Barriers to financial access of disabled people to health services in rural areas: A case study of Iran.

BACKGROUND: People with disabilities (PWDs) account for a significant percentage of the world's population, with a higher prevalence in less developed countries. Access to healthcare services is the main component of health systems performance, with lower access for PWDs living in rural areas. The current study aimed to investigate PWD's access to healthcare services in rural areas of Iran and, secondly, factors that contribute to this issue. MATERIALS AND METHODS: Following a cross-sectional design, the current descriptive-analytical study is performed in the north of Iran. Using the quota sampling technique, 471 PWDs were recruited. Data were collected using a valid and reliable questionnaire, covering three dimensions of access, by face-to-face interview. Data analysis was administered using central tendency indicators and multiple regression by SPSS version 17. Statistical significance was considered when the P value <0.05. RESULTS: The mean score of PWD's access to healthcare services for dimensions of utilization, availability, and affordability was 8.91 (±6.86), 14.54 (±2.3), and 51.91 (±8.78), indicating very low, low, and moderate levels of access. All three regression models were significant (P < 0.05), and variables of gender, age, marital status, education level, residence status, the income of the household head, receiving financial aid, and house area showed a significant effect (P < 0.05). CONCLUSION: This study demonstrated the seriousness of paying attention to PWD's financial access to healthcare services, particularly in rural areas of Iran. Hence, policymakers should better focus on this problem, mainly regarding accessibility and utilization and factors that result in inequalities.

Prediction of hypercholesterolemia using machine learning techniques.

Purpose: Hypercholesterolemia is a major risk factor for a wide range of cardiovascular diseases. Developing countries are more susceptible to hypercholesterolemia and its complications due to the increasing prevalence and the lack of adequate resources for conducting screening and/or prevention programs. Using machine learning techniques to identify factors contributing to hypercholesterolemia and developing predictive models can help early detection of hypercholesterolemia, especially in developing countries. Methods: Data from the nationwide 2016 STEPs study in Iran were used to identify socioeconomic, lifestyle, and metabolic risk factors associated with hypercholesterolemia. Furthermore, the predictive power of the identified risk factors was assessed using five commonly used machine learning algorithms (random forest; gradient boosting; support vector machine; logistic regression; artificial neural network) and 10-fold cross validation in terms of specificity, sensitivity, and the area under the receiver operating characteristic curve. Results: A total of 14,667 individuals were included in this study, of those 12.8% (n = 1879) had (undiagnosed) hypercholesterolemia. Based on multivariate logistic regression analysis the five most important risk factors for hypercholesterolemia were: older age (for the elderly group: OR = 2.243; for the middle-aged group: OR = 1.869), obesity-related factors including high BMI status (morbidly obese: OR = 1.884; obese: OR = 1.499; overweight: OR = 1.426) and AO (OR = 1.339), raised BP (hypertension: OR = 1.729; prehypertension: OR = 1.577), consuming fish once or twice per week (OR = 1.261), and having risky diet (OR = 1.163). Furthermore, all the five hypercholesterolemia prediction models achieved AUC around 0.62, and models based on random forest (AUC = 0.6282; specificity = 65.14%; sensitivity = 60.51%) and gradient boosting (AUC = 0.6263; specificity = 64.11%; sensitivity = 61.15%) had the optimal performance. Conclusion: The study shows that socioeconomic inequalities, unhealthy lifestyle, and metabolic syndrome (including obesity and hypertension) are significant predictors of hypercholesterolemia. Therefore controlling these factors is necessary to reduce the burden of hypercholesterolemia. Furthermore, machine learning algorithms such as random forest and gradient boosting can be employed for hypercholesterolemia screening and its timely diagnosis. Applying deep learning algorithms as well as techniques for handling the class overlap problem seems necessary to improve the performance of the models.

Hyperglycemia screening based on survey data: an international instrument based on WHO STEPs dataset.

