Claim Missing Document
Check
Articles

Found 15 Documents
Search

Utilizing Artificial Intelligence to Analyze Gender Differences in Hypertension Risk Factors Husnul Khuluq; Tri Cahyani Widiastuti; Lazuardi Fatahillah Hamdi; Tunjung Winarno
Indonesian Journal of Global Health Research Vol 7 No 1 (2025): Indonesian Journal of Global Health Research
Publisher : GLOBAL HEALTH SCIENCE GROUP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37287/ijghr.v7i1.4929

Abstract

Hypertension continues to pose a significant challenge to global health. Early identification of risk factors, particularly those influenced by gender differences, has the potential to markedly enhance treatment processes and outcomes. Artificial intelligence (AI), specifically machine learning (ML), offers a promising avenue for identifying and analysing these critical risk factors. Objective: This study aims to explore the influence of gender differences on risk factors affecting hypertensive patients by examining demographic, medication, clinical, and laboratory data.Method: The study utilized medical records of hospitalized hypertensive patients at PKU Muhammadiyah Hospital Yogyakarta, covering the years 2022 to 2023. Logistic regression analysis with Lasso penalty was applied to determine the most influential variables. Additionally, the Random Forest algorithm implemented in WEKA, combined with a 10-fold cross-validation approach, was employed to evaluate the model’s diagnostic performance using metrics such as precision, sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (ROC-AUC). Results: A total of 1,006 patients were included in the sample, comprising 504 males and 502 females. Among the 33 clinical variables analysed, 13 demonstrated non-zero coefficients. For female hypertensive patients, the five most significant risk factors, along with their coefficients, were Haemoglobin (0.03), Diabetes Mellitus (0.04), Lymphocytes (0.06), Anaemia (0.13), and Creatinine (0.15). In male hypertensive patients, the top five risk factors and their coefficients were Acute Kidney Injury (-0.32), Erythrocytes (-0.15), Congestive Heart Failure (-0.03), Leukocytes (-0.02), and Length of Stay (LOS) (-0.01). The model’s overall performance, as reflected by a ROC-AUC score of 0.805, indicates a good level of predictive accuracy. Conclusions: The findings reveal a significant association between gender and hypertension risk factors. These results underscore the potential for gender-specific customization of hypertension treatments, paving the way for more individualized therapeutic strategies and improved patient outcomes.
Identification of Genomic Databases and Bioinformatics Analysis of Gene Variations in Behçet Syndrome Across Continental Populations Dwiki Fitri; Husnul Khuluq; Diah Kurniasih; Muhammad Ma'ruf
Indonesian Journal of Global Health Research Vol. 8 No. 2 (2026): Indonesian Journal of Global Health Research
Publisher : GLOBAL HEALTH SCIENCE GROUP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37287/ijghr.v8i2.751

Abstract

Behçet's Syndrome is a rare multisystem inflammatory disorder with an etiology that is not yet fully understood. The disease is characterized by various clinical manifestations, including recurrent oral and genital ulcers, ocular lesions, skin abnormalities, arthritis, central nervous system involvement, and vascular complications. Understanding the genetic factors associated with Behçet's Syndrome across different populations may provide insights into its pathogenesis and potential therapeutic targets. This study aims to identify genetic variations associated with Behçet's Syndrome across populations from different continents using a bioinformatics approach. Data were analyzed from the GWAS Catalog, HaploReg v4.2, GTEx Portal, and Ensembl Genome. Single nucleotide polymorphisms (SNPs) associated with Behçet's Syndrome were identified, and their tissue-specific gene expression and allele frequency across populations were investigated. Two main SNPs, rs17482078 and rs2617170, were identified as missense mutations in the ERAP1 and KLRC4 genes, respectively, both of which have been linked to various autoimmune diseases. GTEx Portal analysis revealed that ERAP1 is expressed in 30 tissues, including skeletal muscle, blood, brain regions (putamen, caudate, hypothalamus), skin, pancreas, esophagus, and other organs. KLRC4 expression was observed in 18 tissues, including the cerebral cortex, lungs, heart, small intestine, thyroid, prostate, and additional tissues. Ensembl Genome data indicated population-specific allele frequency variation: rs17482078 in ERAP1 was highest in Africa (94.6%), followed by East Asia (94.2%), South Asia (93.5%), the Americas (88%), and Europe (78%). SNP rs2617170 showed the highest frequency in Africa (57%), followed by South Asia (46%), East Asia (45%), Europe (34%), and the Americas (33%). The findings highlight ERAP1 and KLRC4 as key genetic factors associated with Behçet's Syndrome and demonstrate population-specific allele frequency differences. These results provide valuable insights into the genetic architecture of the disease and may guide future studies on its pathogenesis and potential therapeutic strategies.
MODEL PREDIKSI FAKTOR-FAKTOR RISIKO OBESITAS MENGGUNAKAN MACHINE LEARNING Husnul Khuluq; Lazuardi Fatahillah Hamdi; Ayu Nissa Ainni; Tri Cahyani Widiastuti
Journal of Health Service Management Vol 29 No 00 (2026): Vol 29/Edisi Khusus/Februari/2026
Publisher : Departemen of Health Policy and Management, Faculty of Medicine, Public Health, and Nursing, Universitas Gadjah Mada, Yogyakarta Jl. Farmako Sekip Utara Yogyakarta 55281 Telp 0274-547490

