Publication Search

Heart disease is the leading cause of death in Indonesia and globally, necessitating an early screening system that is both accurate and clinically trustworthy. Although XGBoost demonstrates high predictive performance, its black-box nature undermines clinical trust, while low recall risks missed diagnosis an unacceptable consequence in population screening, especially in middle-income countries with limited healthcare resources. This study aims to develop a sensitive, transparent, and implementation-ready heart disease screening framework through the integration of SHAP-based Explainable AI. The CDC's Indicators of Heart Disease dataset (319,795 samples) was processed according to WHO/CDC standards, followed by class imbalance handling, hyperparameter optimization using RandomizedSearchCV, evaluation based on metrics sensitive to minority classes (AUC, recall, F1-score, AUC-PR), and threshold tuning to maximize recall. The baseline model showed a very low recall of 12.18%. After optimization and threshold tuning at 0.10, the model achieved recall >96% (96.79%) with a G-mean of 0.7477, supported by SHAP interpretation stability and the ability to capture non-linear interactions between advanced age (AgeCategory_WHO) and poor general health (GenHealth). SHAP analysis confirmed the alignment of dominant features with medical evidence, and its visualizations provide transparent explanations for healthcare professionals indicating its potential implementation as an interpretable clinical decision support system.

Cardiovascular diseases are the leading cause of death worldwide, accounting for 17.9 million deaths annually. Stroke and heart attacks often go undetected due to their silent nature. This community service activity aimed to increase community knowledge about stroke and heart attacks and conduct early detection through health screening. The activity was conducted in Lalimbue Village, Kapoiala District, Konawe Regency on May 11 and 18, 2025. Methods included healthy exercise, educational talk show, first aid workshop, and health screening (blood pressure, blood glucose, cholesterol). Knowledge evaluation used pre-test and post-test with 10 questions. Results showed 56 participants on implementation day and 17 on follow-up. Pre-test showed 23% had good knowledge, 34% moderate, and 43% poor. Post-test showed 87% good knowledge and 13% moderate. Health screening found 10.7% with hypertension and 10.7% with diabetes mellitus on implementation day. Follow-up found 47.1% with hypertension and 23.5% with diabetes mellitus. This study concluded that health education is effective in increasing community knowledge about stroke and heart attack prevention, and health screening is important for early detection of cardiovascular and metabolic diseases.

AImbalanced data remains a significant issue in heart disease classification using machine learning, as it tends to cause models to overestimate the majority class while ignoring minority classes with high clinical value. This can lead to a decrease in accuracy and the model's ability to accurately detect disease cases. Therefore, this study aims to assess the effectiveness of oversampling techniques, namely Random Oversampling and Synthetic Minority Oversampling Technique (SMOTE), in improving the performance of the K-Nearest Neighbors (KNN), Naive Bayes (NB), and Random Forest (RF) algorithms. The dataset used comes from Kaggle and consists of 918 data sets with 12 attributes representing patient information related to heart disease prediction. The research stages include data preprocessing, baseline model testing, and re-evaluation using the two oversampling methods. Experimental results show that oversampling can improve the performance of all algorithms. KNN achieved the best results with SMOTE, with an accuracy of 72.98% and an F1-score of 75.39%. In the Naive Bayes algorithm, both oversampling techniques produced relatively stable performance, with the highest F1-score of 73.56% using SMOTE. Meanwhile, Random Forest showed the most optimal performance when combined with Random Oversampling, with an accuracy of 79.19% and an F1-score of 81.51%. These findings confirm that the success of data balancing techniques is strongly influenced by the characteristics of the classification algorithm used, and provide a practical contribution in determining strategies for handling imbalanced data in health research.

