Singgih
Institut Kesehatan dan Bisnis Surabaya

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

ANALYSIS OF FACTORS RELATED TO HEMOGLOBIN (Hb) LEVELS IN PATIENTS UNDERGOING HEMODIALYSIS (HD) AT BHAYANGKARA HOSPITAL SURABAYA Singgih; Ariska Putri
Jurnal Penelitian Keperawatan Kontemporer Vol 6 No 3 (2026): Juli 2026
Publisher : Program Studi S1 Ilmu Keperawatan dan Ners IKBIS Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59894/jpkk.v6i3.1468

Abstract

Kidney failure (CKD) is a disease that results in reduced kidney function. One of the complications of CKD is anemia. Anemia caused by decreased erythropoietin, shortened red blood cell life span, gastrointestinal bleeding due to toxic irritation and blood loss during hemodialysis. The research design used is correlational research. The type of research used is a cross-sectional study. The population of this study was 60 patients undergoing hemodialysis at Bhayangkara Hospital Surabaya who experienced anemia in the hemodialysis room at Bhayangkara Hospital Surabaya. Sampling used a probability sampling technique, namely proportionate stratified random sampling. The instrument in this research is a checklist sheet. The independent variables in this study include the length of time the patient underwent hemodialysis, the patient's nutritional status and HD adequacy. The data analysis used was the Rank - spearmen test. The research results from 60 respondents, the majority (38.3%) underwent HD for 6 - 8 years. The nutritional status of most patients (67%) was normal. The HD adequacy rate achieved in the hemodialysis room was 40 respondents (67%). The spearmen's rank test calculated significantly the patient's nutritional status, and the achievement of HD adequacy with Hb levels with a p-value of 0.000 (a < 0.05), which means there is a relationship between nutritional status and the achievement of HD adequacy and the Hb levels of patients undergoing hemodialysis at Bhayangkara Hospital, Surabaya. So it is stated that H0 is rejected and Ha is accepted. Then, for the length of HD factor, calculated using the Spearman's rank test, the p-value was 0.18 (a > 0.05), which means there is no relationship with the Hb level of patients undergoing HD at Bhayangkara Hospital, Surabaya, so it is declared that H0 is accepted and Ha is rejected. The conclusion of this research is that nutritional status and HD adequacy factors have a significant relationship with Hb levels in the Hemodialysis Room at Bhayangkara Hospital, Surabaya. It is hoped that this research can be applied by researchers with related parties (research sites).
Analisis Faktor Risiko Kejadian Stunting Menggunakan Pendekatan Machine Learning untuk Prediksi Dini Ariska Putri Hidayathillah; Singgih; Anggun Pranesia; Maria D.J.Murni
Jurnal Penelitian Keperawatan Kontemporer Vol 6 No 1 (2026): Januari 2026
Publisher : Program Studi S1 Ilmu Keperawatan dan Ners IKBIS Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59894/jpkk.v6i1.1225

Abstract

Latar Belakang: Berdasarkan data dari tahun 2020 sampai dengan 2024 faktor stunting yang tercatat di Puskesmas golowelu semakian meningkat. Di tahun 2020 tercatat bahwa sebanyak 243 kasus kejadian stunting Berdasarkan Golowelu data balita stunting bahwa Kecamatan lembor menduduki persentase tertinggi di lembor selatan dengan 57,2% pada tahun 2020. Tujuan: untuk menganalisis faktor risiko kejadian stunting pada balita di wilayah kerja Puskesmas Golowelu Kabupaten Manggarai Barat dengan menggunakan pendekatan Machine Learning untuk prediksi dini. Permasalahan stunting merupakan isu penting kesehatan masyarakat yang berdampak pada perkembangan kognitif, fisik, dan sosial anak. Dengan berkembangnya teknologi analitik data, machine learning dapat digunakan untuk memprediksi risiko stunting berdasarkan berbagai faktor seperti status gizi ibu saat hamil, berat badan lahir, pemberian ASI eksklusif, riwayat penyakit infeksi, dan pola pemberian makan. Metode: Penelitian ini menggunakan desain kuantitatif dengan pendekatan analitik prediktif. Data diperoleh dari rekam kesehatan Puskesmas Golowelu dan hasil survei terhadap 30 responden balita usia 23–59 bulan. Analisis data dilakukan dengan tiga algoritma machine learning, yaitu Regresi Logistik, Random Forest, dan Support Vector Machine (SVM). Hasil: simulasi menunjukkan bahwa model Random Forest memiliki kinerja terbaik dengan akurasi 91,2%, sensitivitas 89,5%, spesifisitas 93,3%, dan Area Under Curve (AUC) sebesar 0,94. Faktor yang paling berpengaruh terhadap prediksi stunting adalah riwayat penyakit infeksi, status gizi ibu saat hamil, dan pola pemberian makan. Kesimpulan: Hasil penelitian ini diharapkan dapat menjadi dasar pengembangan sistem deteksi dini risiko stunting berbasis machine learning di fasilitas pelayanan kesehatan primer.