Traditional Scores Research Articles

Simplifying Complex Figure scoring: Data from the Emory Healthy Brain Study and initial clinical validation.

To introduce the Emory 10-element Complex Figure (CF) scoring system and recognition task. We evaluated the relationship between Emory CF scoring and traditional Osterrieth CF scoring approach in cognitively healthy volunteers. Additionally, a cohort of patients undergoing deep brain stimulation (DBS) evaluation was assessed to compare the scoring methods in a clinical population. The study included 315 volunteers from the Emory Healthy Brain Study (EHBS) with Montreal Cognitive Assessment (MoCA) scores of 24/30 or higher. The clinical group consisted of 84 DBS candidates. Scoring time differences were analyzed in a subset of 48 DBS candidates. High correlations between scoring methods were present for non-recognition components in both cohorts (EHBS: Copy r = 0.76, Immediate r = 0.86, Delayed r = 0.85, Recognition r = 47; DBS: Copy r = 0.80, Immediate r = 0.84, Delayed Recall r = 0.85, Recognition r = 0.37). Emory CF scoring times were significantly shorter than Osterrieth times across non-recognition conditions (all p < 0.00001, individual Cohen's d: 1.4-2.4), resulting in an average time savings of 57%. DBS patients scored lower than EHBS participants across CF memory measures, with larger effect sizes for Emory CF scoring (Cohen's d range = 1.0-1.2). Emory CF scoring demonstrated better group classification in logistic regression models, improving DBS candidate classification from 16.7% to 32.1% compared to Osterrieth scoring. Emory CF scoring yields results that are highly correlated with traditional Osterrieth scoring, significantly reduces scoring time burden, and demonstrates greater sensitivity to memory decline in DBS candidates. Its efficiency and sensitivity make Emory CF scoring well-suited for broader implementation in clinical research.

Abstract 4138355: Machine Learning for Prediction of All-Cause Mortality in Acute Coronary Syndrome

Background: Acute coronary syndrome (ACS) remains one of the leading causes of death globally. Accurate and reliable mortality risk prediction of ACS patients is essential for developing targeted treatment strategies. Existing traditional models offer moderate discriminative value, and do not incorporate contemporary predictors of ACS prognosis. Machine learning (ML) models have emerged as an alternate method that may offer improved risk assessment. This study aims to compare machine learning models with traditional risk scores for predicting all-cause mortality in patients with ACS. Methods: PubMed, EMBASE, Web of Science and Cochrane databases were searched until 1 st November 2023 for studies comparing ML models with traditional statistical methods for event prediction of ACS patients. The primary outcome was comparative discrimination measured by C-statistics with 95% confidence intervals between ML models and traditional methods in estimating the risk of all-cause mortality. Results: Ten studies were included (239627 patients). The summary C-statistic of all ML models across all endpoints was 0.89 (95% CI, 0.86-0.92), compared to traditional methods 0.82 (95% CI, 0.79-0.85). The difference in C-statistic between all ML models and traditional methods was 0.07 (p&lt;0.05). Three models undertook external validation, and calibration was inconsistently reported. Conclusion: ML models demonstrated superior discrimination of all-cause mortality for ACS patients compared to traditional risk scores. Despite outperforming well-established prognostic tools such as the GRACE and TIMI scores, current clinical applications of ML approaches remain uncertain, particularly in view of the methodological limitations of existing studies and the need for greater model validation.

Abstract 4117834: Utility of Abdominal Aortic Calcification Assessment for the Prediction of Major Adverse Cardiovascular Events in Liver Transplant Patients