Hipertensi merupakan salah satu kondisi medis yang dapat menyebabkan berbagai komplikasi serius, seperti penyakit jantung koroner, stroke, dan gagal ginjal . Manajemen perawatan diri (self-care management) menjadi faktor penting dalam mengontrol tekanan darah pada penderita hipertensi . Self-care management mencakup regulasi diri, kepatuhan terhadap pengobatan, pemantauan tekanan darah, serta interaksi dengan tenaga medis . Penelitian ini menggunakan pendekatan kuantitatif dengan desain deskriptif korelasional dan metode cross-sectional . Sampel penelitian berjumlah 159 pasien hipertensi yang berobat di RS Islam Sultan Agung Semarang. Dari analisis univariat, mayoritas responden berada dalam rentang usia 45-59 tahun, berpendidikan terakhir SD, bekerja sebagai wiraswasta, serta memiliki tekanan darah tinggi selama rata-rata 3 tahun. Hasil analisis bivariat menunjukkan terdapat hubungan signifikan antara self-care management dan tekanan darah sistolik (p = 0,035) serta tekanan darah diastolik (p = 0,041) . Kesimpulannya terdapat hubungan antara self-care management dengan tekanan darah pada pasien hipertensi . Dengan meningkatkan self-care management, pasien dapat mengelola tekanan darah secara lebih efektif.

Coronary heart disease is one of the major health problems that not only affects the physical condition of patients but also impacts their psychological state, particularly anxiety. Anxiety levels in patients with coronary heart disease usually increase when they are about to undergo invasive medical procedures such as Percutaneous Coronary Intervention (PCI). Anxiety can be influenced by several factors, including age, gender, educational level, and occupation. High levels of anxiety may worsen the patient’s clinical condition, making appropriate non-pharmacological interventions highly necessary to help reduce anxiety. This study aims to determine the effect of spiritual support in the form of dzikir on the anxiety levels of patients with coronary heart disease. The research design used was a true experimental design with a pretest-posttest control group design. The sample consisted of 30 respondents who were evenly divided into two groups: 15 respondents in the intervention group and 15 respondents in the control group. The sampling technique used was total sampling. The instrument for measuring anxiety was the Hamilton Anxiety Rating Scale (HARS). The results showed that providing spiritual support in the form of dzikir was effective in reducing patient anxiety, with a p-value of 0.001. In addition, there was a significant difference in post-therapy anxiety levels between the control and intervention groups, with a p-value of 0.019 (p < 0.05). These findings demonstrate that dzikir, as a form of spiritual support, can be used as a non-pharmacological intervention to reduce anxiety in patients with coronary heart disease. Thus, spiritual support can be an important component of nursing care for patients in the ICU.

Penyakit jantung merupakan salah satu penyakit dengan angka kematian tertinggi di negara maju bahkan dunia. Penyakit jantung dapat mengancam jiwa jika tidak ditangani dengan serius. Jumlah penderita penyakit jantung meningkat setiap tahunnya. Penyakit jantung dapat disebabkan oleh beberapa faktor, yang utama adalah konsumsi alkohol berlebihan, kebiasaan merokok, dan faktor keturunan. Penelitian ini bertujuan untuk memprediksi dan mencegah penyakit jantung sejak dini menggunakan algoritma pembelajaran mesin, yaitu regresi logistik. Data yang digunakan untuk pelatihan dan pengujian algoritma regresi logistik sebanyak 1.190 data, yang terbagi menjadi 80% data pelatihan dan 20% data pengujian. Hasil pengujian menunjukkan bahwa model dapat memprediksi dengan akurasi sebesar 86%. Setelah model dibuat, model tersebut diimplementasikan ke dalam situs web. Penelitian ini diharapkan dapat berkontribusi pada diagnostik yang dapat membantu deteksi dini penyakit jantung.

