Factors Associated With Trabecular Bone Score and Bone Mineral Density; A Machine Learning Approach.

INTRODUCTION: Bone indexes including trabecular bone score (TBS) and bone mineral density (BMD) have been shown to be associated with wide spectrum of variables including physical activity, vitamin D, liver enzymes, biochemical measurements, mental and sleep disorders, and quality of life. Here we aimed to determine the most important factors related to TBS and BMD in SUVINA dataset. METHODS: Data were extracted from the Survey of Ultraviolet Intake by Nutritional Approach (SUVINA study) including all 306 subjects entered this survey. All the available parameters in the SUVINA database were included the analysis. XGBoost modeler software was used to define the most important features associated with bone indexes including TBS and BMD in various sites. RESULTS: Applying XGBoost modeling for 4 bone indexes indicated that this algorithm could identify the most important variables in relation to bone indexes with an accuracy of 92%, 93%, 90% and 90% respectively for TBS T-score, lumbar Z-score, neck of femur Z-score and Radius Z-score. Serum vitamin D, pro-oxidant-oxidant balance (PAB) and physical activity level (PAL) were the most important factors related to bone indices in different sites of the body. CONCLUSIONS: Our findings indicated that XGBoost could identify the most important variables with an accuracy of >90% for TBS and BMD. The most important features associated with bone indexes were serum vitamin D, PAB and PAL.

Potential value and impact of data mining and machine learning in clinical diagnostics.

Data mining involves the use of mathematical sciences, statistics, artificial intelligence, and machine learning to determine the relationships between variables from a large sample of data. It has previously been shown that data mining can improve the prediction and diagnostic precision of type 2 diabetes mellitus. A few studies have applied machine learning to assess hypertension and metabolic syndrome-related biomarkers, as well as refine the assessment of cardiovascular disease risk. Machine learning methods have also been applied to assess new biomarkers and survival outcomes in patients with renal diseases to predict the development of chronic kidney disease, disease progression, and renal graft survival. In the latter, random forest methods were found to be the best for the prediction of chronic kidney disease. Some studies have investigated the prognosis of nonalcoholic fatty liver disease and acute liver failure, as well as therapy response prediction in patients with viral disorders, using decision tree models. Machine learning techniques, such as Sparse High-Order Interaction Model with Rejection Option, have been used for diagnosing Alzheimer's disease. Data mining techniques have also been applied to identify the risk factors for serious mental illness, such as depression and dementia, and help to diagnose and predict the quality of life of such patients. In relation to child health, some studies have determined the best algorithms for predicting obesity and malnutrition. Machine learning has determined the important risk factors for preterm birth and low birth weight. Published studies of patients with cancer and bacterial diseases are limited and should perhaps be addressed more comprehensively in future studies. Herein, we provide an in-depth review of studies in which biochemical biomarker data were analyzed using machine learning methods to assess the risk of several common diseases, in order to summarize the potential applications of data mining methods in clinical diagnosis. Data mining techniques have now been increasingly applied to clinical diagnostics, and they have the potential to support this field.

Association of a genetic variant in the AKT gene locus and cardiovascular risk factors.