Background: Cardiovascular disease is a leading cause of postoperative morbidity and mortality following liver transplantation (LT). Presence of abdominal aortic calcification (AAC) has been linked to cardiovascular events in the general population. We investigated whether AAC on pre-transplant computed tomography (CT) predicts major adverse cardiovascular events (MACE) post-LT. Methods: Consecutive LT patients between 2010-2018 from the Victorian Liver Transplant Unit (Australia) were included. Extent of AAC was quantified in a blinded fashion, with high AAC defined as a calcium score of ≥500. MACE was defined as any recorded episodes of acute coronary syndrome (ACS), ventricular arrhythmia, decompensated heart failure, or stroke. The primary outcome was post-LT MACE at 30 days and the secondary outcome was all-cause mortality at maximal follow-up. Results: Of 461 patients undergoing LT, 350 had suitable CTs for analysis, of which 90 (25.7%) had also undergone CT coronary angiography. High AAC was identified in 98 patients (28.0%). This finding demonstrated a moderate correlation with high coronary artery calcium score (CACS) ≥400 (r=0.52, p&lt;0.001). Fifty-eight MACE occurred in 42 patients (12.0%) within 30-days. High AAC was associated with increased risk of 30-day MACE (OR=2.68 (95%CI 1.39-5.17), p=0.004), and long-term mortality (HR=2.52 (95%CI 1.29-4.92), p=0.007) at a median follow-up of 4.0 years. In addition, high AAC predicted an increased risk of ACS (OR 3.80 (95%CI 1.18-12.27), p=0.025), heart failure (OR 3.07 (95%CI 1.21-7.80), p=0.020) and atrial fibrillation (OR 2.04 (95%CI 1.02-4.07), p=0.048), with a trend to increased prevalence of ventricular arrhythmia (OR 2.67 (95%CI 0.84-8.50), p=0.10). Following multivariate analysis, high AAC remained a strong independent predictor of MACE (OR=3.49, 95%CI 1.21-10.06, p=0.021). Addition of AAC to the revised cardiac risk index (RCRI) improved model fit for predicting MACE (net reclassification improvement of 52.7% (p&lt;0.001)). Conclusions: This study demonstrates for the first time that high AAC on routine abdominal CT scans is associated with a 3-fold increased risk of 30-day MACE post-LT, and improves cardiovascular risk prediction compared to traditional risk scores. Quantification of AAC may offer a simple method of improving cardiovascular risk assessment and implementation of preventative strategies in liver transplant patients, using pre-existing scans without additional cost or patient risk.

Abstract 4136721: Reducing the Use of Transesophageal Echocardiogram Prior to Cardioversion Using Machine Learning

Introduction/Background: Direct current cardioversion (DCC) is used to terminate atrial fibrillation and atrial flutter. Due to increased stroke risk post DCC, a transesophageal echocardiogram (TEE) is performed in selected patients to rule out left atrial appendage thrombus (LAAT) prior to DCC. The prevalence of LAAT is around 2.5% in the era of direct oral anticoagulants. This is a large proportion of patients with no LAAT on TEE and calls for strategies to improve patient selections for TEE before DCC. Research Questions/Hypothesis: In this study we aimed to determine if the use of machine learning could accurately predict the presence of LAAT among patients with nonvalvular atrial fibrillation and atrial flutter. Methods/Approach: We collected demographic, comorbid, and transthoracic echocardiographic data on 795 patients who underwent TEE prior to DCC for nonvalvular atrial fibrillation and atrial flutter. We developed and validated an explainable machine learning model using the eXtreme Gradient Boosting algorithm with 5x5 nested cross-validation. The algorithm used 37 variables to predict the probability of LAAT. Results/Data: The prevalence of LAAT in our cohort was 11.3%. Our model achieved an area under the curve (AUC) of 0.79 in predicting LAAT, figure 1A. In comparison, CHA2DS2-VASc score performed poorly in our cohort with an AUC of 0.48, figure 1B. The ranking of variables most strongly predictive of LAAT is shown in figure 1C, with left ventricle ejection fraction as the most instrumental. Patients were categorized into 10 groups based on the percentile of their predicted probability of having a thrombus. A lower percentile (e.g., 10%) indicates a lower probability of having a thrombus. By utilizing a cutoff point of 0.16, which includes 10.0% of the patients, we can exclude the presence of thrombus with 100% certainty. Conclusion: Machine learning, compared to traditional risk scores, offers enhanced predictive model for identifying LAAT and provides better guidance for TEE and anticoagulation therapy before DCC.

Abstract 4136550: In-hospital cardiac arrest can be detected by Innovative smart healthcare syste

Background: Predicting in-hospital cardiac arrest (IHCA) is crucial for preventing patient fatalities. However, it remains challenging due to the irregularities in time series data across various features. Previous studies relied on traditional medical scoring systems, but their accuracy was limited as the models were overly simplistic. Recent research using machine learning methods has shown improved results. In our work, we employ deep learning and time series approaches, which are considered the most powerful models for addressing complex problems in recent years. Method/Research Design: The cohort study took place in a hospital in Taiwan from January 2016 to August 2022, involving 252,000 patients in general wards. Input data encompassed basic information, vital signs, Glasgow Coma Scale scores, medication, etc., to predict IHCA occurrences within 24 hours. Given the immediacy of IHCA events, we utilized left alignment to handle time series. Evaluation metrics included the area under the receiver operating characteristic curve (AUROC). Results: We compared three types of settings. The first was based on scoring systems, where the national early warning system (NEWS) achieved an AUROC of 0.756, and the modified early warning score (MEWS) reached 0.653. In the next setting, based on the data summary within a given time interval, the machine learning models XGBoost and deep learning model TabNet achieved AUROCs of 0.863 and 0.839, respectively. This indicates that machine learning outperforms traditional medical methods. The final setting involved time series analysis, where XGBoost and the Gate Recurrent Unit (GRU) network achieved 0.848 and 0.904, respectively, surpassing all previous settings. Conclusion: Our study demonstrates that learning-based methods outperform rule-based methods in predicting IHCA events. Machine learning algorithms offer more possibilities and have the potential to address complex problems effectively. Moreover, considering time series data rather than summarizing within fixed intervals preserves information and leads to better scores. Leveraging the time series deep learning method, GRU shows promising potential in significantly reducing the risk of IHCA events.