Tingkat keberhasilan deteksi penyakit jantung sangat bergantung pada akurasi model klasifikasi yang digunakan. Penelitian ini bertujuan membandingkan kinerja dua algoritma klasifikasi, yaitu K-Nearest Neighbor (KNN) dan Support Vector Machine (SVM), dalam mendeteksi penyakit jantung menggunakan dataset berjumlah 1025 sampel dengan dua kelas target, yakni sehat dan penyakit jantung. Proses pra-pemrosesan data meliputi pembersihan dan normalisasi fitur medis seperti usia, tekanan darah, serta kadar kolesterol. Evaluasi performa model dilakukan menggunakan metode Confusion Matrix, K-Fold Cross Validation, kurva Receiver Operating Characteristic (ROC), dan kurva Precision-Recall untuk mengukur akurasi, presisi, recall, serta keseimbangan antara presisi dan recall. Hasil pengujian menunjukkan bahwa algoritma KNN unggul dalam menghasilkan akurasi tinggi yaitu 99% dengan AUC ROC sempurna 1.00 dan presisi yang hampir konsisten sepanjang recall, sementara SVM menunjukkan performa stabil dengan akurasi 91%, AUC ROC 0.97, dan AP Precision-Recall sebesar 0.96. Penelitian ini menegaskan efektivitas KNN dalam menghasilkan prediksi penyakit jantung yang sangat akurat dengan potensi risiko overfitting pada parameter k kecil, sedangkan SVM memberikan kestabilan model dengan kemampuan generalisasi yang lebih baik. Temuan ini diharapkan dapat menjadi referensi dalam pemilihan algoritma klasifikasi yang sesuai untuk mendukung diagnosis penyakit jantung secara klinis.

Coronary Heart Disease (CHD) is the leading cause of death in Indonesia. CHD is a disease caused by blockages in blood vessels (atherosclerosis) that disrupt blood flow to the heart. There are several risk factors for CHD, including smoking and hypertension. The purpose of this study was to determine the relationship between smoking and hypertension in patients with CHD. This research method uses the methodliterature review. Data were obtained from secondary data using documentation techniques. This documentation was done by searching for articles through Google Scholar and Pubmed. The selected articles were in accordance with the research variables and inclusion criteria. The articles were analyzed using the procedurecompare, contrast, criticize, synthesize, dan summarize. From the study, 3 articles were obtained that had data related to smoking and CHD variables (p < 0.05) and 3 articles that had data related to hypertension and CHD variables (p < 0.05). Conclusion: There is a significant relationship between smoking and hypertension in CHD patients.

Penelitian ini menyoroti tingginya angka kematian akibat penyakit kardiovaskular di Indonesia, terutama karena henti jantung mendadak yang sering terjadi di luar rumah sakit dan minimnya pertolongan pertama yang tepat. Dengan melibatkan 30 siswa kelas X MA Sunan Pandanaran Yogyakarta sebagai sampel, penelitian pre-eksperimental ini menggunakan desain one group pretest-posttest untuk menilai pengaruh simulasi Bantuan Hidup Dasar (BHD) terhadap sikap kesiapsiagaan siswa. Setelah diberikan edukasi dan praktik simulasi BHD selama 30 menit, hasil menunjukkan peningkatan signifikan sikap kesiapsiagaan siswa dari kategori “cukup” menjadi “baik”, dengan uji Wilcoxon menghasilkan nilai p = 0,000 (p < 0,05). Simpulan penelitian ini adalah simulasi BHD efektif meningkatkan kesiapsiagaan siswa dalam menghadapi situasi darurat medis, sehingga disarankan agar metode ini diintegrasikan ke dalam kurikulum pendidikan kesehatan di sekolah menengah dan diperluas ke kelompok remaja di berbagai institusi pendidikan.

Coronary heart disease (CHD) remains a leading cause of mortality worldwide. Early detection is essential to reduce complications and improve patient outcomes. This study aims to develop a classification model using machine learning algorithms to predict CHD risk based on clinical symptoms. The dataset used is the Cleveland Heart Disease dataset from the UCI Machine Learning Repository, consisting of 303 patient records with 14 clinical features. The preprocessing stage involved handling missing values, normalizing features, and transforming categorical variables. Four classification algorithms were applied: K-Nearest Neighbors (K-NN), Decision Tree, Random Forest, and Support Vector Machine (SVM). Each model was trained using stratified 10-fold cross-validation to ensure generalizability. Evaluation using accuracy, precision, recall, F1-score, and ROC-AUC metrics showed that the Random Forest algorithm achieved the highest performance with 87.2% accuracy. Feature importance analysis indicated that chest pain type, resting blood pressure, cholesterol, and ST depression were the most influential indicators. These results demonstrate that machine learning, particularly Random Forest, can effectively support early diagnosis of CHD in clinical settings and has the potential to be integrated into clinical decision support systems (CDSS).

