Traditional Scores Research Articles

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<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 <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

Comparison of mortality scores performance in transcatheter aortic valve replacement: suiting up to percutaneous intervention

Abstract Introduction As transcatheter aortic valve replacement (TAVR) is increasingly relevant for patients with severe symptomatic aortic stenosis, having a reliable procedure specific risk-prediction tool is paramount to provide high-quality care. Surgical scores as the EuroScore II and the Society of Thoracic Surgeons (STS) score II have been widely used to identify patients with high surgical risk in whom percutaneous treatment might be more favorable. However, current literature lacks a consensual specific predictive model for short-term and mid-term prognosis in patients undergoing transcatheter aortic valve implantation (TAVI). Purpose We aimed to access short and midterm (30 days and one year) mortality and to access the ability of a directly adapted score in estimating mortality in a real-world population. Methods We conducted a retrospective observational study in patients who implanted TAVR in a single center. Surgical mortality scores – EUROSCORE II and STS score II – and adapted score Society of Thoracic Surgeons (STS)/American College of Cardiology (ACC) transcatheter valve therapy (TVT) score were used to estimate mortality. Predictive abilities of these three scores were compared using area under the receiver operating characteristics (ROC) curve for 30-day and one year mortality. Results From January 2018 to December 2021, 416 patients were submitted to TAVR procedure in our center. The mean age was 83+-6 years old and 229 (55%) were female. 94% had hypertension, 80% dyslipidemia, 40% diabetes mellitus, 35% coronary artery disease, 32% chronic kidney disease. Mean ejection fraction was 56%. During a mean follow-up (FUP) of 816 ± 492 days, 30-day mortality was 1,7% and after 1 year mortality rate was 12,2% (higher than reported in PARTNER 3 trial, 8,5%). The Mean EuroSCORE was 3,4±3,2, mean STS-II 3,9±1,8 and mean value for STS/ACC-TVT score was 3,55±1,34. ROC curve analysis showed a significantly higher discriminative power of STS/ACC-TVT (AUC 0,749, 95% CI 0,681-0,818) compared with surgical scores (p=0,001) – figure 1. We also divided population into quartiles and compared the mortality rate at 30 days and 1 year in each quartile using either STSII or STS/ACC-TVT; As can be seen in figure 2, mortality rates correlated better with the STS/ACC-TVT score than with the STS score. Conclusion A score adapted to a TAVI population showed better predictive capacity than traditional surgical scores. Less preponderance of previous surgical status, relevance of access site and more adapted weight of age might explain the best performance of STS/ACC-TVT score. Surgical scores are helpful in choosing treatment option, but adapted scores are better to predict pos-TAVR mortality.

Which is better for predicting and discriminating cardiovascular events: a traditional risk score, a calcium score or a genetic risk score?

Abstract Background The most effective approach to prevent coronary artery disease (CAD) in the general population remains to quantify the individual risk of CAD followed by controlling risk factors. There has been a lot of curiosity to investigate several scores individually for improving risk prediction. However, whether one would be better than the other in the same population is still unclear. Aim To evaluate the performance of the three individual scores, European SCORE2, Coronary artery calcium score (CACS) and a Genetic risk score (GRS), in predicting and discriminating cardiovascular (CV) events in an asymptomatic Portuguese population. Methods Prospective, observational population-based study, including 1002 asymptomatic subjects (mean age 53.1±6.8 years, 73.8% male) selected from a normal Portuguese population, without apparent CAD and diabetes at baseline. Data were recorded at the end of an extended follow-up (average 6.5±4.9 years). The European SCORE2, a computed tomography CACS, and a GRS were created to evaluate CV events’ predictive and discriminative ability through Receiver Operating Characteristics (ROC) analysis and Harrell’s C-statistics. Results ROC curve analysis showed 0.723 for SCORE2, 0.815 for CACS and 0.649 for GRS. Harrell’s C-statistics were 0.731 in the SCORE2, 0.785 for CACS and 0.684 for GRS. Conclusion The CAC score was the best individual score to predict and discriminate CV events in our asymptomatic population. Its capacity to identify high-risk individuals and those asymptomatic with subclinical atherosclerosis may improve CV risk management strategies to prevent future cardiovascular events. This result can be explained because CAC score, more than a risk marker, represents the existence of disease in the vessel wall.

