Adherence to dietary recommendations by socioeconomic status in the United Kingdom biobank cohort study.

Introduction: Understanding how socioeconomic markers interact could inform future policies aimed at increasing adherence to a healthy diet. Methods: This cross-sectional study included 437,860 participants from the UK Biobank. Dietary intake was self-reported. Were used as measures socioeconomic education level, income and Townsend deprivation index. A healthy diet score was defined using current dietary recommendations for nine food items and one point was assigned for meeting the recommendation for each. Good adherence to a healthy diet was defined as the top 75th percentile, while poor adherence was defined as the lowest 25th percentile. Poisson regression was used to investigate adherence to dietary recommendations. Results: There were significant trends whereby diet scores tended to be less healthy as deprivation markers increased. The diet score trends were greater for education compared to area deprivation and income. Compared to participants with the highest level of education, those with the lowest education were found to be 48% less likely to adhere to a healthy diet (95% Confidence Interval [CI]: 0.60-0.64). Additionally, participants with the lowest income level were 33% less likely to maintain a healthy diet (95% CI: 0.73-0.81), and those in the most deprived areas were 13% less likely (95% CI: 0.84-0.91). Discussion/conclussion: Among the three measured proxies of socioeconomic status - education, income, and area deprivation - low education emerged as the strongest factor associated with lower adherence to a healthy diet.

Measuring congestion with a non-invasive monitoring device in heart failure and haemodialysis: CONGEST-HF.

AIMS: We examined the effectiveness of a novel cardiopulmonary management wearable sensor (worn for less than 5 mins) at measuring congestion and correlated the device findings with established clinical measures of congestion. METHODS AND RESULTS: We enrolled three cohorts of patients: (1) patients with heart failure (HF) receiving intravenous diuretics in hospital; (2) patients established on haemodialysis, and (3) HF patients undergoing right heart catheterization (RHC). The primary outcomes in the respective cohorts were a Spearman correlation between (1) change in weight and change in thoracic impedance (TI) (from enrolment, 24 h after admission to discharge) in patients hospitalized for HF; (2) lung ultrasound B-lines and volume removed during dialysis with device measured TI, and (3) pulmonary capillary wedge pressure (PCWP) and sub-acoustic diastolic, third heart sound (S3) in the patients undergoing RHC. A total of 66 patients were enrolled. In HF patients (n = 25), change in weight was correlated with both change in device TI (Spearman correlation [rsp] = -0.64, p = 0.002) and change in device S3 (rsp = -0.53, p = 0.014). In the haemodialysis cohort (n = 21), B-lines and TI were strongly correlated before (rsp = -0.71, p < 0.001) and after (rsp = -0.77, p < 0.001) dialysis. Volume of fluid removed by dialysis was correlated with change in device TI (rsp = 0.49, p = 0.024). In the RHC cohort (n = 20), PCWP measured at one time point and device S3 were not significantly correlated (rsp = 0.230, p = 0.204). There were no device-related adverse events. CONCLUSIONS: A non-invasive device was able to detect changes in congestion in patients with HF receiving decongestion therapy and patients having fluid removed at haemodialysis. The cardiopulmonary management device, which measures multiple parameters, is a potentially useful tool to monitor patients with HF to prevent hospitalizations.

Dapagliflozin and quality of life measured using the EuroQol 5-dimension questionnaire in patients with heart failure with reduced and mildly reduced/preserved ejection fraction.

