Showing 104 results for Hi
E Abdalmaleki, Zh Abdi, M Gohrimehr, R Alvandi, S Riazi Isfahani , E Ahmadnezhad ,
Volume 16, Issue 2 (8-2020)
Abstract
Background and Objectives: One of the data sources for monitoring the progress towards Sustainable Development Goals and Universal Health Coverage (UHC) is household surveys such as Multiple Indicator Cluster Survey (MICS) and Demographic and health Survey (DHS). This study was conducted to assess the implementation of these surveys in the Eastern Mediterranean Region (EMR) to evaluate the experience of Iran in conducting these surveys and to propose one of them as the best option for implementation in Iran.
Methods: In this review article, by reviewing the databases of the relevant organizations, the implementation history, instructions, protocols, and the generated indicators of these two surveys were assessed.
Results: So far, 26 standard DHS and 56 standard MICS have been implemented in the EMR. Iraq implemented the highest number of MICS and Egypt carried out the highest number of DHS. In the global reports, no DHS/MICS surveys were conducted in Iran after 2000 However, according to the official reports, Iran conducted two rounds of a survey called MIDHS (a combination of DHS and MICS) in 2010 and 2015.
Conclusion: The EMR has performed well in implementing these surveys. According to the findings, DHS is more suitable for Iran. However, right now, what is important is not to decide which survey to be conducted. Considering the international commitments for monitoring the progress towards UHC, it is important to conduct either one in 2020 in Iran.
M Ostadghaderi, Aa Hanafi Bojd , Sh Nematollahi, K Holakoui-Naeini ,
Volume 17, Issue 1 (5-2021)
Abstract
Background and Objectives: The incidence of colorectal cancer has increased significantly in Iran in recent decades. The pattern of occurrence varies in different populations. A study was conducted to perform a spatial analysis of colorectal cancer and some of its risk factors in Iran using GIS.
Methods: The data of this descriptive-analytic study included colorectal cancer incidence as a dependent variable and physical activity, Body Mass Index and smoking as independent variables recorded by the Cancer Department, Center for Non-Communicable Diseases Management, the Ministry of Health and Medical Education and the care system for non-communicable disease risk factors according to province and gender in 2009. Data was analyzed using the ArcGIS 10.3 software and spatial correlation analysis, hot spots analysis, and geographic weighted regression model.
Results: The spatial relationship between the disease and some of its risk factors was confirmed by the model of geographical weight regression, according to which the northern and central provinces had the highest risk of colorectal cancer compared to other regions of the country.
Conclusion: The results of this study showed that spatial analysis could be useful in identifying disease patterns, prioritizing the factors affecting it, and controlling the disease through strategic planning and interventions.
A Darvishi, S Emamgholipour Sefiddashti , M Rajabi, Mh Mehrolhassani, V Yazdi Feyzabadi,
Volume 17, Issue 1 (5-2021)
Abstract
Background and Objectives: Fair financial protection against health expenditures is one of the most critical goals of health systems. This study was conducted to investigate the most appropriate threshold for measuring the exposure to catastrophic health expenditure (CHE) in Iran.
Methods: The present study was conducted using 2018 national household income and expenditure data of the Iran statistics center. The occurrence and intensity of the households' exposure to CHE at different thresholds and for economic quintiles was measured using two World Health Organization (WHO) and World Bank (WB) methodologies. The most appropriate threshold for each methodology was also determined using the Kappa statistics adaptation estimation.
Results: The occurrence of households’ exposure to CHE was 3.02% and 8.51% in urban households and 4.66% and 9.22% in rural households, respectively. According to asset quintiles, the highest occurrence was in the first quintile and the lowest in the fifth quintile. In addition, the results of adaptation estimation based on Kappa statistics showed that a threshold of 40% in the WHO methodology and 25% in the WB methodology were the most appropriate thresholds.
Conclusion: The results showed a relatively high rate of exposure to CHE. CHE occurrence was also more in poorer households, and common thresholds were the most appropriate thresholds for estimating CHE.