Clinical Observation of the Therapeutic Effects of Wenzhong Hewei Formula in Treating Spleen and Stomach Qi Deficiency Syndrome in Internal Medicine Diseases

Objective: To observe the clinical efficacy and safety of Wenzhong Hewei Formula in treating spleen and stomach qi deficiency syndrome in internal medicine diseases. Methods: Sixty patients with spleen and stomach qi deficiency syndrome admitted to the hospital from April 2022 to June 2023 were randomly divided into observation and control groups, with 30 patients in each group. The control group received conventional internal medicine treatment, while the observation group was additionally treated with Wenzhong Hewei Formula on the basis of conventional treatment. Both groups were treated for 4 weeks. Results: The total effective rate of treatment in the observation group was higher than that of the control group (P < 0.05). After treatment, the traditional Chinese medicine syndrome scores of both groups were significantly lower than before treatment, with the observation group showing a more pronounced reduction (P < 0.05). There was no statistically significant difference in the incidence of adverse reactions between the two groups (P > 0.05). Conclusion: Wenzhong Hewei Formula can effectively improve clinical symptoms in patients with spleen and stomach qi deficiency syndrome, enhance clinical efficacy, and have a high level of safety, making it worthy of clinical promotion.

ASCVD risk scores versus a novel cancer-specific Machine Learning-based calculator among patients with breast, colorectal, lung or prostate cancer

Abstract Background Patients with cancer have up to a 3-fold higher risk for cardiovascular disease (CVD) than the general population. Consequently, traditional risk scores developed to predict CVD in the general population (i.e., Pooled Cohort Equations (PCE), Predicting Risk of cardiovascular disease EVENTs [PREVENT]) may provide less accurate risk prediction for this population. Purpose Compare cancer-specific Machine Learning (ML)-based score to PCE and PREVENT to predict 10-year CVD risk in patients with breast cancer (BC), colorectal cancer (CRC), lung cancer (LC), or prostate cancer (PC). Methods Patients aged ≥18 years, diagnosed with BC, CRC, LC, or PC between 2005-2012 at a large hybrid academic-community practice in Northeast Ohio, United States, were included. An ML Extreme Gradient Boosting (XGBoost) algorithm, adapted for survival modeling, was developed using a training subset of the cohort (55% train + 20% test) and ranked 40 to 50 covariates (including social determinants of health, cancer treatment) for predicting 10-year CVD risk for each cancer type using SHAP (SHapley Additive exPlanations) values. The top 10 ML predictors were utilized to create a predictive equation using logistic regression models. This equation was then tested in the cohort validation subset (25%) and subsequently compared to the PCE and PREVENT (both simple and enhanced versions) using the area under the curve (AUC) of the time-dependent receiver operating characteristic curve. The CVD events were identified using ICD codes corresponding to Acute Coronary Syndrome, Ischemic Stroke, and Heart Failure. CVD risk was assessed through Kaplan-Meier. Results We included 10,240 patients (Table 1). The actual 10-year CVD events were: BC 21% (95% CI 19-23), CRC 10% (95% CI 8-12), LC 27% (95% CI 24-30), and PC 20% (95% CI 17-23). The ACC/AHA PCE predicted mean 10-year CVD risks of 16% (95% CI 15-18) for BC, 19% (95% CI 17-21) for CRC, 28% (95% CI 25-32) for LC, and 19% (95% CI 19-20) for PC, with corresponding AUCs of 0.75, 0.65, 0.76, and 0.61, respectively. The PREVENT simple version predicted mean 10-year CVD risks of 13% (95% CI 13-14) for BC, 13% (95% CI 12-13) for CRC, 15% (95% CI 14-15) for LC, and 16% (95% CI 12-19) for PC, with AUCs of 0.55, 0.55, 0.55, and 0.53, respectively. The PREVENT enhanced equation predicted mean 10-year CVD risks of 17% (95% CI 17-18) for BC, 15% (95% CI 14-15) for CRC, 15% (95% CI 15-16) for LC, and 17% (95% 16-19) for PC, with AUCs of 0.75, 0.62, 0.79, and 0.63, respectively. The predictive equation derived from the top 10 ML predictors (Table 2) achieved AUCs of 0.84 for BC, 0.76 for CRC, 0.83 for LC, and 0.71 for PC. Conclusion(s) Conventional CVD equations inadequately assess the risk in patients with BC, CRC, LC, or PC, often resulting in underestimation or overestimation. Cancer-specific ML-derived equations show good performance and emphasize the importance of integrating cancer-related covariates for precise prediction.Table 1Table 2