Heart failure is the most common cardiovascular disease. Gambiran Regional Hospital has the 1st position of heart failure cases out of the top 10 diseases with the largest population in hospitalizations. To determine the prediction of heart failure disease in 2025-2028 which will increase or decrease. Using a descriptive research method, with a retrospective study research approach The population of all heart failure patients in 2021-2024 at Gambiran Regional Hospital, with a sampling technique of total sampling, the number of samples of inpatient heart failure patients in 2021-2024 at Gambiran Regional Hospital. Data collection was carried out by observation. The total number of heart failure patients increased significantly to 259 (2022). The trend has increased and decreased, the number of male patients jumped sharply to 150,3 (2024), while for women it jumped to 92,3 (2024). Overall, the prediction of the highest heart failure patient in 2028 will reach 316,2 while the lowest will be in 2025. The number of heart failure hospitalizations shows a trend of change that tends to increase during 2021–2024. Based on gender, male patients dominated visits. The 2025–2028 prediction predicts an increase in the number of patients, with the highest number in male patients and total visits reaching 316,2.: Hospitals can collaborate with local health departments to hold routine screening programs for those at high risk.

Coronary heart disease (CHD) is one of the leading causes of death worldwide due to impaired blood and oxygen supply to the heart muscle. This study aims to explore the potential of two natural compounds—kaempferol from Moringa oleifera and geranylated chalcone (GTDC) from Artocarpus altilis—as therapeutic candidates for CHD through a molecular docking approach. Medicinal chemistry analysis revealed that kaempferol exhibits significant affinity for the NF-κB protein, forming key hydrogen bonds with residues involved in the inflammatory process of atherosclerosis. Meanwhile, GTDC demonstrates strong binding to the P2Y12 receptor, which plays a crucial role in platelet aggregation, with a docking score lower than that of the natural ligand ADP. Structurally, hydroxyl group positioning and the lipophilic geranyl chain enhance both bioactivity and pharmacokinetic properties. In conclusion, a medicinal chemistry approach involving in silico docking, structure–activity relationship (SAR) analysis, and ligand optimization strategies confirms the potential of kaempferol and GTDC as promising multifunctional therapeutic agents for CHD. Further validation through in vivo studies and clinical testing is required.    

Masalah kesehatan internasional adalah hipertensi, penyebab utama gagal ginjal, stroke, dan penyakit jantung. Diperkirakan 34,1% orang di Indonesia menderita hipertensi, dan sebagian besar dari mereka tidak mendapatkan pengobatan. Meskipun Puskesmas Welahan 1 menangani hipertensi, pasien sering mengalami kesulitan mengontrol tekanan darah mereka karena berbagai macam obat yang tersedia. Tujuan dari penelitian ini adalah untuk mengetahui seberapa efektif terapi monoterapi dan kombinasi untuk mencapai target tekanan darah pasien hipertensi di Puskesmas Welahan 1 dan bagaimana berbagai obat mempengaruhi kontrol tekanan darah. Data dari 60 pasien hipertensi yang memenuhi kriteria inklusi dianalisis selama tiga bulan menggunakan pendekatan cross-sectional. Digunakan statistik inferensial dan deskriptif, seperti uji chi-square. Tidak ada korelasi signifikan antara kontrol tekanan darah sistolik dan diastolik dan jenis terapi obat (p > 0,05). Namun, pasien yang menerima amlodipine atau amlodipine + captopril lebih mampu mengontrol tekanan darah mereka, dengan rasio kemungkinan 0,857 untuk tekanan sistolik dan 6,429 untuk tekanan diastolik, masing-masing.  Hasilnya menunjukkan bahwa terapi kombinasi mungkin membantu mengontrol tekanan darah diastolik, meskipun jenis obat tidak mempengaruhi tekanan darah secara langsung