Abstract 4124446: Traditional Risk Factors, Cardiovascular Health, and Elevated Lipoprotein(a): The Multi-Ethnic Study of Atherosclerosis

Introduction: One in five individuals have elevated lipoprotein(a) [Lp(a)], an inheritable risk factor that is causally associated with atherosclerotic cardiovascular disease (ASCVD). Whether individuals with elevated Lp(a) derive similar benefit from control of ASCVD risk factors has not been well-studied. Hypothesis: The magnitude of benefit associated with optimal cardiovascular health will be similar across the spectrum of Lp(a). Aim: To assess the association of traditional risk factor burden and Life’s Simple 7 (LS7) score with incident ASCVD across Lp(a) values. Methods: We studied 6,676 participants from the Multi-Ethnic Study of Atherosclerosis who underwent Lp(a) testing and were followed for incident ASCVD events (coronary heart disease and stroke). Elevated Lp(a) was defined as &gt; 50 mg/dL. As defined by the American Heart Association, LS7 metrics included smoking, physical activity, body mass index, diet, total cholesterol, blood pressure, and glucose. Multivariable Cox proportional hazards regression assessed the association of traditional risk factor burden and LS7 score (poor: 0-8, average: 9-10, optimal: 11-14) with incident ASCVD for individuals with and without elevated Lp(a) during a median follow-up of 17.7 years. Results: The mean age was 62.1 years, 53% were women, and 61% were non-white. The median Lp(a) was 17 mg/dL and 20% had Lp(a) &gt; 50 mg/dL. Individuals with Lp(a) &gt; 50 mg/dL had the highest burden of traditional risk factors except cigarette smoking. Compared to those with a poor LS7 score, those with an optimal LS7 score had a lower ASCVD risk that was significant for participants with Lp(a) &lt;50 mg/dL (HR=0.37, 95% CI: 0.25-0.55), but borderline significant for participants with Lp(a) &gt; 50 mg/dL (HR=0.41, 95% CI: 0.16-1.02). Individuals with Lp(a) &gt; 50 mg/dL had the highest absolute event rates across all LS7 categories, and there was no significant interaction between Lp(a) and LS7 score on incident ASCVD (p-interaction=0.64, Figure ). Conclusions: Participants with an optimal LS7 score had similar reduction in ASCVD risk regardless of their Lp(a) burden. These results emphasize the importance of a healthy lifestyle and ASCVD risk factor control among patients with elevated Lp(a).

Exploring the potential of large language models in identifying metabolic dysfunction-associated steatotic liver disease: A comparative study of non-invasive tests and artificial intelligence-generated responses.

This study sought to assess the capabilities of large language models (LLMs) in identifying clinically significant metabolic dysfunction-associated steatotic liver disease (MASLD). We included individuals from NHANES 2017-2018. The validity and reliability of MASLD diagnosis by GPT-3.5 and GPT-4 were quantitatively examined and compared with those of the Fatty Liver Index (FLI) and United States FLI (USFLI). A receiver operating characteristic curve was conducted to assess the accuracy of MASLD diagnosis via different scoring systems. Additionally, GPT-4V's potential in clinical diagnosis using ultrasound images from MASLD patients was evaluated to provide assessments of LLM capabilities in both textual and visual data interpretation. GPT-4 demonstrated comparable performance in MASLD diagnosis to FLI and USFLI with the AUROC values of .831 (95% CI .796-.867), .817 (95% CI .797-.837) and .827 (95% CI .807-.848), respectively. GPT-4 exhibited a trend of enhanced accuracy, clinical relevance and efficiency compared to GPT-3.5 based on clinician evaluation. Additionally, Pearson's r values between GPT-4 and FLI, as well as USFLI, were .718 and .695, respectively, indicating robust and moderate correlations. Moreover, GPT-4V showed potential in understanding characteristics from hepatic ultrasound imaging but exhibited limited interpretive accuracy in diagnosing MASLD compared to skilled radiologists. GPT-4 achieved performance comparable to traditional risk scores in diagnosing MASLD and exhibited improved convenience, versatility and the capacity to offer user-friendly outputs. The integration of GPT-4V highlights the capacities of LLMs in handling both textual and visual medical data, reinforcing their expansive utility in healthcare practice.