Machine learning based prediction models for cardiovascular disease risk using electronic health records data: systematic review and meta-analysis

Abstract Background Cardiovascular disease (CVD) remains a major cause of mortality in the UK, prompting the need for improved risk predictive models for primary prevention. Machine learning (ML) models utilizing electronic health records (EHR) offer potential enhancements over traditional risk scores like QRISK3 and ASCVD. Objective To systematically evaluate and compare the efficacy of ML models against conventional CVD risk prediction algorithms using EHR data for medium to long-term (5-10 years) CVD risk prediction. Methods A systematic review and random-effect meta-analysis were conducted according to PRISMA guidelines, assessing studies from 2010 to 2024. We retrieved 32 ML models and 26 conventional statistical models from 20 selected studies, focusing on performance metrics such as Area Under the Curve (AUC) and heterogeneity across models. Results ML models, particularly random forest and deep learning, demonstrated superior performance, with the highest recorded pooled AUCs of 0.865 (95% CI: 0.812-0.917) and 0.847 (95% CI: 0.766-0.927), respectively. These significantly outperformed the conventional risk score of 0.765 (95% CI: 0.734-0.796). However, significant heterogeneity (I² > 99%) and potential publication bias were noted across the studies. Conclusion While ML models show enhanced calibration for CVD risk, substantial variability and methodological concerns limit their current clinical applicability. Future research should address these issues by enhancing methodological transparency and standardization to improve the reliability and utility of these models in clinical settings. Implications This study highlights the advanced capabilities of ML models in CVD risk prediction and emphasizes the need for rigorous validation to facilitate their integration into clinical practice. This review was registered with PROSPERO (CRD42021250058).

Accuracy of alternative PHQ-9 scoring algorithms to screen for depression in people living with HIV in Sub-Saharan Africa.

Screening for depression remains a priority for people living with HIV (PLWH) accessing care. The nine-item Patient Health Questionnaire (PHQ-9) is a widely used depression screening tool, but has limited accuracy when applied across various cultural contexts. We aimed to evaluate the performance of alternative PHQ-9 scoring algorithms in sub-Saharan African PLWH. five HIV programs in Cameroon, Côte d'Ivoire, Kenya, Senegal and the Republic of Congo. Adult PLWH were screened for depression during the 2018-2022 period. Diagnosis confirmation was done by psychiatrist blinded clinical evaluation (gold standard). Diagnostic performances, including sensitivity, and area under the curve (AUC)) of the traditional PHQ-9 scoring (positive screening - score≥10) was compared to alternative scoring algorithms including: i) the presence of ≥1 mood symptom (PHQ-9 items 1&2) combined with ≥2 other symptoms listed in the PHQ-9, and ii) a simplified recoding of each 4-response item into two categories (absence/presence). A total of 735 participants were included (54% female, median age 42 years [IQR 34-50]). Depression was diagnosed by a psychiatrist in 95(13%) participants. Alternative scoring sensitivities (0.59 to 0.74) were higher than that of the traditional score's (0.39). Compared to traditional scoring, AUC were significantly higher for PHQ-9 alternative scoring. Across settings, alternative scoring algorithms increased sensitivity and reduced variability. As a primary screening test, new scoring algorithms appeared to improve the PHQ-9 sensitivity in identifying depression and reduce heterogeneity across settings. This alternative might be considered to identify PLWH in need of referral for further diagnostic evaluations.

