Search

Abstract Background Imbalanced datasets pose significant challenges in predictive modeling, leading to biased outcomes and reduced model reliability. This study addresses data imbalance in diabetes prediction using machine learning techniques. Utilizing data from the Fasa Adult Cohort Study (FACS) with a 5-year follow-up of 10,000 participants, we developed predictive models for Type 2 diabetes. Methods We employed various data-level and algorithm-level interventions, including SMOTE, ADASYN, SMOTEENN, Random Over Sampling and KMeansSMOTE, paired with Random Forest, Gradient Boosting, Decision Tree and Multi-Layer Perceptron (MLP) classifier. We evaluated model performance using F1 score, AUC, and G-means—metrics chosen to provide a comprehensive assessment of model accuracy, discrimination ability, and overall balance in performance, particularly in the context of imbalanced datasets. Results our study uncovered key factors influencing diabetes risk and evaluated the performance of various machine learning models. Feature importance analysis revealed that the most influential predictors of diabetes differ between males and females. For females, the most important factors are triglyceride (TG), basal metabolic rate (BMR), and total cholesterol (CHOL), whereas for males, the key predictors are body Mass Index (BMI), serum glutamate Oxaloacetate Transaminase (SGOT), and Gamma-Glutamyl (GGT). Across the entire dataset, BMI remains the most important variable, followed by SGOT, BMR, and energy intake. These insights suggest that gender-specific risk profiles should be considered in diabetes prevention and management strategies. In terms of model performance, our results show that ADASYN with MLP classifier achieved an F1 score of 82.17 ± 3.38, AUC of 89.61 ± 2.09, and G-means of 89.15 ± 2.31. SMOTE with MLP followed closely with an F1 score of 79.85 ± 3.91, AUC of 89.7 ± 2.54, and G-means of 89.31 ± 2.78. The SMOTEENN with Random Forest combination achieved an F1 score of 78.27 ± 1.54, AUC of 87.18 ± 1.12, and G-means of 86.47 ± 1.28. Conclusion These combinations effectively address class imbalance, improving the accuracy and reliability of diabetes predictions. The findings highlight the importance of using appropriate data-balancing techniques in medical data analysis.

Objective: With the COVID-19 outbreak in countries around the world, the countries’ healthcare systemsunderwent an unprecedented shock. This study aimed to examine the resilience of the medical service deliverysystem in providing emergency services during the Covid-19 pandemic.Methods: This study was conducted in a reference hospital in Kerman that provided emergency services totrauma patients. It compared service delivery before and after COVID-19, as well as during the COVID-19 peakand non-peak periods. The compared variables were the number of trauma patients admitted to the hospital andthe ICU, the number of patients who died in the hospital due to trauma, and the length of stay in the hospitaland the ICU.Results: The pre- and post-COVID-19 comparisons showed no significant difference in the number of dailyhospital admissions, ICU admissions, and patient deaths. The median length of stay in the ICU was significantlyreduced by almost 2 days during the COVID-19 outbreak. However, the length of stay at the hospital was almostthe same. Furthermore, a comparison of the COVID-19 peaks and non-peak periods indicated no statisticallysignificant difference in the number of admissions in the ICU, hospital and ICU length of stay, and traumainduced mortality.Conclusion: Despite the substantial workload imposed by COVID-19 on hospitals, especially during the peakperiods of the disease, the provision of medical services to emergency trauma patients did not drop significantly,and the quality of services provided to patients was within the acceptable range.