Cardiovascular disease (CVDs) is the leading cause of morbidity and death worldwide. Most genetic variants could be identified by several genome-wide-association-studies (GWAS), including within genes encoding proteins involved in the AKT/PI3K pathways that are related with an increased risk of metabolic syndrome and CVDs. Therefore, due to the importance of genetic variants in the prognosis of diseases, we examined the genetic polymorphism of AKT-rs1130233 located on chromosome 14 with cardiovascular risk factors. In this cross-sectional study, 721 subjects recruited from the Mashhad-Stroke and Heart-Atherosclerotic-Disorders (MASHAD) cohort study. The participants including 257 subjects with metabolic syndrome, 144 subjects with cardiovascular disease and 320 subjects as a control group. Anthropometric, biochemical and demographic information measures were prepared. Dietary assessment was managed by 24h dietary recall. DNA extraction and genotyping were carried out by using the TaqMan real-time-PCR based method. The association of AKT rs1130233 locus with dietary intakes, metabolic syndrome and cardiovascular risk factors were assessed. Data were analyzed by using SPSS 21 software. Frequencies of genotypes AA, AG and GG of the AKT rs1130233 polymorphism were 12.6%, 44.5% and 42.9% in subjects with metabolic syndrome and 9.7%, 39.6% and 50.7% in subjects with cardiovascular disease, respectively. The frequency of allele A and G in cardiovascular disease and metabolic syndrome population were 29.5%, 70.5% and 34.8%, 65.2%, respectively. We have found no significant association between the AKT rs1130233 polymorphism with cardiovascular risk factors and metabolic syndrome. The results of dietary intake showed that the levels of phosphorus intake (p=0.008), calcium intake (p=0.007) and iodine intake (p=0.04) were different in subjects with and without metabolic syndrome. And also, energy intake was significantly different in subjects with cardiovascular disease (p=0.01) compared to the control group. Our findings suggest that AKT rs1130233 was not associated with the risk of metabolic syndrome and cardiovascular disease in the Iranian population. More studies are needed to validate our results. We did functional analysis, due to certify our investigation about value of this genetic biomarker for CVD risk.

Dietary Inflammatory Index is associated with Healthy Eating Index, Alternative Healthy Eating Index, and dietary patterns among Iranian adults.

BACKGROUND: Recent investigations have evaluated the effect of the inflammatory potential of diet in several populations by calculating the Dietary Inflammatory Index (DII) score. We aimed to evaluate the association of the DII with the Healthy Eating Index (HEI), the Alternative Healthy Eating Index (AHEI), and dietary pattern (DP) among healthy Iranian adults. METHODS: A cross-sectional study was conducted among 4365 middle-aged adults. Major DPs and DII score were identified using a validated semi-quantitative food frequency questionnaire (FFQ). Poisson regression was used to evaluate the association of DPs, HEI, and AHEI across tertiles of DII. RESULTS: After adjustment for confounding variables, a low HEI (HEI < 55) and AHEI (AHEI < 56.5) were more prevalent among the participants in the highest tertile of DII compared to the first tertile (PR: 1.13, P-value <.05; PR: 1.10, P-value <.05; respectively). Adherence to a balanced healthy dietary pattern was significantly lower in subjects with a diet that was more pro-inflammatory compared to those with anti-inflammatory diet (PR: 0.85, P-value P < .01). No significant association was found between the DII and a western DP. High levels of HDL and hip and waist circumference were observed in the highest tertile of DII, and high levels of dietary intake of protein and fiber, minerals, fasting blood glucose, and monounsaturated fat were reported in the lowest tertile of DII. CONCLUSION: The highest tertile of the DII (a pro-inflammatory diet) was associated with a lower HEI, AHEI, and lower adherence to balanced DP in a representative sample of adults in Iran.

Comprehensive laboratory reference intervals for routine biochemical markers and pro-oxidant-antioxidant balance (PAB) in male adults.

BACKGROUND: Reference values of biochemical markers are influenced by various parameters including age, sex, region, and lifestyle. Hence, we aimed to determine age- and BMI-specific reference intervals (RIs) for important clinical biomarkers in a healthy adult male population from northeastern Iran. This is also the first study to investigate reference values for pro-oxidant-antioxidant balance (PAB). METHODS: Seven hundred and twenty (720) healthy men, aged 20-60 years, were recruited from Sarakhs in the northeast region of Iran. Reference values for lipid profiles (total cholesterol, triglyceride, HDL-C and LDL-C), fasting blood glucose, inflammatory factors (hs-CRP and PAB), minerals (zinc and copper), uric acid, and blood pressure were measured and statistically analyzed to establish accurate age- and BMI-specific RIs in alignment with CLSI Ep28-A3 guidelines. RESULTS: RIs for lipid profiles, inflammatory factors, minerals, and uric acid required no age partitioning with the exception of fasting blood glucose and blood pressure, which demonstrated significantly higher values in subjects aged 50 years and older. Among these biomarkers, only uric acid, blood pressure, and triglycerides demonstrated statistically significant increases in reference value concentrations with increasing BMI. CONCLUSION: In this study, age- and BMI-specific RIs for several biochemical markers were determined in healthy adult Iranian men. Partitioning by age and BMI was only required for a few analytes with most demonstrating no statistically significant changes with these covariates. These data can be useful to monitor various diseases in male adults with varying BMI in this region and others.