BACKGROUND: Hyperglycemia is rising globally and its associated complications impose heavy health and economic burden on the countries. Developing effective survey-based screening tools for hyperglycemia using reliable surveillance data, such as the WHO STEPs surveys, would be of great importance in early detection and/or prevention of hyperglycemia, especially in low or middle-income regions. METHODS: In this study, data from the nationwide 2016 STEPs study in Iran were used to identify socioeconomic, lifestyle, and metabolic factors associated with hyperglycemia. Furthermore, the ability of five commonly used machine learning algorithms (random forest; gradient boosting; support vector machine; logistic regression; artificial neural network) in the prediction of hyperglycemia on STEPs dataset were compared via tenfold cross validation in terms of specificity, sensitivity, and the area under the receiver operating characteristic curve. RESULTS: A total of 17,705 individuals were included in this study, of those 29.624% (n = 5245) had (undiagnosed) hyperglycemia. Multivariate logistic regression analysis showed that older age (for the elderly group: OR = 5.096; for the middle-aged group: OR = 2.784), high BMI status (morbidly obese: OR = 3.465; obese: OR = 1.992), having hypertension (OR = 1.647), consuming fish more than twice per week (OR = 1.496), and abdominal obesity (OR = 1.464) were the five most important risk factors for hyperglycemia. Furthermore, all the five hyperglycemia prediction models achieved AUC around 0.70, and logistic regression (specificity = 70.22%; sensitivity = 70.2%) and random forest (specificity = 70.75%; sensitivity = 69.78%) had the optimal performance. CONCLUSIONS: This study shows that it is possible to develop survey-based screening tools for early detection of hyperglycemia using data from nationwide surveys, such as WHO STEPs surveys, and machine learning techniques, such as random forest and logistic regression, without using blood tests. Such screening tools can potentially improve hyperglycemia control, especially in low or middle-income countries.

Successful implementation of general health policies in the Islamic Republic of Iran: barriers and mechanisms.

BACKGROUND: The general health policies for the Islamic Republic of Iran were approved in April 2014. AIMS: This study examined the barriers currently faced by general health policies and the mechanisms required for the successful implementation of these polices. METHODS: This qualitative study was conducted as a two-phase project based on standard CAN-IMPLEMENT guidelines. A set of qualitative methods, including face-to-face in-depth interviews, focus groups, and in-person consensus meetings, were used to clarify mechanisms and barriers. RESULTS: Twenty-one mechanisms and 13 barriers were identified. The majority of mechanisms were related to the development of health infrastructures and appropriate allocation of resources. The most significant barriers to implementation of general health policies were lack of formulated strategies, poor management, lack of a comprehensive national action plan, minimal information infrastructures, and inadequate funding. CONCLUSIONS: A thorough understanding of barriers and mechanisms for implementation of general health policies can provide the necessary background to ensure successful health promotion in the country.

Measuring Efficiency of Knowledge Production in Health Research Centers Using Data Envelopment Analysis (DEA): A Case Study in Iran.

INTRODUCTION: Efficiency analysis is necessary in order to avoid waste of materials, energy, effort, money, and time during scientific research. Therefore, analyzing efficiency of knowledge production in health areas is necessary, especially for developing and in-transition countries. As the first step in this field, the aim of this study was the analysis of selected health research center efficiency using data envelopment analysis (DEA). METHODS: This retrospective and applied study was conducted in 2015 using input and output data of 16 health research centers affiliated with a health sciences university in Iran during 2010-2014. The technical efficiency of health research centers was evaluated based on three basic data envelopment analysis (DEA) models: input-oriented, output-oriented, and hyperbolic-oriented. The input and output data of each health research center for years 2010-2014 were collected from the Iran Ministry of Health and Medical Education (MOHE) profile and analyzed by R software. RESULTS: The mean efficiency score in input-oriented, output-oriented, and hyperbolic-oriented models was 0.781, 0.671, and 0.798, respectively. Based on results of the study, half of the health research centers are operating below full efficiency, and about one-third of them are operating under the average efficiency level. There is also a large gap between health research center efficiency relative to each other. CONCLUSION: It is necessary for health research centers to improve their efficiency in knowledge production through better management of available resources. The higher level of efficiency in a significant number of health research centers is achievable through more efficient management of human resources and capital. Further research is needed to measure and follow the efficiency of knowledge production by health research centers around the world and over a period of time.