Abstract Evidence shows a growing trend of the HIV epidemic in the Middle East and North Africa (MENA). We aimed to project the incidence, mortality, and disability-adjusted life years (DALY) in the region from 1990 to 2019 and assess its trend by 2025, and 2030. We extracted the HIV incidence, mortality, and DALY data from the Global Burden of Disease (GBD) and UNAIDS databases. The joinpoint regression model was used to examine changes in HIV trends. The trend changes were estimated by average annual percent change (AAPC). In most countries, an increasing trend was observed in HIV incidence, mortality, and DALY. Specifically, the highest growth in the annual incidence rate was related to Egypt (AAPC = 14.4, GBD) and Iran (AAPC = 9.6, UNAIDS). Notably, Qatar (AAPC = − 5.6, GBD), Bahrain (AAPC = − 3.3, GBD), and Somalia (AAPC = − 4.2, UNAIDS) demonstrated a significant reduction in incidence. Regarding mortality rates, Djibouti (AAPC = 24.2, GBD) and Iran (AAPC = 16.2, UNAIDS) exhibited a significant increasing pattern. Furthermore, the estimated increase in incidence by 2030 was most marked in Djibouti (985%) and Iran (174%). Iran (422%) and Egypt (339%) showed a prominent rise in mortality rates. GBD data showed 16 countries had an increasing pattern in DALY in both genders. According to age and period effects, there was a significant upward trend in incidence, mortality rates, and DALY. Findings highlighted the urgent need for improved prevention and treatment services, including expanding access to HIV testing, promoting safe practices, increasing antiretroviral therapy coverage, and supporting targeted interventions for high-risk populations.

Abstract Background Parents play a critical role in caring for their children with diabetes and bear a significant burden of care. Health education has increasingly focused on empowering parents through new strategic methods. The present study aims to investigate the impact of a family-centered empowerment model on the burden of care in parents and blood glucose levels of children with type I diabetes. Methods An interventional study was conducted in Kerman, Iran, where 100 children with type I diabetes and their parents were randomly selected as participants. The study aimed to implement a family-centered empowerment model in the intervention group, which consisted of four stages (educational phase, increasing self-efficacy, improving self-confidence, and evaluation) over a period of one month. The control group received routine training. The Zarit Caregiver Burden questionnaire and HbA1c log sheet were utilized to evaluate the effectiveness of the intervention. Questionnaires were administered before, after, and two months post-intervention, and data were analyzed using SPSS 15. Non-parametric tests were employed, and statistical significance was set at p

Background: Patients’ quality of life is affected by chronic diseases, including kidney failure. Hemodialysis and peritoneal dialysis are an important renal replacement methods in these patients.Objectives: In this study, the quality of life in Iranian hemodialysis and peritoneal dialysis patients was compared.Methods: This cross-sectional study was conducted between April and September 2021 on 84 hemodialysis and 31 peritoneal dialysis patients in a teaching hospital in Kerman, Iran. The data collection tool was the standard KDQOL-SF™ questionnaire. This questionnaire had 78 questions and measured the general and specific aspects of patients' quality of life. Data were compare between two groups by SPSS version 18 statistical software.Results: The mean age of peritoneal dialysis and hemodialysis patients was 52.1±18.8 and 56.8±15.6 years, respectively. 54.8% of peritoneal dialysis patients and 61.9% of hemodialysis patients were men. In most dimensions, the score of quality of life of patients treated with peritoneal dialysis was better than other group. The most difference in specific dimensions of quality of life was related to the effect of kidney disease in peritoneal patients (69.97±24.46) and hemodialysis patients (54.46±23.55) (P≤0.05). The most difference in general dimensions of quality of life was related to pain in peritoneal patients (59.52±23.55) and hemodialysis patients (43.46±28.58) (P≤0.05).Conclusion: Considering the better quality of life in peritoneal patients, it is recommended that physicians and nurses encourage patients to use peritoneal dialysis methods.