Prognostic Implications of Initial Radiological Findings of Pulmonary Fibrosis in Patients with Acute SARS-CoV-2 Infection: A Prospective Multicentric Study

Pulmonary fibrosis detected during the acute phase of SARS-CoV-2 infection may significantly influence patient prognosis. This study aimed to evaluate the prognostic value of initial high-resolution computed tomography (HRCT) findings of pulmonary fibrosis in hospitalized COVID-19 patients and to examine how these findings relate to disease severity and clinical outcomes, with a particular focus on the development and validation of predictive scoring systems. In this multicentric prospective cohort study from January 2023 to January 2024, 120 adult patients with confirmed SARS-CoV-2 infection requiring hospitalization were enrolled from two Romanian university hospitals. Patients were categorized based on the presence (n = 60) or absence (n = 60) of pulmonary fibrosis signs on admission HRCT scans, identified by reticular opacities, traction bronchiectasis, honeycombing, and architectural distortion. Biochemical analyses, severity scores (SOFA, APACHE II, NEWS 2), and novel compound scores combining clinical and radiological data were assessed. Patients with HRCT evidence of pulmonary fibrosis had significantly higher severity scores and worse clinical outcomes. The HRCT score alone was a strong predictor of severe COVID-19 (area under the ROC curve [AUC] = 0.885), with a best cutoff value of 9.72, yielding 85.7% sensitivity and 79.8% specificity. Compound Score 1, integrating SOFA, APACHE II, and HRCT scores, demonstrated excellent predictive performance with an AUC of 0.947, sensitivity of 92.5%, and specificity of 88.9%. Compound Score 2, combining systemic inflammation markers (SIRI, SII) and NEWS 2, also showed a strong predictive capability (AUC = 0.913), with 89.2% sensitivity and 85.7% specificity at the optimal cutoff. Regression analysis revealed that Compound Score 1 had the highest hazard ratio for severe COVID-19 outcomes (HR = 4.89; 95% CI: 3.40–7.05), indicating its superior prognostic value over individual markers and traditional severity scores. Initial HRCT findings of pulmonary fibrosis are significantly associated with increased disease severity in hospitalized COVID-19 patients. The HRCT score is a valuable prognostic tool, and, when combined with clinical severity scores into Compound Score 1, it enhances the prediction of severe COVID-19 outcomes with high sensitivity and specificity. These compound scores facilitate the early identification of high-risk patients, guiding clinical decision-making and optimizing patient management to improve outcomes.

Fuzheng-Buyi formula for treating castration-resistant prostate cancer: A systematic review and meta-analysis.

The study was designed to systematically evaluate the efficacy and safety of Fuzheng-Buyi formula in treating castration-resistant prostate cancer (CRPC). A computer-based search were conducted in the databases, including CNKI, WanFang Data, VIP, CBM, PubMed, EMbase, and the Cochrane database to identify all randomized controlled trials. The studies investigating the efficacy and safety of Fuzheng-Buyi formula combined with Western medicine for the treatment of CRPC were included from January 1st, 2010 to December 31st, 2023. The quality of the included studies was evaluated according to the Cochrane Handbook manual, and meta-analysis was performed using Review Manager 5.3 and R Studio 4.2.3 software. In this study, a total of 18 trials were included, encompassing a population of 1093 patients diagnosed with CRPC. The results of the meta-analysis showed that the combination of Fuzheng-Buyi formula and Western drugs was more effective in increasing the overall efficacy rate (risk ratio = 1.31, 95% confidence interval [CI] [1.17, 1.46], P < .00001), decreasing Traditional Chinese Medicine syndrome score (mean difference [MD] = -4.40, 95% CI [-6.10, -2.70], P < .00001), and quality of life scale (physiological condition MD = -2.31, 95% CI [-3.13, -1.48], P < .00001; social well-being MD = 1.26, 95% CI [0. 59, 1.94], P = .0002; emotional well-being MD = -2.04, 95% CI [-2.96, -1.12], P < .00001; functional well-being MD = -3.18, 95% CI [2.11, 4.26], P < .00001; others should be paid to MD = -3.15, 95% CI [-4.93, -1.37], P = .0005) compared with the Western medicine alone. And the incidence of adverse events was significantly lower in the combination treatment group compared with Western medicine group (risk ratio = 0.58, 95% CI [0.46, 0.73], P < .00001). The combination of Fuzheng-Buyi formula and Western medicine was more effective in improving the clinical efficacy and quality of life of CRPC patients, with lower incidence of adverse events compared with Western medicine alone.

Epigenomic biomarkers of cardiometabolic disease: How far are we from daily practice?