Heart disease is one of the biggest causes of death in the world. This research examines the use of the Artificial Neural Network (ANN) algorithm to classify heart disease based on 303 medical data of heart disease patients obtained from the Kaggle dataset center. The data used includes medical parameters such as age, gender, blood pressure, cholesterol levels and other examination results. Various ANN architectures were tested to find the optimal configuration in terms of the number of hidden layers and neurons in each layer. Model performance is evaluated using metrics such as accuracy, precision, recall, and F1-score. From the results of the performance measurement research, an accuracy rate of 97.06%, precision of 92.30%, recall of 92.30%, and F1-Score of 92.30% were obtained.

Decoction water betel leaf is a traditional Balinese medicine containing the active compound hydroxychavikol, has antioxidant and antidyslipemic activity. From the results of the study it was reported that decoction water of betel leaf contains the active compound hydroxycavicol (HC). The active compound hiroksikavikol has activity as an antioxidant and antidyslipidemia. As an anti-oxidant, it can scavenge ROS and inhibit the activity of free radicals. As an antidyslipidemia, it can normalize lipid metabolism by lowering total cholesterol, triglyceride, LDL and VLDL levels and increasing blood serum HDL levels. Oxidative stress and dyslipidemia are major risk factors for heart disease caused by atherosclerosis. Atherosclerosis is the occurrence of plaque formation in the lumen of blood vessels triggered by oxidative stress through endothelial cell dysfunction, inflammation and lipid peroxidation. Oxidative stress causes endothelial cell dysfunction, increased contractility, VSMC growth, monocyte invasion and lipid peroxidation, inflammation and increased deposition of extracellular protein matrix. Based on these things, it was concluded that HC loloh boiled water of betel leaf has antioxidant and antidyslipidemic activity to prevent heart disease.

Middle adulthood ranges from 40 years to 60 years. The needs of heart disease sufferers in middle adulthood are needs that prioritize physical health such as exercise, diet and regular medication. This research aims to find out how important the needs of individuals suffering from heart disease are. The research method used is a qualitative method with a literature and interview approach. Data was obtained from analysis of related literature as well as in-depth interviews with informants who suffered from heart disease at the age of 58 years. The research results show that the needs of middle adults who suffer from heart disease prioritize health restoration recommended by doctors by means of bypass surgery. This is shown by the improvement in physical health experienced by the informants, by maintaining their diet, taking prescribed medication, exercising regularly, and monitoring their health at recommended clinics. This result has been felt by the informant that changes in his physical condition are currently starting to improve and he is still in the recovery stage.

Hypertension is a strong and important risk factor for cardiovascular diseases and kidney diseases, such as coronary heart disease, heart failure, and kidney failure. High blood pressure can be influenced by genetic factors, environmental factors and the interaction between the two factors.This study aims to determine the relationship between hypertension and lifestyle in coronary heart disease patients at Wulan Windy Marelan General Hospital in 2024.The research design used in this study uses an analytical survey method with a cross-sectional approach. This study was conducted at the Heart Polyclinic of Wulan Windy Marelan General Hospital, Medan in 2024. The population in this study were coronary heart patients totaling 4676 respondents from December 2023-February 2024. The sampling technique used was purposive sampling with reference to the Slovin formula, namely 100 respondents. The data collection instrument used univariate and bivariate analysis. The test used was the Chi-Square test. Research results Based on statistical tests using the chi-square test, the p-value = (0.038) (α = <0.05) is obtained, which is less than or not more than α = 0.05, which means that Ho is rejected, Ha is accepted, which means that there is a significant relationship between hypertension and lifestyle in coronary heart disease patients at Wulan Windy Marelan General Hospital in 2024.The conclusion in this study shows that statistically there is a relationship between hypertension and lifestyle in coronary heart disease patients at Wulan Windy Marelan General Hospital in 2024.

