| NIM | K1B022011 |
|---|
| Namamhs | ALYA NUROTUL AFIFAH |
|---|
| Judul Artikel | KLASIFIKASI STATUS PERAWATAN PASIEN BERDASARKAN DATA PADA REKAM MEDIS ELEKTRONIK MENGGUNAKAN METODE XGBOOST
|
|---|
| Abstrak (Bhs. Indonesia) | Rekam Medis Elektronik (RME) tidak hanya berfungsi sebagai sarana pencatatan data pasien, tetapi juga berpotensi mendukung pengambilan keputusan medis berbasis data. Penelitian ini bertujuan membangun model klasifikasi status perawatan pasien (rawat inap dan rawat jalan) menggunakan algoritma eXtreme Gradient Boosting (XGBoost) serta mengevaluasi kinerjanya. Data yang digunakan adalah EHR Dataset for Patient Treatment Classification dari Mendeley Data. Tahapan penelitian meliputi analisis data, data preprocessing, perancangan skenario pemodelan dengan variasi data balancing dan penghapusan variabel, pembagian data dengan rasio 70:30, 80:20, dan 90:10, serta hyperparameter tuning. Evaluasi model dilakukan menggunakan confusion matrix dengan metrik accuracy, precision, dan recall. Hasil penelitian menunjukkan bahwa model tanpa data balancing dan tanpa penghapusan variabel dengan rasio 90:10 memberikan kinerja terbaik, yaitu accuracy 77,38%, precision 77,10%, dan recall 89,81%. |
|---|
| Abtrak (Bhs. Inggris) | Electronic Health Records (EHR) not only function as a means of recording patient data but also have the potential to support data-driven medical decision-making. This study aims to develop a classification model for patient treatment status (inpatient and outpatient) using the eXtreme Gradient Boosting (XGBoost) algorithm and to evaluate its performance. The data used in this study is the EHR Dataset for Patient Treatment Classification obtained from Mendeley Data. The research stages include data analysis, data preprocessing, the design of modeling scenarios with variations in data balancing and variable removal, data splitting with ratios of 70:30, 80:20, and 90:10, as well as hyperparameter tuning. Model evaluation is conducted using a confusion matrix with accuracy, precision, and recall metrics. The results show that the model without data balancing and without variable removal, using a 90:10 data split ratio, achieves the best performance, with an accuracy of 77.38%, precision of 77.10%, and recall of 89.81%. |
|---|
| Kata kunci | RME, klasifikasi, machine learning, XGBoost |
|---|
| Pembimbing 1 | Dra. Mutia Nur Estri, M.Kom. |
|---|
| Pembimbing 2 | Najmah Istikaanah, S.Si., M.Sc. |
|---|
| Pembimbing 3 | - |
|---|
| Tahun | 2026 |
|---|
| Jumlah Halaman | 12 |
|---|
| Tgl. Entri | 2026-04-13 08:50:11.082413 |
|---|