Negative Emotions Are Associated With Older Self-perceived Age: A Cross-section Study From the UK Biobank.

BACKGROUND: Prior research has indicated a potential connection between psychological stress and how individuals perceive their own age. Building on this foundation, the current study explores the relationship between negative emotions and self-perceived age. METHODS: We conducted a cross-sectional analysis using data from the UK Biobank, a comprehensive cohort study representing the UK population. The analysis included 347 892 participants, aged between 39 and 73 years, of which 184 765 were women, accounting for 53.1% of the sample. Participants were categorized into three groups based on their self-perceived age: feeling younger than their chronological age (group Younger), feeling older than their chronological age (group Older), and feeling as old as their actual age (group Same). To investigate the relationship between negative emotions and self-perceived age, we utilized a multinomial logistic regression model with the Younger group serving as the reference category. RESULTS: Of 347 892 participants, after adjusted for covariates, the results showed that participants with irritability, nervous feelings, worrier/anxious feelings or fed-up feelings, worry too long and loneliness/isolation are more likely to be rated as "about your age" or "older than you are," with "younger than you are" as the reference group, indicating that negative emotions may influence one's self-perceived age. Among those negative emotions, irritability has the most significant impact self-perceived age, with the odds ratios (ORs) being 1.44 (95% CI: 1.35-1.54) and 1.11 (95% CI: 1.09-1.14). CONCLUSION: Negative emotions are associated with older self-perceived age, and irritability has the greatest impact. Further studies analyzing self-perceived age are needed to take psychological factors into consideration.

Modelling the rapid detection of Carbapenemase-resistant Klebsiella pneumoniae based on machine learning and matrix-assisted laser desorption/ionization time-of-flight mass spectrometry.

In this study, 80 carbapenem-resistant Klebsiella pneumoniae (CR-KP) and 160 carbapenem-susceptible Klebsiella pneumoniae (CS-KP) strains detected in the clinic were selected and their matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) peaks were collected. K-means clustering was performed on the MS peak data to obtain the best "feature peaks", and four different machine learning models were built to compare the area under the ROC curve, specificity, sensitivity, test set score, and ten-fold cross-validation score of the models. By adjusting the model parameters, the test efficacy of the model is increased on the basis of reducing model overfitting. The area under the ROC curve of the Random Forest, Support Vector Machine, Logistic Regression, and Xgboost models used in this study are 0.99, 0.97, 0.96, and 0.97, respectively; the model scores on the test set are 0.94, 0.91, 0.90, and 0.93, respectively; and the results of the ten-fold cross-validation are 0.84, 0.81, 0.81, and 0.85, respectively. Based on the machine learning algorithms and MALDI-TOF MS assay data can realize rapid detection of CR-KP, shorten the in-laboratory reporting time, and provide fast and reliable identification results of CR-KP and CS-KP.

Random forests for the analysis of matched case-control studies.

BACKGROUND: Conditional logistic regression trees have been proposed as a flexible alternative to the standard method of conditional logistic regression for the analysis of matched case-control studies. While they allow to avoid the strict assumption of linearity and automatically incorporate interactions, conditional logistic regression trees may suffer from a relatively high variability. Further machine learning methods for the analysis of matched case-control studies are missing because conventional machine learning methods cannot handle the matched structure of the data. RESULTS: A random forest method for the analysis of matched case-control studies based on conditional logistic regression trees is proposed, which overcomes the issue of high variability. It provides an accurate estimation of exposure effects while being more flexible in the functional form of covariate effects. The efficacy of the method is illustrated in a simulation study and within an application to real-world data from a matched case-control study on the effect of regular participation in cervical cancer screening on the development of cervical cancer. CONCLUSIONS: The proposed random forest method is a promising add-on to the toolbox for the analysis of matched case-control studies and addresses the need for machine-learning methods in this field. It provides a more flexible approach compared to the standard method of conditional logistic regression, but also compared to conditional logistic regression trees. It allows for non-linearity and the automatic inclusion of interaction effects and is suitable both for exploratory and explanatory analyses.

Resolving autism spectrum disorder (ASD) through brain topologies using fMRI dataset with multi-layer perceptron (MLP).

