Abstract:
Premature birth is a birth that can occur before the 37th week of pregnancy. Infants
who are born prematurely may suffer more serious health problems than those born on
schedule. This is because the immaturity of the organs in the baby's body is
malfunctioning. This research aims to implement an algorithm K-Nearest Neighbor for
prediction the birth of premature babies at the RSIA Budhi Mulia Pekanbaru. The
stages in this research are in accordance with the stages in data mining. This research
uses 100 datasets which are then divided into training and testing data by dividing the
data using k-fold cross validation as much as 10 folds. So that training data is obtained
for each fold total of 90 data and testing data total of 10 data. Based on the results of
calculations using the KNN method on the medical record data of patients giving birth
to RSIA Budhi Mulia Pekanbaru, it produced the highest levels of accuracy in fold 1,
which is 90%, with precision is 87.5% and recall is 100%.
