High Discrimination Accuracy Research Articles

Diagnostic significance of ultrasound characteristics in discriminating follicular thyroid carcinoma from adenoma

BackgroundFollicular thyroid carcinoma (FTC) is the second most common cancer of the thyroid gland and has a greater propensity for haematogenous metastasis. However, the preoperative differentiation of FTC from follicular thyroid adenoma (FTA) is not well established. Certain ultrasound characteristics are associated with an increased risk of thyroid malignancy, but mainly for papillary thyroid cancers and not for FTC.ObjectivesThis retrospective study aimed to evaluate the ultrasound characteristics of FTC and the value of ultrasound characteristics in differentiating FTC from FTA.MethodsA total of 96 patients with pathologically confirmed FTC or FTA who underwent preoperative thyroid ultrasound were included in this study. The ultrasound and pathological characteristics were evaluated.ResultsOur data revealed that the incidences of lesions with tubercle-in-nodule, spiculated/microlobulated margins, mixed vascularization, egg-shell calcification, central stellate scarring, extension toward the capsule and chronic lymphocytic thyroiditis were significantly higher in the FTC group (all p < 0.05). After adjusting for confounding factors, lesions with mixed vascularization (odds ratio [OR]: 2.038, P = 0.019), central stellate scarring (OR: 87.992, P = 0.007), extension toward the capsule (OR: 22.587, P = 0.010), and chronic lymphocytic thyroiditis (OR: 9.195, P = 0.006) were independently associated with FTC. Furthermore, combined with chronic lymphocytic thyroiditis, mixed vascularization, central stellate scarring, and extension toward the capsule showed high discriminatory accuracy in predicting FTC (AUC: 0.914; sensitivity: 96.5%; specificity: 71.8%; p < 0.001).ConclusionsIn combination with chronic lymphocytic thyroiditis, mixed vascularization, central stellate scarring, and extension toward the capsule have greater accuracy in differentiating FTCs from FTAs.

Establishment and Validation of a Dynamic Nomogram for Persistent Organ Failure in Acute Biliary Pancreatitis: A Retrospective Study.

The objective of this study was to create a predictive model for the onset of persistent organ failure (POF) in individuals suffering from acute biliary pancreatitis (ABP) by utilizing indicators observed within 24hours of hospital admission. Early detection of high-risk POF patients is crucial for clinical decision-making. Clinical data and laboratory indicators within 24hours of admission from ABP patients diagnosed at The First Affiliated Hospital of Wenzhou Medical University between January 1, 2016, and January 1, 2024 were collected and retrospectively analyzed. The Least Absolute Shrinkage and Selection Operator (LASSO) regression and multivariate logistic regression (stepwise regression) methods were employed to identify variables for constructing the prediction model. The prediction model's performance was evaluated using the area under the curve (AUC), calibration curve, and decision curve analysis (DCA). It was compared with other scoring systems such as SIRS, BISAP, APACHE II, CTSI, and MCTSI. Additionally, a web-based calculator was created to simplify the calculation process. Out of 324 ABP patients, 25 developed POF. Initial screening identified 18 variables; through LASSO regression and multivariable logistic regression analysis, five variables including BMI, Hb, ALB, Ca, and LIP were determined as independent predictors of POF. According to these factors to build prediction model, draw the nomogram. The AUC's receiver operating characteristic curve analysis demonstrated a significantly higher value in comparison to other scoring systems. Calibration curve and DCA show that the established model to predict the accuracy of POF is higher, clinical decision of net benefit is also higher. A network calculator utilizing this predictive model was developed. A predictive model incorporating five risk indicators has been established exhibiting high discriminatory power and accuracy which aids in early identification of ABP patients at risk for developing POF. This holds significant value in guiding clinical decision-making.

Waiting for hip fracture surgery: Analysis of individual heterogeneity and discriminatory accuracy