Abstract Background: Chronic pruritus is one of the most common skin manifestations in patients with End-Stage Renal Disease (ESRD).Omega-3 fatty acids could be used as an efficient drug for treatment of pruritus in uremic patients. Chia seed oil is one of the richest plant sources of omega-3. Aim: This study aimed to compare the effect of topical chia oil and coconut oil on pruritus and laboratory parameters in ESRD patients. Method: This semi-experimental study with control group was performed on 105 hemodialysis patients in Kerman, Iran in 2021. The participants were randomly assigned into two intervention groups (chia oil and coconut oil) and one control group. The chia and coconut oils were applied topically twice a day for two weeks. Pruritus was measured before, at the end, and two weeks after the intervention. Some laboratory parameters were measured before and at the end of the intervention. Data collection tool was Yosipovitch pruritus questionnaire. P0.05). Implications for Practice: Chia and coconut oil were effective on reducing pruritus in ESRD patients. Chia oil and coconut oil are cost-effective without any major complications that canbe used to reduce pruritus.

Background: Electronic health (e-health) technologies play an important role in improving public knowledge and behavior to control the COVID-19 pandemic. The present study aimed to investigate the role of e-health on the public knowledge and behavior in preventing COVID-19 in Kerman, a city in Iran. Methods: The present descriptive cross-sectional study used an online survey in Kerman in November 2021. The research instrument was a tripartite questionnaire that included demographic information, the level of respondents' knowledge about COVID-19, the extent of change in respondents’ behavior influenced by e-health. Negative binomial regression analysis was run to test the relationship between individual characteristics and the research variables with knowledge and behavior. Spearman correlation test was used to measure the correlation between the two main parts of the survey. Results: As the negative binomial regression analysis results showed, the relationship between no demographic variable and the public knowledge and behavior was statistically significant (p

Introduction: Lung cancer (LC) is the most common type of cancer and causes of death among males. This study aims to estimate the survival rate of lung cancer patients by employing the benefits of Bayesian modeling in determining factors affecting the survival of lung cancer in Kerman province, Iran. Methods: We conducted a historical cohort study of 195 patients with lung cancer from 2016 to 2018. In this study, we used linear dependent Dirichlet process (LDDP), and employed some results of the previous study as informative prior for better estimation. Results: Of the 195 patients, 160 died. The mean age of patients at the time of diagnosis was 62.43±12.55. The median survival time of patients was 10.4 months. Men accounted for 75.9% of the total patients. One, two, and three-year survival rate was 44.5%, 22.9%, and 16.4%, respectively. The multivariable model results showed that treatments were significant. Other variables had no significant effect. Conclusion: Our study highlights the importance of prompt diagnosis and appropriate treatment in improving the survival rate of lung cancer patients. We found that patients who received at least one usual lung cancer treatment, such as chemotherapy, radiation therapy, or surgery, had higher survival rates compared to those who did not receive any treatment. While our study has some limitations, such as its retrospective design, our use of Bayesian modeling techniques allowed us to effectively incorporate prior information from previous studies to improve estimation accuracy

Abstract Background Many adulthood illnesses are rooted in childhood, especially in the “first thousand days of life”. Despite parents’ role in children’s development, no study has examined parental awareness concerning this period. This study aimed to examine the awareness of parents concerning the “first thousand days of life” and the relationship between parents’ demographics and their awareness. Methods This study was conducted on 135 parents in Kerman, Iran, using a valid and reliable questionnaire developed by researchers based on the opinion of experts and relevant references. The relationship between participants’ demographics and their awareness was examined by multiple regression. The relationship between homogeneity of couples’ education degree and awareness was analyzed using ANOVA. Chi-square was used to examine the relationship between information sources and parents’ familiarity and to compare parents’ preferred sources. Results The average parental awareness was 41.96 ± 11.90. Eighty-three percent of the parents have not heard about the “first thousand days of life”. The source of information for 57% of the parents was friends and relatives (p

Background: Identification of human errors and their related factors in nurses dealing with the health of humans is important. Considering that much workload can increase the risk of human error, this study aimed to investigate the relationship between workload and human errors among nurses working in educational hospitals of Kerman University of Medical Sciences. Methods: This descriptive-analytical study was performed on 145 nurses from educational hospitals affiliated to Kerman University of Medical Sciences in 20. The workload was evaluated using the NASA-TLX questionnaire and human errors with SHERPA technique. The statistical test used was logistic regression model and the statistical significance level was considered

