Publication Search

Independent Nursing Practice (INP) is a form of healthcare service that provides direct care to the community, including Homecare services. Public interest in these services is influenced by various factors; however, the dominant factors affecting interest in the Tambah Rejo area have not been clearly identified. This study aimed to identify and analyze factors associated with interest in Homecare services at independent nursing practices and to determine the most influential factor. This study employed a quantitative approach using an analytical survey design with a cross-sectional method. A total of 153 respondents were selected through purposive sampling. Data were collected using questionnaires and analyzed using the Chi-square test and multiple logistic regression. The results showed significant relationships between economic factors (p = 0.023; OR = 2.187), distance (p = 0.003; OR = 0.361), comfort (p < 0.001; OR = 49.67), service quality (p = 0.009; OR = 0.404), family support (p < 0.001; OR = 52.62), patient satisfaction (p < 0.001; OR = 0.212), and interest in Homecare services. Multiple logistic regression analysis revealed that comfort was the most dominant factor influencing interest in Homecare services (p < 0.001; OR = 0.124). Comfort was identified as the strongest determinant affecting community interest in Homecare services at independent nursing practices. Therefore, improving comfort in service delivery should be a primary priority in the development of independent nursing practices.

Independent Nursing Practice (INP) is a form of healthcare service that provides direct care to the community, including Homecare services. Public interest in these services is influenced by various factors; however, the dominant factors affecting interest in the Tambah Rejo area have not been clearly identified. This study aimed to identify and analyze factors associated with interest in Homecare services at independent nursing practices and to determine the most influential factor. This study employed a quantitative approach using an analytical survey design with a cross-sectional method. A total of 153 respondents were selected through purposive sampling. Data were collected using questionnaires and analyzed using the Chi-square test and multiple logistic regression. The results showed significant relationships between economic factors (p = 0.023; OR = 2.187), distance (p = 0.003; OR = 0.361), comfort (p < 0.001; OR = 49.67), service quality (p = 0.009; OR = 0.404), family support (p < 0.001; OR = 52.62), patient satisfaction (p < 0.001; OR = 0.212), and interest in Homecare services. Multiple logistic regression analysis revealed that comfort was the most dominant factor influencing interest in Homecare services (p < 0.001; OR = 0.124). Comfort was identified as the strongest determinant affecting community interest in Homecare services at independent nursing practices. Therefore, improving comfort in service delivery should be a primary priority in the development of independent nursing practices.

Diabetes Mellitus is a non-communicable disease with an increasing prevalence and has become a major public health concern globally and nationally. The incidence of diabetes mellitus is influenced by various individual and environmental factors. This study aimed to analyze the relationship between age, gender, and residential proximity to landfill areas and the incidence of diabetes mellitus in Bendosari District. A quantitative analytic observational design with a cross-sectional approach was employed. The study population consisted of 1,890 patient visit records recorded in the Management Information System of Bendosari Public Health Center in 2025. A total of 363 respondents were selected using proportionate stratified random sampling. Data were analyzed through univariate analysis, bivariate analysis using the Chi-Square test, and multivariate analysis using multiple logistic regression. The findings showed that age was significantly associated with diabetes mellitus incidence (p=0.000; OR=79.790; 95% CI=53.511–118.974). Gender was also significantly related to diabetes mellitus incidence (p=0.000; OR=0.298; 95% CI=0.203–0.435), indicating that females had a higher risk than males. In contrast, residential proximity to landfill areas was not significantly associated with diabetes mellitus incidence (p=0.308; OR=1.247; 95% CI=0.439–3.540). Multivariate analysis revealed that age and gender were the dominant factors influencing diabetes mellitus incidence, with the model explaining 56.1% of the variation. The study concludes that age and gender are significant determinants of diabetes mellitus incidence, whereas residential proximity to landfill areas has not been proven to significantly affect its occurrence.