Abstract Background Evaluation of healthcare inequality could be improved by considering (i) the intersection of socioeconomic axes of inequality, (ii) the existence of individual heterogeneity and (iii) criteria to quantify group differences and how those differences translate into recommendations for universal or targeted interventions. In this study we illustrate how to achieve these improvements. Methods We applied analysis of individual heterogeneity and discriminatory accuracy (AIHDA) to analyze data from the Swedish patient registry for the quality indicator hip fracture (HF) surgery within the same day. We analyzed 57,340 patients residing in Sweden during 2011-2014 and belonging to 36 socioeconomic strata defined by age, sex, income, and country of birth and the 21 Swedish regions. We calculated prevalences and 95% confidence intervals as well as the absolute number of cases. The benchmark was set to 80%. To quantify group differences, we evaluated the discriminatory accuracy (DA) using the area under the ROC curve (AUC). Results 68% (39,073/57,340) of the patients were operated in time. The prevalence across the 36 sociodemographic strata ranged from 51% (43-58%) to 81% (67-91%). However, the DA was low (AUC= 0.562) indicating very small group differences. About half of the operated HP (n = 20,287) occurs in 18/36 strata with the lowest prevalences of operations in time. The regions’ prevalences ranged from 37% (36-38%) to 88% (88-89%) with a rather high DA (AUC= 0.736) indicating larger differences. About half of the operated HP (n = 19,677) occurs in 12/21 regions with the lowest prevalence of operations in time. Conclusions The 80% benchmark was only achieved in one socioeconomic stratum and the group differences were very small. 6/21 regions achieved the benchmark and the group differences were large. Interventions aiming to reach the benchmark in the entire population should proportionately target regions and be universal and tailored to sociodemographic strata. Key messages • The AIHDA-framework improves evaluations of healthcare inequalities. • Both differences between group averages and the groups’ DA need be considered when planning healthcare interventions.

Fronto-Central Changes in Multiple Frequency Bands in Active Tactile Width Discrimination Task.

The neural basis of tactile processing in humans has been extensively studied; however, the neurophysiological basis of human width discrimination remains relatively unexplored. In particular, the changes that occur in neural networks underlying active tactile width discrimination learning have yet to be described. Here, it is hypothesized that subjects learning to perform the active version of the width discrimination task would present changes in behavioral data and in the neurophysiological activity, specifically in networks of electrodes relevant for tactile and motor processing. The specific hypotheses tested here were that the performance and response latency of subjects would change between the first and the second blocks; the power of the different frequency bands would change between the first and the second blocks; electrode F4 would encode task performance and response latency through changes in the power of the delta, theta, alpha, beta, and low-gamma frequency bands; the relative power in the alpha and beta frequency bands in electrodes C3 and C4 (Interhemispheric Spectral Difference-ISD) would change because of learning between the first and the second blocks. To test this hypothesis, we recorded and analyzed electroencephalographic (EEG) activity while subjects performed a session where they were tested twice (i.e., two different blocks) in an active tactile width discrimination task using their right index finger. Subjects (n = 18) presented high performances (high discrimination accuracy) already in their first block, and therefore no significant improvements were found in the second block. Meanwhile, a reduction in response latency was observed between the two blocks. EEG recordings revealed an increase in power for the low-gamma frequency band (30-45 Hz) for electrodes F3 and C3 from the first to the second block. This change was correlated with neither performance nor latency. Analysis of the neural activity in electrode F4 revealed that the beta frequency band encoded the subjects' performance. Meanwhile, the delta frequency band in the same electrode revealed a complex pattern where blocks appeared clustered in two different patterns: an Upper Pattern (UP), where power and latency were highly correlated (Rho = 0.950), and a sparser and more uncorrelated Lower Pattern (LP). Blocks belonging to the UP or LP patterns did not differ in performance and were not specific to the first or the second block. However, blocks belonging to the LP presented an increase in response latency, increased variability in performance, and an increased ISD in alpha and beta frequency bands for the pair of electrodes C3-C4, suggesting that the LP may reflect a state related to increased cognitive load or task difficulty. These results suggest that changes in performance and latency in an active tactile width discrimination task are encoded in the delta, alpha, beta, and low-gamma frequency bands in a fronto-central network. The main contribution of this study is therefore related to the description of neural dynamics in frontal and central networks involved in the learning process of active tactile width discrimination.

Patient, Practice, and Organizational Factors Associated With Early Mobility Performance in Critically Ill Adults.

Adoption of early mobility interventions into intensive care unit (ICU) practice has been slow and varied. To examine factors associated with early mobility performance in critically ill adults and evaluate factors' effects on predicting next-day early mobility performance. A secondary analysis of 66 ICUs' data from patients admitted for at least 24 hours. Mixed-effects logistic regression modeling was done, with area under the receiver operating characteristic curve (AUC) calculated. In 12 489 patients, factors independently associated with higher odds of next-day mobility included significant pain (adjusted odds ratio [AOR], 1.16; 95% CI, 1.09-1.23), documented sedation target (AOR, 1.09; 95% CI, 1.01-1.18), performance of spontaneous awakening trials (AOR, 1.77; 95% CI, 1.59-1.96), spontaneous breathing trials (AOR, 2.35; 95% CI, 2.14-2.58), mobility safety screening (AOR, 2.26; 95% CI, 2.04-2.49), and prior-day physical/occupational therapy (AOR, 1.44; 95% CI, 1.30-1.59). Factors independently associated with lower odds of next-day mobility included deep sedation (AOR, 0.44; 95% CI, 0.39-0.49), delirium (AOR, 0.63; 95% CI, 0.59-0.69), benzodiazepine administration (AOR, 0.85; 95% CI, 0.79-0.92), physical restraints (AOR, 0.74; 95% CI, 0.68-0.80), and mechanical ventilation (AOR, 0.73; 95% CI, 0.68-0.78). Black and Hispanic patients had lower odds of next-day mobility than other patients. Models incorporating patient, practice, and between-unit variations displayed high discriminant accuracy (AUC, 0.853) in predicting next-day early mobility performance. Collectively, several modifiable and nonmodifiable factors provide excellent prediction of next-day early mobility performance.