M Sabaghchi, A Askari Nodoushan, M Torkashvand,
Volume 17, Issue 1 (5-2021)
Abstract
Background and Objectives: Human resources, especially youth work force, are considered as the main capital for every society. Maintaining the quantity and quality of human resources is essential for every policymaking. The present study was conducted to estimate the Years of Life Lost (YLL) due to early death amongst the working age population (i.e. 15-64 years) of two provinces with very different levels of socio-economic development in Iran. For this purpose, premature mortality was compared between Yazd and Sistan & Baluchistan provinces in 2016.
Methods: This cross-sectional study used secondary data. The target statistical population of the study was all deaths registered in the age groups 15 to 64 years in the provinces of Yazd and Sistan & Baluchistan during March 2016 to March 2017. The mentioned provinces reflect completely different and unequal development at the national level: Yazd is amongst one of the highly developed regions of Iran, while Sistan & Baluchistan is as one of underdeveloped provinces. The data were obtained from health departments of Yazd and Sistan & Baluchistan provinces’ medical universities. The YLL was calculated according to the standard procedure provided by the World Health Organization.
Results: Our findings showed that the lost human capital due to early death was about two times higher in Sistan & Baluchistan compared to Yazd. The main causes of death were unintentional injuries in the younger working age group (15-44 years) and cardiovascular disease and cancers in the older working age group (45-64 years).
Conclusion: Causes of death were different in Yazd and Sistan & Baluchistan provinces according to the regional level of development. Therefore, health policies have to be implemented as regional policies. In general, the results showed that as the epidemiologic transition passes, the cause of death changes from causes that are less related to medical conditions and more related to social situations. Consequently, it is required to consider social policymaking when designing health policies.
Mh Rabiee, H Akbarin, S Bokaie, Mh Fallah Mehrabadi , A Sadrzadeh, F Tehrani,
Volume 17, Issue 1 (5-2021)
Abstract
Background and Objectives: The commercial layer chicken farming is one of the most important sectors of the poultry industry. This study was conducted to evaluate the status of biosecurity of commercial layer chicken farms in 9 Iranian provinces with the highest layer chicken population.
Methods: In this cross-sectional study, 202 commercial layer chicken farms were selected from nine Iranian provinces in 2019 using stratified random sampling. Then, the required data were collected using a questionnaire by presenting to the farms in person. The results are expressed as mean, standard variation, sum and adoption rate index.
Results: The results showed that the adoption level of total biosecurity measures was 68.18% in the commercial layer chicken farms in Iran. This figure was 72.11%, 75% and 60.82% for conceptual, structural and operational biosecurity measures, respectively. Among conceptual biosecurity measures, the lowest adoption level (29.20%) was for distance to the nearest garden and agriculture land. Among structural biosecurity measures, the lowest adoption level (28.96%) was for a hand disinfection spot before shed. Among the operational biosecurity measures, the lowest adoption level was for water filtrations (31.18%) and microbial testing of water (33.91%).
Conclusion: This study investigated the biosecurity status of commercial layer chicken farms in nine Iranian provinces with the highest layer chicken population and revealed some weaknesses in the implementation of these measures at conceptual, structural and operational levels.
Mohsen Mahdinia, Seyyed Hassan Adeli, Hamidreza Heidari, Abolfazl Mohammadbeigi, Mohammadreza Khaksar, Ahmad Soltanzadeh,
Volume 17, Issue 2 (9-2021)
Abstract
Background and Objectives: Pulmonary consequences of exposure to low concentrations of ammonia have been less studied. The purpose of this study was to model the pulmonary consequences of exposure to low concentrations of ammonia.
Methods: This historical cohort study was conducted in the fertilizer industries in 2019. The participants were divided into two groups of exposed (n=98) and non-exposed (n=105). The exposure level, pulmonary symptoms, and pulmonary function parameters were assessed using the NMAM 6016 and American Thoracic Society and European Respiratory society (ATS&ERS) protocols. Data analysis was performed using the IBM SPSS v. 22.0, and multivariate linear and logistic regression models.