Autism is a neurodevelopmental disorder that manifests in individuals during childhood and has enduring consequences for their social interactions and communication. The prediction of Autism Spectrum Disorder (ASD) in individuals based on the differences in brain networks and activities have been studied extensively in the recent past, however, with lower accuracies. Therefore in this research, identification at the early stage through computer-aided algorithms to differentiate between ASD and TD patients is proposed. In order to identify features, a Multi-Layer Perceptron (MLP) model is developed which utilizes logistic regression on characteristics extracted from connectivity matrices of subjects derived from fMRI images. The features that significantly contribute to the classification of individuals as having Autism Spectrum Disorder (ASD) or typically developing (TD) are identified by the logistic regression model. To enhance emphasis on essential attributes, an AND operation is integrated. This involves selecting features demonstrating statistical significance across diverse logistic regression analyses conducted on various random distributions. The iterative approach contributes to a comprehensive understanding of relevant features for accurate classification. By implementing this methodology, the estimation of feature importance became more dependable, and the potential for overfitting is moderated through the evaluation of model performance on various subsets of data. It is observed from the experimentation that the highly correlated Left Lateral Occipital Cortex and Right Lateral Occipital Cortex ROIs are only found in ASD. Also, it is noticed that the highly correlated Left Cerebellum Tonsil and Right Cerebellum Tonsil are only found in TD participants. Among the MLP classifier, a recall of 82.61 % is achieved followed by Logistic Regression with an accuracy of 72.46 %. MLP also stands out with a commendable accuracy of 83.57 % and AUC of 0.978.

Establishment of a nomogram model for predicting therapy complications in patients with polycythemia and deep venous thrombosis.

BACKGROUND: Patients with deep venous thrombosis (DVT) residing at high altitudes can only rely on anticoagulation therapy, missing the optimal window for surgery or thrombolysis. Concurrently, under these conditions, patient outcomes can be easily complicated by high-altitude polycythemia (HAPC), which increases the difficulty of treatment and the risk of recurrent thrombosis. To prevent reaching this point, effective screening and targeted interventions are crucial. Thus, this study analyzes and provides a reference for the clinical prediction of thrombosis recurrence in patients with lower-extremity DVT combined with HAPC. AIM: To apply the nomogram model in the evaluation of complications in patients with HAPC and DVT who underwent anticoagulation therapy. METHODS: A total of 123 patients with HAPC complicated by lower-extremity DVT were followed up for 6-12 months and divided into recurrence and non-recurrence groups according to whether they experienced recurrence of lower-extremity DVT. Clinical data and laboratory indices were compared between the groups to determine the influencing factors of thrombosis recurrence in patients with lower-extremity DVT and HAPC. This study aimed to establish and verify the value of a nomogram model for predicting the risk of thrombus recurrence. RESULTS: Logistic regression analysis showed that age, immobilization during follow-up, medication compliance, compliance with wearing elastic stockings, and peripheral blood D-dimer and fibrin degradation product levels were indepen-dent risk factors for thrombosis recurrence in patients with HAPC complicated by DVT. A Hosmer-Lemeshow goodness-of-fit test demonstrated that the nomogram model established based on the results of multivariate logistic regression analysis was effective in predicting the risk of thrombosis recurrence in patients with lower-extremity DVT complicated by HAPC (χ 2 = 0.873; P > 0.05). The consistency index of the model was 0.802 (95%CI: 0.799-0.997), indicating its good accuracy and discrimination. CONCLUSION: The column chart model for the personalized prediction of thrombotic recurrence risk has good application value in predicting thrombotic recurrence in patients with lower-limb DVT combined with HAPC after discharge.

Tutorial on Firth's Logistic Regression Models for Biomarkers in Preclinical Space.

Preclinical studies are broad and can encompass cellular research, animal trials, and small human trials. Preclinical studies tend to be exploratory and have smaller datasets that often consist of biomarker data. Logistic regression is typically the model of choice for modeling a binary outcome with explanatory variables such as genetic, imaging, and clinical data. Small preclinical studies can have challenging data that may include a complete separation or quasi-complete separation issue that will result in logistic regression inflated coefficient estimates and standard errors. Penalized regression approaches such as Firth's logistic regression are a solution to reduce the bias in the estimates. In this tutorial, a number of examples with separation (complete or quasi-complete) are illustrated and the results from both logistic regression and Firth's logistic regression are compared to demonstrate the inflated estimates from the standard logistic regression model and bias-reduction of the estimates from the penalized Firth's approach. R code and datasets are provided in the supplement.