Changes in physiological signal entropy in patients with obstructive sleep apnoea: a systematic review

Background and Objective Obstructive sleep apnoea (OSA) affects an estimated 936 million people worldwide, yet only 15% receive a definitive diagnosis. Diagnosis of OSA poses challenges due to the dynamic nature of physiological signals such as oxygen saturation (SpO2) and heart rate variability (HRV). Linear analysis methods may not fully capture the irregularities present in these signals. The application of entropy of routine physiological signals offers a promising method to better measure variabilities in dynamic biological data. This review aims to explore entropy changes in physiological signals among individuals with OSA.&#xD;Methods Keyword and title searches were performed on Medline, Embase, Scopus, and CINAHL databases. Studies had to analyse physiological signals in OSA using entropy. Quality assessment used the Newcastle-Ottawa Scale. Evidence was qualitatively synthesized, considering entropy signals, entropy type, and time-series length.&#xD;Main results Twenty-two studies were included. Multiple physiological signals related to OSA, including SpO2, HRV, and the oxygen desaturation index (ODI), have been investigated using entropy. Results revealed a significant decrease in HRV entropy in those with OSA compared to control groups. Conversely, SpO2 and ODI entropy values were increased in OSA. Despite variations in entropy types, time scales, and data extraction devices, studies using receiver operating characteristic (ROC) curves demonstrated a high discriminative accuracy (>80% AUC) in distinguishing OSA patients from control groups. &#xD;Conclusions This review highlights the potential of SpO2 entropy analysis in developing new diagnostic indices for patients with OSA. Further investigation is needed before applying this technique clinically.&#xD;&#xD.

Validation of Lung Ultrasound for Coronavirus Disease 2019 Prognostication in an International Multicenter Cohort Study.

Despite many studies evaluating lung ultrasound (LUS) for coronavirus disease 2019 (COVID-19) prognostication, the generalizability and utility across clinical settings are uncertain. Adults (≥18 years of age) with COVID-19 were enrolled at 2 military hospitals, an emergency department, home visits, and a homeless shelter in the United States, and in a referral hospital in Uganda. Participants had a 12-zone LUS scan performed at time of enrollment and clips were read off-site. The primary outcome was progression to higher level of care after the ultrasound scan. We calculated the cross-validated area under the curve for the validation cohort for individual LUS features. We enrolled 191 participants with COVID-19 (57.9% female; median age, 45.0 years [interquartile range, 31.5-58.0 years]). Nine participants clinically deteriorated. The top predictors of worsening disease in the validation cohort measured by cross-validated area under the curve were B-lines (0.88 [95% confidence interval {CI}, .87-.90]), discrete B-lines (0.87 [95% CI, .85-.88]), oxygen saturation (0.82 [95%, CI, .81-.84]), and A-lines (0.80 [95% CI, .78-.81]). In an international multisite point-of-care ultrasound cohort, LUS parameters had high discriminative accuracy. Ultrasound can be applied toward triage across a wide breadth of care settings during a pandemic.

A predictive model for ischemic colitis: Integrating clinical and laboratory parameters