Results: The ammonia exposure level was 4.80±1.54 ppm in the exposed group. There was no significant difference in most of the individual variables between the two groups (P>0.05). The frequency of all pulmonary symptoms was significantly higher in the exposed group compared to the non-exposed group (P<0.05). The highest prevalence of pulmonary symptoms in the exposed group was for cough (25.51%), wheezing (19.39%) and shortness of breath (18.37%). All lung function parameters were significantly lower in the exposed group versus the non-exposed group (P<0.05). The values of lung function parameters in the exposed group including FVC, FEV1 and FEV1 / FVC were 86.0%, 82.47% and 81.97%, respectively. Regression modeling results showed that ammonia exposure had a significant relationship with all pulmonary symptoms and lung function parameters (P<0.05).
Conclusion: The findings indicated that exposure to low concentrations of ammonia should be considered as a major risk factor in the prevalence of pulmonary symptoms and reduced lung function parameters.
A Hosseinzadeh, Mr Baneshi, B Sedighi, J Kermanchi, Aa Haghdoost,
Volume 18, Issue 1 (5-2022)
Abstract
Background and Objectives: Dementia is a chronic disease that imposes a huge financial and social burden on the health system. Knowledge of the prevalence of dementia is essential for healthcare planning and ensuring that there is an adequate service for people with the condition. Considering that the prevalence and geographical variation of dementia are not well known in Iran, the present study was conducted to investigate the prevalence of dementia and its geographic variations in Iran.
Methods: In this study, the prevalence of dementia was estimated indirectly using the frequency of prescribed specialized medicines in one year by generic and brand names in each province. Choropleth maps were used to visually assess the geographical variation of dementia prevalence at the provincial level. Moran I and Getis-Ord Gi (Gi) geographical tests were used to investigate the spatial autocorrelation and geographical variability of dementia prevalence at a significant level of 0.05, respectively.
Results: In this study, the prevalence of dementia was 49.6 and 508.9 in 100000 in the general and over 60-year population, respectively. In the general population, the lowest prevalence was in Hormozgan Province (9.4/100000) and the highest prevalence was in East Azarbayjan Province (96.4/100000). In the over 60-year population, the lowest prevalence was in Hormozgan Province (141.5/100000) and the highest in Isfahan Province (862.5/1000000). According to Moran I and Getis-Ord Gi (Gi) tests, spatial autocorrelation and geographical variability of dementia prevalence were not significant.
Conclusion: The prevalence of dementia in the Iranian over 60-year population is lower compared to western countries; however, it is comparable with the reported dementia prevalence from developing countries. It should be noted that the dementia prevalence is high, similar to developed countries, in some developed provinces of Iran.
E Amiri, Aa Rafieirad, N Rafieisadr, H Sharifi,
Volume 18, Issue 1 (5-2022)
Abstract
Background and Objectives: Although everyone needs to adopt a healthy lifestyle, it is absolutely important for people living with chronic diseases like HIV/AIDS to lead a positive lifestyle because these people are more vulnerable than others. Considering this fact, the present study was conducted to investigates the lifestyle of women living with HIV/AIDS in Kerman.
Methods:The Health-promoting Lifestyle Profile II (HPLP-II) was used in this survey, which includes six aspects as follows: responsibility, moral development, workout, nutrition, individual relations and stress management. Statistical population included 35 women living with HIV/AIDS in Kerman in 2019.
Results: According to the findings of this study, 34.14% of people who participated in this study had a positive lifestyle and the remaining 62.86% had a negative lifestyle. Based on the findings related to the women’s lifestyle, there was a significant difference in family income and job status. No significant difference was found in other variables such as marital status, age group, education and years living with HIV.
Conclusion: As economic variables (family income and job status) play an important role in adopting a positive lifestyle for people living with HIV/AIDS, it is necessary to help them become self-employed or support them financially so that they can lead a healthy lifestyle.
Nasrin Talkhi, Nooshin Akbari Sharak, Zahra Rajabzadeh, Maryam Salari, Seyed Masoud Sadati, Mohammad Taghi Shakeri,
Volume 18, Issue 3 (12-2022)
Abstract
Background and Objectives: Due to the high prevalence of COVID-19 disease and its high mortality rate, it is necessary to identify the symptoms, demographic information and underlying diseases that effectively predict COVID-19 death. Therefore, in this study, we aimed to predict the mortality behavior due to COVID-19 in Khorasan Razavi province.