Menstrual problems in adolescence: relationship to serum vitamins A and E, and systemic inflammation.

BACKGROUND: Vitamin status and inflammatory mechanisms may be related to menstrual cycle abnormalities. We investigated the associations between serum fat soluble vitamin (vitamins A and E) concentrations and biomarkers of inflammation and antioxidant status with menstrual characteristics, primary dysmenorrhea (PD) and premenstrual syndrome (PMS) in healthy adolescents. METHODS: A total of 897 adolescent girls either suffering from PMS (n = 134), PD (n = 322), PMS and PD (n = 293) or healthy adolescents (n = 148) were recruited. Serum vitamin A and E, high-sensitivity C-reactive protein (hs-CRP), antibody titers to Hsp27 (anti-Hsp27), serum prooxidant-antioxidant balance (PAB), WBC, mean platelet volume (MPV), and platelet distribution width (PDW) and RBC distribution width (RDW) were measured. Neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR) and RDW-to-platelet ratio (RPR) were calculated. RESULTS: Girls with long bleeding periods had lower concentrations of serum vitamin E compared to those who reported a normal period duration. There were significantly differences between the groups reporting oligomenorrhea, regular menses and polymenorrhea with respect to NLR, RPR, MPV and PDW. Logistic regression demonstrated that the presence of both PMS and PD was positively related to higher serum hs-CRP, PAB and NLR, while serum vitamin A level was inversely related to the presence of PMS. CONCLUSIONS: We found that serum vitamin A, hs-CRP, PAB and NLR are significantly associated with the presence of PMS and PD. Inflammatory processes may contribute to the etiology, symptoms and severity of menstrual disorders. Prospective studies are needed to elucidate the possibility of targeting oxidative stress and inflammatory process for the amelioration of menstrual symptoms.

The relationship between short stature and menstrual pattern in a large cohort of Iranian girls.

The aim of this study was to investigate the relationship between stature and menstrual pattern. Nine hundred and seventy six girls were selected from regions within two cities in north-eastern Iran in 2015. They were assessed with respect to: their stature and menstrual pattern, age of menstruation, severity of dysmenorrhoea, duration of their menstrual cycle and flow. 841 girls had experienced menarche. 10.5% had a short stature. There were significant differences in age, height, weight and body mass index between those who had experienced their first menstrual cycle and others (p < .001). There were weak and negative correlation between age of menarche and height percentiles (r = -0.12, p < .001). Premenstrual syndrome, duration of menstruation cycle and bleeding period did not differ between these two groups (p > .05). We found that dysmenorrhoea was significantly influenced by height. Although the mean age at menarche was statistically significant among different statures, the range was narrow (12.2-12.7). Further studies considering environmental factors, including socioeconomic status and nutrition concurrently, are also required.Impact statementWhat is already known on this subject? Various menstrual characteristics, including age of menarche, severity of dysmenorrhoea and duration of menstrual period may be associated with height. But, there have been few studies on the relationship between short stature and its impact on health status and menstrual patterns in adolescents.What do the results of this study add? There were significant differences in age, height, weight and body mass index between adolescent girls who had experienced their first menstrual cycle, and others. There were weak, negative, significant correlations between age of menarche and height percentiles. Dysmenorrhoea was significantly influenced by height.What are the implications of these findings for clinical practice and/or further research? Life style modification and nutritional interventions that optimise the height of girls may resolve their menstrual problems and dysmenorrhoea.