AbstractObjectiveWe aimed to develop a predictive model for the clinical diagnosis of ischemic colitis (IC).MethodsClinical data were collected from patients with acute IC lesions who were diagnosed and admitted to Beijing Tsinghua Changgung Hospital from January 2016 to December 2022. These patients were included in the IC case group in this retrospective observational study. The control group comprised patients aged ≥40 years who were diagnosed with abdominal pain during the same period, excluding those with IC. All patients were divided into a training and test sets based on the time window. Least absolute shrinkage and selection operator regression was used to screen risk factors for the occurrence of IC. Logistic stepwise regression (maximum likelihood ratio method) was performed in multifactorial analysis, and a diagnostic prediction model for IC was established using R language. The area under the receiver operating characteristic (ROC) curve (AUC) was examined to assess differentiation using working ROC curves. We used bootstrap resampling (1000 times) for internal validation. Model calibration curves and decision curve analysis (DCA) were also applied.ResultsOur study indicates that constipation, hematochezia, neutrophil counts, and specific abdominal computed tomography (CT) (plain scan) findings, including intestinal wall edema and thickening, intestinal lumen stenosis, and dilation, are independent predictors of IC. The predictive model exhibited high discriminative ability with an AUC of 0.9788 in the training set, and the calibration and DCA curves demonstrated excellent model performance. After validation, the AUC remained robust at 0.9868, underscoring the model's reliability in predicting IC.ConclusionAccording to our model, constipation accompanied by hematochezia necessitates careful consideration of IC. Abdominal CT (plain scan) is an effective diagnostic tool for IC, and it is common for patients to exhibit elevated neutrophil counts. The predictive model, demonstrating high discriminative ability and accuracy, shows promise for practical application in clinical settings, aiding in the early diagnosis and management of IC.

Identifying behaviour-related and physiological risk factors for suicide attempts in the UK Biobank.

Suicide is a global public health challenge, yet considerable uncertainty remains regarding the associations of both behaviour-related and physiological factors with suicide attempts (SA). Here we first estimated polygenic risk scores (PRS) for SA in 334,706 UK Biobank participants and conducted phenome-wide association analyses considering 2,291 factors. We identified 246 (63.07%) behaviour-related and 200 (10.41%, encompassing neuroimaging, blood and metabolic biomarkers, and proteins) physiological factors significantly associated with SA-PRS, with robust associations observed in lifestyle factors and mental health. Further case-control analyses involving 3,558 SA cases and 149,976 controls mirrored behaviour-related associations observed with SA-PRS. Moreover, Mendelian randomization analyses supported a potential causal effect of liability to 58 factors on SA, such as age at first intercourse, neuroticism, smoking, overall health rating and depression. Notably, machine-learning classification models based on behaviour-related factors exhibited high discriminative accuracy in distinguishing those with and without SA (area under the receiver operating characteristic curve 0.909 ± 0.006). This study provides comprehensive insights into diverse risk factors for SA, shedding light on potential avenues for targeted prevention and intervention strategies.

Development and Validation of a Machine Learning Algorithm to Predict the Risk of Blood Transfusion after Total Hip Replacement in Patients with Femoral Neck Fractures: A Multicenter Retrospective Cohort Study.

Total hip arthroplasty (THA) remains the primary treatment option for femoral neck fractures in elderly patients. This study aims to explore the risk factors associated with allogeneic blood transfusion after surgery and to develop a dynamic prediction model to predict post-operative blood transfusion requirements. This will provide more accurate guidance for perioperative humoral management and rational allocation of medical resources. We retrospectively analyzed data from 829 patients who underwent total hip arthroplasty for femoral neck fractures at three third-class hospitals between January 2017 and August 2023. Patient data from one hospital were used for model development, whereas data from the other two hospitals were used for external validation. Logistic regression analysis was used to screen the characteristic subsets related to blood transfusion. Various machine learning algorithms, including logistic regression, SVA (support vector machine), K-NN (k-nearest neighbors), MLP (multilayer perceptron), naive Bayes, decision tree, random forest, and gradient boosting, were used to process the data and construct prediction models. A 10-fold cross-validation algorithm facilitated the comparison of the predictive performance of the models, resulting in the selection of the best-performing model for the development of an open-source computing program. BMI (body mass index), surgical duration, IBL (intraoperative blood loss), anticoagulant history, utilization rate of tranexamic acid, Pre-Hb, and Pre-ALB were included in the model as well as independent risk factors. The average area under curve (AUC) values for each model were as follows: logistic regression (0.98); SVA (0.91); k-NN (0.87) MLP, (0.96); naive Bayes (0.97); decision tree (0.87); random forest (0.96); and gradient boosting (0.97). A web calculator based on the best model is available at: (https://nomo99.shinyapps.io/dynnomapp/). Utilizing a computer algorithm, a prediction model with a high discrimination accuracy (AUC > 0.5) was developed. The logistic regression model demonstrated superior differentiation and reliability, thereby successfully passing external validation. The model's strong generalizability and applicability have significant implications for clinicians, aiding in the identification of patients at high risk for postoperative blood transfusion.