Methods: This study collected data from 51, 460 patients admitted to the hospitals of Khorasan Razavi province from 25 March 2017 to 12 September 2014. Logistic regression and Neural network methods, including machine learning methods, were used to identify survivors and non-survivors caused by COVID-19.
Results: Decreased consciousness, cough, PO2 level less than 93%, age, cancer, chronic kidney diseases, fever, headache, smoking status, and chronic blood diseases are the most important predictors of death. The accuracy of the artificial neural network model was 89.90% in the test phase. Also, the sensitivity, specificity and area under the rock curve in this model are equal to 76.14%, 91.99% and 77.65%, respectively.
Conclusion: Our findings highlight the importance of some demographic information, underlying diseases, and clinical signs in predicting survivors and non-survivors of COVID-19. Also, the neural network model provided high accuracy in prediction. However, medical research in this field will lead to complementary results by using other methods of machine learning and their high power.
Mahbuobeh Hojati, Neda Yaqoubieh, Jalal Karimi, Mansour Firouzbakht, Omid Iravani,
Volume 18, Issue 3 (12-2022)
Abstract
Background and Objectives: childhood is the most dangerous period of the life of humans. So, investigating the causes of children's death and preventing them has an essential role in the health and productivity of the family and society. This study aims to investigate the epidemiological factors related to the mortality of under-five years in Isfahan province.
Methods: In this cross-sectional-analytical and retrospective study, the files of 194 children under five years (109 boys and 85 girls) who were referred to Isfahan Legal Medicine Center between 2017 and 2021; were investigated and the causes of death and their demographic and clinical characteristics were extracted. The obtained data were analyzed using the Chi square statistical test and Fisher’s exact test.
Results: In terms of the distribution, unnatural causes of death was, 30.4% died due to domestic incidents, 22.7% died due to chronic diseases, 21.1% died due to vehicle accidents, 17.5% died due to acute diseases, 2.1% Death due to asphyxia, 1.3% death due to sudden death syndrome and 1.3% death due to various causes. There is a statistically significant difference between the cause of death and age group, place of death, disease history and year of death (P<0.05), but there is no statistically significant difference between the cause of death and gender and nationality (P>0.05).
Conclusion: Considering the ability to take preventive measures against child deaths and its trend in the country, it is necessary to make future policies to promote legal investigations to ensure children's health and safety.
Layla Halimi, Eshagh Dortaj Rabari, Reza Majdzadeh, Aliakbar Haghdoost,
Volume 18, Issue 4 (3-2023)
Abstract
Background and Objectives: In adolescence, there is a heightened inclination to cultivate stronger social networks within schools, resulting in the exchange of information. This study investigates the influential factors that shape the exchange of information among students within their classrooms.
Methods: The study involved 350 male and female middle and high school students in Hamadan. Two types of networks were constructed within each class: the communication network, representing ordinary students’ interactions, and the specific network, which focused on the exchange of sensitive information about puberty. The network centrality index was calculated, and factors influencing information transfer were evaluated through a questionnaire.
Results: The degree of centrality in the social network of boys exceeded that of girls, with values of 55.4% versus 47.6% in the communication network, and 33.4% versus 20.1% in the specific network, respectively. The degree of centrality of students had significant positive association with the length of time that they spent with their friends. Moreover, we found the degree of centrality of students in both networks, particularly in special network, was stronger in high schools.
Conclusion: During adolescence, boys tend to possess a broader communication network within their classrooms, enabling them to effectively exchange information about puberty. Factors such as effective communication skills, knowledge about puberty, and spending time with their classmates play crucial roles in facilitating the exchange of information among adolescents in schools.
Yaser Mesri, Mina Pakkhesal, Aliakbar Naghavialhosseini, Fatemeh Mirzaei, Abdolhalim Rajabi,
Volume 18, Issue 4 (3-2023)
Abstract
Background and Objectives: Considering the impact of the COVID-19 pandemic on health and the significance of oral health, this study aims to investigate the effects of the COVID-19 pandemic on dental care utilization among children.