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/jmpk.v29i00.25716

Abstract

Background: Obesity is a major global health concern and a key risk factor for various non-communicable diseases, including diabetes, hypertension, and cardiovascular disorders. Despite extensive studies, accurately identifying the key contributing factors remains a challenge. Objective: This study aims to predict the likelihood of obesity using a machine learning algorithm, based on questionnaire-derived clinical and behavioral data. Several supervised machine learning algorithms—logistic regression, naïve Bayes, support vector machine (SVM), and random forest—will be employed to build predictive models. Model performance will be evaluated using accuracy, precision, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). Methods: We used an open-access dataset from Kaggle comprising 2,111 samples with anthropometric, demographic, and lifestyle data. Of these, 972 individuals were categorized as obese and 1,139 as non-obese. The target variable was categorized into binary labels: "Obesity" and "Non-Obesity." Preprocessing included one-hot encoding, label encoding, and train-test splitting. All four ML models were trained and evaluated using accuracy, area under the curve (AUC), precision, sensitivity, and specificity metrics. Results: The model achieved an accuracy of 98.58%, AUC of 99.96%, sensitivity of 98.99%, specificity of 98.21%, and precision of 98.01%. The most influential predictors were weight, frequent consumption of high-caloric food, family history of being overweight, physical activity frequency, and daily water intake. Conclusion: The model demonstrated high performance and identified key lifestyle-related features. These findings support machine learning's potential for obesity screening and public health strategy development.
Machine Learning-Based Prediction of Diabetes Medication Use: A Pharmacoepidemiological Analysis of the Indonesia Family Life Survey Husnul Khuluq; Imam Tri Suryadin; Tri Cahyani Widiastuti; Ayu Nissa Ainni
Indonesian Journal of Global Health Research Vol. 8 No. 6 (2026): Indonesian Journal of Global Health Research: December 2026
Publisher : GLOBAL HEALTH SCIENCE GROUP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37287/ijghr.v8i6.2740

Abstract

Diabetes pharmacotherapy frequently coexists with treatment for cardiovascular and metabolic comorbidities, highlighting the potential role of data-driven methods in pharmaceutical care. This study aimed to develop and compare machine learning models for predicting diabetes medication use using the fifth wave of the Indonesia Family Life Survey (IFLS5), conducted in Indonesia in 2014–2015. A secondary analysis included 48,139 participants with valid outcome information, of whom 353 (0.73%) reported diabetes medication use. Predictors included age, sex, pregnancy status, weight, height, hemoglobin, systolic and diastolic blood pressure, pulse, and medication use for anemia, hypertension, and hypercholesterolemia. Class imbalance was addressed using Synthetic Minority Over-sampling Technique for Nominal and Continuous features (SMOTENC) exclusively within training folds. LASSO-based feature selection was also performed within stratified 10-fold cross-validation. Random Forest, linear Support Vector Machine (SVM), Logistic Regression, and Gaussian Naive Bayes were compared. Logistic Regression achieved 80.13% accuracy, 76.20% sensitivity, 80.16% specificity, and an AUC of 0.870. Linear SVM showed comparable discrimination (AUC=0.870). Random Forest achieved high accuracy (97.86%) but low sensitivity (18.13%), whereas Naive Bayes achieved high sensitivity (98.30%) but low specificity (26.77%). LASSO consistently identified pregnancy status, cholesterol medication use, hypertension medication use, and weight among the strongest predictors. Logistic Regression provided the most balanced classification performance and may support further pharmacoepidemiological investigation of diabetes medication-use patterns.
FAKTOR-FAKTOR RISIKO YANG MEMPENGARUHI LAMA RAWAT INAP PASIEN GAGAL GINJAL KRONIK Dzakiyah Putri Kurniawati; Husnul Khuluq; Ayu Nissa Ainni
Jurnal 'Aisyiyah Medika Vol 10, No 1: Februari 2025 Jurnal 'Aisyiyah Medika
Publisher : stikes 'aisyiyah palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36729/jam.v10i1.1340

Abstract

Latar Belakang: Gangguan fungsi ginjal ini terjadi ketika tubuh gagal untuk mempertahankan metabolisme dan keseimbangan cairan dan elektrolit sehingga mengakibatkan retensi urea dan sampah nitrogen lain dalam darah. Tujuan: Penelitian ini bertujuan untuk mengetahui faktor risiko yang mempengaruhi lama rawat inap pasien Gagal Ginjal Kronik di RSUD Prembun Kabupaten Kebumen periode 2023. Metode: Penelitian ini dilakukan secara retrospektif. Pada penelitian ini menggunakan uji bivariat metode deskriptif korelatif dengan uji chi-square kemudian dilihat hubungan antara lama rawat inap pasien dengan variabel terikat yaitu data demografi, data laboratorium, data obat, data klinik. Hasil: Dari hasil penelitian ini parameter umur pada pasien Gagal Ginjal Kronik yaitu umur diatas 65 tahun menaikan resiko lama di rawat tetapi tidak signifikan OR = 1,570 (0,518-4,756) ; p = 0,301. Parameter jenis kelamin (Wanita) pada pasien Gagal Ginjal Kronik berisiko menurunkan lama dirawat tetapi tidak signifikan dengan OR = 0,787 (0,331-1,870) ; p = 0,372. Parameter umur dan jenis kelamin dapat menurunkan lama dirawat tetapi tidak signifikan. Saran : Perlu dilakukan penelitian lebih lanjut terkait faktor risiko pasien Diabetes Melitus Tipe II dengan lama rawat inap. Kata kunci : Gagal Ginjal Kronik, Hemodialisa, Lama Perawatan