Determining whether someone has cardiometabolic disease (CMD), especially in the early stages, can be complicated. Risk stratification ordinarily depends on an extended process relying on medical history that typically considers blood pressure, cholesterol, smoking and diabetes status. Physicians have long relied on these key patient characteristics to assess CMD risk. However, these widely used clinical assessments are often identified later in life and by definition, in those individuals with progressed disease. This is partly because the onset of CMD naturally occurs in adulthood, however, the underlying processes can occur much earlier in life, even in the absence of obvious symptoms. For one thing, the pathways towards pathology may exist for years before symptom onset. Thus, among other things, there are opportunities to provide doctors with better insights into future disease prediction especially in younger adults with diabetes. The rapid rise in CMD together with the increased rates of obesity and diabetes in this population only emphasises the importance of predictive molecular biomarkers. One notable aspect is that traditional risk scores, such as those based on cholesterol measurements, are frequently found to be within normal ranges in younger populations. At the same time, given the significant overlap in risk factors for cardiovascular disease (CVD) and diabetes, the unmet clinical need is for early biomarkers of CMD that may help improve risk assessment in younger adults. This editorial highlights advances in the use of polygenic risk scores and emerging utility of genetic biomarkers to define intermediate CMD phenotypes discussing new classification criteria involving DNA methylation of genes to improve risk assessment. CMD is the number one cause of mortality and accounts for 31% of all global deaths. CMD is also multifactorial, comprising cardiovascular disease (CVD) and diabetes that have significant overlap in risk factors and disease biology. Diabetes is arguably the strongest risk factor for CVD development. Accounting for almost 90% of diabetes cases worldwide, type 2 diabetes (T2D) affects about 527 million people. The global economic burden is estimated at 1.3 trillion USD annually and is close to 1.8% of global GDP [1]. Despite the progress in preventive and therapeutic measures of CVD, the increasing CMD rates only underscore the important need of molecular biomarkers for early detection [2]. Determining whether someone has CMD usually involves an extended diagnostic process that has become essential for risk stratification and disease prevention [3]. While the onset of CMD typically occurs in adulthood, disease development commences much earlier, and this has scientists questioning whether molecular biomarkers could improve current prognostic risk scores. Predicting which people with T2D are most likely to develop CVD remains a significant challenge despite the recent advances in genetic mapping.Graphical abstract

Prediction of Severe Acute Pancreatitis at a Very Early Stage of the Disease Using Artificial Intelligence Techniques, Without Laboratory Data or Imaging Tests: The PANCREATIA Study.

To evaluate machine learning models' performance in predicting acute pancreatitis severity using early-stage variables while excluding laboratory and imaging tests. Severe acute pancreatitis (SAP) affects approximately 20% of acute pancreatitis (AP) patients and is associated with high mortality rates. Accurate early prediction of SAP and in-hospital mortality is crucial for effective management. Traditional scores such as APACHE-II and BISAP are complex and require laboratory tests, while early predictive models are lacking. Machine learning (ML) has shown promising results in predictive modelling, potentially outperforming traditional methods. We analysed data from a prospective database of AP patients admitted to Vall d'Hebron Hospital from November 2015 to January 2022. Inclusion criteria were adults diagnosed with AP according to the 2012 Atlanta classification. Data included basal characteristics, current medication, and vital signs. We developed machine learning models to predict SAP, in-hospital mortality, and intensive care unit (ICU) admission. The modelling process included two stages: Stage 0, which used basal characteristics and medication, and Stage 1, which included data from Stage 0 and vital signs. Out of 634 cases, 594 were analysed. The Stage 0 model showed AUC values of 0.698 for mortality, 0.721 for ICU admission, and 0.707 for persistent organ failure. The Stage 1 model improved performance with AUC values of 0.849 for mortality, 0.786 for ICU admission, and 0.783 for persistent organ failure. The models demonstrated comparable or superior performance to APACHE-II and BISAP scores. The ML models showed good predictive capacity for SAP, ICU admission, and mortality using early-stage data without laboratory or imaging tests. This approach could revolutionise AP patients' initial triage and management, providing a personalised prediction method based on early clinical data.

Automated Evaluation Method for Risk Behaviors of Quay Crane Operators at Ports Using Virtual Reality

Currently, the operational risk assessment of quay crane operators at ports relies on manual evaluations based on experience, but this method lacks objectivity and fairness. As port throughput continues to grow, the port accident rate has also increased, making it crucial to scientifically evaluate the risk behaviors of operators and improve their safety awareness. This paper proposes an automated evaluation method based on a Deep Q-Network (DQN) to assess the risk behaviors of quay crane operators in virtual scenarios. A risk simulation module has been added to the existing automated quay crane remote operation simulation system to simulate potential risks during operations. Based on the collected data, a DQN-based benchmark model reflecting the operational behaviors and decision-making processes of skilled operators has been developed. This model enables a quantitative evaluation of operators’ behaviors, ensuring the objectivity and accuracy of the assessment process. The experimental results show that, compared with traditional manual scoring methods, the proposed method is more stable and objective, effectively reducing subjective biases and providing a reliable alternative to conventional manual evaluations. Additionally, this method enhances operators’ safety awareness and their ability to handle risks, helping them identify and avoid risks during actual operations, thereby ensuring both operational safety and efficiency.

