Stratification Model Research Articles

Improving event prediction using general practitioner clinical judgement in a digital risk stratification model: a pilot study

BackgroundNumerous tools based on electronic health record (EHR) data that predict risk of unscheduled care and mortality exist. These are often criticised due to lack of external validation, potential for low predictive ability and the use of thresholds that can lead to large numbers being escalated for assessment that would not have an adverse outcome leading to unsuccessful active case management. Evidence supports the importance of clinical judgement in risk prediction particularly when ruling out disease. The aim of this pilot study was to explore performance analysis of a digitally driven risk stratification model combined with GP clinical judgement to identify patients with escalating urgent care and mortality events.MethodsClinically risk stratified cohort study of 6 GP practices in a deprived, multi-ethnic UK city. Initial digital driven risk stratification into Escalated and Non-escalated groups used 7 risk factors. The Escalated group underwent stratification using GP global clinical judgement (GCJ) into Concern and No concern groupings.Results3968 out of 31,392 patients were data stratified into the Escalated group and further categorised into No concern (n = 3450 (10.9%)) or Concern (n = 518 (1.7%)) by GPs. The 30-day combined event rate (unscheduled care or death) per 1,000 was 19.0 in the whole population, 67.8 in the Escalated group and 168.0 in the Concern group (p < 0.001). The de-escalation effect of GP assessment into No Concern versus Concern was strongly negatively predictive (OR 0.25 (95%CI 0.19–0.33; p < 0.001)).The whole population ROC for the global approach (Non-escalated, GP No Concern, GP Concern) was 0.614 (0.592—0.637), p < 0.001, and the increase in the ROC area under the curve for 30-day events was all focused here (+ 0.4% (0.3–0.6%, p < 0.001), translating into a specific ROC c-statistic for GP GCJ of 0.603 ((0.565—0.642), p < 0.001).ConclusionsThe digital only component of the model performed well but adding GP clinical judgement significantly improved risk prediction, particularly by adding negative predictive value.

Reassessing cardiovascular risk stratification in men with erectile dysfunction.

Erectile dysfunction (ED) is an independent and strong marker of cardiovascular disease (CVD) risk. The Princeton Consensus aimed to evaluate and manage cardiovascular risk in men with ED and no known cardiovascular disease, focusing on identifying those requiring additional cardiologic work-up. It has recently been updated to the American population demographics, but European recommendations are needed. It was developed a cross-sectional investigation including erectile dysfunction patients. Data were collected from hospital registries. Two risk stratification models were employed and compared: Princeton Consensus Criteria (PC) and European Society of Cardiology (ESC) CVD Risk Criteria. The objective was to stress the importance of the changes in IV Princeton Consensus recommendations in stratifying CVD risk in men with erectile dysfunction using a model validated in European men. A total of 137 patients with ED, with a mean age of 57.1 years old, were included. According to the PC criteria, 39.7% of the patients were "Low Risk". When using ESC criteria, the proportion of "Low Risk" patients were significantly lower (12%, p < 0.05). Among "Low Risk" patients according to the PC, 52.5% and 20% were classified as High and Very high risk according to ESC criteria, respectively. One myocardial infarction was reported. The patient was classified as "Low Risk" according to the PC, but the ESC criteria categorized him as "high risk". PC is less sensitive than ESC recommendations detecting CVD. It raises concerns that Urologists could be overlooking patients with undiagnosed CVD, consequently missing out on opportunities for prevention of major cardiovascular events (MACEs) and premature deaths.

Clinical profiles in autism spectrum disorder: Enhancing diagnosis, treatment, and overall health outcomes

AbstractBackgroundAutism spectrum disorder (ASD) is a neurodevelopmental condition characterized by significant challenges in communication, behavior, and social interaction. The prevalence of ASD is rising, with current estimates indicating that it affects 1 in 36 children in the United States. Traditional diagnostic methods often fail to capture the full complexity of ASD, leading to incomplete treatment approaches. This study aimed to enhance diagnostic and therapeutic approaches to ASD by identifying and categorizing 10 clinical profiles using precision medicine.MethodsThis study presents a new stratification model for ASD that classifies individuals based on prevalent comorbidities and underlying biological mechanisms. The model is based on a synthesis of existing literature, clinical observations, and expert insights. Data were collected from detailed clinical evaluations, patient histories, and laboratory tests, and the model was refined through iterative analysis. It integrates findings from genetic, neurological, and psychiatric research to develop a comprehensive approach for diagnosing and treating ASD‐related comorbidities.ResultsThe study proposes 10 clinical profiles of ASD: syndromic, gastrointestinal, metabolic, mitochondrial, endocrine, bioaccumulative, infectious, immunological, inflammatory, and Neurological. Each profile is associated with specific symptoms and comorbidities influenced by genetic, environmental, and biological factors.ConclusionsThe stratification model proposed in this study enhances the diagnosis and treatment of ASD by recognizing its heterogeneity. By identifying specific clinical profiles, healthcare providers can develop personalized and integrated therapeutic strategies to improve the overall health outcomes of individuals with ASD.

