Predicting survival of Iranian COVID-19 patients infected by various variants including omicron from CT Scan images and clinical data using deep neural networks.

Purpose: The rapid spread of the COVID-19 omicron variant virus has resulted in an overload of hospitals around the globe. As a result, many patients are deprived of hospital facilities, increasing mortality rates. Therefore, mortality rates can be reduced by efficiently assigning facilities to higher-risk patients. Therefore, it is crucial to estimate patients' survival probability based on their conditions at the time of admission so that the minimum required facilities can be provided, allowing more opportunities to be available for those who need them. Although radiologic findings in chest computerized tomography scans show various patterns, considering the individual risk factors and other underlying diseases, it is difficult to predict patient prognosis through routine clinical or statistical analysis. Method: In this study, a deep neural network model is proposed for predicting survival based on simple clinical features, blood tests, axial computerized tomography scan images of lungs, and the patients' planned treatment. The model's architecture combines a Convolutional Neural Network and a Long Short Term Memory network. The model was trained using 390 survivors and 108 deceased patients from the Rasoul Akram Hospital and evaluated 109 surviving and 36 deceased patients infected by the omicron variant. Results: The proposed model reached an accuracy of 87.5% on the test data, indicating survival prediction possibility. The accuracy was significantly higher than the accuracy achieved by classical machine learning methods without considering computerized tomography scan images (p-value <= 4E-5). The images were also replaced with hand-crafted features related to the ratio of infected lung lobes used in classical machine-learning models. The highest-performing model reached an accuracy of 84.5%, which was considerably higher than the models trained on mere clinical information (p-value <= 0.006). However, the performance was still significantly less than the deep model (p-value <= 0.016). Conclusion: The proposed deep model achieved a higher accuracy than classical machine learning methods trained on features other than computerized tomography scan images. This proves the images contain extra information. Meanwhile, Artificial Intelligence methods with multimodal inputs can be more reliable and accurate than computerized tomography severity scores.

How Interoperability Challenges Are Addressed in Healthcare IoT Projects.

The rapid development and implementation of Internet of Medical Things has made interoperability a serious challenge. In this scoping review, we provide an overview of the interoperability challenge, as reported in the health literature, and highlight the proposed solutions. After searching between January 2018 and June 2023 in Compendex via Engineering Village and PubMed, we found 18 publications. The interoperability challenges identified were device heterogeneity, system heterogeneity, data standardization, security and safety, system and architecture standard, system and workflow integration and regulatory and compliance requirements. Solutions included ontology approaches, conceptual semantic frameworks, improved standards, design of middleware, and using blockchain technology.

The Internet of Medical Things: Opportunities, Benefits, Challenges and Concerns.

In this narrative review, we investigate the potential opportunities and benefits, as well as the challenges and concerns of integrating the Internet of Things in healthcare. The opportunities include enhanced patient monitoring and management, improved efficiency and resource utilization, personalized and precision medicine, empowering patients and promoting self-management, and data-driven decision-making, while the challenges include security and privacy risks, interoperability and integration, regulatory and compliance issues, ethical considerations and impact on healthcare professionals and patients. These challenges must be carefully weighed against the benefits before deployment of the IoMT-enabled services.

Clinical Decision Support Systems for Brain Tumour Diagnosis and Prognosis: A Systematic Review.

CDSSs are being continuously developed and integrated into routine clinical practice as they assist clinicians and radiologists in dealing with an enormous amount of medical data, reduce clinical errors, and improve diagnostic capabilities. They assist detection, classification, and grading of brain tumours as well as alert physicians of treatment change plans. The aim of this systematic review is to identify various CDSSs that are used in brain tumour diagnosis and prognosis and rely on data captured by any imaging modality. Based on the 2020 preferred reporting items for systematic reviews and meta-analyses (PRISMA) protocol, the literature search was conducted in PubMed and Engineering Village Compendex databases. Different types of CDSSs identified through this review include Curiam BT, FASMA, MIROR, HealthAgents, and INTERPRET, among others. This review also examines various CDSS tool types, system features, techniques, accuracy, and outcomes, to provide the latest evidence available in the field of neuro-oncology. An overview of such CDSSs used to support clinical decision-making in the management and treatment of brain tumours, along with their benefits, challenges, and future perspectives has been provided. Although a CDSS improves diagnostic capabilities and healthcare delivery, there is lack of specific evidence to support these claims. The absence of empirical data slows down both user acceptance and evaluation of the actual impact of CDSS on brain tumour management. Instead of emphasizing the advantages of implementing CDSS, it is important to address its potential drawbacks and ethical implications. By doing so, it can promote the responsible use of CDSS and facilitate its faster adoption in clinical settings.