AIMS: Although much is known about the usefulness of heart failure (HF)-specific instruments for assessing patient well-being, less is known about the value of generic instruments for the measurement of health-related quality of life (HRQL) in HF. The aim of this study was to assess the relationship between the EuroQol 5-dimension 5-level (EQ-5D-5L) visual analogue scale (VAS) and index scores, clinical characteristics, and outcomes in patients with HF and the effect of dapagliflozin on these scores. METHODS AND RESULTS: We performed a patient-level pooled analysis of the DAPA-HF and DELIVER trials, which investigated the effectiveness and safety of dapagliflozin in patients with HF and reduced ejection fraction (HFrEF) and mildly reduced/preserved ejection fraction (HFmrEF/HFpEF), respectively. Patients reporting higher (better) EQ-5D-5L VAS and index scores had a lower prevalence of comorbidities, including atrial fibrillation and hypertension, than patients with a worse score. They were also more likely to have better investigator-reported (New York Heart Association class) and patient-self-reported (Kansas City Cardiomyopathy Questionnaire) health status and lower median N-terminal pro-B-type natriuretic peptide levels. Compared to patients with the lowest scores (Q1), those with higher EQ-5D-5L VAS scores had better outcomes: the hazard ratio for the composite of cardiovascular death or worsening HF was 0.81 (95% confidence interval 0.72-0.91) in Q2, 0.74 (0.65-0.84) in Q3, and 0.62 (0.54-0.72) in Q4. The risk of each component of the composite outcome, and all-cause death, was also lower in patients with better scores. Similar findings were observed for the index score. Treatment with dapagliflozin improved both EQ-5D-5L VAS and index scores across the range of ejection fraction. CONCLUSIONS: Both higher (better) EQ-5D-5L VAS and index scores were associated with better outcomes. Dapagliflozin treatment improved EQ-5D-5L VAS and index scores, irrespective of ejection fraction.

Dapagliflozin and Days of Full Health Lost in the DAPA-HF Trial.

BACKGROUND: Conventional time-to-first-event analyses cannot incorporate recurrent hospitalizations and patient well-being in a single outcome. OBJECTIVES: To overcome this limitation, we tested an integrated measure that includes days lost from death and hospitalization, and additional days of full health lost through diminished well-being. METHODS: The effect of dapagliflozin on this integrated measure was assessed in the DAPA-HF (Dapagliflozin and Prevention of Adverse Outcomes in Heart Failure) trial, which examined the efficacy of dapagliflozin, compared with placebo, in patients with NYHA functional class II to IV heart failure and a left ventricular ejection fraction ≤40%. RESULTS: Over 360 days, patients in the dapagliflozin group (n = 2,127) lost 10.6 ± 1.0 (2.9%) of potential follow-up days through cardiovascular death and heart failure hospitalization, compared with 14.4 ± 1.0 days (4.0%) in the placebo group (n = 2,108), and this component of all measures of days lost accounted for the greatest between-treatment difference (-3.8 days [95% CI: -6.6 to -1.0 days]). Patients receiving dapagliflozin also had fewer days lost to death and hospitalization from all causes vs placebo (15.5 ± 1.1 days [4.3%] vs 20.3 ± 1.1 days [5.6%]). When additional days of full health lost (ie, adjusted for Kansas City Cardiomyopathy Questionnaire-overall summary score) were added, total days lost were 110.6 ± 1.6 days (30.7%) with dapagliflozin vs 116.9 ± 1.6 days (32.5%) with placebo. The difference in all measures between the 2 groups increased over time (ie, days lost by death and hospitalization -0.9 days [-0.7%] at 120 days, -2.3 days [-1.0%] at 240 days, and -4.8 days [-1.3%] at 360 days). CONCLUSIONS: Dapagliflozin reduced the total days of potential full health lost due to death, hospitalizations, and impaired well-being, and this benefit increased over time during the first year. (Study to Evaluate the Effect of Dapagliflozin on the Incidence of Worsening Heart Failure or Cardiovascular Death in Patients With Chronic Heart Failure; NCT03036124).

Prognostic Models for Mortality and Morbidity in Heart Failure With Preserved Ejection Fraction.