Prevalence and Socio-Demographic Correlates of Mental Health Problems Among Iranian Health Sciences Students.

OBJECTIVE: The primary objective of the present study was to compare the mental health status of Iranian medical vs other health sciences students and to examine how demographic factors relate to their mental health problems. METHODS: A total of 560 medical and other health sciences students (250 (44.6%) males and 310 (55.4%) females) were recruited from Iran University of Medical Sciences. Data were obtained by self-administered questionnaire, including questions on socio-demographic characteristics. The Beck Depression Inventory, Beck Anxiety Inventory, General Health Questionnaire, and WHO well-being index were used to assess mental health status of students. RESULTS: Ten percent of students had BDI scores consistent with clinically significant depression (6.6% mild, 1.8% moderate, 1.6% severe), and 28.7% had BAI scores consistent with clinically significant anxiety (20.7% mild, 7.1% moderate, 0.9% severe). Kurdish students had an odds ratio (OR) of 2.71 (95% CL, 1.22-6.02) for mild to severe depression symptoms when compared to Persian students. The prevalence of distressed health sciences students and poor psychological well-being was 13.4% and 14.1%, respectively. Maternal education gave an OR of 0.57 (0.35-0.93) for anxiety symptoms, after adjustment for all other factors. The possibility of general psychiatric morbidity was significantly lower in students who studied medicine (OR, 0.40 (0.21-0.71)). Being born in the capital city was associated with better psychological well-being (OR, 0.48 (0.26-0.86)). CONCLUSIONS: Ethnicity, birthplace, discipline, and maternal educational level were major determinants of mental health status among health sciences students. Further research should be undertaken to determine the prevalence of psychological disorders using more reliable diagnostic interview.

Association of a genetic variant in the angiopoietin-like protein 4 gene with metabolic syndrome.

BACKGROUND: Metabolic syndrome (MetS) is characterized by a clustering of cardiovascular risk factors that include: abdominal obesity, dyslipidemia, hypertension and glucose intolerance. Angiopoietin-like protein 4 (ANGPTL4) is a circulating peptide that is an inhibitor of lipoprotein lipase, a key enzyme in lipid metabolism. The objective of this study was to investigate the association of ANGPTL4 gene variants (E40K) with fasting serum triglyceride levels and with cardiovascular risk factors, that included the presence of MetS in 817 subjects recruited from the Mashhad stroke and heart Atherosclerosis Disorders (MASHAD) cohort Study. METHOD: ANGPTL4 genotypes were determined using a TaqMan genotyping based real time PCR method. The association of the genetic variant with the risk of metabolic syndrome and its relationship with lipid profile were determined. RESULT: The frequency of GG, GA and AA genotypes were 96.9, 2.7 and 0.4% in individuals with MetS, and 78.8, 20.8, 0.4%, in those without MetS. The GA genotype of the rs116843064 polymorphism was associated with a lower risk for MetS (e.g., OR in Codominant genetic model: 0.14, 95% CI: (0.06-0.33), p < 0.0001). Subject with an A allele had a higher risk for MetS (OR: 6.72, 95% CI: (3.05-14.82), p < 0.0001). There was a significant difference in fasted lipid profiles across the genotypes for ANGPTL4. Carriers of the AG genotype had higher levels of serum HDL-cholesterol (HDL-C) and lower TG, compared to the GG homozygotes genotype. CONCLUSION: The G allele at the rs116843064 polymorphic locus of the ANGPTL4 gene was associated with a lower prevalence of MetS.

The relationship between adherence to a Dietary Approach to Stop Hypertension (DASH) dietary pattern and insomnia.