Role of artificial intelligence in predicting neurological outcomes in post cardiac resuscitation

Being an extremely high mortality rate condition, cardiac arrest cases have rightfully been evaluated via various studies and scoring factors for effective resuscitative practices and neurological outcomes post resuscitation. This narrative review aims to explore the role of Artificial Intelligence (AI) in predicting neurological outcomes post cardiac resuscitation. Methodology involved detailed review of all relevant recent studies of AI, different machine learning algorithms, prediction tools and assessing their benefit in predicting neurological outcomes in post cardiac resuscitation cases as compared to more traditional prognostic scoring systems and tools. Previously, outcome determining clinical, blood and radiological factors were prone to other influencing factors like limited accuracy and time constraints. Studies conducted also emphasized that to predict poor neurological outcomes, a more multimodal approach helped adjust for confounding factors, interpret diverse datasets and provide a reliable prognosis which only demonstrates need for AI to help overcome challenges faced. Advanced machine learning algorithms like Artificial Neural Networks (ANN) using supervised learning by AI have improved accuracy of prognostic models outperforming conventional models. Several real-world cases of effective AI powered algorithm models have been cited here. Studies comparing machine learning tools like XGBoost, AI Watson, hyperspectral imaging, ChatGPT-4 and AI based gradient boosting have noted their beneficial uses. AI could help reduce workload, healthcare costs and help personalize care, process vast genetic and lifestyle data and help reduce side effects from treatments. Limitations of AI have been covered extensively in this article including data quality, bias, privacy issues and transparency. Our objectives should be to use more diverse data sources, use interpretable data output giving process explanation, validation method and implement policies to safeguard patient data. Despite the limitations, the advancements already made by AI and its potential in predicting neurological outcomes in post cardiac resuscitation cases has been quite promising and boosts a continually improving system, albeit requiring close human supervision with training and improving models, with plans to educate clinicians, the public and sharing collected data.

Exploring the Role of Hemogram-Derived Ratios and Liver Fibrosis Scores in Pulmonary Fibrosis

Background and Objectives: Pulmonary fibrosis, including idiopathic pulmonary fibrosis (IPF) and secondary pulmonary fibrosis (SPF), is a progressive lung disease that significantly impairs respiratory function. Accurate differentiation between IPF and SPF is crucial for effective management. This study explores the association between pulmonary fibrosis and hepatic conditions, evaluating the utility of various hemogram-derived ratios and hepatic fibrosis scores in distinguishing between IPF and SPF. Materials and Methods: We conducted a retrospective study involving patients diagnosed with IPF or SPF at the “Leon Daniello” Clinical Hospital of Pneumology in Cluj-Napoca, Romania. Pulmonary fibrosis was confirmed via imaging techniques, and hepatic steatosis and fibrosis were assessed using non-invasive scores. We analyzed clinical, laboratory, and pulmonary function data, focusing on hemogram-derived ratios and hepatic scores. Statistical analyses, including ROC curves, were used to evaluate the effectiveness of these biomarkers in differentiating IPF from SPF. Results: We included a total of 38 patients with IPF and 28 patients with SPF. Our findings revealed that IPF patients had a significantly higher FIB-4 score compared to SPF patients, suggesting increased hepatic fibrosis risk in IPF, as well as an increased RDW/PLT ratio. Conversely, SPF patients exhibited elevated PLR, PNR, and SII, reflecting a more pronounced inflammatory profile. PLR and PNR demonstrated the highest discriminatory ability between IPF and SPF, while traditional hepatic fibrosis scores showed limited differentiation capabilities. No significant differences in pulmonary function tests were observed across hepatic fibrosis risk categories. Conclusions: The study highlights the value of biomarkers like PLR and PNR in differentiating between IPF and SPF, offering additional diagnostic insights beyond traditional imaging. Integrating hepatic assessments into the management of pulmonary fibrosis could improve diagnostic accuracy and patient care.