Distinct characteristics of the gut virome in patients with osteoarthritis and gouty arthritis

Background/purpose(s)The gut microbiota and its metabolites play crucial roles in pathogenesis of arthritis, highlighting gut microbiota as a promising avenue for modulating autoimmunity. However, the characterization of the gut virome in arthritis patients, including osteoarthritis (OA) and gouty arthritis (GA), requires further investigation.MethodsWe employed virus-like particle (VLP)-based metagenomic sequencing to analyze gut viral community in 20 OA patients, 26 GA patients, and 31 healthy controls, encompassing a total of 77 fecal samples.ResultsOur analysis generated 6819 vOTUs, with a considerable proportion of viral genomes differing from existing catalogs. The gut virome in OA and GA patients differed significantly from healthy controls, showing variations in diversity and viral family abundances. We identified 157 OA-associated and 94 GA-associated vOTUs, achieving high accuracy in patient-control discrimination with random forest models. OA-associated viruses were predicted to infect pro-inflammatory bacteria or bacteria associated with immunoglobulin A production, while GA-associated viruses were linked to Bacteroidaceae or Lachnospiraceae phages. Furthermore, several viral functional orthologs displayed significant differences in frequency between OA-enriched and GA-enriched vOTUs, suggesting potential functional roles of these viruses. Additionally, we trained classification models based on gut viral signatures to effectively discriminate OA or GA patients from healthy controls, yielding AUC values up to 0.97, indicating the clinical utility of the gut virome in diagnosing OA or GA.ConclusionOur study highlights distinctive alterations in viral diversity and taxonomy within gut virome of OA and GA patients, offering insights into arthritis etiology and potential treatment and prevention strategies.Graphical

Development and validation of a prediction model for frailty in breast cancer patients with extended survival.

Breast cancer (BC) patients with extended survival show a higher incidence of frailty. This study aimed to develop and validate a novel model combining sociodemographic factors (SF) and disease-related factors (DRF) to identify frailty in BC patients with extended survival. This cross-sectional study examined data from 1167 patients admitted to a large urban academic medical centre. Three types of predictive models were constructed in the training set (817 patients): the SF model, the DRF model, and the SF + DRF model (combined model). The model performance and effectiveness were assessed using receiver operating characteristic (ROC) curves, calibration plots and decision curves analysis (DCA). Then the model was subsequently validated on the validation set. The incidence of frailty in BC patients with extended survival was 35.8%. We identified six independent risk factors including age, health status, chemotherapy, endocrine therapy, number of comorbidities and oral medications. Ultimately, we constructed an optimal model (combined model C) for frailty. The predictive model showed significantly high discriminative accuracy in the training set AUC: 0.754, (95% CI, 0.719-0.789; sensitivity: 76.8%, specificity: 62.2%) and validation set AUC: 0.805, (95% CI, 0.76-0.85), sensitivity: 60.8%, specificity: 87.1%) respectively. A prediction nomogram was constructed for the training and validation sets. Calibration and DCA were performed, which indicated that the clinical model presented satisfactory calibration and clinical utility. Ultimately, we implemented the prediction model into a mobile-friendly web application that provides an accurate and individualized prediction for BC. The present study demonstrated that the prevalence of frailty in BC patients with extended survival was 35.8%. We developed a novel model for screening frailty, which may provide evidence for frailty screening and prevention.

Rice Origin Tracing Technology Based on Fluorescence Spectroscopy and Stoichiometry.

The origin of agricultural products is crucial to their quality and safety. This study explored the differences in chemical composition and structure of rice from different origins using fluorescence detection technology. These differences are mainly affected by climate, environment, geology and other factors. By identifying the fluorescence characteristic absorption peaks of the same rice seed varieties from different origins, and comparing them with known or standard samples, this study aims to authenticate rice, protect brands, and achieve traceability. The study selected the same variety of rice seed planted in different regions of Jilin Province in the same year as samples. Fluorescence spectroscopy was used to collect spectral data, which was preprocessed by normalization, smoothing, and wavelet transformation to remove noise, scattering, and burrs. The processed spectral data was used as input for the long short-term memory (LSTM) model. The study focused on the processing and analysis of rice spectra based on NZ-WT-processed data. To simplify the model, uninformative variable elimination (UVE) and successive projections algorithm (SPA) were used to screen the best wavelengths. These wavelengths were used as input for the support vector machine (SVM) prediction model to achieve efficient and accurate predictions. Within the fluorescence spectral range of 475-525 nm and 665-690 nm, absorption peaks of nicotinamide adenine dinucleotide (NADPH), riboflavin (B2), starch, and protein were observed. The origin tracing prediction model established using SVM exhibited stable performance with a classification accuracy of up to 99.5%.The experiment demonstrated that fluorescence spectroscopy technology has high discrimination accuracy in tracing the origin of rice, providing a new method for rapid identification of rice origin.