099. Artificial Intelligence and Machine Learning in Trauma Outcome Prediction: A Literature Review

Introduction: Trauma remains a leading cause of mortality and disability globally, particularly among young adults. Despite advancements, accurate prediction of trauma outcomes remains challenging. Artificial intelligence (AI) and machine learning (ML) has the potential to detect patterns and analyzing complex relationship of data from trauma patients to support decision making in the management of trauma. This study aims to explore the potential of AI and ML to enhance trauma outcome prediction in order to healthcare workers with basic understanding of AI and ML and the potential for them to utilize it management of trauma patients. Methods: A literature review was conducted using studies from PubMed, SCOPUS, Cochrane, EBSCOHost, and ScienceDirect database using PRISMA protocol. Data extraction focused on study design, population, interventions, outcomes, and methodological quality using the Oxford Centre for Evidence-Based Medicine levels of evidence. Results: From the literature review, 15 studies from total of 585 studies were included in this literature review. XGBoost and Neural Networks were the most common algorithms (60%). While six studies predicted mortality, others focused on length of stay and discharge outcomes. Overall, ML significantly improved trauma diagnosis by enhancing predictive models for injury severity and mortality. Conclusions: Machine learning models have shown superior performance compared to traditional scoring systems in their ability to predict trauma outcomes and could effectively forecast critical outcomes and guide treatment decisions. Subsequent studies should concentrate on creating more resilient models based on prospectively gathered data to enhance the performance of created algorithms.

Efficacy and mechanism of Tiaoshu Anshen Decoction in treating insomnia with spleen and stomach Qi dysfunction: A retrospective study.

This study investigates the clinical efficacy of Tiaoshu Anshen Decoction in treating insomnia characterized by spleen and stomach Qi dysfunction. According to the differences of previous treatment, 94 patients were divided into treatment group and control group. The treatment group was treated with Tiaoshu Anshen Decoction, and the control group was treated with oral esazolam for 2 weeks. We compared serum levels of 5-hydroxyindoleacetic acid (5-HIAA), 5-hydroxytryptamine (5-HT), norepinephrine (NE), dopamine (DA), DASS-21, and HAMD scores before and after treatment. We also evaluated gastrointestinal function, traditional Chinese medicine syndrome scores, quality of life, and adverse reactions, with statistical analysis conducted using SPSS 25.0. The overall efficacy and clinical outcomes were comparable between the 2 groups. Both groups showed increased serum factor levels and decreased Pittsburgh Sleep Quality Index (PSQI), HAMD, and DASS-21 scores post-treatment. Notably, the treatment group exhibited significant improvement in stool consistency, digestive symptoms, DOB < 4 and DOB ≥ 4 distribution, and TCM syndrome scores, outperforming the control group. No adverse reactions were reported in either group. This study suggests that spleen and stomach Qi dysfunction significantly contribute to insomnia, affecting its occurrence, type, and severity. Tiaoshu Anshen Decoction effectively enhances 5-HIAA, 5-HT, NE, and DA levels, reduces inflammatory factors, and improves sleep quality, gastrointestinal function, and overall quality of life. The decoction may exert its effects by regulating Qi dynamics and gastrointestinal function, indicating the gastrointestinal system as a potential key target in treating sleep disorders.

Guanxinning for Residual Inflammation of Stable Coronary Artery Disease: A Pilot Randomized Controlled Trial.