Factors Associated with Patient Engagement in a Health and Social Needs Case Management Program.

INTRODUCTION: Many patients offered case management services to address their health and social needs choose not to engage. Factors that drive engagement remain unclear. We sought to understand patient characteristics associated with engagement in a social needs case management program and variability by case manager. METHODS: Between August 2017 and February 2021, 43,347 Medicaid beneficiaries with an elevated risk of hospital or emergency department use were offered case management in Contra Costa County, California. Results were analyzed in 2022 using descriptive statistics and multilevel logistic regression models to examine 1) associations between patient engagement and patient characteristics and 2) variation in engagement attributable to case managers. Engagement was defined as responding to case manager outreach and documentation of at least 1 topic to mutually address. A sensitivity analysis was performed by stratifying the pre-COVID-19 and COVID-19 cohorts. RESULTS: A total of 16,811 (39%) of eligible patients engaged. Adjusted analyses indicate associations between higher patient engagement and female gender, age 40 and over, Black/African American race, Hispanic/Latino ethnicity, history of homelessness, and a medical history of certain chronic conditions and depressive disorder. The intraclass correlation coefficient indicates that 6% of the variation in engagement was explained at the case manager level. CONCLUSIONS: Medicaid patients with a history of housing instability and specific medical conditions were more likely to enroll in case management services, consistent with prior evidence that patients with greater need are more receptive to assistance. Case managers accounted for a small percentage of variation in patient engagement.

Establishment of a diagnostic model for urinary calculi in pregnant women: A retrospective cohort study.

OBJECTIVE: The diagnosis of symptomatic urinary stones during pregnancy is challenging; ultrasonography has a low specificity and sensitivity for diagnosing urinary stones. This study aimed to develop a clinical diagnostic model to assist clinicians in distinguishing symptomatic urinary stones in pregnant women. METHODS: In this retrospective cohort study, we consecutively collected clinical data from pregnant women who presented with acute abdominal, lumbar, and lumbar and abdominal pain at the emergency department of our hospital between January 1, 2017, and December 31, 2019. To distinguish patients with urinary calculi from those without, we reviewed the follow-up records within 2 weeks post-consultation, ultrasonography results within 2 weeks, or self-reports of stone passage within 2 weeks. We selected risk factors from the baseline clinical and laboratory data of patients to establish a diagnostic model. RESULTS: Of the total patients included in the study, 105 patients were diagnosed as having symptomatic urinary stones and 126 were determined to have abdominal pain for reasons other than urinary stones. The initial model had an area under the curve (AUC) of 0.9966. The No-Lab Model had an AUC of 0.9856. The Lab Model had an AUC of 0.832. The Stone Model had an AUC of 0.9952. The simplified Stone Model did not show a decrease in discriminative ability. CONCLUSION: Of the four diagnostic models that we established for preliminary diagnosis of symptomatic urinary tract stones in pregnant women, the simplified Stone Model demonstrated excellent performance. Users can scan quick response codes to access web-based diagnostic model interfaces, facilitating easy clinical operation.

Risk Factors of Alcohol Use Disorders Among Inpatients with Schizophrenia: An Institutional-Based Cross-sectional Survey.

Objective: This study aimed to elucidate the risk factors associated with alcohol use disorders (AUDs) among inpatients with schizophrenia at a specialized mental hospital in Baoding city, China. Methods: This cross-sectional survey comprised 301 comorbid patients. Three binary logistic regression models were used to investigate the factors linked to AUDs in patients with schizophrenia. Propensity score matching analysis was conducted to validate inconsistent variables identified by the regression models. Results: Significant differences were observed between the comorbid and non-comorbid groups concerning sex (P < .001), disposition (P = .049), smoking habits (P < .001), place of residence (P = .010), family relationships (P = .002), family history of mental disorders (P = .008), history of alcoholism (P = .003), onset latency (P = .005), impulsivity (P < .001), suicide or self-injury history (P < .001), and obvious aggressive behavior (P < .001) in univariate analyses. The area under the curve values for the three regression models were 0.83 (P < .001), 0.80 (P < .001), and 0.81 (P < .001), respectively. Binary logistic regression and propensity score matching analyses indicated that introverted disposition, smoking, acute onset, impulsivity, and suicide or self-injury history were independent risk factors associated with AUDs in inpatients with schizophrenia with an odds ratio of > 1. Conclusion: Introverted disposition, smoking, acute onset, impulsivity, and suicide or self-injury history were independently associated with the AUDs in inpatients with schizophrenia. Future studies should prioritize longitudinal studies to discern the evolving dynamics of potential confounding risk factors.