Interoperable E-Health System Using Structural and Semantic Interoperability Approaches in CAREPATH.

Technical and semantic interoperability are broadly used components of interoperability technology in healthcare. Technical Interoperability provides interoperability interfaces to enable data exchange within different healthcare systems, despite any underlying heterogeneity. Semantic interoperability make different healthcare systems understand and interpret the meaning of the data that is exchanged, by using and mapping standardized terminologies, coding systems, and data models to describe the concept and structure of data. We propose a solution using Semantic and Structural Mapping techniques within CAREPATH; a research project designed to develop ICT solutions for the care management of elderly multimorbid patients with mild cognitive impairment or mild dementia. Our technical interoperability solution supplies a standard-based data exchange protocol to enable information exchange between local care systems and CAREPATH components. Our semantic interoperability solution supplies programmable interfaces, in order to semantically mediate different clinical data representation formats and incorporating data format and terminology mapping features. The solution offers a more reliable, flexible and resource efficient method across EHRs.

How Do Iranian Researchers Measure Spirituality in Health Studies? A Scoping Review.

Background: Despite the existing literature on the effect of spirituality on health, lack of consensus on definition and evaluation methods are major barriers to applying the results of these studies. In this scoping review, we intend to identify the instruments used for evaluating spirituality in health in Iran and evaluate their domains. Methods: We searched PubMed, Scopus and Web of Science, Islamic World Science Citation Center, Scientific Information Database, and Magiran between 1994 and 2020. We then identified the questionnaires and searched for the original article reporting the development or translation, as well as the psychometric evaluation process. We extracted data on their type (developed/translated), and other psychometric properties. Finally, we categorized the questionnaires accordingly. Results: After selecting the studies and evaluating the questionnaires, we identified 33 questionnaires evaluating religiosity (10 questionnaires), spiritual health (8 questionnaires), spirituality (5 questionnaires), religious attitude (4 questionnaires), spiritual need (3 questionnaires) and spiritual coping (3 questionnaires). Other existing questionnaires had issues in the development or translation process or lacked reported psychometric evaluations. Conclusion: Many questionnaires have been used in spiritual health studies in the Iranian population. These questionnaires cover different subscales according to their theoretical base and the developers' perspectives. Researchers should be informed about these aspects of the questionnaires and select the instruments meticulously based on the aim of their study and the characteristics of the questionnaires.

Improving data adequacy of ultrasonography reports for non-alcoholic fatty liver disease (NAFLD) through a national structured template.

BACKGROUND: Non-alcoholic fatty liver disease (NAFLD) is a prevalent disorder that increases due to lifestyle, the rising rate of obesity, and population ages worldwide. Diagnostic ways, including sonography, do not have an explicit reporting structure. PURPOSE: To create a structure template for NAFLD reporting, investigate its completeness, and assess the specialist opinions of using it in clinical practice. MATERIAL AND METHODS: A structured reporting template (SRT) was designed and implemented in four stages. At first, important features were extracted from a comprehensive literature review and were evaluated by 10 radiologists and gastroenterologists using the Likert scale. Finally, the usefulness of the SRT in comparison with the conventional reporting template (CRT) was judged by 10 gastroenterologists completing the questionnaire. RESULTS: Demographic information and sonography of the liver, gallbladder, and spleen organs were the most critical features. The completeness scores of SRT reports were higher than CRT scores for almost all the factors studied. The difference in the scores was significant for most of the parameters. Moreover, the total completeness score increased from 42% in CRT to 92% in SRT. A comparison of the report adequacy of two reports was seen in all items. The SRT obtained more rates from specialists. CONCLUSION: Introduction of the SRT for NAFLD significantly enhanced the completeness of reporting to reduce variability in the interpretation of the related reports by clinicians. Nevertheless, more studies are needed to generalize the results in real scales for patients with NAFLD.