Machine-learning approaches for risk prediction after percutaneous coronary intervention: a systematic review and meta-analysis

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. Methods This study was reported according to PRISMA, CHARMS and TRIPOD 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). For all-cause mortality, the pooled C-statistic for top-performing ML models was 0.89 (95% CI, 0.84-0.91), compared to 0.86 (95% CI, 0.80-0.93) for traditional methods (p=0.54). For major bleeding, the pooled C-statistic for ML models was 0.80 (95% CI, 0.77-0.84), versus 0.78 (95% CI, 0.77-0.79) for traditional methods (p=0.02). For MACE, the C-statistic for ML models was 0.83 (95% CI, 0.75-0.91), compared to 0.71 (95% CI, 0.69-0.74) for traditional methods (p=0.007). Out of all included models, only one model was externally validated. Calibration was inconsistently reported across all models. Prediction Model Risk of Bias Assessment Tool (PROBAST) tool demonstrated high risk of bias across all studies. Conclusion ML models marginally outperformed 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 has been hypothesised to improve periprocedural risk stratification, immediate implementation in the clinical setting remains uncertain. Further research is required to overcome methodological and validation limitations​.

Comprehensive risk factor-based nomogram for predicting one-year mortality in patients with sepsis-associated encephalopathy

Sepsis-associated encephalopathy (SAE) is a frequent and severe complication in septic patients, characterized by diffuse brain dysfunction resulting from systemic inflammation. Accurate prediction of long-term mortality in these patients is critical for improving clinical outcomes and guiding treatment strategies. We conducted a retrospective cohort study using the MIMIC IV database to identify adult patients diagnosed with SAE. Patients were randomly divided into a training set (70%) and a validation set (30%). Least absolute shrinkage and selection operator regression and multivariate logistic regression were employed to identify significant predictors of 1-year mortality, which were then used to develop a prognostic nomogram. The model’s discrimination, calibration, and clinical utility were assessed using the area under the receiver operating characteristic curve (AUC), calibration plots, and decision curve analysis, respectively. A total of 3,882 SAE patients were included in the analysis. The nomogram demonstrated strong predictive performance with AUCs of 0.881 (95% CI: 0.865, 0.896) in the training set and 0.859 (95% CI: 0.830, 0.888) in the validation set. Calibration plots indicated good agreement between predicted and observed 1-year mortality rates. The decision curve analysis showed that the nomogram provided greater net benefit across a range of threshold probabilities compared to traditional scoring systems such as Glasgow Coma Scale and Sequential Organ Failure Assessment. Our study presents a robust and clinically applicable nomogram for predicting 1-year mortality in SAE patients. This tool offers superior predictive performance compared to existing severity scoring systems and has significant potential to enhance clinical decision-making and patient management in critical care settings.

Combination therapy of Sanjie Zhentong capsules for endometriosis: Impact on hormone regulation and serum expression of FOLR1 and MSLN.