Background & aim: Adverse childbirth experiences can lead to the emergence of mental disorders, such as acute stress disorder (ASD), in mothers in the postpartum period. Birth trauma can occur following aggressive procedures such as emergency cesarean section. This study aimed to determine the effect of supportive counseling intervention on the symptoms of ASD in women after emergency cesarean delivery. Methods: This randomized clinical trial was conducted on 126 women with traumatic emergency cesarean section at Payambar-E Azam and Afzalipoor hospitals in Kerman, Iran. The participants were selected based on DSM-IV criteria. The subjects were randomly divided into the intervention and control groups. The intervention group received individual and face-to-face supportive counseling. The data collection tool was the Acute Stress Disorder Questionnaire, which was completed one and three weeks post-intervention. The data were analyzed using descriptive and inferential statistics by SPSS, version 13. Results: The two groups were comparable in terms of demographic characteristics, pregnancy complications, and midwifery history. Also, there was no significant difference between two groups regarding the depression and anxiety mean scores at the pre-intervention stage. The results revealed a statistically significant difference between the control and intervention groups in terms of all acute stress disorder symptoms after one and three weeks of the intervention (P

The aim of the present study was to compare the effects of topical anesthesia and acupressure at the Yintang (Extra 1) and the Laogong (P-8) points on the severity of venipuncture pain among hospitalized 6–12-year-old children. A sample (n = 120) of 6–12-year-old hospitalized children was recruited from two teaching hospitals located in Rafsanjan, Iran. The children were allocated to the topical anesthesia, acupressure, and control groups. For children in the topical anesthesia and the acupressure groups, eutectic mixture of local anesthetic (EMLA) cream and two-point acupressure were used, respectively, prior to performing venipuncture, whereas children in the control group only received routine prevenipuncture care. The severity of venipuncture pain was evaluated 5 minutes after performing venipuncture by using the Face, Leg, Activity, Cry, and Consolability behavioral pain assessment scale. The findings revealed that pain severity in both experimental groups was significantly lower than that in the control group, whereas there was no significant difference between the experimental groups regarding pain severity. Although acupressure was as effective as topical anesthesia cream in alleviating children's venipuncture pain, nurses are recommending to use acupressure instead of pharmacological pain management agents because of its greater safety, cost-effectiveness, and applicability.

Headache is one of the most common public health problems in the world, which causes patients to see a doctor. Migraine is the second most common cause of headaches after tension headaches. This study is a randomized, double blinded, placebo - controlled clinical trial, using SF36 questionnaire, to evaluate the effect of combination of Viola odorata L., Rosa damascena Mill. and Coriandrum sativum L. on the quality of life, in patients with migraine after 4 weeks. In all domains of the SF36 questionnaire, the scores after intervention in the drug group were significantly higher than the control group after 4 weeks. This study showed that, combination of V. odorata, R. damascena and C. sativum, improves the quality of life of patients with migraine.

Introduction: Resuscitation self-efficacy is defined as a judgment of perceived capability to organize and execute the process of care during cardiopulmonary resuscitation. It is believed to be an important factor in teaching vital nursing skills especially cardiopulmonary resuscitation. Therefore, this study aimed to investigate the impact of mannequin-based simulation and computer-based simulation on nursing students’ perception of self-efficacy in cardiopulmonary resuscitation. Methods: This quasi-experimental study was performed on 64 nursing students who were randomly assigned to computer-based simulation and mannequin-based simulation groups. Data collection tool was a two-part questionnaire including demographic information and the perceived self-efficacy of cardiopulmonary resuscitation. The data were collected before and after two methods of teaching. Data were analyzed using measures of central tendency and dispersion, Mann-Whitney, and Wilcoxon tests. Results: There was a significant difference in mean score and standard deviation of students’ perception of self-efficacy between mannequin-based group (Z=-5.23,P