Patient satisfaction represents the comparison between expectations before receiving health services and perceptions of the quality of services provided. The assessment of healthcare service quality generally uses the five SERVQUAL dimensions, namely tangibles, reliability, responsiveness, assurance, and empathy. A preliminary survey showed that the reliability dimension obtained the lowest average score compared to other dimensions. This study employed an observational analytic design with a cross-sectional approach. The study population consisted of BPJS (National Health Insurance) patients who received services. A total of 386 respondents were selected using purposive sampling. Data were collected through a SERVQUAL-based questionnaire and analyzed using univariate, bivariate (chi-square test), and multivariate (logistic regression) analyses to identify the dominant factors related to patient satisfaction. The results indicated that the variables of age (p < 0.05) and all five SERVQUAL dimensions (tangible, reliability, responsiveness, assurance, and empathy) were significantly associated with patient satisfaction levels. It can be concluded that most BPJS patients were satisfied with the services provided. The assurance dimension was found to be the most influential factor. Therefore, efforts to improve service quality should focus on strengthening aspects of assurance, trust, and service reliability.

Transportation plays an important role in supporting community mobility and enhancing socio-economic activities in urban areas. The increasing population growth and community activities in Sorong City have led to a higher demand for transportation modes. This study aims to identify the characteristics of transportation users in Kota Sorong and to analyze the probability of selecting different transportation modes using the Multinomial Logit (MNL) method. A quantitative approach was employed in this research. Questionnaires were distributed to 225 transportation users in Sorong City. The variables analyzed included gender, age, occupation, income, trip purpose, travel frequency, and reasons for choosing a transportation mode. The data were analyzed using multinomial logistic regression with SPSS software. The results indicate that transportation mode choice is influenced not only by socio-economic factors, but also by showed that income, trip purpose, travel frequency, and reasons for choosing the mode significantly influenced transportation mode choice, while gender, age, and occupation did not have significant effects. The probability analysis indicated that private vehicles had the highest probability of selection at 89.63%, followed by online transportation at 9.96%, and conventional motorcycle taxis at 0.41%. These findings imply that socio-economic and travel behavior factors strongly influence transportation mode preferences in Sorong City and may serve as a reference for future urban transportation planning and policy development.

Artificial intelligence has the potential to support radiology workflows by assisting in the identification of cases that may require additional clinical attention. However, alert-oriented medical AI systems should provide not only classification outputs but also interpretable evidence that can be reviewed and audited by clinicians. This study develops and evaluates an explainable multimodal framework for binary chest X-ray alert classification using paired radiology reports and chest X-ray images. The text branch employs TF-IDF n-gram features with a class-balanced Logistic Regression classifier, while the image branch fine-tunes a pretrained ResNet18 model. The two branches are integrated through probability-level late fusion using a validation-selected fusion weight. Explainability is implemented in a modality-specific manner: global coefficient analysis is used to identify influential textual cues, while Grad-CAM heatmaps are used to visualize salient image regions. Experiments were conducted on paired samples from the Open-i/IU X-Ray dataset using text-only, image-only, and fusion-based evaluation settings. Additional analyses include case-level complementarity analysis, bootstrap confidence intervals for ROC-AUC, shortcut-feature inspection, and qualitative Grad-CAM auditing. The results indicate that the text modality provides the dominant predictive signal under the current proxy-label setting. Late fusion produced a small descriptive improvement on the test set, increasing accuracy from 0.8533 to 0.8667, F1-score from 0.8817 to 0.8936, and ROC-AUC from 0.8936 to 0.9025 compared with the text-only baseline. However, the observed ROC-AUC improvement was not statistically conclusive based on bootstrap analysis. These findings suggest that the proposed framework is useful as a reproducible and auditable multimodal prototype, while also highlighting important limitations, including proxy-label ambiguity, potential label leakage from radiology reports, limited image-branch contribution, lack of external validation, and the need for stronger explanation and calibration assessment.