Examining the impact of Sanjie Zhentong capsules on hormone levels and serum expression of folate receptor 1 (FOLR1) and Mesothelin (MSLN) in endometriosis patients. A cohort of 150 endometriosis patients admitted between June 2019 and June 2023 was divided into 2 groups based on Sanjie Zhentong intake, comprising 75 cases each. Comparative analyses encompassed uterine artery hemodynamic parameters, ultrasound (B-mode) findings, Visual Analog Scale scores, traditional Chinese medicine symptom scores, Endometriosis Health Profile-30 scores, and serum levels of FOLR1, MSLN, and sex hormones before and after treatment. Post-treatment, both groups exhibited increased peak systolic velocity compared to pretreatment, with the Sanjie Zhentong group showing a significantly higher increase (P < .05). Moreover, resistance index decreased in both groups post-treatment, with the Sanjie Zhentong group displaying a greater reduction (P < .05). Adnexal mass diameters, endometrial thickness, and uterine volume decreased post-treatment in both groups, with the Sanjie Zhentong group experiencing a more pronounced decrease (P < .05). Serum FOLR1, MSLN, and sex hormone levels also decreased post-treatment in both groups, with the Sanjie Zhentong group exhibiting a more significant decrease (P < .05). Additionally, pain scores, traditional Chinese medicine symptoms, and Endometriosis Health Profile-30 scores decreased post-treatment in both groups, with the Sanjie Zhentong group demonstrating a greater reduction (P < .05). Sanjie Zhentong capsules demonstrate efficacy in regulating sex hormones, reducing serum FOLR1 and MSLN expression, alleviating pain, shrinking adnexal masses, decreasing uterine size, and improving uterine artery blood flow in endometriosis patients.

Machine learning and propensity score matching for evaluating the effect of special education services on childrens later math performances

The goal of the research is to analyze the effect of special education service brought to childrens later math performance. The dataset is derived from Early Childhood Longitudinal Studies(ECLS) program and the children being studied come from diverse socioeconomic and racial/ethnic backgrounds. We applied PSM and modern machine learning methods including OLS, KNN, BART and MLP on the data in order to calculate the average treatment effect of special education services. It turned out that all the listed machine learning algorithms with comparatively low STD outperformed the traditional propensity score matching. KNN, BART and OLS excelled, offering much more stable calculations. The value of ATE computed through all the methods appeared below zero. By applying linear regression and PCA on all the influencing factors, the analysis revealed that the differences of some factors between the controlled and exposed groups led better math performances to appear usually in the absence of special treatment. Thus, special treatment effect led the trained model to predict lower scores, which finally caused the difference to be negative.

Impact of a New Preoperative Stratification Based on Cardiac Structural Compromise in Patients with Severe Aortic Stenosis Undergoing Valve Replacement Surgery

Introduction and objectives: Aortic valve replacement surgery (SAVR) remains a recommended indication, though its pre-surgical stratification is an ongoing challenge. Despite the widespread use of scores like the STS and EuroSCORE II, they have a number of limitations, while often neglecting structural parameters like left ventricular hypertrophy or left atrium volume. This study aimed to evaluate whether a new adaptation of the Généreux classification in the preoperative risk stratification of severe aortic stenosis (AS) is associated with the primary outcome, and to compare it with the original classification versus the traditional scores in short- and long-term follow-up. Methods: We conducted a retrospective, single-center study involving patients with confirmed severe AS who underwent SAVR. The new stratification categorized patients into three stages. Cox regression analyses were conducted to identify factors associated with mortality, with survival analysis performed using Kaplan–Meier curves. A p-value &lt; 0.05 was considered statistically significant. Results: A total of 508 patients were included. Stage 3 patients had a lower median age (67 years). The median EuroSCORE II and STS scores were 2.75 and 2.62%, respectively (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). Multivariable 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 variables of mortality. The original Généreux scale AUC was higher (AUC: 0.760, 95% CI: 0.692–0.829) compared to the modified Généreux scale (AUC: 0.758, 95% CI: 0.687–0.829). However, no statistical differences were found between the different scales. Conclusions: Preoperative three-stage classification and low transaortic gradient are factors associated with increased all-cause mortality in patients undergoing SAVR. The proposed staging system performed better in the mortality analysis than EuroSCORE II and STS and was similar to the original classification.