Despite statins and other medications central to atherosclerotic cardiovascular disease (ASCVD) secondary prevention, stable coronary artery disease (SCAD) patients remain at significant cardiovascular risk, partly due to residual inflammation risk (RIR). This study aims to assess if adding Guanxinning to standard ASCVD therapy further mitigates RIR in SCAD patients. In a prospective, randomized, single-blind endpoint design, 50 patients with SCAD who received ASCVD standardized treatment strategy were randomly assigned to either take Guanxinning tablets (4 tablets, thrice daily) or no Guanxinning tablets and were followed up for an average of 12weeks. The primary outcomes were changes in inflammation-related indicators, including interleukin-2 (IL-2), IL-4, IL-6, tumor necrosis factor-α (TNF-α), and high sensitivity C-reactive protein (hs-CRP). Compared with the control group, the intervention group showed significantly greater decreases in the levels of IL-2, IL-6, TNF-α, and hs-CRP (all P < 0.05). However, there was no significant difference in the IL-4 level between the two groups (P > 0.05). Compared with the control group, there were also significant improvements in endothelial function-related indicators (vascular endothelial growth factor (VEGF), nitric oxide (NO), and peroxisome proliferator-activated receptor-γ (PPAR-γ)), blood lipid profile (total cholesterol (Tch), low-density lipoprotein cholesterol (LDL-C)), and chest pain related scores (angina and Traditional Chinese medicine syndrome scores) in the intervention group (all P<0.05). There was no significant difference in the triglyceride (TG) and carotid intima-media thickness between the two groups (P<0.05). Compared to the control group, there was no significant difference in the white blood cell line, liver and kidney function, anemia, and bleeding in the intervention group (all P<0.05). The addition of Guanxinning tablets (4 tablets, thrice daily) to the standard treatment strategy for ASCVD was associated with a reduction in the RIR in patients with SCAD and demonstrated good safety.

Tri-Level Anxiety and Depression Symptom Trajectory in Adolescents:the Role of Emotion Regulation Diversity

Anxiety and depression are associated with impaired emotion regulation (ER). Recently, a novel construct named ER diversity has been proposed to assess the diversity in ER strategy use. Low ER diversity, particularly under stressful circumstances, may be a transdiagnostic vulnerability factor for anxiety and depression. This study utilized a longitudinal design to examine the association between ER diversity and transdiagnostic anxiety and depressive symptom trajectory in adolescents (N = 627 at baseline), while accounting for life stress. Measures of ER strategy use, chronic interpersonal life stress, neuroticism, and transdiagnostic dimensional symptoms of anxiety and depression were assessed. The ER diversity index and the traditional ER sum score were computed. Higher ER diversity index was associated with steeper decline in the Fears symptom factor over time, above and beyond the ER sum score and neuroticism. Moreover, chronic interpersonal life stress influenced these associations. When chronic interpersonal life stress was low, Fears declined over time regardless of the ER diversity level; when chronic interpersonal life stress was high, Fears only declined when ER diversity was high. Thus, low diversity in ER strategy use, particularly under stressful circumstances, may be a vulnerability factor for fear symptom development.

The Impact of Virtual Reality on Programming Algorithm Courses on Student Learning Outcomes

The low learning outcomes of students and the limitations of learning media provide opportunities to develop innovations that can increase student engagement. One form of innovative and interactive media that supports student engagement is VR technology. This study aims to determine the impact of VR compared to traditional learning in improving student learning outcomes on programming algorithm materials. The method applied was a quasi-experimental design through pretest and posttest. The population in this study consists of six classes. Through random sampling techniques, class A was selected as the control class with 19 students and class B as the experimental class with 16 students. In the control class, students apply traditional learning, while the experimental class uses VR-based learning. The data was processed with the Wilcoxon test to see the improvement of learning outcomes in each class and the Mann-Whitney test to compare results in both classes. The results of the Wilcoxon test showed a score of sig (2tailed)&lt;0.05 in both classes which showed that traditional learning and learning with VR encouraged improved student learning outcomes. Traditional learning scores increased from 53 to 67, while group scores. Meanwhile, the results of the Mann-Whitney test showed a score of sig (2tailed)&lt;0.05 which means that the effectiveness of VR is better in improving learning outcomes than traditional learning. Therefore, learning with VR effectively improves student learning outcomes on programming algorithm materials. Other researchers can conduct further research to explore and investigate the impact of VR on health and the use of remote learning.

Comparison of machine learning and traditional methods for prediction of adverse clinical events after percutaneous coronary intervention

Abstract Background Accurate prediction of clinical outcomes following percutaneous coronary intervention (PCI) is essential for mitigating risk and periprocedural planning. Traditional risk models have demonstrated modest predictive value. Machine learning (ML) models offer an alternative risk stratification that may provide improved predictive accuracy. We performed a systematic review and meta-analysis comparing ML models and traditional risk scores for prediction of clinical outcomes after PCI. Methods This study was reported according to PRISMA guidelines. PubMed, EMBASE, Web of Science and Cochrane databases were searched until 1st November, 2023 for studies comparing ML models with traditional statistical methods for event prediction after PCI. The primary outcome was comparative discrimination measured by C-statistics with 95% confidence intervals between ML models and traditional methods in estimating the risk of all-cause mortality, major bleeding and the composite outcome major adverse cardiovascular events (MACE). Results Thirty-four models were included across 13 observational studies (4105916 patients). The summary C-statistic all ML models across all clinical endpoints was 0.81 (95% CI, 0.78-0.85), compared to traditional methods 0.79 (95% CI, 0.74-0.85). The difference in C-statistic was 0.02 (95% CI, 0.002-0.04, p=0.56). Of included studies, only 1 model was externally validated and 10 models were calibrated. Conclusion ML models did not outperform traditional risk scores in the discrimination of all-cause mortality, major bleeding or MACE following PCI. While integration of ML algorithms into electronic healthcare systems may improve periprocedural risk stratification, immediate implementation in the clinical setting remains uncertain. Further research is required to overcome methodological and validation limitations.