Student dropout in higher education remains a persistent socioeconomic challenge, yet many predictive models reported in the literature are methodologically compromised by randomized cross-validation schemes that introduce temporal data leakage and artificially inflate predictive performance. This study proposes a longitudinal prescriptive learning analytics framework integrating three complementary methodological components: a Leave-One-Cohort-Out (LOCO) temporal validation protocol, a hybrid SMOTE-ENN class balancing strategy, and temporal velocity feature engineering derived from Learning Management System (LMS) behavioral trajectories. The framework was evaluated on a longitudinal dataset comprising 464,739 enrollment records and 77 features. Five predictive algorithms—XGBoost, LightGBM, CatBoost, Random Forest, and Logistic Regression—were comparatively assessed on a strictly isolated blind holdout cohort (2022), with CatBoost emerging as the champion estimator, achieving a PR-AUC of 0.8859, a Macro F1-Score of 0.9143, and the lowest Brier Score (0.0221), thereby demonstrating superior calibration and discriminative capability under severe class imbalance (93:7 ratio). Comprehensive ablation analysis revealed that temporal velocity features function not merely as additive predictors, but as a structural prerequisite enabling Synthetic Minority Oversampling Technique with Edited Nearest Neighbors (SMOTE-ENN) to generate high-quality synthetic boundary instances; removing these features reduced minority-class precision from 0.8302 to 0.6721. To operationalize predictive outputs into actionable intervention pathways, Diverse Counterfactual Explanations (DiCE) were implemented under a three-tier causal constraint architecture on 96 borderline high-risk students, generating 384 feasible intervention scenarios exclusively targeting forward-looking behavioral velocity metrics without constraint violations. Collectively, these findings advance the paradigm of prescriptive learning analytics by providing educational institutions with interpretable risk diagnostics and operationally feasible intervention guidance grounded in empirically validated behavioral and temporal dynamics.

Anxiety disorders are common mental health problems among adolescents, particularly high school students who face academic demands, social pressure, and emotional changes. Family support, sleep quality, and academic stress are considered factors related to students’ anxiety levels. This study aimed to examine the relationship between family support, sleep quality, academic stress, and anxiety disorders among students of SMAN 1 Sumbawa Besar. An analytical study with a cross-sectional design was conducted involving 114 students selected through stratified random sampling. Data were collected using the Perceived Social Support–Family (PSS-Fa), Pittsburgh Sleep Quality Index (PSQI), Educational Stress Scale for Adolescence (ESSA), and Depression Anxiety Stress Scale (DASS-42). Bivariate analysis was performed using the chi-square test, while multivariate analysis employed binary logistic regression. Bivariate results indicated significant associations between family support, sleep quality, academic stress, and anxiety disorders (p < 0.05). However, multivariate analysis revealed that only family support and sleep quality were significantly associated with anxiety disorders, while academic stress was not significant after controlling for other variables. These findings suggest that anxiety prevention efforts should prioritize strengthening family support and improving sleep quality, alongside academic stress management within the school environment.

This study aims to analyze the influence of workforce agility, job satisfaction, and job engagement on employee adaptive performance at PT. MMT Buana Logistik. The dynamic logistics industry requires employees who have high adaptability to technological changes and operational demands. This type of research is quantitative causality with an explanatory approach. The population in this study were all employees of PT. MMT Buana Logistik, totaling 49 people, with the sampling technique used saturated sampling (census). Data were collected through questionnaires with a 5-point Likert scale. Data analysis techniques used included instrument testing (validity and reliability), testing of classical assumptions (normality, multicollinearity, and heteroscedasticity), and multiple linear regression analysis. Hypothesis testing was carried out through t-tests (partial), F-tests (simultaneous) and coefficient of determination (R2). The results showed that workforce agility, job satisfaction, and job engagement partially and simultaneously have a positive and significant influence on employee adaptive performance. These findings imply the importance of managing work flexibility, fulfilling employee satisfaction, and increasing work engagement to build adaptive human resources to support company competitiveness in the logistics industry.  

This study examines customer churn prediction in subscription-based telecommunications from a digital marketing perspective using machine learning. The analysis utilizes a secondary dataset of 7,043 customer records that simulate behavioral, contractual, and financial attributes commonly found in telecom services. Three classification algorithms Logistic Regression, Random Forest, and Gradient Boosting are applied to model churn behavior. Data preprocessing includes handling missing values, encoding categorical variables, and splitting data into training and testing sets. Model performance is evaluated using accuracy, recall, and ROC-AUC, with emphasis on recall due to its importance in identifying at-risk customers. The results show that Gradient Boosting achieves the highest overall performance with an ROC-AUC of 0.84, while Logistic Regression provides relatively higher recall. Key drivers of churn include short-term contracts, higher monthly charges, and lower service engagement. However, recall remains moderate, indicating limitations in capturing complex behavioral factors. These findings suggest the need to combine predictive models with behavioral insights and highlight the importance of early customer engagement and long-term retention strategies.