Preliminary report of Iranian Registry of Alzheimer's disease in Tehran province: A cross-sectional study in Iran.

Background and Aims: Alzheimer's disease (AD) is the main cause of dementia and over the 55 million people live with dementia worldwide. We aimed to establish the first database called the Iranian Alzheimer's Disease Registry to create a powerful source for future research in the country. In this report, the design and early results of the Iranian Alzheimer's Disease Registry will be described. Methods: We performed this multicenter investigation and patients' data including age, sex, educational level, disease status, Mini-Mental State Examination (MMSE), and Geriatric Depression Scale (GDS) from 2018 to 2021 were collected, registered, and analyzed by GraphPad Prism software. Results: Totally 200 AD patients were registered in our database. 107 (54%) were women and age of 147 (74%) were over 65. The mean age for men and women was 76.20 ± 8.29 and 76.40 ± 8.83 years, respectively. 132 (66%) were married and 64 (32%) were illiterate. Also, 94 (47%) were in the moderate stage of disease, and 150 (75%) lived at home together with their families. The most frequent neurological comorbidity was psychosis (n = 72, 36%), while hypertension was the most common non-neurological comorbidity (n = 104, 52%). The GDS score of women in the mild stage (5.23 ± 2.9 vs. 6.9 ± 2.6, p = 0.005) and moderate stage (5.36 ± 2.4 vs. 8.21 ± 2.06, p = <0.001) of the disease was significantly greater than men. In univariate analysis, MMSC score was remarkably associated with stroke (ß = -2.25, p = 0.03), psychosis (ß = -2.18, p = 0.009), diabetes (ß = 3.6, p = <0.001), and hypercholesteremia (ß = 1.67, p = 0.05). Also, the MMSE score showed a notable relationship with stroke (ß = -2.13, p = 0.05) and diabetes (ß = 3.26, p = <0.001) in multivariate analysis. Conclusion: Iranian Alzheimer's Disease Registry can provide epidemiological and clinical data to use for purposes such as enhancing the current AD management in clinical centers, filling the gaps in preventative care, and establishing effective monitoring and cure for the disease.

CAREPATH: Developing Digital Integrated Care Solutions for Multimorbid Patients with Dementia.

CAREPATH project is focusing on providing an integrated solution for sustainable care for multimorbid elderly patients with dementia or mild cognitive impairment. The project has a digitally enhanced integrated patient-centered care approach clinical decision and associated intelligent tools with the aim to increase patients' independence, quality of life and intrinsic capacity. In this paper, the conceptual aspects of the CAREPATH project, in terms of technical and clinical requirements and considerations, are presented.

A multi-centre survey on hospital malnutrition: result of PNSI study.

BACKGROUND: Disease-related malnutrition is associated with adverse outcomes such as increased rates of morbidity and mortality, prolonged hospital stay, and extra costs of health care. This study was conducted to assess nutritional status among patients and to determine the risk factors for malnutrition in Iran university f. METHODS: Persian Nutritional Survey In Hospitals (PNSI) was a cross-sectional study that conducted in 20 university hospitals across Iran. All the patients with age range of 18 to 65 years, who were admitted or discharged, were assessed by subjective global assessment (SGA). RESULTS: In total, 2109 patients were evaluated for malnutrition. Mean values of age and body mass index were 44.68 ± 14.65 years and 25.44 ± 6.25 kg/m2, respectively. Malnutrition (SGA-B & C) was identified in 23.92% of the patients, 26.23 and 21% of whom were among the admitted and discharged patients, respectively. The highest prevalence of malnutrition was in burns (77.70%) and heart surgery (57.84%) patients. Multivariate analysis presented male gender (OR = 1.02, P < 0.00), malignant disease (OR = 1.40, P < 0.00), length of hospital stay (OR = 1.20, P < 0.00), and polypharmacy (OR = 1.06, P < 0.00) as independent risk factors for malnutrition. Malnutrition was not associated with age (P = 0.10). CONCLUSION: This study provides an overall and comprehensive illustration of hospital malnutrition in Iran university hospitals, finding that one out of four patients were malnourished; thus, appropriate consideration and measures should be taken to this issue.