Association between dietary retinol intake and rheumatoid arthritis based on NHANES database.

OBJECTIVE: This study focused on the investigation of the correlation between dietary retinol intake and rheumatoid arthritis (RA) using the National Health and Nutrition Examination Survey (NHANES) database. METHODS: Data from five NHANES cycles from 2003 to 2012 were utilized for this study. Dietary retinol intake was considered as the independent variable, and RA was the dependent variable. A weighted logistic regression method was applied to construct the relational model of the two variables. Stratified analysis without adjusting for confounding factors and subgroup analysis with confounding factors adjusted were conducted to explore the association between dietary retinol intake and RA. The optimal intake of dietary retinol was determined by the restricted cubic splines (RCS) analysis. RESULTS: 22,971 samples were included in this study. The weighted logistic regression model was employed to construct the relational model of dietary retinol intake and RA (OR: 0.95, 95% CI: 0.91-0.99, p = 0.019). Stratified analysis displayed a great influence on the relational model exerted by the interaction between gender and retinol intake (p for interaction = 0.014). A significant association between retinol intake and RA was also indicated in the model adjusted for demographic characteristics (OR: 0.95, 95% CI: 0.90-1.00, p = 0.029). Subgroup analysis by gender showed that in the female population, unadjusted model (OR: 0.90, 95% CI: 0.84-0.96, p = 0.002), model adjusted for demographic characteristics only (OR: 0.89, 95% CI: 0.83-0.96, p = 0.002), and model adjusted for all confounding factors (OR: 0.91, 95% CI: 0.85-0.99, p = 0.019) indicated dietary retinol intake as a protective factor against RA. RCS analysis demonstrated that in the female population, regardless of the model used (Crude, Model I, and Model II), an intake of dietary retinol > 354.86 mcg was associated with RA disease reduction (OR < 1.0, p-non-linear < 0.05, p-overall < 0.05). CONCLUSION: Increased dietary retinol intake was associated with RA disease reduction, particularly in the female population. Women are recommended to increase their dietary retinol intake (> 354.86 mcg) to reduce the risk of RA.

Determinants of active trachoma among rural children aged 1-9 years old in Aw-Bare Wereda, Somali Region of Ethiopia: a cross-sectional study.

INTRODUCTION: Chronic and highly contagious, trachoma is a condition characterized by recurrent bacterial infection with ocular strains of Mycoplasma trachoma. It spreads through fingers, flies, and fomites, especially in situations where there is overcrowding. If untreated, the illness may result in blindness. Trachoma is an ancient disease and has previously been a significant public health problem in many areas of the world, including parts of Europe and North America. There are at least 400 million cases of active trachoma in the world, 8 million of which have resulted in blindness. Trachoma is a serious public health issue that is very common in Ethiopia. Therefore, the objective of this study is to identify the determinants of active trachoma among rural children aged 1-9 years old in Aw-bare woreda, Somali region of Ethiopia. METHOD: A cross-sectional community-based study involving children aged 1-9 who lived in six selected rural kebeles in the Awbare woreda Somali region and carried out using an ordinal logistic regression model. The study comprised 377 children in total. Our sample youngsters were chosen through a two-stage cluster sampling procedure. Then also chose our sample kebeles by simple random sampling. The main environmental, personal, and demographic factors that influenced the outcomes of active trachoma status were modeled using partial proportional odds modeling and descriptive statistics. RESULT: The study showed that the prevalence of active trachoma was found to be 47.7%. The covariate secondary level of education of mother OR = 1.357; 95% CI (1.051, 1.75), P-value = 0.0192, Inside house cooking place of children family OR = 0.789:95% CI (0.687, 0.927), P-value = 0.0031, children stay at home OR = 2.203:95%CI (1.526, 3.473), P-value = 0.0057,rich income family OR = 1.335:95%CI(1.166,1.528),P-value = 0.0001,Amount of water fetched per day OR = 2.129,95%CI(1.780,2.547),P-Vaue = 0.0001 were significant effect on active trachoma. PPOM represents the best fit as it has the smallest AIC and BIC. It is also more parsimonious. CONCLUSION: The mother's educational level, the location where the children spent the majority of their time indoors cooking, the fly density during the interview, the family's income, the child's age in years, the distance to the water source, the quantity of water fetched daily, and the number of people sharing a room have all been found to be significant predictors of the child's active trachoma status. Thus, increasing maternal education, access to clean water, and socioeconomic position are all crucial measures in preventing trachoma. Preventing trachoma also involves reducing the number of kids in a room and enhancing activities linked to personal cleanliness, such as giving kids a thorough facial wash to remove debris and discharge from their eyes.