Assessing the Speed–Accuracy Tradeoff in Psychological Testing Using Experimental Manipulations

The speed–accuracy tradeoff (SAT), where increased response speed often leads to decreased accuracy, is well established in experimental psychology. However, its implications for psychological assessments, especially in high-stakes settings, remain less understood. This study presents an experimental approach to investigate the SAT within a high-stakes spatial ability assessment. By manipulating instructions in a within-subjects design to induce speed variations in a large sample ( N = 1,305) of applicants for an air traffic controller training program, we demonstrate the feasibility of manipulating working speed. Our findings confirm the presence of the SAT for most participants, suggesting that traditional ability scores may not fully reflect performance in high-stakes assessments. Importantly, we observed individual differences in the SAT, challenging the assumption of uniform SAT functions across test takers. These results highlight the complexity of interpreting high-stakes assessment outcomes and the influence of test conditions on performance dynamics. This study offers a valuable addition to the methodological toolkit for assessing the intraindividual relationship between speed and accuracy in psychological testing (including SAT research), providing a controlled approach while acknowledging the need to address potential confounders. Future research may apply this method across various cognitive domains, populations, and testing contexts to deepen our understanding of the SAT’s broader implications for psychological measurement.

Comparing ensemble learning algorithms and severity of illness scoring systems in cardiac intensive care units: a retrospective study.

Beatriz Nistal-Nuño designed a machine learning system type of ensemble learning for patients undergoing cardiac surgery and intensive care unit cardiology patients, based on sequences of cardiovascular physiological measurements and other intensive care unit physiological measurements in addition to static features, which generates a score for prediction of mortality of cardiac intensive care unit patients. ■ Gradient Boosting Machine and Random Forest models were built for prediction of mortality at cardiac intensive care units. ■ A total of 9,761 intensive care unit stays of patients admitted under a Cardiac Surgery and Cardiac Medical services were studied. ■ The AUROC and AUPRC values were significantly superior to seven conventional systems compared. ■ The machine learning models' calibration curves were substantially closer to the ideal line. Logistic Regression has been used traditionally for the development of most predictor tools of intensive care unit mortality. The purpose of this study is to combine shared risk factors between patients undergoing cardiac surgery and intensive care unit cardiology patients to develop a risk score for prediction of mortality in cardiac intensive care unit patients, using machine learning. Gradient Boosting Machine and Distributed Random Forest models were developed based on 9,761 intensive care unit-stays from the MIMIC-III database. Sequential and static features were collected. The primary endpoint was intensive care unit mortality prediction. Discrimination, calibration, and accuracy statistics were evaluated. The predictive performance of traditional scoring systems was compared. Machine learning models' AUROC and AUPRC were significantly superior to all conventional systems for the primary endpoint (p<0.05), with AUROC of 0.9413 for Gradient Boosting Machine and 0.9311 for Distributed Random Forest. Sensitivity was 0.6421 for Gradient Boosting Machine, 0.6 for Distributed Random Forest, and <0.3 for all conventional systems except for serial SOFA (0.6316). Precision was 0.574 for Gradient Boosting Machine, 0.566 for Distributed Random Forest, and <0.5 for all conventional systems. Diagnostic odds ratio was 58.8144 for Gradient Boosting Machine, 51.2926 for Distributed Random Forest and <34 for all conventional systems. Brier score was 0.025 for Gradient Boosting Machine and 0.028 for Distributed Random Forest, being worse for the traditional systems. Calibration curves of Gradient Boosting Machine and Distributed Random Forest were substantially closer to the ideal line. The machine learning models showed superiority over the traditional scoring systems compared, with Gradient Boosting Machine having the best performance. Discrimination and calibration were excellent for Gradient Boosting Machine, followed by Distributed Random Forest. The machine learning methods exhibited better capacity for most accuracy statistics.