The dimensions of healthcare service quality are a concept for measuring service quality. This study aims to determine the effect of the dimensions of healthcare service quality on the satisfaction of inpatients at Cut Nyak Dhien General Hospital in Langsa City. This study uses a quantitative design of the Survey Analytic type with a cross-sectional approach. The population consisted of 121 inpatients with a sample size of 55 respondents using purposive sampling technique. Analysis used multiple logistic regression test (α=0.05). The research results show that there is an influence between Responsiveness p<0.042 with an EXP (B) value of 11.361, Assurance p<0.008 with an EXP (B) value of 20.163, Empathy p<0.018 with an EXP (B) value of 13.547, Reliability p<0.033 with an EXP (B) value of 6.896 on inpatient patient satisfaction (p<0.05), while the Tangible variable shows no influence with p<0.088 and an EXP (B) value of 4.967. Among these variables, the one that significantly affects inpatient patient satisfaction is the Assurance variable with p<0.008 and an EXP (B) value of 20.163. It is recommended to continuously improve the quality of service comprehensively in every dimension of service quality, strengthen the competence and professionalism of healthcare personnel, enhance the speed and accuracy of service, and build good communication to improve the quality of inpatient services and maintain patient trust in the hospital.  

The agricultural sector plays a strategic role in meeting food needs while maintaining environmental sustainability and community welfare. However, conventional farming practices that rely on chemical inputs have caused various problems, such as soil degradation, loss of biodiversity, and environmental pollution. This condition has encouraged the adoption of the Sustainable Agriculture concept, which emphasizes a balance between ecological, economic, and social aspects. Its successful implementation is strongly influenced by farmers’ perceptions as the main actors. This study aims to analyze rice farmers’ perceptions of the implementation of Sustainable Agriculture in swampy areas of Tebas District, Sambas Regency. The research was conducted from October to November 2025 using a survey method involving 95 farmers selected through the Slovin formula and proportional random sampling technique. Data were collected through observation, interviews, and Likert-scale questionnaires, and analyzed using descriptive analysis and binary logistic regression. The results show that farmers’ perceptions are generally positive, particularly regarding water management, variety selection, and cropping patterns. However, the use of organic fertilizers, environmentally friendly pest control, and post-harvest management are still considered difficult. Education level and non-farming occupations significantly influence farmers’ perceptions. Therefore, enhancing extension services, training, and support for business diversification is necessary to promote the adoption of Sustainable Agriculture.

This research benchmarks multiple machine learning (ML) algorithms for large-scale loan default prediction using a real-world dataset of 255,000 borrower records, where default cases represent only ~9–12% of total observations. The study addresses the persistent gap in comparative analyses of ML models that balance predictive accuracy, interpretability, and computational efficiency for credit risk assessment. Six algorithmic families were evaluated Logistic Regression, Random Forest, XGBoost, LightGBM, CatBoost, Artificial Neural Networks (ANN), and Stacked Ensemble—using standardized preprocessing, hybrid imbalance handling (SMOTE, class weighting, under-sampling), and comprehensive evaluation metrics (AUC, F1, Recall, Precision, PR-AUC, and Brier Score). Empirical results show Logistic Regression achieved the highest AUC of 0.732, outperforming nonlinear models under the baseline configuration, while LightGBM attained perfect recall (1.0) but low precision (0.116), indicating over-prediction of defaults. Gradient boosting models demonstrated robust calibration (Brier ≈ 0.114–0.116) and the best computational efficiency, with LightGBM showing the fastest training and lowest memory use. CatBoost exhibited strong recall but the slowest computation, and ANN underperformed on tabular data (AUC ≈ 0.56). The Stacked Ensemble delivered balanced results with AUC = 0.664 and improved overall stability. These findings confirm that boosting-based models, particularly LightGBM and CatBoost, offer superior scalability and calibration, whereas Logistic Regression remains a valuable interpretable baseline. The study concludes that effective default prediction requires integrating rebalancing, calibration, and threshold optimization to enhance recall and operational deployment reliability in large-scale credit ecosystems.