BACKGROUND: Adherence to a DASH- style diet has been reported to be associated with several health-related outcomes. A limited number of reports suggest that diet is an important behavioral determinant of insomnia. The current study aimed to explore the relationship between adherence to a DASH diet and the prevalence of insomnia in adolescent girls. METHODS: A total of 488 adolescent girls aged 12-18 years old were recruited from different regions of Khorasan Razavi in northeastern of Iran, using a random cluster sampling method. DASH scores were determined according to the method of Fung et al. A validated Iranian version of the Insomnia Severity Index questionnaire was used to assess sleep insomnia. To assess the association between the DASH dietary pattern and insomnia, we applied logistic regression analysis in crude and adjusted models. RESULTS: As may be expected, participants in the upper quintile of the DASH diet had significantly higher intakes of fruits, vegetables, low fat dairy products, fish and nuts and lower consumption of refined grains, red and processed meat, sugar-sweetened beverages and sweets. We found that a high adherence to a DASH-style diet was associated with a lower odds of insomnia (OR: 0.51; 95% CI 0.26-1.00) compared with those with lowest adherence. Similar results were found after adjustment for potential confounders. CONCLUSIONS: There is an inverse association between adherence to DASH dietary patterns and insomnia. Further prospective studies are required to demonstrate these findings.

High dose vitamin D supplementation can improve menstrual problems, dysmenorrhea, and premenstrual syndrome in adolescents.

Vitamin D has a crucial role in female reproduction, possibly through its effects on calcium homeostasis, cyclic sex steroid hormone fluctuations, or neurotransmitter function. We have assessed the effects of vitamin D supplementation on dysmenorrhea and premenstrual syndrome (PMS) in adolescents. In this study, 897 adolescent girls living in Mashhad and Sabzevar, Iran, received nine high-dose vitamin D supplements (as 50,000 IU/week of cholecalciferol) and were followed up over 9 weeks. We evaluated the effect of vitamin D supplementation on individuals in four categories: those with only PMS; individuals with only dysmenorrhea; subjects with both PMS and dysmenorrhea and normal subjects. The prevalence of PMS after the intervention fell from 14.9% to 4.8% (p < .001). Similar results were also found for the prevalence of subjects with dysmenorrhea (35.9% reduced to 32.4%), and in subjects with both PMS and dysmenorrhea (32.7% reduced 25.7%). Vitamin D supplementation was associated with a reduction in the incidence of several symptoms of PMS such as backache and tendency to cry easily as well as decrement in pain severity of dysmenorrhea (p < .05). High dose vitamin D supplementation can reduce the prevalence of PMS and dysmenorrhea as well as has positive effects on the physical and psychological symptoms of PMS.

Nutrients intake, and serum calcium and phosphorus levels: An evidence-based study.

INTRODUCTION: Dietary calcium and phosphorus appear to be important determinants of dyslipidemia and hypertension. We have investigated (1) the prevalence of hypocalcemia and hypophosphatemia in an Iranian population, and (2) the association between nutrient's intake and serum levels of calcium and phosphorus. METHODS: A total of 908 individuals were enrolled using a stratified-cluster sampling method from the Mashhad stroke and heart atherosclerosis disorder (MASHHAD) study. Dietplan6 software was used for 24-hour recalls and food frequency questionnaire to investigate macro- and micronutrient intakes of our population, followed by univariate analysis for evaluation of the association of dairy consumption with serum calcium and phosphorus. RESULTS: We observed that the mean dietary Ca intake was 862.4 mg/d (672.7-1052) for men and 864.2 mg/d (604.5-1123) for women in our population, which is lower than the dietary reference intake for Ca. Moreover, a significant relationship was detected between serum calcium level and dietary intakes of saturated fatty acids, copper, iodine, sucrose, potato, and juices. Of note, we observed a negative association between copper intake, and serum Ca (P˂.01). Also, a significant association was found between serum phosphorus levels and dietary intakes of chicken meat and fresh fruits. Interestingly, we observed an inverse relationship between tea and Ca/P ratio (eg, -r=.098; P=.02). CONCLUSION: We found that the dietary intake of Ca was not sufficient in our population and was associated with the dietary intake of some macro- and micronutrient, supporting further investigation on clinical impact of this condition on calcium/phosphorus deficiency related diseases.

Prevalence of combined and noncombined dyslipidemia in an Iranian population.