A-174 Comparison of Bleeding Risk Scales in Elderly Patients With Persistent Atrial Fibrillation

Abstract Background Atrial fibrillation is a significant cause of thromboembolism and sudden death in the world making anticoagulant treatment a cornerstone; however, it is associated with bleeding risk. Currently, there are no studies in Ecuador that support the prognostic validity of the recent bleeding risk scales, as well as the lack of research to discover novel methods that are applicable and more accessible to use within the medical care setting.The Hemorr2hages, ORBIT and ATRIA scores represent a promising approach for those health centers that do not have INR available and consequently cannot measure risk through HASBLED (internationally recommended score). In this way, hemorrhagic events can be prevented in patients with atrial fibrillation with anticoagulant treatment without exception. Our main goal is to compare the predictive bleeding risk scores of 3 scales (Hemorr2hages, ORBIT, ATRIA) versus traditional HASBLED score. Methods In this retrospective cohort study, we assessed chronic persistent atrial fibrillation in 100 patients using the electronic medical records in an outpatient clinic in Guayaquil, Ecuador. We calculated 3 bleeding risk scores for each patient according to the variables measured in each one of them and used those to compare the categories against HASBLED’s. A Pearson correlation index was obtained, and ROC performance curves were made. P value &amp;lt;0.05 was deemed statistically significant. Results Of the 100 patients included, 65% were males, and mean age was 75±10.73. We reported only 6% bleeding events during the follow up. According to HASBLED score: 31% were at high risk. In comparison: 40% and 37% were also at high risk in Hemorr2hages and ATRIA scores, respectively. HASBLED was fairly correlated with Hemorr2hages and ATRIA scores (Pearson’s R: 0.617, p:&amp;lt;0.001; R:0.528, p:&amp;lt;0.001, respectively). Only 22% were classified at high risk by the ORBIT score. ROC curve analysis showed ORBIT’s AUC was 0.963, while Hemorr2hages, ATRIA and HASBLED were 0.931, 0.925, and 0.732 (p:&amp;lt;0.001), respectively. Conclusions In our sample, ORBIT score was better correlated with bleeding episodes than the other scales. This a promising approach for those health centers that do not count with INR reactive materials available for it to be measured at their laboratories. Further research is needed to accurately analyze whether criterion included in ORBIT score might predict bleeding scores better than HASBLED, Hemorr2hages and ORBIT tools; since the items required to calculate it are more readily accessible.

The SpO2/FiO2 Ratio Combined with Prognostic Scores for Pneumonia and COVID-19 Increases Their Accuracy in Predicting Mortality of COVID-19 Patients

Background: Identifying high-risk COVID-19 patients is critical for emergency department decision-making. Our study’s primary objective was to identify new independent predictors of mortality and their predictive utility in combination with traditional pneumonia risk assessment scores and new risk scores for COVID-19 developed during the pandemic. Methods: A retrospective study was performed in two Italian University Hospitals. A multivariable logistic model was used to locate independent parameters associated with mortality. Results: Age, PaO2/FiO2, and SpO2/FiO2 ratios were found to be independent parameters associated with mortality. This study found that the Pneumonia Severity Index (PSI) was superior to many of the risk scores developed during the pandemic, for example, the International Severe Acute Respiratory Infection Consortium Coronavirus Clinical Characterisation Consortium (ISARIC 4C) (AUC 0.845 vs. 0.687, p &lt; 0.001), and to many of the risk scores already in use, for example, the National Early Warning Score 2 (NEWS2) (AUC 0.845 vs. 0.589, p &lt; 0.001). Furthermore, our study found that the Pneumonia Severity Index had a similar performance to other risk scores, such as CRB-65 (AUC 0.845 vs. 0.823, p = 0.294). Combining the PaO2/FiO2 or SpO2/FiO2 ratios with the risk scores analyzed improved the prognostic accuracy. Conclusions: Adding the SpO2/FiO2 ratio to the traditional, validated, and already internationally known pre-pandemic prognostic scores seems to be a valid and rapid alternative to the need for developing new prognostic scores. Future research should focus on integrating these markers into existing pneumonia scores to improve their prognostic accuracy.