Indonesia ranks second in the world and Bandar Lampung City is the region with the highest TB incidence in Lampung Province with a treatment success rate that is still below the national target. This study aims to analyze the risk factors associated with the incidence of pulmonary TB in the Kedaton Community Health Center Working Area of ​​Bandar Lampung City using a quantitative analytical study with a case-control design. The study sample consisted of 40 cases (smear-positive pulmonary TB patients) and 40 controls (closest neighbors without TB) taken using a consecutive sampling technique, where data were collected through interviews, observations, and measurements using questionnaires and physical measuring instruments at home. The results of the bivariate analysis showed that employment status (p = 0.024) and bedroom ventilation (p = 0.040) had a significant relationship with the incidence of pulmonary TB, while the results of the multivariate analysis using multiple logistic regression showed that gender (p = 0.015) and bedroom ventilation (p = 0.009) were significantly related variables. The conclusion of this study determined that bedroom ventilation was the most dominant variable associated with pulmonary TB incidence, with inadequate ventilation having a 3.91-fold increased risk (OR=3.91; 95%CI=1.41-10.94) compared to adequate ventilation after controlling for gender.

This study comprehensively analyzes the impact of sectarian conflict on mental health in Kirkuk through an ethnoreligious meta-analysis of 42 studies with a total of N=15,427 participants published between 2003 and 2023. The quantitative synthesis indicates a PTSD prevalence of 47.3% (95% CI: 44.2–50.4) among victims of sectarian conflict, with an uneven distribution across groups, where the Turkmen minority records the highest prevalence at 56.8%, exceeding Arab Sunni at 43.2% and Kurdish at 41.5%. Logistic regression analysis demonstrates that direct exposure to sectarian violence increases the risk of major depression by 3.4 times (OR=3.42, p<.001), anxiety by 2.8 times (OR=2.83, p<.001), and psychosomatic disorders by 2.5 times (OR=2.54, p<.001). Further meta-regression identifies duration of conflict exposure (β=.426, p<.001) and intensity of sectarian violence (β=.389, p<.001) as significant predictors of symptom severity. In contrast to the findings of Cummings et al. (2013) and Eltally (2019), which emphasize the general impact of conflict, this study reveals specific intergenerational trauma patterns within distinct ethnoreligious communities, with the highest transmission observed among families of sectarian massacre victims (d=0.82), while simultaneously highlighting variations in communal resilience across groups as a differential determinant of post-conflict psychosocial dynamics.

The auditor's responsibilities include not only assessing the accuracy of financial statements and detecting fraud, but also evaluating the company's ability to continue its business on an ongoing basis. This responsibility arises from the expectations of shareholders and other stakeholders that auditors provide timely and relevant information about the company's future prospects to support rational and evidence-based investment decision-making. In this context, audit opinions related to business continuity are an important instrument in reducing information asymmetry between management and investors. This study aims to analyze the impact of liquidity, solvency, and audit quality on the issuance of business continuity declarations. The research sample consisted of coal mining companies listed on the Indonesia Stock Exchange between 2014 and 2017, a period marked by fluctuations in commodity prices and global economic uncertainty. Logistic regression is used as an analysis method because dependent variables are dichotomous. The results showed that audit quality had a significant negative impact on the issuance of business continuity declarations, while liquidity and solvency did not have a significant impact on the issuance of the declarations, indicating that the factors of governance and auditor independence were more decisive than short-term financial conditions.