Methods: This retrospective study utilized available data from the archives of the dental clinic at Gorgan Pediatric Hospital in 2022. Information regarding demographic characteristics and the types of received services were collected and entered to SPSS version 26 statistical analysis software. The chi-square test was used to compare the annual differences in the frequency of different service types, and the Cochrane-Armitage test was employed to examine the linear trend of changes in each service.
Results: A total of 24,185 different dental services were received by children aged between 2 and 14 years old referred to dental clinic of Taleghani Children Hospital from March 2020 to February 2022. Comparing the frequency of dental services in 2021 to that of 2020 revealed a 31% decrease in the total number of services. The types of services utilized during the first year of the pandemic exhibited significant changes compared to the pre-pandemic year. This included an increase in tooth extraction (P = 0.001) and a reduction in restorations (P = 0.000). Additionally, a noticeable increase in pulp treatment (P = 0.003) was observed, particularly in the second year of the pandemic.
Conclusion: The frequency of dental care utilization, types of services received, and insurance utilization underwent significant changes during the pandemic. It is crucial to plan for future required treatments and establish infrastructures to address similar pandemics.
Nafiseh Salehnia, Abbas Assari Arani, Hossein Sadeghi Saghdel, Alireza Olyaeemanesh,
Volume 18, Issue 4 (3-2023)
Abstract
Background and Objectives: Health promotion is a crucial task for policymakers. Therefore, this study aims to identify the key factors that determine population health in Iran and illustrate the causal relationships between these factors.
Methods: The research was conducted using a mixed-method approach in three stages. First, macro social determinants of health were identified by analyzing available resources from 2000 to 2019. Screening of factors was carried out through the fuzzy Delphi method and a survey involving 15 experts. Finally, the causal relationships between the social determinants of health were depicted using a fuzzy cognitive map.
Results: Initially, 96 health determinants were identified at the national and global levels. After the screening, 8 factors that had less significance in population health were excluded. In terms of causal relationships, the economic system emerged as the most important and influential factor, with a centrality degree of 21.06 and an out-degree of 10.91. Following that, governance and policy-making, as well as national policies, were ranked with centrality degrees of 20.25 and 20.19, respectively.
Conclusion: Irrespective of the causal relationships, the health system holds the utmost importance in population health. However, when considering the causal relationships, the economic system takes precedence as the most critical factor, while the health system does not rank among the top three factors. Therefore, the analysis of fuzzy cognitive maps assists policymakers in understanding priorities and the interconnectedness between sectors in developing and implementing health-oriented policies across all sectors, enabling the adoption of the most effective policies.
Tina Fallah, Ameneh Elikaei, Roxana Mansour Ghanaie, Abdollah Karimi, Iraj Sedighi, Marjan Tariverdi, Arezu Amirali, Tayebe Nazari, Negin Nahanmoghadam, Alireza Nateghian, Seyed Hamidreza Monavari, Seyed Mohsen Zahraei, Sussan Mahmoudi, Masoud Alebouyeh,
Volume 19, Issue 1 (6-2023)
Abstract
Background and Objectives: Identification of rotavirus genotypes in children is clinically important. This study aimed to determine the spectrum of rotavirus genotypes and assess their correlation with demographic variables and clinical manifestations in hospitalized children.
Methods: To determine rotavirus genotypes, rotavirus positive stool samples of symptomatic children were included in the study between December 2019 and March 2020. RNA extraction and cDNA synthesis for VP7 and VP4 genes were performed following standard protocols. Genotypes were determined using specific primers. Validation of results was done through sequencing and bioinformatic analysis. Data were statistically analyzed using SPSS version 20 and GraphPad version 9.5.0.
Results: Among the infected patients, three genotypes emerged as dominant in the studied population. The study demonstrated a significant correlation between genotype frequency and seasonal variations (p-value=0.0077), as well as between genotypes, hospitalization, and severity of diarrhea. While significantly more types of rotavirus group A were identified with increasing age, no correlation was observed between the genotypes and gender (p-value=0.473). Furthermore, there was no significant association between genotype, dehydration rates, and the presence or absence of fever.
Conclusion: This study revealed a relatively high diversity of rotavirus genotypes in children. The findings suggest the need for further research to validate the identified correlations between certain genotypes and age groups, seasonal variations, clinical symptoms, and the efficacy of available vaccines.