Association between ankle-brachial blood pressure index and erectile dysfunction in US adults: a large population-based cross-sectional study.

Background: Erectile dysfunction (ED) is a very common condition among adult men and its prevalence increases with age. The ankle-brachial blood pressure index (ABPI) is a noninvasive tool used to assess peripheral vascular disease (PAD) and vascular stiffness. However, the association between ABPI and ED is unclear. We aimed to explore the association between ABPI and ED in the US population. Methods: Our study used data from two separate National Health and Nutrition Examination Survey (NHANES) datasets (2001-2002 and 2003-2004). Survey-weighted logistic regression models were used to explore the association between ABPI as a continuous variable and quartiles with ED. We further assessed the association between ABPI and ED using restricted cubic regression while selecting ABPI thresholds using two-piecewise Cox regression models. In addition, we performed subgroup analyses stratified by BMI, race, marital status, diabetes, and hypertension. Main outcome measure: ABPI was calculated by dividing the mean systolic blood pressure at the ankle by the mean systolic blood pressure at the arm. Results: Finally, 2089 participants were enrolled in this study, including 750 (35.90%) ED patients and 1339 (64.10%) participants without ED. After adjusting for all confounding covariates, logistic regression analyses showed a significant association between ABPI and ED (OR=0.19; 95% CI, 0.06-0.56, P=0.01); with ABPI as a categorical variable, compared with the lowest quartile, the OR and 95% CI for the second quartile were 0.58 (0.34-0.97; P = 0.04).Besides, splines indicated that there was an L-shaped relationship between ABPI levels and the risk of ED. Piecewise Cox regression demonstrated the inflection point at 1.14, below which the OR for ED was 0.06 (0.02-0.20; P < 0.001), and above which the OR was 2.79 (0.17-4.53; P = 0.469). Conclusion: In our study, lower ABPI was independently associated with ED risk. In addition, the lowest ABPI level associated with ED risk was 1.14, below this level, lower ABPI was associated with higher ED risk.

Pitfalls of single-study external validation illustrated with a model predicting functional outcome after aneurysmal subarachnoid hemorrhage.

BACKGROUND: Prediction models are often externally validated with data from a single study or cohort. However, the interpretation of performance estimates obtained with single-study external validation is not as straightforward as assumed. We aimed to illustrate this by conducting a large number of external validations of a prediction model for functional outcome in subarachnoid hemorrhage (SAH) patients. METHODS: We used data from the Subarachnoid Hemorrhage International Trialists (SAHIT) data repository (n = 11,931, 14 studies) to refit the SAHIT model for predicting a dichotomous functional outcome (favorable versus unfavorable), with the (extended) Glasgow Outcome Scale or modified Rankin Scale score, at a minimum of three months after discharge. We performed leave-one-cluster-out cross-validation to mimic the process of multiple single-study external validations. Each study represented one cluster. In each of these validations, we assessed discrimination with Harrell's c-statistic and calibration with calibration plots, the intercepts, and the slopes. We used random effects meta-analysis to obtain the (reference) mean performance estimates and between-study heterogeneity (I2-statistic). The influence of case-mix variation on discriminative performance was assessed with the model-based c-statistic and we fitted a "membership model" to obtain a gross estimate of transportability. RESULTS: Across 14 single-study external validations, model performance was highly variable. The mean c-statistic was 0.74 (95%CI 0.70-0.78, range 0.52-0.84, I2 = 0.92), the mean intercept was -0.06 (95%CI -0.37-0.24, range -1.40-0.75, I2 = 0.97), and the mean slope was 0.96 (95%CI 0.78-1.13, range 0.53-1.31, I2 = 0.90). The decrease in discriminative performance was attributable to case-mix variation, between-study heterogeneity, or a combination of both. Incidentally, we observed poor generalizability or transportability of the model. CONCLUSIONS: We demonstrate two potential pitfalls in the interpretation of model performance with single-study external validation. With single-study external validation. (1) model performance is highly variable and depends on the choice of validation data and (2) no insight is provided into generalizability or transportability of the model that is needed to guide local implementation. As such, a single single-study external validation can easily be misinterpreted and lead to a false appreciation of the clinical prediction model. Cross-validation is better equipped to address these pitfalls.