Machine learning for prediction of all-cause mortality in acute coronary syndrome

Abstract Background Acute coronary syndrome (ACS) remains one of the leading causes of death globally. Accurate and reliable mortality risk prediction of ACS patients is essential for developing targeted treatment strategies and improve prognostication. Traditional models for risk stratification such as the Global Registry of Acute Coronary Events (GRACE) and the Thrombolysis In Myocardial Infarction (TIMI) risk scores offer moderate discriminative value, and do not incorporate contemporary predictors of ACS prognosis. Machine learning (ML) models have emerged as an alternate method that may offer improved risk assessment. This study aims to compare machine learning models with traditional risk scores for predicting all-cause mortality in patients with ACS. Methods PubMed, EMBASE, Web of Science and Cochrane databases were searched until 1st November 2023 for studies comparing ML models with traditional statistical methods for event prediction of ACS patients. The primary outcome was comparative discrimination measured by C-statistics with 95% confidence intervals between ML models and traditional methods in estimating the risk of all-cause mortality. Results Ten studies were included (239627 patients). The summary C-statistic of all ML models across all endpoints was 0.89 (95% CI, 0.86-0.92), compared to traditional methods 0.82 (95% CI, 0.79-0.85). The difference in C-statistic between all ML models and traditional methods was 0.07 (p&amp;lt;0.05). Three models undertook external validation, and calibration was inconsistently reported. Conclusion ML models demonstrated superior discrimination of all-cause mortality for ACS patients compared to traditional risk scores. Despite outperforming well-established prognostic tools such as the GRACE and TIMI scores, current clinical applications of ML approaches remain uncertain, particularly in view of the methodological limitations of existing models and the need for greater validation.

Comparative analysis of a novel preoperative stratification method versus traditional scores in patients with severe aortic stenosis undergoing aortic valve surgery

Abstract Introduction It is crucial to consider factors that complicate the indication of transcatheter aortic valve replacement (TAVR) in patients with aortic stenosis (AS), such as narrow valve ring, extensive calcification or inadequate vascular access. (1-4) Thus, aortic valve replacement surgery (SAVR) remains a recommended indication, with its pre-surgical stratification being a challenge. (1-3) Despite the widespread use of scores like the STS and EuroSCORE II, they exhibit limitations, being validated primarily for populations outside Latin America and focusing predominantly on individual factors while often neglecting structural parameters like left ventricular hypertrophy, diastolic dysfunction, or left atrium volume. (3-5) Purpose This study aimed to assess whether a novel modified Généreux stratification method offers superior predictive value for postoperative mortality in AS patients compared to traditional scoring systems. Methods We conducted a retrospective, single-center study involving patients with confirmed severe AS who underwent aortic valve replacement surgery between January 2017 and December 2021. The new stratification method categorized patients into three stages based on echocardiographic parameters (see Figure 1). Univariate and multivariate Cox regression analyses were conducted to identify predictors of mortality, with survival analysis performed using Kaplan-Meier curves. A p-value &amp;lt;0.05 was considered statistically significant. Results A total of 508 patients were included in the study. Stage 1 patients had a lower median age (62 years vs. 67 years in stages 2 and 3). The median EuroSCORE and STS were 2.75 and 2.62%, respectively, with stage 3 showing significantly higher scores (p ≤0.001). Over a median follow-up of 81 months, 56 deaths occurred (11%). Kaplan-Meier curve analysis revealed significant differences in all-cause mortality among the three groups (HR 4.073, log-rank p≤0.001), as illustrated in Figure 1. Multivariate analysis identified the three preoperative stages (HR 3.22, [95% CI 1.44-7.20], p=0.004) and mean transaortic gradient (HR 0.96, [95% CI 0.92-0.99], p=0.021) as independent predictors of mortality. The new stages demonstrated a superior area under the ROC curve of 0.758 compared to traditional scores (see Figure 1). Conclusions The novel three-stage preoperative classification and low transaortic gradient serve as significant predictors of mortality in patients undergoing SAVR. These stages exhibit robust predictive capability for mortality compared to EuroSCORE II and STS.Baseline and multivariate analysisKaplan-meier and ROC curve