Importance: Accurate risk prediction of morbidity and mortality in patients with heart failure with preserved ejection fraction (HFpEF) may help clinicians risk stratify and inform care decisions. Objective: To develop and validate a novel prediction model for clinical outcomes in patients with HFpEF using routinely collected variables and to compare it with a biomarker-driven approach. Design, Setting, and Participants: Data were used from the Dapagliflozin Evaluation to Improve the Lives of Patients With Preserved Ejection Fraction Heart Failure (DELIVER) trial to derive the prediction model, and data from the Angiotensin Receptor Neprilysin Inhibition in Heart Failure With Preserved Ejection Fraction (PARAGON-HF) and the Irbesartan in Heart Failure With Preserved Ejection Fraction Study (I-PRESERVE) trials were used to validate it. The outcomes were the composite of HF hospitalization (HFH) or cardiovascular death, cardiovascular death, and all-cause death. A total of 30 baseline candidate variables were selected in a stepwise fashion using multivariable analyses to create the models. Data were analyzed from January 2023 to June 2023. Exposures: Models to estimate the 1-year and 2-year risk of cardiovascular death or hospitalization for heart failure, cardiovascular death, and all-cause death. Results: Data from 6263 individuals in the DELIVER trial were used to derive the prediction model and data from 4796 individuals in the PARAGON-HF trial and 4128 individuals in the I-PRESERVE trial were used to validate it. The final prediction model for the composite outcome included 11 variables: N-terminal pro-brain natriuretic peptide (NT-proBNP) level, HFH within the past 6 months, creatinine level, diabetes, geographic region, HF duration, treatment with a sodium-glucose cotransporter 2 inhibitor, chronic obstructive pulmonary disease, transient ischemic attack/stroke, any previous HFH, and heart rate. This model showed good discrimination (C statistic at 1 year, 0.73; 95% CI, 0.71-0.75) in both validation cohorts (C statistic at 1 year, 0.71; 95% CI, 0.69-0.74 in PARAGON-HF and 0.75; 95% CI, 0.73-0.78 in I-PRESERVE) and calibration. The model showed similar discrimination to a biomarker-driven model including high-sensitivity cardiac troponin T and significantly better discrimination than the Meta-Analysis Global Group in Chronic (MAGGIC) risk score (C statistic at 1 year, 0.60; 95% CI, 0.58-0.63; delta C statistic, 0.13; 95% CI, 0.10-0.15; P < .001) and NT-proBNP level alone (C statistic at 1 year, 0.66; 95% CI, 0.64-0.68; delta C statistic, 0.07; 95% CI, 0.05-0.08; P < .001). Models derived for the prediction of all-cause and cardiovascular death also performed well. An online calculator was created to allow calculation of an individual's risk. Conclusions and Relevance: In this prognostic study, a robust prediction model for clinical outcomes in HFpEF was developed and validated using routinely collected variables. The model performed better than NT-proBNP level alone. The model may help clinicians to identify high-risk patients and guide treatment decisions in HFpEF.

The impact of vitamin D changes during pregnancy on the development of maternal adverse events: a random forest analysis.

BACKGROUND: Maternal vitamin D deficiency during pregnancy has been associated with various maternal adverse events (MAE). However, the evidence regarding the effect of vitamin D supplementation on these outcomes is still inconclusive. METHODS: This secondary analysis utilized a case-control design. 403 samples with MAE and 403 samples without any outcomes were selected from the Khuzestan Vitamin D Deficiency Screening Program in Pregnancy study. Random forest (RF) analysis was used to evaluate the effect of maternal vitamin D changes during pregnancy on MAE. RESULTS: The results showed that women who remained deficient (35.2%) or who worsened from sufficient to deficient (30.0%) had more MAE than women who improved (16.4%) or stayed sufficient (11.8%). The RF model had an AUC of 0.74, sensitivity of 72.6%, and specificity of 69%, which indicate a moderate to high performance for predicting MAE. The ranked variables revealed that systolic blood pressure is the most important variable for MAE, followed by diastolic blood pressure and vitamin D changes during pregnancy. CONCLUSION: This study provides evidence that maternal vitamin D changes during pregnancy have a significant impact on MAE. Our findings suggest that monitoring and treatment of vitamin D deficiency during pregnancy may be a potential preventive strategy for reducing the risk of MAE. The presented RF model had a moderate to high performance for predicting MAE.

Machine learning-based classifiers to predict metastasis in colorectal cancer patients.