TLS fingerprint for encrypted malicious traffic detection with attributed graph kernel

Recently, more and more applications have adopted security protocols like Transport Layer Security (TLS) for data encryption. However, these privacy-enhancing approaches have also been abused by the attackers to deliver malicious payloads. Many existing encrypted network classification methods suffer from the imbalanced volume of normal and malicious traffic, which leads to bad model robustness. In this paper, we propose a novel TLS fingerprinting approach to capture the characteristics of encrypted network traffic. The fingerprints are attributed graphs obtained from TLS sessions, which can simultaneously take into consideration the sequential and statistical features of these sessions. As the communication patterns of different applications differ considerably, the graphs representing TLS connections could be used to characterize the network with the help of the graph kernel method, which results in a model with high accuracy in malicious TLS session detection and application discrimination. Moreover, we adopt Locality-Sensitive Hashing (LSH) and filtering techniques to reduce the time cost of our model. Model evaluation on real-world datasets shows that our model is more robust than existing methods presented in this work when the malicious traffic takes up an extremely small portion of the whole traffic.

Abstract 1020: Comparative Assessment Of Hscrp And Apolipoprotein B As Ascvd Risk Biomarkers

According to the American Heart Association, the accumulation of plaque in the walls of arteries is identified as the primary cause of atherosclerotic cardiovascular disease (ASCVD). Currently, ASCVD-related conditions remain the leading cause of morbidity and mortality globally. Apolipoprotein B has been identified as a more precise cardiovascular risk marker than LDL-C, while hsCRP has shown potential as a cardiovascular disease indicator. This study aims to investigate the diagnostic performance and routine screening cut-off of hsCRP for early atherosclerosis vascular diseases (ASCVD) risk in adult patients, comparing it with Apo B. Objective: To compare the diagnostic performance of high-sensitivity C-reactive protein (hsCRP) with apolipoprotein B in assessing ASCVD risk. Method: A sample of 494 individuals from the NHANES 2015-2016 laboratory dataset, with a mean age greater than 17 years, was used for this study. ASCVD risk was measured by non-HDL-C, categorized into low and high risk based on the Mayo Clinic reference range. Predictors included Apo B, and hs-CRP. Binomial logistic regression and ROC curve analyses were conducted using the generalised linear models and pROC packages in RStudio IDE. Hypotheses were validated at p≤0.05, and diagnostic performance metrics such as ROC AUC, sensitivity, and specificity were measured on a scale of 0-1. Result: The findings revealed that for every 1g/L increase in apo B concentration, the odds of high ASCVD risk were approximately 3.8 х1011 times higher. Additionally, the model indicated that the odds of high ASCVD risk were 1.03 times higher for every 1mg/L increase in hsCRP concentration. However, this indicate that hsCRP level was not associated with odds of ASCVD risk. The ROC AUC for apo B and hsCRP were approximately 0.9739 and 0.6165, respectively, with cut-off values (sensitivity, specificity) of approximately 0.9g/L (0.927, 0.897) and 2.4 mg/L (0.596, 0.601), respectively. Thus, levels above these thresholds for both apo B and hsCRP are associated with high ASCVD risk. Conclusion: The study demonstrates that apo B exhibits high discriminatory and diagnostic accuracy, making it a suitable ASCVD risk biomarker compared to hsCRP. While hsCRP shows moderate diagnostic accuracy, it is not sufficient as a standalone ASCVD risk diagnostic marker. Therefore, apo B could serve as a replacement for LDL-C, while hsCRP could possibly serve as an add-on test in ASCVD risk assessment.

Constructing a predictive model for the death risk of patients with septic shock based on supervised machine learning algorithms