Progress towards Every Newborn Action Plan (ENAP) implementation in Iran: obstacles and bottlenecks.

BACKGROUND: Neonatal mortality accounts for more than 47% of deaths among children under five globally but proper care at and around the time of birth could prevent about two-thirds of these deaths. The Every Newborn Action Plan (ENAP) offers a plan and vision to improve and achieve equitable and high-quality care for mothers and newborns. We applied the bottleneck analysis tool offered by ENAP to identify obstacles and bottlenecks hindering the scale-up of newborn care across seven health system building blocks. METHODS: We applied the every newborn bottleneck analysis tool to identify obstacles hindering the scale-up of newborn care across seven health system building blocks. We used qualitative methods to collect data from five medical universities and their corresponding hospitals in three provinces. We also interviewed other national experts, key informants, and stakeholders in neonatal care. In addition, we reviewed and qualitatively analyzed the performance report of neonatal care and services from 16 medical universities around the country. RESULTS: We identified many challenges and bottlenecks in the scale-up of newborn care in Iran. The major obstacles included but were not limited to the lack of a single leading and governing entity for newborn care, insufficient financial resources for neonatal care services, insufficient number of skilled health professionals, and inadequate patient transfer. CONCLUSIONS: To address identified bottlenecks in neonatal health care in Iran, some of our recommendations were as follows: establishing a single national authorizing and leading entity, allocating specific budget to newborn care, matching high-quality neonatal health care providers to the needs of all urban and rural areas, maintaining clear policies on the distribution of NICUs to minimize the need for patient transfer, and using the available and reliable private sector NICU ambulances for safe patient transfer.

Developing a Prognostic Model to Predict Mortality in Patients with Acute Bacterial Meningitis.

Bacterial meningitis is one of the harmful and deadly infectious diseases, and any delay in its treatment will lead to death. In this paper, a prognostic model was developed to predict the risk of death amongst probable cases of bacterial meningitis. Our prognostic model was developed using a decision tree algorithm on the national meningitis registry of the Iranian Center for Disease and Prevention (ICDCP) containing 3,923 records of meningitis suspected cases in 2018-2019. The most important features have been selected for the model construction. This model can predict the mortality risk for the meningitis probable cases with 78% accuracy, 84% sensitivity, and 73% specificity. The identified variables in prognosis the death included age and CSF protein level. CSF protein level (mg/dl) <= 65 versus > 65 provided the first branch of our decision tree. The highest mortality risk (85.8%) was seen in the patients >65 CSF protein level with 30 years < of age. For the patients <=30 year of age with CSF protein level >137 (mg/dl), the mortality risk was 60%. The prognostic factors identified in the present study draw the attention of clinicians to provide early specific measures, such as the admission of patients with a higher risk of death to intensive care units (ICU). It could also provide a helpful risk score tool in decision-making in the early phases of admission in pandemics, decrease mortality rate and improve public health operations efficiently in infectious diseases.

HIV prevalence among men who have sex with men in Iran: A systematic review and meta-analysis.

Background: The need for informed policymaking highlights the importance of data on human immunodeficiency virus (HIV) prevalence on key populations. In this systematic review and meta-analysis, we aimed to provide an overview of HIV prevalence in men who have sex with men (MSM) in Iran. Methods: We searched literature published between January 2008 and December 2019 to identify studies reporting the prevalence of HIV infection or acquired immunodeficiency syndrome (AIDS) in a population of adult Iranian men with history of sexual contact with other men. We employed Metaprop command in Stata to pool proportions from different studies. Results: Among the 16 studies retrieved, 2 were performed on MSM population directly, 7 among people who inject drugs, 4 among prisoners, 2 among the homeless, and 1 among methamphetamine users. HIV prevalence was 7% (95% CI, 5%-10%) based on the meta-analysis, although noticeable heterogeneity existed because of target population, study year, and study location, which imposed limitations to provide a robust summary measure for the prevalence of HIV. Conclusion: There is a potential risk of observing a high prevalence of HIV in MSM that could hamper the results of various preventive strategies and their achievements in other subpopulations.