As HIV transitions into a manageable chronic condition, optimizing lifestyle behaviors is key to achieving long-term health outcomes. This study aims to explore lifestyle behaviors in people with HIV (ODHIV) who participate in peer support groups as well as identify socioeconomic and clinical predictors of healthy lifestyle engagement. The research design was a cross-cutting analysis involving 250 ODHIV registered in a community support group. Lifestyle behavior was measured using  a modified Health-Promoting Lifestyle Profile II (HPLP-II) instrument. Multivariate logistic regression analysis was used to determine independent predictors, with Nagelkerke R² and Hosmer–Lemeshow tests  to assess model suitability. The results showed that 56.2% of respondents had a healthy lifestyle. Factors of higher education (OR = 2.77; p = 0.006), older age (OR = 2.32; p = 0.015), employment status (OR = 2.00; p = 0.029), and longer duration of ART therapy (OR = 1.17 per year; p = 0.003) were significant predictors. The model explains 32% of lifestyle variations, with ART compliance and substance control as the strongest behavioral domains. These findings confirm the role of peer support groups as a behavioural reinforcement environment, but socioeconomic disparities remain influential. The integration of theory-based lifestyle interventions into community-based HIV services is necessary to optimize chronic disease outcomes.

Health workers contribute up to 80% to the success of health development. For this reason, effective employee performance management is needed according to service performance for communicable and non-communicable diseases. The aim of this research is to analyze the factors that influence the performance of nurses in health services for non-communicable diseases and infectious diseases at the UPT Puskesmas Kuala, Kuala District, Langkat Regency.The research design used was an analytical survey with a cross sectional approach. The population of this study were all 31 nurses with a sample using a total sampling technique of 31 people. The data analysis used is the binary logistic regression test.The research results show that ability has a sig-p value of 0.025, attitude sig-p 0.014, learning sig-p 0.036, motivation sig-p 0.022, leadership sig-p 0.031 and work environment sig-p 0.048, which means it has an influence on nurse performance , while age sig-p 1.000 and perception sig-p 0.496 have no influence on nurse performance. Attitude is the dominant factor with an OR value of 28.446. In conclusion, ability, attitude, learning, motivation, leadership, and work environment influence nurse performance, while age and perception have no effect. Attitude is the most dominant factor influencing nurse performance.

PT Pos Indonesia (Persero), as a long-established Indonesian state-owned enterprise, faces increasing competitive pressure in the logistics industry due to the rapid growth of e-commerce and the emergence of digital-based private courier services. This study focuses on the Pati Branch Post Office, which has experienced rising delivery demand while continuing to encounter challenges related to service quality, promotional effectiveness, and customer price perceptions—factors that potentially influence customer satisfaction. The study aims to analyze the partial and simultaneous effects of service quality, promotion, and pricing on customer satisfaction at the Pati Branch Post Office. A quantitative research approach was employed using survey data collected through questionnaires distributed to customers. The data were analyzed using multiple linear regression to examine the relationships among variables. The results indicate that service quality is the most dominant factor influencing customer satisfaction. Promotion and pricing also have a statistically significant effect, although their influence is relatively weaker compared to service quality. These findings highlight the importance for PT Pos Indonesia to prioritize improvements in service reliability, responsiveness, and assurance to enhance the overall customer experience. In addition, strengthening digital-based promotional strategies and implementing value-based pricing are shown to positively shape customer perceptions. Overall, this study concludes that improving customer satisfaction at the Pati Branch Post Office is primarily driven by service quality enhancement, supported by effective promotion and appropriate pricing strategies aligned with customer value expectations.

Urban mobility in Surabaya faces serious challenges due to the high ownership of private vehicles and the low use of public transportation. The Surabaya City Government launched Suroboyo Bus Electric in November 2024 as a sustainable transportation innovation on the Purabaya–ITS route. This study aims to analyze commuter preferences for the Suroboyo Bus Electric mode over private vehicles, by emphasizing functional factors (cost, travel time, comfort) and symbolic factors (status, identity, modern image). The research method used a quantitative descriptive approach with 400 respondents, primary data was obtained through questionnaires, while secondary data came from government documents and literature. The analysis was carried out through descriptive statistics, chi-square tests, and logistic regression. The results showed that the majority of respondents chose Suroboyo Bus Electric as the main mode (62%), with the dominance of young, middle-income users, and mostly women. Most of the respondents have one unit of private vehicle, but still use electric buses as a mode of complementing mobility. Travel destinations are dominated by social, economic, and educational activities, with an average travel time of 16–30 minutes. In terms of cost, more than half of the respondents spent Rp 5,000-Rp 10,000 per trip, indicating the affordability of fares. Symbolic factors also play an important role, where Suroboyo Bus Electric is perceived as a modern, clean, and sustainable city identity.