Background: The increasing prevalence of colorectal cancer (CRC) in Iran over the past three decades has made it a key public health burden. This study aimed to predict metastasis in CRC patients using machine learning (ML) approaches in terms of demographic and clinical factors. Methods: This study focuses on 1,127 CRC patients who underwent appropriate treatments at Taleghani Hospital, a tertiary care facility. The patients were divided into training and test datasets in an 80:20 ratio. Various ML methods, including Naive Bayes (NB), random rorest (RF), support vector machine (SVM), neural network (NN), decision tree (DT), and logistic regression (LR), were used for predicting metastasis in CRC patients. Model performance was evaluated using 5-fold cross-validation, reporting sensitivity, specificity, the area under the curve (AUC), and other indexes. Results: Among the 1,127 patients, 183 (16%) had experienced metastasis. In the predictionof metastasis, both the NN and RF algorithms had the highest AUC, while SVM ranked third in both the original and balanced datasets. The NN and RF algorithms achieved the highest AUC (100%), sensitivity (100% and 100%, respectively), and accuracy (99.2% and 99.3%, respectively) on the balanced dataset, followed by the SVM with an AUC of 98.8%, a sensitivity of 97.5%, and an accuracy of 97%. Moreover, lower false negative rate (FNR), false positive rate (FPR), and higher negative predictive value (NPV) can be confirmed by these two methods. The results also showed that all methods exhibited good performance in the test datasets, and the balanced dataset improved the performance of most ML methods. The most important variables for predicting metastasis were the tumor stage, the number of involved lymph nodes, and the treatment type. In a separate analysis of patients with tumor stages I-III, it was identified that tumor grade, tumor size, and tumor stage are the most important features. Conclusion: This study indicated that NN and RF were the best among ML-based approaches for predicting metastasis in CRC patients. Both the tumor stage and the number of involved lymph nodes were considered the most important features.

Peptic ulcer characteristics in oral opium and non-opium user patients with upper gastrointestinal bleeding.

BACKGROUND/AIMS: Upper gastrointestinal bleeding (UGIB) is a frequent medical issue. The primary risk factors for bleeding peptic ulcers are Helicobacter pylori infection and non-steroidal anti-inflammatory drugs. The association between acute gastric/duodenal ulcer and opium use has been previously proposed; however, there is no available data on endoscopic findings of patients with acute UGIB who use opium. MATERIALS AND METHODS: In the present descriptive cross-sectional study, endoscopic data of 50 consecutive patients with oral opium use and 50 consecutive patients without any opium use who were admitted for UGIB were recorded. The size (5-10 mm, 11-20 mm, or more than 20 mm), number (single, double, or multiple), and location of the ulcers (esophagus, gastric corpus including the fundus and body, antrum, angulus, or duodenum) were examined by endoscopy in both groups. RESULTS: Three or more ulcers were observed in 46% and 16% of patients with oral opium use and without opium use, respectively (P-value = 0.001). The rate of giant ulcers (> 20 mm) was significantly higher in patients who used oral opium (40% vs. 12%; P-value = 0.007). Esophageal ulcers were also more common in oral opium users (30%) than non-users (8%) with UGIB (P-value = 0.01). Nevertheless, the location of the ulcers between the two groups generally was not statistically different. CONCLUSIONS: This study has demonstrated that multiple, large peptic ulcers in GIB are potential complications of oral opium use. This could aid the needed modifications in the treatment protocol for these patients.

Longitudinal trend of urolithiasis incidence rates among world countries during past decades.

INTRODUCTION: This study explores the trend of urolithiasis in various countries and categorizes the countries in terms of how their urolithiasis incidence rate has changed over time. METHODS: The incidence rate of urolithiasis in 204 countries from 1990 to 2019, extracted from the Global Burden of Disease study, has been analyzed. RESULTS: According to the results, all regions had experienced an increasing trend in urolithiasis rate, except for Eastern Europe, Central Europe, and Southeast Asia regions (decreasing rates of -71.4, -56.2, and -9.2 per 100000, respectively). Moreover, the Caribbean region had the highest increasing trend of urolithiasis rates, and Central Asia was in the next rank (increasing rate of 48.3 and 34.3 per 100,000, respectively, p-value < .05). Also, African regions revealed significant increasing trends over time (p-value < 0.05). The outstanding findings in cluster analysis showed that Afghanistan, Andorra, and Comoros had the most decreasing trend in urolithiasis rates over time (decreasing rate of -128.2 per 100000, p-value < .001). Cuba, Cyprus, Czechia, the Democratic People's Republic of Korea, Denmark, and Djibouti were in the next rank in terms of decreasing rate (decreasing rate of -92.3 per 100000, p-value < .001). In addition, urolithiasis rates in Congo, Eswatini, Gabon, and Grenada have the most increasing trend (increasing rate of 116.1 per 100000, p-value < .001). CONCLUSION: The trend of urolithiasis rates was significantly increased in most countries, and Congo, Eswatini, Gabon, and Grenada had the highest trend among others. Also, Afghanistan, Andorra, and Comoros revealed the most decreasing rates, and the trend has dropped remarkably in several other countries.