To construct and validate the best predictive model for 28-day death risk in patients with septic shock based on different supervised machine learning algorithms. The patients with septic shock meeting the Sepsis-3 criteria were selected from Medical Information Mart for Intensive Care-IV v2.0 (MIMIC-IV v2.0). According to the principle of random allocation, 70% of these patients were used as the training set, and 30% as the validation set. Relevant predictive variables were extracted from three aspects: demographic characteristics and basic vital signs, serum indicators within 24 hours of intensive care unit (ICU) admission and complications possibly affecting indicators, functional scoring and advanced life support. The predictive efficacy of models constructed using five mainstream machine learning algorithms including decision tree classification and regression tree (CART), random forest (RF), support vector machine (SVM), linear regression (LR), and super learner [SL; combined CART, RF and extreme gradient boosting (XGBoost)] for 28-day death in patients with septic shock was compared, and the best algorithm model was selected. The optimal predictive variables were determined by intersecting the results from LASSO regression, RF, and XGBoost algorithms, and a predictive model was constructed. The predictive efficacy of the model was validated by drawing receiver operator characteristic curve (ROC curve), the accuracy of the model was assessed using calibration curves, and the practicality of the model was verified through decision curve analysis (DCA). A total of 3 295 patients with septic shock were included, with 2 164 surviving and 1 131 dying within 28 days, resulting in a mortality of 34.32%. Of these, 2 307 were in the training set (with 792 deaths within 28 days, a mortality of 34.33%), and 988 in the validation set (with 339 deaths within 28 days, a mortality of 34.31%). Five machine learning models were established based on the training set data. After including variables at three aspects, the area under the ROC curve (AUC) of RF, SVM, and LR machine learning algorithm models for predicting 28-day death in septic shock patients in the validation set was 0.823 [95% confidence interval (95%CI) was 0.795-0.849], 0.823 (95%CI was 0.796-0.849), and 0.810 (95%CI was 0.782-0.838), respectively, which were higher than that of the CART algorithm model (AUC = 0.750, 95%CI was 0.717-0.782) and SL algorithm model (AUC = 0.756, 95%CI was 0.724-0.789). Thus above three algorithm models were determined to be the best algorithm models. After integrating variables from three aspects, 16 optimal predictive variables were identified through intersection by LASSO regression, RF, and XGBoost algorithms, including the highest pH value, the highest albumin (Alb), the highest body temperature, the lowest lactic acid (Lac), the highest Lac, the highest serum creatinine (SCr), the highest Ca2+, the lowest hemoglobin (Hb), the lowest white blood cell count (WBC), age, simplified acute physiology score III (SAPS III), the highest WBC, acute physiology score III (APS III), the lowest Na+, body mass index (BMI), and the shortest activated partial thromboplastin time (APTT) within 24 hours of ICU admission. ROC curve analysis showed that the Logistic regression model constructed with above 16 optimal predictive variables was the best predictive model, with an AUC of 0.806 (95%CI was 0.778-0.835) in the validation set. The calibration curve and DCA curve showed that this model had high accuracy and the highest net benefit could reach 0.3, which was significantly outperforming traditional models based on single functional score [APS III score, SAPS III score, and sequential organ failure assessment (SOFA) score] with AUC (95%CI) of 0.746 (0.715-0.778), 0.765 (0.734-0.796), and 0.625 (0.589-0.661), respectively. The Logistic regression model, constructed using 16 optimal predictive variables including pH value, Alb, body temperature, Lac, SCr, Ca2+, Hb, WBC, SAPS III score, APS III score, Na+, BMI, and APTT, is identified as the best predictive model for the 28-day death risk in patients with septic shock. Its performance is stable, with high discriminative ability and accuracy.

Plasma Metabolic Profiling and Multiclass Diagnostic Model Development for Stable Angina Pectoris and Acute Myocardial Infarction.

Coronary heart disease remains a major global health challenge, with a clear need for enhanced early risk assessment. This study aimed to elucidate metabolic signatures across various stages of coronary heart disease and develop an effective multiclass diagnostic model. Using metabolomic approaches, gas chromatography-mass and liquid chromatography-tandem mass spectrometry were used to analyze plasma samples from healthy controls, patients with stable angina pectoris, and those with acute myocardial infarction. Pathway enrichment analysis was conducted on metabolites exhibiting significant differences. The key metabolites were identified using Random Forest and Recursive Feature Elimination strategies to construct a multiclass diagnostic model. The performance of the model was validated through 10-fold cross-validation and evaluated using confusion matrices, receiver operating characteristic curves, and calibration curves. Metabolomics was used to identify 1491 metabolites, with 216, 567, and 295 distinctly present among the healthy controls, patients with stable angina pectoris, and those with acute myocardial infarction, respectively. This implicated pathways such as the glucagon signaling pathway, d-amino acid metabolism, pyruvate metabolism, and amoebiasis across various stages of coronary heart disease. After selection, testosterone isobutyrate, N-acetyl-tryptophan, d-fructose, l-glutamic acid, erythritol, and gluconic acid were identified as core metabolites in the multiclass diagnostic model. Evaluating the diagnostic model demonstrated its high discriminative ability and accuracy. This study revealed metabolic pathway perturbations at different stages of coronary heart disease, and a precise multiclass diagnostic model was established based on these findings. This study provides new insights and tools for the early diagnosis and treatment of coronary heart disease.