Nutritional adequacy in critically ill patients: Result of PNSI study.

BACKGROUND & AIMS: Critically ill patients are provided with the intensive care medicine to prevent further complications, including malnutrition, disease progression, and even death. This study was intended to assess nutritional support and its' efficacy in the Intensive Care Units (ICUs) of Iran. METHODS: This cross-sectional study assessed 50 ICU's patients out of 25 hospitals in the 10 major regions of Iran's health system and was performed using the multistage cluster sampling design. The data were collected from patient's medical records, ICU nursing sheets, patients or their relatives from 2017 to 2018. Nutritional status was investigated by modified NUTRIC score and food frequency checklist. RESULTS: This study included 1321 ICU patients with the mean age of 54.8 ± 19.97 years, mean mNUTRIC score of 3.4 ± 2.14, and malnutrition rate of 32.6%. The mean time of first feeding was the second day and most of patients (66%) received nutrition support, mainly through enteral (57.2%) or oral (37%) route during ICU stay. The patients received 59.2 ± 37.78 percent of required calorie and 55.5 ± 30.04 percent of required protein. Adequate intake of energy and protein was provided for 16.2% and 10.7% of the patients, respectively. The result of regression analysis showed that the odds ratio of mNUTRIC score was 0.85 (95% confidence interval [CI] = 0.74-0.98) and APACHE II was 0.92 (95%CI = 0.89-0.95) for the prediction of energy deficiency. Nutrition intake was significantly different from patient's nutritional requirements both in terms of energy (p < 0.001) and protein (p < 0.001). Also, mean mNUTRIC score varied notably (p = 0.011) with changing in energy intake, defined as underfeeding, adequate feeding, and overfeeding. CONCLUSION: The present findings shown that, provided nutritional care for ICU patients is not adequate for their requirements and nutritional status.

Obstructive Sleep Apnea: A Prediction Model Using Supervised Machine Learning Method.

Obstructive Sleep Apnea (OSA) is the most common breathing-related sleep disorder, leading to increased risk of health problems. In this study, we investigated and evaluated the supervised machine learning methods to predict OSA. We used popular machine learning algorithms to develop the prediction models, using a dataset with non-invasive features containing 231 records. Based on the methodology, the CRISP-DM, the dataset was checked and the blanked data were replaced with average/most frequented items. Then, the popular machine learning algorithms were applied for modeling and the 10-fold cross-validation method was used for performance comparison purposes. The dataset has 231 records, of which 152 (65.8%) were diagnosed with OSA. The majority was male (143, 61.9%). The results showed that the best prediction model with an overall AUC reached the Naïve Bayes and Logistic Regression classifier with 0.768 and 0.761, respectively. The SVM with 93.42% sensitivity and the Naïve Bayes of 59.49% specificity can be suitable for screening high-risk people with OSA. The machine learning methods with easily available features had adequate power of discrimination, and physicians can screen high-risk OSA as a supplementary tool.

Nutritional status of patients hospitalized in the intensive care unit: A comprehensive report from Iranian hospitals, 2018.