Associations and predictive performance of 11 anthropometric measures with incident type 2 diabetes: A prospective cohort study from the UK Biobank.

OBJECTIVE: The study aim was to investigate associations of 11 anthropometric measures with incident type 2 diabetes and compare their predictive performance. METHODS: This prospective cohort study included 161,127 White European UK Biobank participants who were free of diabetes at baseline. Anthropometric measures included height, weight, BMI, A Body Shape Index, waist circumference, waist to hip ratio, waist to height ratio (WHtR), hip circumference, visceral adiposity index, hip index, and anthropometric risk index. The associations were examined using Cox proportional hazard models. The differences in C-index were used to compare predictive performance between BMI and other anthropometric measures. RESULTS: The median follow-up was 10.0 (interquartile range: 9.3-10.8) years, during which 6315 participants developed type 2 diabetes. All markers except height and hip index were positively associated with incident type 2 diabetes. The strongest associations were found for WHtR (hazard ratio per 1-SD increment: 2.27 [95% CI 2.19-2.35] in women; 1.96 [95% CI 1.90-2.01] in men). Compared with BMI, WHtR and anthropometric risk index had significantly better type 2 diabetes risk discrimination. CONCLUSIONS: Although most adiposity markers were associated with type 2 diabetes, the magnitude of the associations differed. WHtR had the strongest associations and predictive ability for type 2 diabetes and thus could be a more suitable marker for clinical use.

Lifestyle and occupational risks assessment of bladder cancer using machine learning-based prediction models.

BACKGROUND: Bladder cancer, one of the most prevalent cancers globally, can be regarded as considerable morbidity and mortality for patients. The bladder is an organ that comes in constant exposure to the environment and other risk factors such as inflammation. AIMS: In the current study, we used machine learning (ML) methods and developed risk prediction models for bladder cancer. METHODS: This population-based case-control study is focused on 692 cases of bladder cancer and 692 healthy people. The ML, including Neural Network (NN), Random Forest (RF), Decision Tree (DT), Naive Bayes (NB), Gradient Boosting (GB), and Logistic Regression (LR), were applied, and the model performance was evaluated. RESULTS: The RF (AUC = .86, precision = 79%) had the best performance, and the RT (AUC = .78, precision = 73%) was in the next rank. Based on variable importance analysis in RF, recurrent infection, bladder stone history, neurogenic bladder, smoking and opium use, chronic renal failure, spinal cord paralysis, analgesic, family history of bladder cancer, diabetic mellitus, low dietary intake of fruit and vegetable, high dietary intake of ham, sausage, can and pickles were respectively the most important factors, which effect on the probability of bladder cancer. CONCLUSION: Machine learning approaches can predict the probability of bladder cancer according to medical history, occupational risk factors, and dietary and demographical characteristics.

Predicting the COVID-19 Patients Status Using Chest CT Scan Findings: A Risk Assessment Model Based on Decision Tree Analysis.