Epidemiology and Prognostic Nomogram for Predicting Long-Term Disease-Specific Survival in Patients With Pancreatic Carcinoid Tumor: A SEER-Based Study.

Pancreatic carcinoid tumor (PCT) is described as a malignant form of carcinoid tumors. However, the epidemiology and prognostic factors for PCT are poorly understood. The data of 2447 PCT patients were included in this study from the Surveillance, Epidemiology, and End Results database and randomly divided into a training cohort (1959) and a validation cohort (488). The epidemiology of PCT was calculated, and independent prognostic factors were identified to construct a prognostic nomogram for predicting long-term disease-specific survival (DSS) among PCT patients. The incidence of PCT increased remarkably from 2000 to 2018. The 1-, 5-, and 10-year DSS rates were 96.4%, 90.3%, and 86.5%, respectively. Age at diagnosis, stage, surgery, radiotherapy, and chemotherapy were identified as independent prognostic factors to construct a prognostic nomogram. The C -indices; area under the receiver operating characteristic curves for predicting 1-, 5-, and 10-year DSS, and calibration plots of the nomogram in both cohorts indicated a high discriminatory accuracy, preferable survival predictive ability, and optimal concordances, respectively. The incidence of PCT has increased rapidly since 2000. In addition, we established a practical, effective, and accurate prognostic nomogram for predicting the long-term DSS of PCT patients.

Classification of hand and wrist movements via surface electromyogram using the random convolutional kernels transform

Prosthetic devices are vital for enhancing personal autonomy and the quality of life for amputees. However, the rejection rate for electric upper-limb prostheses remains high at around 30%, often due to issues like functionality, control, reliability, and cost. Thus, developing reliable, robust, and cost-effective human-machine interfaces is crucial for user acceptance. Machine learning algorithms using Surface Electromyography (sEMG) signal classification hold promise for natural prosthetic control. This study aims to enhance hand and wrist movement classification using sEMG signals, treated as time series data. A novel approach is employed, combining a variation of the Random Convolutional Kernel Transform (ROCKET) for feature extraction with a cross-validation ridge classifier. Traditionally, achieving high accuracy in time series classification required complex, computationally intensive methods. However, recent advances show that simple linear classifiers combined with ROCKET can achieve state-of-the-art accuracy with reduced computational complexity. The algorithm was tested on the UCI sEMG hand movement dataset, as well as on the Ninapro DB5 and DB7 datasets. We demonstrate how the proposed approach delivers high discrimination accuracy with minimal parameter tuning requirements, offering a promising solution to improve prosthetic control and user satisfaction.

Random forest analysis of midbrain hypometabolism using [18F]-FDG PET identifies Parkinson's disease at the subject-level.

Parkinson's disease (PD) is currently diagnosed largely on the basis of expert judgement with neuroimaging serving only as a supportive tool. In a recent study, we identified a hypometabolic midbrain cluster, which includes parts of the substantia nigra, as the best differentiating metabolic feature for PD-patients based on group comparison of [18F]-fluorodeoxyglucose ([18F]-FDG) PET scans. Longitudinal analyses confirmed progressive metabolic changes in this region and, an independent study showed great potential of nigral metabolism for diagnostic workup of parkinsonian syndromes. In this study, we applied a machine learning approach to evaluate midbrain metabolism measured by [18F]-FDG PET as a diagnostic marker for PD. In total, 51 mid-stage PD-patients and 16 healthy control subjects underwent high-resolution [18F]-FDG PET. Normalized tracer update values of the midbrain cluster identified by between-group comparison were extracted voxel-wise from individuals' scans. Extracted uptake values were subjected to a random forest feature classification algorithm. An adapted leave-one-out cross validation approach was applied for testing robustness of the model for differentiating between patients and controls. Performance of the model across all runs was evaluated by calculating sensitivity, specificity and model accuracy for the validation data set and the percentage of correctly categorized subjects for test data sets. The random forest feature classification of voxel-based uptake values from the midbrain cluster identified patients in the validation data set with an average sensitivity of 0.91 (Min: 0.82, Max: 0.94). For all 67 runs, in which each of the individuals was treated once as test data set, the test data set was correctly categorized by our model. The applied feature importance extraction consistently identified a subset of voxels within the midbrain cluster with highest importance across all runs which spatially converged with the left substantia nigra. Our data suggest midbrain metabolism measured by [18F]-FDG PET as a promising diagnostic imaging tool for PD. Given its close relationship to PD pathophysiology and very high discriminatory accuracy, this approach could help to objectify PD diagnosis and enable more accurate classification in relation to clinical trials, which could also be applicable to patients with prodromal disease.