BACKGROUND: Combination of dyslipidemic phenotypes, including elevated plasma levels of low-density lipoprotein cholesterol (LDL-C), elevated plasma triglycerides (TG), and decreased low-density lipoprotein cholesterol (HDL-C) concentrations, is important because of the association of individual phenotypes with increased risk of cardiovascular disease (CVD). We investigated the prevalence of combined dyslipidemias and their effects on CVD risk in an Iranian large population. METHOD: A total of 9847 individuals were recruited as part of the Mashhad Stroke and Heart Atherosclerotic Disorders (MASHAD) cohort study. Anthropometric parameters and biochemical indices were measured in all of the subjects. Different types of combined dyslipidemias including high TG + low HDL-C, high TG + low HDL-C + high LDL-C, low HDL-C + high LDL-C, high TG + high LDL-C, and finally high TG + high LDL-C + low HDL-C were considered. Ten-year CVD risk was calculated using the QRISK2 risk algorithm and adjustments were made as suggested by the Joint British Societies' (JBS2). Logistic regression analyses were performed to determine the association between different combined dyslipidemias and categorical QRISK. RESULTS: A total of 3952 males and 5895 females were included in this current study. Among the included subjects, 83.4% had one form of dyslipidemia, and 16.6% subjects were not dyslipidemic. The mean age was 48.88 ± 7.9 and 47.02 ± 8.54 years for dyslipidemic and nondyslipidemic groups, respectively. The results showed that the frequency of dyslipidemia was 98%, 87.1%, and 90% in subjects with metabolic syndrome, CVD, and diabetes, respectively. Our results suggested that around 15.7% of study population were at 10 years CVD risk (high ≥20) and it was higher in men than women (P < .001). Moreover, risk of CVD was higher in TG↑ & HDL↓ & LDL↑ group than other groups. CONCLUSION: Prevalence of dyslipidemia was 83.4% among Iranian adults. The results showed that individuals with increased plasma TG and LDL-C, and low HDL-C levels had the highest 10 years CVD risk compared to other combined dyslipidemic phenotypes.

Association of hematocrit with blood pressure and hypertension.

BACKGROUND: Hypertension (HTN) is a risk factor for stroke, renal failure, and cardiovascular disease. The association between biochemical and hematological parameters with high blood pressure may provide a more precise approach to risk prediction conferred by HTN in these patients. OBJECTIVE: The aim of current study was to explore whether biochemical and hematological parameters are associated with HTN in a cohort study with a 7-year follow-up. MATERIALS AND METHODS: A total of 9808 individuals were enrolled and recruited as part of the Mashhad Stroke and Heart Atherosclerotic Disorders (MASHAD) cohort study, and biochemical and hematological factors were measured in all subjects. Univariate and multivariate logistic regression analysis were performed to determine the association of biochemical and hematological parameters with HTN. RESULTS: Several biochemical parameters including fasting plasma glucose (FBG), serum high-sensitivity C-reactive protein (hs-CRP), triglyceride (TG), total cholesterol (TC), low-density lipoprotein cholesterol (LDL-C), and uric acid were increased in hypertensive participants. In contrast, serum high-density lipoprotein cholesterol (HDL-C) was lower in hypertensive individuals. Furthermore, we demonstrated that hematological parameters including white blood cell (WBC) count, red blood cell (RBC) count, hemoglobin (HGB), hematocrit (HCT), and mean corpuscular hemoglobin (MCH) were higher in the hypertensive group compared to the control group. But mean corpuscular volume (MCV), and red cell distribution width (RDW), were decreased in the hypertensive group. Furthermore, our results strongly suggested that among these parameters, hematocrit was the independent risk factor for hypertension in the population. CONCLUSION: We demonstrated the association of altered biochemical and hematological factors with hypertension supporting the value of emerging markers for early prediction of high blood pressure in prone individuals.

Nutrient patterns and their relationship to metabolic syndrome in Iranian adults.