BACKGROUND: The role of chest computed tomography (CT) to diagnose coronavirus disease 2019 (COVID-19) is still an open field to be explored. The aim of this study was to apply the decision tree (DT) model to predict critical or non-critical status of patients infected with COVID-19 based on available information on non-contrast CT scans. METHODS: This retrospective study was performed on patients with COVID-19 who underwent chest CT scans. Medical records of 1078 patients with COVID-19 were evaluated. The classification and regression tree (CART) of decision tree model and k-fold cross-validation were used to predict the status of patients using sensitivity, specificity, and area under the curve (AUC) assessments. RESULTS: The subjects comprised of 169 critical cases and 909 non-critical cases. The bilateral distribution and multifocal lung involvement were 165 (97.6%) and 766 (84.3%) in critical patients, respectively. According to the DT model, total opacity score, age, lesion types, and gender were statistically significant predictors for critical outcomes. Moreover, the results showed that the accuracy, sensitivity and specificity of the DT model were 93.3%, 72.8%, and 97.1%, respectively. CONCLUSIONS: The presented algorithm demonstrates the factors affecting health conditions in COVID-19 disease patients. This model has the potential characteristics for clinical applications and can identify high-risk subpopulations that need specific prevention. Further developments including integration of blood biomarkers are underway to increase the performance of the model.

Effect of Dapagliflozin on Total Heart Failure Events in Patients With Heart Failure With Mildly Reduced or Preserved Ejection Fraction: A Prespecified Analysis of the DELIVER Trial.

Importance: In the Dapagliflozin Evaluation to Improve the Lives of Patients With Preserved Ejection Fraction Heart Failure (DELIVER) trial, dapagliflozin reduced the risk of time to first worsening heart failure (HF) event or cardiovascular death in patients with HF with mildly reduced or preserved ejection fraction (EF). Objective: To evaluate the effect of dapagliflozin on total (ie, first and recurrent) HF events and cardiovascular death in this population. Design, Setting, and Participants: In this prespecified analysis of the DELIVER trial, the proportional rates approach of Lin, Wei, Yang, and Ying (LWYY) and a joint frailty model were used to examine the effect of dapagliflozin on total HF events and cardiovascular death. Several subgroups were examined to test for heterogeneity in the effect of dapagliflozin, including left ventricular EF. Participants were enrolled from August 2018 to December 2020, and data were analyzed from August to October 2022. Interventions: Dapagliflozin, 10 mg, once daily or matching placebo. Main Outcomes and Measures: The outcome was total episodes of worsening HF (hospitalization for HF or urgent HF visit requiring intravenous HF therapies) and cardiovascular death. Results: Of 6263 included patients, 2747 (43.9%) were women, and the mean (SD) age was 71.7 (9.6) years. There were 1057 HF events and cardiovascular deaths in the placebo group compared with 815 in the dapagliflozin group. Patients with more HF events had features of more severe HF, such as higher N-terminal pro-B-type natriuretic peptide level, worse kidney function, more prior HF hospitalizations, and longer duration of HF, although EF was similar to those with no HF events. In the LWYY model, the rate ratio for total HF events and cardiovascular death for dapagliflozin compared with placebo was 0.77 (95% CI, 0.67-0.89; P < .001) compared with a hazard ratio of 0.82 (95% CI, 0.73-0.92; P < .001) in a traditional time to first event analysis. In the joint frailty model, the rate ratio was 0.72 (95% CI, 0.65-0.81; P < .001) for total HF events and 0.87 (95% CI, 0.72-1.05; P = .14) for cardiovascular death. The results were similar for total HF hospitalizations (without urgent HF visits) and cardiovascular death and in all subgroups, including those defined by EF. Conclusions and Relevance: In the DELIVER trial, dapagliflozin reduced the rate of total HF events (first and subsequent HF hospitalizations and urgent HF visits) and cardiovascular death regardless of patient characteristics, including EF. Trial Registration: ClinicalTrials.gov Identifier: NCT03619213.

The frequency of fatty liver in patients with alopecia areata: A case-control study.