Mild-moderate alcohol consumption and diabetes are associated with liver fibrosis in patients with biopsy-proven MASLD.

Background: It is unclear whether patients with metabolic dysfunction-associated steatotic liver disease (MASLD) are allowed variable low levels of alcohol. This study aimed to evaluate the effect of mild-moderate alcohol consumption on the biochemical and histological characteristics of patients with MASLD. Methods: Alcohol consumption was assessed in 713 patients with steatotic liver disease (SLD) who underwent liver biopsy. Non-drinking, mild-moderate drinking, and excessive drinking were defined as 0 g/day, 1-<20 g/day, and >20 g/day for women and 0 g/day, 1-<30 g/day, and >30 g/day for men, respectively. Liver biopsies were scored according to the NASH CRN system. Results: A total of 713 participants (median age 39.0 years and 77.1% male) with biopsy-proven SLD were enrolled, including 239 nondrinkers, 269 mild-moderate drinkers and 205 excessive drinkers. Excessive drinking was associated with increased risks for lobular inflammation and liver fibrosis compared to nondrinkers and mild-moderate drinkers. Compared with non-drinkers, mild-moderate drinkers had significantly lower odds for steatosis (OR = 0.60, 95% CI = 0.38-0.93, p = 0.025), hepatocellular ballooning (OR = 0.52, 95% CI = 0.29-0.91, p = 0.020) and fibrosis (OR = 0.50, 95% CI = 0.31-0.81, p = 0.005). However, in non-excessive drinkers with type 2 diabetes mellitus (T2DM), there was no association between mild-moderate alcohol consumption and liver fibrosis (OR = 0.562, 95% CI = 0.207-1.530, p = 0.257). Conclusions: Mild-moderate alcohol consumption might be protective against liver fibrosis in MASLD patients, which is modified by the presence of T2DM. However, further longitudinal studies are needed to determine the effect of ongoing alcohol consumption on disease severity.

Predictive value of D-dimer to albumin ratio for severe illness and mortality in patients with COVID-19.

Objective: Although the impact of the variants of COVID-19 on the general population is diminishing, there is still a certain mortality rate for severe and critically ill patients, especially for the elderly with comorbidities. The present study investigated whether the D-dimer to albumin ratio (DAR) can predict the severity of illness and mortality in COVID-19 patients. Methods: A total of 1,993 patients with COVID-19 were retrospectively reviewed and the association of DAR with severe or critical illness or death during hospitalization was analyzed. The area under the ROC curve was used to screen the best indicators, Chi-square test, rank sum test, and univariate and multivariate binary logistic regression analysis were used to calculate the mean value of difference and adjusted odds ratio (aORs) with their 95% CI, and finally, survival was analyzed using Kaplan-Meier (KM) curves. Results: Among 1,993 patients with COVID-19, 13.4% were severely ill, and the mortality rate was 2.3%. The area under the curve (AUC) using DAR to predict severe and critically ill patients was higher than that using other parameters. The best cut-off value of DAR was 21 in the ROC with a sensitivity of 83.1% and a specificity of 68.7%. After adjusting age, gender, comorbidities, and treatment, the binary logistic regression analysis showed that elevated DAR was an independent risk factor for severely ill and mortality of COVID-19 patients. The KM curve suggested that patients with a higher DAR was associated with worse survival. The negative predictive value of DAR (21) for adverse prognosis and death was 95.98 and 99.84%, respectively, with a sensitivity of 80.9 and 95.65%, respectively. Conclusion: The DAR may be an important predictor for severe illness and mortality in COVID-19 patients.

Comparison between Three Radiomics Models and Clinical Nomograms for Prediction of Lymph Node Involvement in PCa Patients Combining Clinical and Radiomic Features.

