it is imperative to improve missing
data completion processes to provide more reliable data in the
detection phase. In this research, we offer a unique method that
combines multiple imputations with a genetic algorithm to
optimize multiple regression imputation processes and obtain
the optimum fitness values for missing data from patients. We
used 583 patient records from a public, available database to
train and evaluate our proposed algorithm, separated into 416
liver patient records and 167 non-liver patient records. Results
are proven that the proposed approach has the most
improvement for missing data results. We were able to reach the
optimal value which was measured by fitness value to 233
instead of using the normal equation in multiple imputations
which gave 92.72 as the uttermost fitness value of it. The
suggested model may be validated using a large database and
used in HCC laboratories to assist doctors in making an
accurate diagnosis.