BACKGROUND: Alopecia areata (AA) is an immune-mediated nonscarring hair loss disorder with multiple subtypes, including alopecia universalis (AU). Previous studies have shown a link between serum lipid profile and alopecia. We aimed to investigate the frequency of fatty liver in patients with AU and patchy alopecia areata (PAA) compared to a control group. METHODS: This case-control study included patients with AU and PAA referred to a dermatology clinic from September 23, 2019 to September 23, 2020. A group of individuals without hair loss disorders attending the same clinic were selected as controls. Participants' general information, including age, sex, weight, height, and waist circumference (WC), was recorded. Body mass index (BMI) was calculated for all participants. Also, hyperlipidemia and statin use were noted and liver enzymes were evaluated. For AU and PAA patients, disease duration and the Severity of Alopecia Tool (SALT) score were also recorded. Then, all subjects underwent ultrasound to assess fatty liver and its grade. RESULTS: Overall, 32 patients were included in each group. All three groups were comparable in age, sex, weight, height, BMI, WC, hyperlipidemia, abnormal liver enzymes, and statin use. Disease duration and SALT score were significantly higher in the AU than in the PAA group (p = 0.009 and p < 0.001, respectively). The frequency of fatty liver was the highest in AU patients (40.6%), followed by 34.4% in PAA patients, and 21.9% in controls (p = 0.263). This was also the case for grade-1 fatty liver, while grade-2 was more common in PAA patients, and grade-3 was only observed in one patient from the AU group (p = 0.496). CONCLUSIONS: Fatty liver was more frequent in AU and PAA patients than controls, without statistically significant differences. There might be an association between fatty liver and AA, particularly the AU subtype.

Predicting metastasis in gastric cancer patients: machine learning-based approaches.

Gastric cancer (GC), with a 5-year survival rate of less than 40%, is known as the fourth principal reason of cancer-related mortality over the world. This study aims to develop predictive models using different machine learning (ML) classifiers based on both demographic and clinical variables to predict metastasis status of patients with GC. The data applied in this study including 733 of GC patients, divided into a train and test groups at a ratio of 8:2, diagnosed at Taleghani tertiary hospital. In order to predict metastasis in GC, ML-based algorithms, including Naive Bayes (NB), Random Forest (RF), Support Vector Machine (SVM), Neural Network (NN), Decision Tree (RT) and Logistic Regression (LR), with 5-fold cross validation were performed. To assess the model performance, F1 score, precision, sensitivity, specificity, area under the curve (AUC) of receiver operating characteristic (ROC) curve and precision-recall AUC (PR-AUC) were obtained. 262 (36%) experienced metastasis among 733 patients with GC. Although all models have optimal performance, the indices of SVM model seems to be more appropiate (training set: AUC: 0.94, Sensitivity: 0.94; testing set: AUC: 0.85, Sensitivity: 0.92). Then, NN has the higher AUC among ML approaches (training set: AUC: 0.98; testing set: AUC: 0.86). The RF of ML-based models, which determine size of tumor and age as two essential variables, is considered as the third efficient model, because of higher specificity and AUC (84% and 87%). Based on the demographic and clinical characteristics, ML approaches can predict the metastasis status in GC patients. According to AUC, sensitivity and specificity in both SVM and NN can be regarded as better algorithms among 6 applied ML-based methods.

Association between walking pace and incident type 2 diabetes by adiposity level: A prospective cohort study from the UK Biobank.

AIMS: To investigate the combined association of adiposity and walking pace with incident type 2 diabetes. METHODS: We undertook a prospective cohort study in 194 304 White-European participants (mean age 56.5 years, 55.9% women). Participants' walking pace was self-reported as brisk, average or slow. Adiposity measures included body mass index (BMI), waist circumference (WC) and body fat percentage (BF%). Associations were investigated using Cox proportional hazard models, with a 2-year landmark analysis. A four-way decomposition analysis was used for mediation and additive interaction. RESULTS: The median (interquartile range) follow-up was 5.4 (4.8-6.3) years. During the follow-up period, 4564 participants developed type 2 diabetes. Compared to brisk-walking participants with normal BMI, those with obesity who walked briskly were at an approximately 10- to 12-fold higher risk of type 2 diabetes (hazard ratio [HR] 9.64, 95% confidence interval [CI] 7.24-12.84, in women; HR 11.91, 95% CI 8.80-16.12, in men), whereas those with obesity and walked slowly had an approximately 12- to 15-fold higher risk (HR 12.68, 95% CI 9.62-16.71, in women; HR 15.41, 95% CI 11.27-21.06, in men). There was evidence of an additive interaction between WC and BF% and walking pace among women, explaining 17.8% and 47.9% excess risk respectively. Obesity mediated the association in women and men, accounting for 60.1% and 44.9%, respectively. CONCLUSIONS: Slow walking pace is a risk factor for type 2 diabetes independent of adiposity. Promoting brisk walking as well as weight management might be an effective type 2 diabetes prevention strategy given their synergistic effects.