Maryam Ghahramany, Nooshin Peyman, Monavar Afzalaghaee,
Volume 19, Issue 2 (9-2023)
Abstract
Background and Objectives: In recent years, there have been significant demographic changes. One of the most important changes has been the decrease in the fertility rate in many countries, including Iran. In recent decades, considering the vital role of men in having children, the question is whether domestic research on the issue of men's attitude towards having children has enough maturity. Moreover, what are the gaps in the research process of this issue in the country?
Methods: The present study used Iranian research articles published in domestic and foreign journals. To obtain relevant articles from domestic Iran databases (magiran, SID) and international databases (Web of Science, Scopus PubMed,) as well as the Google Scholar search engine was used from the beginning until May 2022 with the keywords: attitude, motivation, intention, childbearing, childbirth, fertility, reproduction.
Results: 18 articles related to the purpose of the research were included in the study. The pattern of two children was the dominant pattern of childbearing among men. A large proportion of men had a positive attitude towards childbearing. Among the variables related to men's attitude towards childbearing were education, socio-economic class, a feeling of loneliness, place of residence, and the amount of internet usage.
Conclusion: It is necessary to increase encouragement policies, raise awareness about the importance of having children, provide proper occupations for men, suitable housing, and implement comprehensive educational programs to strengthen men's optimistic view of having children.
Faezeh Joghataei, Payam Roshanfekr, Meroe Vameghi, Zahra Jorjoran Shushtari, Neda Soleimanvandiazar, Peimaneh Shirin Bayan, Gholamreza Ghaedamini Harouni,
Volume 19, Issue 4 (3-2024)
Abstract
Background and Objectives: Rapid Assessment and Response (RAR) is an approach that has been used in health research since the 1990s, and several guidelines have been designed for it. This study examines and compares different guidelines in this field.
Methods: This review study was conducted on the 6 guidelines published in PubMed and Scopus databases. After the initial review, the main dimensions of these guidelines, including the definition and target group, methods used, steps to conduct the research, and time planning were extracted in the form of a comparative table.
Results: In six guidelines, the RAR approach has been defined in relation to the comprehensive and rapid investigation of a health-related problem. There are differences in terms of the number of 'steps' of rapid assessment and response, as well as in 'time planning'; a period of 12 to 16 weeks is considered. Among the methods used in the reviewed guides, the following can be mentioned: reviewing available information, conducting interviews (open, structured, and semi-structured), focused group discussions, and other methods such as observation, surveys, narrative methods, and mapping.
Conclusion: The rapid assessment and response (RAR) can be used as an approach, with high flexibility and consideration of scientific and practical aspects, to assess health problems and high-risk behaviors in hard-to-reach groups.
Elahe Faghihifar, Marjan Ajami, Sareh Shakerian,
Volume 19, Issue 4 (3-2024)
Abstract
Background and Objectives: Childhood obesity has become a global challenge today. Many studies have shown the relationship between obesity and socioeconomic factors. Therefore, this study aimed to evaluate socio-economic inequalities with nutritional patterns and obesity in children.
Methods: This study was conducted using the structural analysis methodology on 80 children from 6 to 13 years old, selected randomly from those referred to the health assessment centers of Sonqor and Kolyai, Iran. The body mass index was calculated using the standard method. Nutritional patterns were measured using the 24-hour food recall questionnaire, and socioeconomic status was assessed using related standard questionnaires. The data were analyzed using SPSS 24 and AMOS 24 software.
Results: The results showed that 28.75% of the subjects were obese or overweight. The structural analysis showed that the socioeconomic variable directly affected the nutritional pattern and body mass (-0.43) with an impact coefficient of as much as 0.65. The nutritional pattern variable affected BMI with an impact factor (-0.74). The bootstrap test results indicated that the significant effect of socio-economic status on BMI is mediated by nutritional pattern (-0.48). Prediction values show two economic-social and nutritional pattern variables predicted 0.16 and 0.29 BMI changes, respectively.
Conclusion: The findings of this study showed the effect of socioeconomic status on nutritional patterns and body mass index in the research community. Today, The issue of increasing body mass in the world and our country is one of the most important social challenges. Considering the heterogeneous effects of socioeconomic status on nutritional patterns and body mass index, it is necessary to formulate and implement preventive policies according to the conditions of the communities to achieve effective results.