BACKGROUND: The prevalence of metabolic syndrome (MetS) is increasing globally. It is associated with a significant risk of developing type 2 diabetes mellitus and cardiovascular disease. MATERIALS AND METHODS: The relationship between adherence to several different dietary patterns and the presence of MetS was explored in an Iranian population sample of 5764 subjects. RESULTS: We observed that the prevalence of MetS was 13% and 18% in men and women, respectively. There were three main dietary patterns: the first pattern was characterized by protein, carbohydrate, starch, glucose, fructose, sucrose, maltose, dietary fibre, potassium, calcium, magnesium, phosphorus, iron, zinc, manganese, thiamine, riboflavin, carotene, vitamin c and lactose; second representative of fat, saturated fat, monounsaturated fat, polyunsaturated fat, cholesterol, sodium, calcium, zinc, phosphorus, iodine, vitamin D, chloride, betaine, niacin; third consisting of copper, selenium, vitamin A, riboflavin, vitamin B12. In this dietary pattern, individuals in first quintile had a higher consumption of total fat, saturated fatty acid, monounsaturated fatty acid, polyunsaturated fatty acid, cholesterol and vitamin A. In the second pattern, individuals in the fifth quintile ate less carbohydrate, dietary fibre, glucose, Fructose, potassium compared to first quintile. We found that individuals in the first quintile in pattern 3 had higher intakes of protein, zinc and calcium compared to other quintiles. CONCLUSIONS: We have found that a nutrient pattern which mostly characterized by dietary protein, carbohydrate, starch, glucose, fructose, sucrose, maltose was associated with a higher risk of MetS in both genders, while a pattern which was represent of copper, selenium, Vitamin A, riboflavin, vitamin B12 was associated with greater odds of Mets, in women.

Reduced Serum Levels of Zinc and Superoxide Dismutase in Obese Individuals.

The oxidant-stress (OS) has an essential role to play in the pathogenesis and progression of many diseases. OS is the outcome when the level of free-radical-formation is increased or protective-antioxidant-mechanisms are compromised. Its value is expected to increase, although its emerging roles have not been conclusive in different studies. The objective of this study was to explore the level of zinc, copper, and antioxidant in response to obesity-related-stress by measuring superoxide-dismutase (SOD) levels as a key antioxidant-enzyme in 706 individuals with/without obesity. Anthropometric/biochemical parameters including total-cholesterol (TC), fasting-blood-glucose, high-density-lipoprotein (HDL), low-density-lipoprotein, and triglycerides were determined. The activity of SOD was measured followed by the measurement of Cu and Zn levels. Obese subjects had a significantly higher level of body mass index (BMI) and TC, while the level of HDL was lower in the obese group, as compared to the related values in control subjects. The level of Zn was significantly decreased in the obese group, while the level of Cu and Cu/Zn ratio increased. Additionally, we observed that the SOD level was less in obese subjects when compared to that in the non-obese subjects. In addition to the complications of high BMI, low level of Zn and SOD in obesity can be considered a risk factor, resulting in a reduced antioxidant response, supporting the need for identifying a suitable treatment option for this group.

A multinational study on artificial intelligence adoption: Clinical implementers' perspectives.

BACKGROUND: Despite substantial progress in AI research for healthcare, translating research achievements to AI systems in clinical settings is challenging and, in many cases, unsatisfactory. As a result, many AI investments have stalled at the prototype level, never reaching clinical settings. OBJECTIVE: To improve the chances of future AI implementation projects succeeding, we analyzed the experiences of clinical AI system implementers to better understand the challenges and success factors in their implementations. METHODS: Thirty-seven implementers of clinical AI from European and North and South American countries were interviewed. Semi-structured interviews were transcribed and analyzed qualitatively with the framework method, identifying the success factors and the reasons for challenges as well as documenting proposals from implementers to improve AI adoption in clinical settings. RESULTS: We gathered the implementers' requirements for facilitating AI adoption in the clinical setting. The main findings include 1) the lesser importance of AI explainability in favor of proper clinical validation studies, 2) the need to actively involve clinical practitioners, and not only clinical researchers, in the inception of AI research projects, 3) the need for better information structures and processes to manage data access and the ethical approval of AI projects, 4) the need for better support for regulatory compliance and avoidance of duplications in data management approval bodies, 5) the need to increase both clinicians' and citizens' literacy as respects the benefits and limitations of AI, and 6) the need for better funding schemes to support the implementation, embedding, and validation of AI in the clinical workflow, beyond pilots. CONCLUSION: Participants in the interviews are positive about the future of AI in clinical settings. At the same time, they proposenumerous measures to transfer research advancesinto implementations that will benefit healthcare personnel. Transferring AI research into benefits for healthcare workers and patients requires adjustments in regulations, data access procedures, education, funding schemes, and validation of AI systems.