INTRODUCTION AND AIM: Malnutrition is a complication of hospitalization in critically ill patients. This event is occurred because of disease and therapeutic processes for curing the patients. Determination of nutritional status helps physicians and clinical nutritionists decide on the best regimen which should be prescribed for a patient. In the current study, we aimed to report the nutritional status ofpatientshospitalizedin the intensive care unit (ICU). METHOD OF STUDY: We used three standard tolls, including Subjective global assessment (SGA), Nutrition Risk in the Critically Ill (NUTRIC) Score and nutrition risk screening (NRS) questionnaires via a multi-stage sampling for different ICU wards of 32 university hospitals in Iran. Frequencies and rates of nutritional scores, comparative studies, and determined agreement of scoring systems and nutritional status in any ward of hospitals were evaluated. RESULTS: There were 771 males and 540 female Cancer and trauma patients had the best and worst nutritional scores, respectively. Using NRS and NUTRIC, the low-risk scores were more frequent than thehigh-riskscores among ICU patients. SGA showed that most patients were in grades A (well nutritional status) or B (moderate nutritional status), andfew caseswere in grade C (poor nutritional status).The high-risk nutritional score wasobtained for older patients. NUTRIC and NRS had better agreement for diagnosis and differentiation of malnutrition than NUTRIC-SGA or NRS-SGA pairs. However, there was no strong agreement between the mentioned pairs. CONCLUSION: Nutritional status of patients hospitalized in ICU wards in Iran wassomewhat better than other countries that this could be due to the highly observed guidelines of patient's care in Iran. Anyway,it is suggested that a more precise tool of nutritional scoresto be validated for patients hospitalized in ICU·In addition, better medical care needs a well evaluation of nutritional insufficiencies and what is necessary for compensation using complementary regimens.

Reflection on Mobile Applications for Blood Pressure Management: A Systematic Review on Potential Effects and Initiatives.

INTRODUCTION: Ischemic heart disease and stroke have been considered as the first global leading cause of death in last decades [1]. Blood pressure (BP) management is one of the easiest ways suggested for preventing and controlling cardiovascular diseases before the patient develops complications and death-following outcomes. Appearance of technology advancements in the health system has motivated researchers and health providers to study its different aspects and applications in order to improve disease prevention and management. Following these efforts, mobile health (mHealth) technologies were presented to provide people with fast and easier-to-use services. Although there are some unsolved challenges, these technologies have become popular among many people. As an important part of mHealth, mobile applications (apps) have been the focused subject of many studies in the last decade. The objective of this systematic review is to assess the potential effects of mobile apps designed for BP management by scrutinizing the related studies. MATERIALS AND METHODS: Search methods: We searched the following electronic databases in December 2016: Medline (PubMed), National Center for Biotechnology Information (NCBI), Cochrane Central Register of Controlled Trials (CENTRAL), PsycINFO, Cumulative Index to Nursing and Allied Health Literature (CINAHL), Education Resources Information Center(ERIC), Web of Science, ProQuest, and Google Scholar. No language restriction and start point limitation were imposed. SELECTION CRITERIA: We included studies that evaluated and assessed mobile apps for BP management and related clinical trials that considered mobile app as the only difference between intervention and control groups. DATA COLLECTION AND ANALYSIS: Two review authors applied the eligibility criteria, extracted data and assessed the quality of included studies. RESULTS: Literature search resulted in 13 included studies and 27 reviews. 12 records of 13 included studies identified as interventional studies. The review showed that the mobile apps may improve individual's BP condition and medication adherence. CONCLUSION: Most of the studies had emphasized positive effects of mobile apps in BP management. However, there is a necessity for performing further investigations due to the identified issues in this study such as low number of participants and limited intervention period in randomized controlled trials, and interventions limited to only hypertensive or high-risked individual.

Decision tree-based modelling for identification of potential interactions between type 2 diabetes risk factors: a decade follow-up in a Middle East prospective cohort study.

OBJECTIVE: The current study was undertaken for use of the decision tree (DT) method for development of different prediction models for incidence of type 2 diabetes (T2D) and for exploring interactions between predictor variables in those models. DESIGN: Prospective cohort study. SETTING: Tehran Lipid and Glucose Study (TLGS). METHODS: A total of 6647 participants (43.4% men) aged >20 years, without T2D at baselines ((1999-2001) and (2002-2005)), were followed until 2012. 2 series of models (with and without 2-hour postchallenge plasma glucose (2h-PCPG)) were developed using 3 types of DT algorithms. The performances of the models were assessed using sensitivity, specificity, area under the ROC curve (AUC), geometric mean (G-Mean) and F-Measure. PRIMARY OUTCOME MEASURE: T2D was primary outcome which defined if fasting plasma glucose (FPG) was ≥7 mmol/L or if the 2h-PCPG was ≥11.1 mmol/L or if the participant was taking antidiabetic medication. RESULTS: During a median follow-up of 9.5 years, 729 new cases of T2D were identified. The Quick Unbiased Efficient Statistical Tree (QUEST) algorithm had the highest sensitivity and G-Mean among all the models for men and women. The models that included 2h-PCPG had sensitivity and G-Mean of (78% and 0.75%) and (78% and 0.78%) for men and women, respectively. Both models achieved good discrimination power with AUC above 0.78. FPG, 2h-PCPG, waist-to-height ratio (WHtR) and mean arterial blood pressure (MAP) were the most important factors to incidence of T2D in both genders. Among men, those with an FPG≤4.9 mmol/L and 2h-PCPG≤7.7 mmol/L had the lowest risk, and those with an FPG>5.3 mmol/L and 2h-PCPG>4.4 mmol/L had the highest risk for T2D incidence. In women, those with an FPG≤5.2 mmol/L and WHtR≤0.55 had the lowest risk, and those with an FPG>5.2 mmol/L and WHtR>0.56 had the highest risk for T2D incidence. CONCLUSIONS: Our study emphasises the utility of DT for exploring interactions between predictor variables.