Ramin Farrokhi, Samaneh Hosseinzadeh, Abbas Habibelahi, Akbar Biglarian,
Volume 20, Issue 1 (6-2024)
Abstract
Background and Objectives: Identifying pregnant women who are at risk of premature birth and determining its risk factors is essential because it affects their health. This study aimed to use an interpretable machine-learning model to predict premature birth.
Methods: In this study, data from 149,350 births in Tehran in 2019 were utilized from the Iranian Mothers and Babies Network (IMaN) dataset. Various factors related to the mother and the fetus, such as the mother's demographic variables and health status, medical history, pregnancy conditions, childbirth, and associated risks, were considered. The machine learning models, including multilayer neural networks, random forest, and XGBoost, were employed to predict the occurrence of preterm birth after data preprocessing. The models were evaluated based on accuracy, sensitivity, specificity, and area under the ROC curve. The Python programming language version 3.10.0 was applied to analyze the data.
Results: About 8.67% of births were premature. The XGBoost algorithm achieved the highest prediction accuracy (90%). According to the model output, multiple births, which account for 46% of pregnant women's births, had the highest importance score. Delivery risk factors had a score of 41%, and other variables, including neurological and mental illness, preeclampsia, and cardiovascular disease, were subsequently ranked in order of importance for this particular individual.
Conclusion: Using an interpretable machine learning method could predict the occurrence of premature birth. Based on risk factors, the interpretable machine learning method can provide personalized preventive recommendations for every pregnant woman, aiming to reduce the risk of preterm birth.
Monireh Rahimkhani, Maryam Gilani,
Volume 20, Issue 1 (6-2024)
Abstract
Antibiotic resistance has increased significantly in recent years. On the other hand, machine learning (ML) algorithms are increasingly used in medical research and healthcare and are gradually improving clinical performance.
Using ML to fight antimicrobial resistance (AMR) is one of the most critical areas of interest among the various applications of these new methods. The rise of antibiotic resistance and managing multidrug-resistant infections that are difficult to treat are important challenges.
Both supervised and unsupervised machine learning tools have been successfully used to predict early antibiotic resistance and thus support clinicians in selecting the appropriate treatment. Machine learning and artificial intelligence (AI) in predicting antimicrobial resistance are among today's sciences. Therefore, an antimicrobial stewardship program (ASP) should be implemented to optimize antibiotic prescribing and limit AMR.
Zahra Gaeini, Sevda Alvirdizadeh, Parvin Mirmiran, Fereidoun Azizi,
Volume 20, Issue 2 (9-2024)
Abstract
Background and Objectives: The association between the consumption of dairy products and the risk of cardiovascular disease (CVD) is not well-known yet. Here, we aimed to determine the potential effects of total intake and subtypes of dairy products on the development of CVD in an Iranian adult population.
Methods: Among adult participants of the third phase of the Tehran Lipid and Glucose Study (TLGS), after excluding those with incomplete dietary, biochemical and anthropometric data, and those who had CVD events at baseline, 2635 adults were selected and followed up till the sixth phase of the TLGS. Baseline dietary intakes were evaluated using a validated food frequency questionnaire with 168 items. There was no significant difference between the baseline characteristics of participants who did not complete the FFQ and those of the total population in the third phase of the TLGS. Finally, the risk of CVD events after adjusting for potential confounding variables was evaluated across the tertile categories of dairy products using the Cox proportional hazard regression models.
Results: During a 10.6-year follow-up, the incidence rate of CVD was 6.5%. After adjusting for confounding factors, there was no significant association between CVD risk and total dairy, low-fat and high-fat dairy, fermented and non-fermented dairy products, high- and low-fat milk, high- and low-fat yogurt, cheese, and cream cheese, as well as ice cream.
Conclusion: According to numerous evidence in previous studies that revealed there is no association between the consumption of dairy products, and CVD risk, independent of high-fat or low-fat dairy products. Hence, it is vital to reconsider dietary recommendations on lowering the intake of high-fat dairy products for the prevention of CVD.