PURPOSE: We aim to compare the performance of three different radiomics models (logistic regression (LR), random forest (RF), and support vector machine (SVM)) and clinical nomograms (Briganti, MSKCC, Yale, and Roach) for predicting lymph node involvement (LNI) in prostate cancer (PCa) patients. MATERIALS AND METHODS: The retrospective study includes 95 patients who underwent mp-MRI and radical prostatectomy for PCa with pelvic lymphadenectomy. Imaging data (intensity in T2, DWI, ADC, and PIRADS), clinical data (age and pre-MRI PSA), histological data (Gleason score, TNM staging, histological type, capsule invasion, seminal vesicle invasion, and neurovascular bundle involvement), and clinical nomograms (Yale, Roach, MSKCC, and Briganti) were collected for each patient. Manual segmentation of the index lesions was performed for each patient using an open-source program (3D SLICER). Radiomic features were extracted for each segmentation using the Pyradiomics library for each sequence (T2, DWI, and ADC). The features were then selected and used to train and test three different radiomics models (LR, RF, and SVM) independently using ChatGPT software (v 4o). The coefficient value of each feature was calculated (significant value for coefficient ≥ ±0.5). The predictive performance of the radiomics models and clinical nomograms was assessed using accuracy and area under the curve (AUC) (significant value for p ≤ 0.05). Thus, the diagnostic accuracy between the radiomics and clinical models were compared. RESULTS: This study identified 343 features per patient (330 radiomics features and 13 clinical features). The most significant features were T2_nodulofirstordervariance and T2_nodulofirstorderkurtosis. The highest predictive performance was achieved by the RF model with DWI (accuracy 86%, AUC 0.89) and ADC (accuracy 89%, AUC 0.67). Clinical nomograms demonstrated satisfactory but lower predictive performance compared to the RF model in the DWI sequences. CONCLUSIONS: Among the prediction models developed using integrated data (radiomics and semantics), RF shows slightly higher diagnostic accuracy in terms of AUC compared to clinical nomograms in PCa lymph node involvement prediction.

Radio Signal Modulation Recognition Method Based on Hybrid Feature and Ensemble Learning: For Radar and Jamming Signals.

The detection performance of radar is significantly impaired by active jamming and mutual interference from other radars. This paper proposes a radio signal modulation recognition method to accurately recognize these signals, which helps in the jamming cancellation decisions. Based on the ensemble learning stacking algorithm improved by meta-feature enhancement, the proposed method adopts random forests, K-nearest neighbors, and Gaussian naive Bayes as the base-learners, with logistic regression serving as the meta-learner. It takes the multi-domain features of signals as input, which include time-domain features including fuzzy entropy, slope entropy, and Hjorth parameters; frequency-domain features, including spectral entropy; and fractal-domain features, including fractal dimension. The simulation experiment, including seven common signal types of radar and active jamming, was performed for the effectiveness validation and performance evaluation. Results proved the proposed method's performance superiority to other classification methods, as well as its ability to meet the requirements of low signal-to-noise ratio and few-shot learning.

Level of medication adherence and its determinants of cardiovascular disease patients attending at specialized teaching hospitals of Amhara regional state, Ethiopia: a multicenter cross-sectional study.

Background: Non-adherence to medication in patients with cardiovascular disease continues to be a main cause of suboptimal management, increased morbidity and mortality, and increased healthcare expenses. The present study assessed the level of medication adherence and its determinants of cardiovascular disease patients. Methods: An institutional-based multicenter cross-sectional study was conducted with patients with cardiovascular disease in Northwest Ethiopian teaching hospitals. The level of medication adherence was evaluated using a standardized questionnaire of the Adherence in Chronic Disease Scale (ACDS). To find determinants of the level of medication adherence, an ordinal logistic regression model was employed. Statistics were significant when P ≤ 0.05 at a 95% confidence interval (CI). Results: In the end, 336 participants were included in the research. According to this study, one-third of patients had low medication adherence, half had medium adherence, and one-fifth had high medication adherence. Elderly patients [adjusted odds ratio (AOR) = 2.691; 95% confidence interval (CI), 1.704-4.251; P < 0.000], marital status (AOR = 1.921; 95% CI, 1.214-3.039; P = 0.005), alcoholic patients (AOR = 2.782; 95% CI, 1.745-4.435; P < 0.000), Patients without physical activity (AOR = 1.987; 95% CI 1.251-3.156; P = 0.004), non health insurances (AOR = 1.593; 95% CI 1.003-2.529; P = 0.049), sever Charles comorbidity index (AOR = 2.486; 95% CI 1.103-5.604; P = 0.028), patients with polypharmacy (AOR = 2.998 (1.817-4.947) P < 0.000) and, manypolypharmacy (AOR = 3.031 (1.331-6.898) P = 0.008) were more likely to have low medication adherence. Conclusion: The current study concluded that one-third of study participants had low medication adherence. Older age, marital status, drinker, physical inactivity, drug source, comorbidity, and polypharmacy all contributed to the low level of medication adherence. To improve patients with cardiovascular disease's adherence to their medications, intervention is necessary.