Classification-based data mining for identification of risk patterns associated with hypertension in Middle Eastern population: A 12-year longitudinal study.

Hypertension is a critical public health concern worldwide. Identification of risk factors using traditional multivariable models has been a field of active research. The present study was undertaken to identify risk patterns associated with hypertension incidence using data mining methods in a cohort of Iranian adult population.Data on 6205 participants (44% men) age > 20 years, free from hypertension at baseline with no history of cardiovascular disease, were used to develop a series of prediction models by 3 types of decision tree (DT) algorithms. The performances of all classifiers were evaluated on the testing data set.The Quick Unbiased Efficient Statistical Tree algorithm among men and women and Classification and Regression Tree among the total population had the best performance. The C-statistic and sensitivity for the prediction models were (0.70 and 71%) in men, (0.79 and 71%) in women, and (0.78 and 72%) in total population, respectively. In DT models, systolic blood pressure (SBP), diastolic blood pressure, age, and waist circumference significantly contributed to the risk of incident hypertension in both genders and total population, wrist circumference and 2-h postchallenge plasma glucose among women and fasting plasma glucose among men. In men, the highest hypertension risk was seen in those with SBP > 115 mm Hg and age > 30 years. In women those with SBP > 114 mm Hg and age > 33 years had the highest risk for hypertension. For the total population, higher risk was observed in those with SBP > 114 mm Hg and age > 38 years.Our study emphasizes the utility of DTs for prediction of hypertension and exploring interaction between predictors. DT models used the easily available variables to identify homogeneous subgroups with different risk pattern for the hypertension.

The Impact of Oversampling with SMOTE on the Performance of 3 Classifiers in Prediction of Type 2 Diabetes.

OBJECTIVE: To evaluate the impact of the synthetic minority oversampling technique (SMOTE) on the performance of probabilistic neural network (PNN), naïve Bayes (NB), and decision tree (DT) classifiers for predicting diabetes in a prospective cohort of the Tehran Lipid and Glucose Study (TLGS). METHODS: . Data of the 6647 nondiabetic participants, aged 20 years or older with more than 10 years of follow-up, were used to develop prediction models based on 21 common risk factors. The minority class in the training dataset was oversampled using the SMOTE technique, at 100%, 200%, 300%, 400%, 500%, 600%, and 700% of its original size. The original and the oversampled training datasets were used to establish the classification models. Accuracy, sensitivity, specificity, precision, F-measure, and Youden's index were used to evaluated the performance of classifiers in the test dataset. To compare the performance of the 3 classification models, we used the ROC convex hull (ROCCH). RESULTS: Oversampling the minority class at 700% (completely balanced) increased the sensitivity of the PNN, DT, and NB by 64%, 51%, and 5%, respectively, but decreased the accuracy and specificity of the 3 classification methods. NB had the best Youden's index before and after oversampling. The ROCCH showed that PNN is suboptimal for any class and cost conditions. CONCLUSIONS: To determine a classifier with a machine learning algorithm like the PNN and DT, class skew in data should be considered. The NB and DT were optimal classifiers in a prediction task in an imbalanced medical database.