Investigating the inflammatory status in the patients candidate for second angiography after coronary stent implantation.

BACKGROUND: Inflammation has been shown to be an important feature of atherosclerosis. We aimed to assess a profile of inflammatory cytokines and growth factors in patients with established coronary artery disease (CAD), 12 months after stent implantation. METHODS: A total of 193 patients with CAD, who were candidates for angiography, 12 months after stent implantation (cases), were compared with 107 patients with CAD, who were candidates for their first angiography (controls). Fasting blood glucose (FBG), triglycerides (TGs), total cholesterol (TC), low-density lipoprotein cholesterol (LDL-C), high-density lipoprotein cholesterol (HDL-C) and high-sensitive C-reactive protein (hs-CRP) were measured using routine methods. The serum concentrations of IL-1α, IL-1ß, IL-2, IL-4, IL-6, IL-8, IL-10, TNF-α, IFN-γ, MCP-1, EGF and VEGF were determined using competitive chemiluminescence immunoassays. RESULTS: Serum levels of FBG (p = .002), TG (p = .029) and hs-CRP (p = .005) were significantly lower in cases than controls. The cytokines and growth factor profiles in cases were significantly different from controls. After multivariate analysis, serum levels of IL-2 (p < .001), IL-4 (p = .028) were significantly lower in cases compared with the controls while serum levels of IL-8, TNF-α, MCP-1, EGF and VEGF were significantly higher in the cases (p < .001). CONCLUSIONS: In patients with CAD and higher consumption of drug used (statins, aspirin and glucose lowering agents) to mitigate the risk of a secondary event, the level of hs-CRP one year after stent implantation decreased despite of significant higher serum levels of pro- and anti-inflammatory cytokines and growth factors.

Early diagnosis of candidemia with explainable machine learning on automatically extracted laboratory and microbiological data: results of the AUTO-CAND project.

BACKGROUND: Candidemia is associated with a heavy burden of morbidity and mortality in hospitalized patients. The availability of blood culture results could require up to 48-72 h after blood draw; thus, early treatment decisions are made in the absence of a definite diagnosis. METHODS: In this retrospective study, we assessed the performance of different supervised machine learning algorithms for the early differential diagnosis of candidemia and bacteremia in adult patients on a large dataset automatically extracted within the AUTO-CAND project. RESULTS: Overall, 12,483 episodes of candidemia (1275; 10%) or bacteremia (11,208; 90%) were included in the analysis. A random forest classifier achieved the best diagnostic performance for candidemia, with sensitivity 0.98 and specificity 0.65 on the training set (true skill statistic [TSS] = 0.63) and sensitivity 0.74 and specificity 0.57 on the test set (TSS = 0.31). Then, the random classifier was trained in the subgroup of patients with available serum ß-D-glucan (BDG) and procalcitonin (PCT) values by exploiting the feature ranking learned in the entire dataset. Although no statistically significant differences were observed from the performance measures obtained by employing BDG and PCT alone, the performance measures of the classifier that included the features selected in the entire dataset, plus BDG and PCT, were the highest in most cases. CONCLUSIONS: Random forest classifiers trained on large datasets of automatically extracted data have the potential to improve current diagnostic algorithms for candidemia. However, further development through implementation of automatically extracted clinical features may be necessary to achieve crucial improvements.