<![CDATA[The length of stay (LoS) of hospital patients is an essential indicator for measuring the efficiency of healthcare services. Accurate LoS prediction helps hospitals optimize resource management, estimate costs, and improve service quality. This study compares the performance of Linear Regression and Polynomial Regression algorithms in predicting patient LoS. The dataset, obtained from Kaggle, consists of 835 patient records that underwent preprocessing and transformation. The independent variables include gender, age, disease type, and type of service, while LoS serves as the dependent variable. The research applies the Knowledge Discovery from Data (KDD) approach, which includes the stages of selection, cleaning, transformation, data mining, and evaluation. Experiments were conducted using three data-splitting ratios (70:30, 80:20, and 90:10) with evaluation metrics MAE, MSE, RMSE, and R². The results show that Linear Regression performed slightly better, with average R² values ranging between 0.18 and 0.20, indicating its potential to support hospital management efficiency.Keywords: Length of Stay; Linear Regression; Polynomial Regression; Data Mining; Prediction. AbstrakDurasi rawat inap pasien (Length of Stay/LoS) merupakan indikator penting dalam mengukur efisiensi pelayanan rumah sakit. Prediksi LoS yang akurat membantu rumah sakit dalam pengelolaan sumber daya, estimasi biaya, dan peningkatan mutu layanan. Penelitian ini membahas perbandingan kinerja algoritma Linear Regression dan Polynomial Regression dalam memprediksi LoS pasien. Data penelitian diperoleh dari Kaggle dengan total 835 data pasien yang melalui proses preprocessing dan transformasi. Variabel independen meliputi gender, umur, jenis penyakit, dan jenis service, sedangkan LoS menjadi variabel dependen. Metode penelitian menggunakan pendekatan Knowledge Discovery from Data (KDD) yang mencakup tahapan selection, cleaning, transformation, data mining, dan evaluation. Pengujian dilakukan pada tiga rasio pembagian data (70:30, 80:20, dan 90:10) menggunakan metrik MAE, MSE, RMSE, dan R². Hasil menunjukkan Linear Regression memiliki performa sedikit lebih unggul dengan rata-rata R² sebesar 0,18–0,20, yang dapat mendukung efisiensi manajemen rumah sakit. ]]>