This research analyzes the relationship between knowledge of dietary patterns and risk factors for heart disease in adolescents, especially students. The method used was quantitative with a cross-sectional design, involving 45 teenagers. The results show that the majority of respondents have low knowledge and negative dietary behavior, with p-value = 0.012, indicating a significant relationship. Knowledge of risk factors for heart disease is very important for establishing healthy eating behavior, which has an impact on future heart health.

Abstrak. Diabetes adalah penyakit metabolik kronis yang ditandai dengan peningkatan kadar glukosa darah (atau gula darah), yang seiring waktu menyebabkan kerusakan serius pada jantung, pembuluh darah, mata, ginjal, dan saraf. Di RSKD Provinsi Maluku metode pemeriksaan untuk mengetahui ada tidaknya protein urine pada penderita diabetes melitus tipe-2 dengan terap metformin adalah menggunakan pemeriksaan protein urine dengan sampel urine pagi. Tujuan: Untuk mengetahui penggunaan terapi metformin pada penderita diabetes melitus tipe-2 dan untuk mengetahui protein urine pada penderita diabetes melitus tipe-2 dengan terapi metformin. Metode: Jenis penelitian adalah deskriptif yang ditunjang dengan pemeriksaan laboratorium menggunakan metode automatic. Jumlah sampel yang digunakan 12 sampel pasien diabetes melitus tipe-2 yang menggunakan terapi metformin dengan menggunakan metode sampling insidental. Hasil: Hasil penelitian didapatkan bahwa seluruh sampel urine pasien diabetes melitus tipe-2 yang menggunakan terapi metformin di RSKD Provinsi Maluku hasilnya negatif sebanyak 10 sampel dengan presentase (80%) dan positif (++) sebanyak 2 sampel dengan presentase (20%). Kesimpulan: Berdasarkan hasil penelitian maka dapat disimpulkan sebanyak 12 sampel Urine pasien diabetes melitus tipe-2 yang menggunakan terapi metformin dengan hasil Negatif (80%) dan Positif (20%), menunjukkan bahwa adanya gangguan pada fungsi ginjal.

Abstrak. Diabetes adalah penyakit metabolik kronis yang ditandai dengan peningkatan kadar glukosa darah (atau gula darah), yang seiring waktu menyebabkan kerusakan serius pada jantung, pembuluh darah, mata, ginjal, dan saraf. Di RSKD Provinsi Maluku metode pemeriksaan untuk mengetahui ada tidaknya protein urine pada penderita diabetes melitus tipe-2 dengan terap metformin adalah menggunakan pemeriksaan protein urine dengan sampel urine pagi. Tujuan: Untuk mengetahui penggunaan terapi metformin pada penderita diabetes melitus tipe-2 dan untuk mengetahui protein urine pada penderita diabetes melitus tipe-2 dengan terapi metformin. Metode: Jenis penelitian adalah deskriptif yang ditunjang dengan pemeriksaan laboratorium menggunakan metode automatic. Jumlah sampel yang digunakan 12 sampel pasien diabetes melitus tipe-2 yang menggunakan terapi metformin dengan menggunakan metode sampling insidental. Hasil: Hasil penelitian didapatkan bahwa seluruh sampel urine pasien diabetes melitus tipe-2 yang menggunakan terapi metformin di RSKD Provinsi Maluku hasilnya negatif sebanyak 10 sampel dengan presentase (80%) dan positif (++) sebanyak 2 sampel dengan presentase (20%). Kesimpulan: Berdasarkan hasil penelitian maka dapat disimpulkan sebanyak 12 sampel Urine pasien diabetes melitus tipe-2 yang menggunakan terapi metformin dengan hasil Negatif (80%) dan Positif (20%), menunjukkan bahwa adanya gangguan pada fungsi ginjal.