Epigenetic regulation of gastrointestinal cancers mediated by long non-coding RNAs.

Long noncoding RNAs (lncRNAs), as well-known modulator of the epigenetic processes, have been shown to contribute to normal cellular physiological and pathological conditions such as cancer. Through the interaction with epigenetic regulators, an aberrant regulation of gene expression can be resulted due to their dysregulation, which in turn, can be involved in tumorigenesis. In the present study, we reviewed the lncRNAs' function and mechanisms that contributed to aberrant epigenetic regulation, which is directly related to gastrointestinal cancer (GI) development and progression. Findings indicated that epigenetic alterations may involve in tumorigenesis and are valuable biomarkers in case of diagnosing, assessing of risk factors, and predicting of GI cancers. This review summarized the accumulated evidence for biological and clinical application to use lncRNAs in GI cancers, including colorectal, gastric, oral, liver, pancreatic and oesophageal cancer.

Neoantigens and their clinical applications in human gastrointestinal cancers.

BACKGROUND: Tumor-specific neoantigens are ideal targets for cancer immunotherapy. As research findings have proved, neoantigen-specific T cell activity is immunotherapy's most important determinant. MAIN TEXT: There is sufficient evidence showing the role of neoantigens in clinically successful immunotherapy, providing a justification for targeting. Because of the significance of the pre-existing anti-tumor immune response for the immune checkpoint inhibitor, it is believed that personalized neoantigen-based therapy may be an imperative approach for cancer therapy. Thus, intensive attention is given to strategies targeting neoantigens for the significant impact with other immunotherapies, such as the immune checkpoint inhibitor. Today, several algorithms are designed and optimized based on Next-Generation Sequencing and public databases, including dbPepNeo, TANTIGEN 2.0, Cancer Antigenic Peptide Database, NEPdb, and CEDAR databases for predicting neoantigens in silico that stimulates the development of T cell therapies, cancer vaccine, and other ongoing immunotherapy approaches. CONCLUSIONS: In this review, we deliberated the current developments in understanding and recognition of the immunogenicity of newly found gastrointestinal neoantigens as well as their functions in immunotherapies and cancer detection. We also described how neoantigens are being developed and how they might be used in the treatment of GI malignancies.

Predicting stroke in heart failure and reduced ejection fraction without atrial fibrillation.

AIMS: Patients with heart failure with reduced ejection fraction (HFrEF) are at significant risk of stroke. Anticoagulation reduces this risk in patients with and without atrial fibrillation (AF), but the risk-to-benefit balance in the latter group, overall, is not favourable. Identification of patients with HFrEF, without AF, at the highest risk of stroke may allow targeted and safer use of prophylactic anticoagulant therapy. METHODS AND RESULTS: In a pooled patient-level cohort of the PARADIGM-HF, ATMOSPHERE, and DAPA-HF trials, a previously derived simple risk model for stroke, consisting of three variables (history of prior stroke, insulin-treated diabetes, and plasma N-terminal pro-B-type natriuretic peptide level), was validated. Of the 20 159 patients included, 12 751 patients did not have AF at baseline. Among patients without AF, 346 (2.7%) experienced a stroke over a median follow up of 2.0 years (rate 11.7 per 1000 patient-years). The risk for stroke increased with increasing risk score: fourth quintile hazard ratio (HR) 2.35 [95% confidence interval (CI) 1.60-3.45]; fifth quintile HR 3.73 (95% CI 2.58-5.38), with the first quintile as reference. For patients in the top quintile, the rate of stroke was 21.2 per 1000 patient-years, similar to participants with AF not receiving anticoagulation (20.1 per 1000 patient-years). Model discrimination was good with a C-index of 0.84 (0.75-0.91). CONCLUSION: It is possible to identify a subset of HFrEF patients without AF with a stroke-risk equivalent to that of patients with AF who are not anticoagulated. In these patients, the risk-to-benefit balance might justify the use of prophylactic anticoagulation, but this hypothesis needs to be tested prospectively.