Quantifying the long-term effects of measles infection - A retrospective cohort study.

OBJECTIVE: To assess whether measles infection has an impact on the rate of non-measles infectious diseases over an extended period. METHODS: This retrospective matched cohort study included 532 measles diagnosed patients which were exactly matched with 2,128 individuals with no previous measles diagnosis. Adjusted Odds ratio for any all - cause infectious diagnosis and any viral infection diagnosis, up to 2 years post measles diagnosis, between the measles and control groups was obtained from a conditional logistic regression model. Cox proportional hazards model was employed to estimate the hazard ratio. RESULTS: - Previous measles (MeV) exposure was associated with an increased risk for all-cause non-measles infectious disease diagnosis (OR = 1.83, 95% CI 1.26-2.64, p = 0.001), with 492 diagnoses in the MeV-exposed group and 1868 diagnoses in the control group. Additionally, previous MeV exposure was linked to a higher risk of viral infection diagnosis (OR = 1.23, 95% CI 1.01-1.59, p < 0.05), with 302 viral infection diagnoses in the MeV-exposed group and 1107 diagnoses in the control group. The hazard ratio for viral diagnosis in the MeV-exposed group compared to the control group was 1.54 (95% CI 1.18-2.02, p < 0.001). CONCLUSION: Individuals diagnosed with measles had a moderate increased risk of being diagnosed with all cause non-measles infectious disease or viral infection. This observational individual level study supports previous ecological and individual population level studies.

Prevalence of childhood hypertension and associated factors in Zhejiang Province: a cross-sectional analysis based on random forest model and logistic regression.

With childhood hypertension emerging as a global public health concern, understanding its associated factors is crucial. This study investigated the prevalence and associated factors of hypertension among Chinese children. This cross-sectional investigation was conducted in Pinghu, Zhejiang province, involving 2,373 children aged 8-14 years from 12 schools. Anthropometric measurements were taken by trained staff. Blood pressure (BP) was measured in three separate occasions, with an interval of at least two weeks. Childhood hypertension was defined as systolic blood pressure (SBP) and/or diastolic blood pressure (DBP) ≥ age-, sex-, and height-specific 95th percentile, across all three visits. A self-administered questionnaire was utilized to collect demographic, socioeconomic, health behavioral, and parental information at the first visit of BP measurement. Random forest (RF) and multivariable logistic regression model were used collectively to identify associated factors. Additionally, population attributable fractions (PAFs) were calculated. The prevalence of childhood hypertension was 5.0% (95% confidence interval [CI]: 4.1-5.9%). Children with body mass index (BMI) ≥ 85th percentile were grouped into abnormal weight, and those with waist circumference (WC) > 90th percentile were sorted into central obesity. Normal weight with central obesity (NWCO, adjusted odds ratio [aOR] = 5.04, 95% CI: 1.96-12.98), abnormal weight with no central obesity (AWNCO, aOR = 4.60, 95% CI: 2.57-8.21), and abnormal weight with central obesity (AWCO, aOR = 9.94, 95% CI: 6.06-16.32) were associated with an increased risk of childhood hypertension. Childhood hypertension was attributable to AWCO mostly (PAF: 0.64, 95% CI: 0.50-0.75), followed by AWNCO (PAF: 0.34, 95% CI: 0.19-0.51), and NWCO (PAF: 0.13, 95% CI: 0.03-0.30). Our results indicated that obesity phenotype is associated with childhood hypertension, and the role of weight management could serve as potential target for intervention.