Development and internal validation of time-to-event risk prediction models for major medical complications within 30 days after elective colectomy.

Patients undergoing colectomy are at risk of numerous major complications. However, existing binary risk stratification models do not predict when a patient may be at highest risks of each complication. Accurate prediction of the timing of complications facilitates targeted, resource-efficient monitoring. We sought to develop and internally validate Cox proportional hazards models to predict time-to-complication of major complications within 30 days after elective colectomy. We studied a retrospective cohort from the multicentered American College of Surgeons National Surgical Quality Improvement Program procedure-targeted colectomy dataset. Patients aged 18 years or above, who underwent elective colectomy between January 1, 2014 and December 31, 2019 were included. A priori candidate predictors were selected based on variable availability, literature review, and multidisciplinary team consensus. Outcomes were mortality, hospital readmission, myocardial infarction, cerebral vascular events, pneumonia, venous thromboembolism, acute renal failure, and sepsis or septic shock within 30 days after surgery. The cohort consisted of 132145 patients (mean ± SD age, 61 ± 15 years; 52% females). Complication rates ranged between 0.3% (n = 383) for cardiac arrest and acute renal failure to 5.3% (n = 6986) for bleeding requiring transfusion, with readmission rate of 8.6% (n = 11415). We observed distinct temporal patterns for each complication: the median [quartiles] postoperative day of complication diagnosis ranged from 1 [0, 2] days for bleeding requiring transfusion to 12 [6, 18] days for venous thromboembolism. Models for mortality, myocardial infarction, pneumonia, and renal failure showed good discrimination with a concordance > 0.8, while models for readmission, venous thromboembolism, and sepsis performed poorly with a concordance of 0.6 to 0.7. Models exhibited good calibration but ranges were limited to low probability areas. We developed and internally validated time-to-event prediction models for complications after elective colectomy. Once further validated, the models can facilitate tailored monitoring of high risk patients during high risk periods. Clinicaltrials.gov (NCT05150548; Principal Investigator: Janny Xue Chen Ke, M.D., M.Sc., F.R.C.P.C.; initial posting: November 25, 2021).

Development of machine learning-based models to predict congenital heart disease: A matched case-control study

BackgroundThe current congenital heart disease (CHD) prediction tools lack adequate interpretability and convenience, hindering the development of personalized CHD management strategies. We developed a machine learning-based risk stratification model for CHD prediction. MethodsThis study utilized data from 1,759 participants in a case-control study of CHD conducted across six birth defects surveillance hospitals located in Xi’an, Shaanxi Province, Northwest China, spanning from January 2014 to December 2016. The data was partitioned into training and testing datasets with a ratio of 7:3. Predictors were selected from a total of 47 input variables through the Least Absolute Shrinkage and Selection Operator (LASSO). Five machine learning algorithms were used to build the CHD risk prediction models. Model performance was assessed based on a range of learning metrics, including the area under the receiver operating characteristic curve (AUROC), F1 score, and Brier score. Permutation feature importance was employed to elucidate the prediction model. The best-performing model was used to conduct the risk scores. ResultsThe eXtreme Gradient Boosting (XGB) model demonstrated superior performance among CHD prediction models, achieving an AUROC of 0.772 (95 % CI 0.728, 0.817) in the testing dataset and 0.738 (0.699, 0.775) in the external validation dataset. The pivotal predictors (top 3) identified by the model included living in rural areas, the low wealth index, and folic acid supplements (<90 days). The resultant risk score exhibited robust calibration capabilities. Utilizing the risk scores, participants were stratified into low, moderate, and high-risk categories, signifying substantial variations in CHD risk. ConclusionThis study underscores the feasibility and efficacy of employing a machine learning-based approach for CHD prediction. The risk scores exhibited potential in identifying pregnant women at high risk for fetal CHD, offering valuable insights for guiding primary prevention and CHD management.

The markers and risk stratification model of intracranial aneurysm instability based on large Chinese cohort

The markers and risk stratification model of intracranial aneurysm instability based on large Chinese cohort

Multi-HCC: A practical model to prioritize patients with hepatocellular carcinoma on the liver transplant waiting list

Background and AimsCurrently, patients with hepatocellular carcinoma (HCC) in the United States are assigned a uniform score relative to the median MELD at transplant (MMaT-3) after a minimum 6-month waiting period. Here, we develop a risk stratification model for patients with HCC, using the available and objective variables at time of listing. MethodsWe identified adult liver transplant candidates with approved HCC exception in the OPTN database from 2015-2022. Cox regression analysis, as well as machine learning models (random survival forest and neural network), were used to develop models predicting waitlist dropout. Predicted waitlist dropout for patients with HCC was scaled to patients without exception using MELD 3.0. Results18,273 patients with HCC were listed for liver transplant with a median MELD 3.0 of 11 (IQR 8-15) and AFP 6 (IQR 4-17). Since all models performed similarly, a parsimonious Cox-based model comprised of MELD 3.0, AFP, and tumor burden, Multi-HCC (Model for Urgency for Liver Transplantation in HCC), was selected, with a c-statistic of 0.71 (95% CI 0.69-0.74) for 6-month dropout in the validation set, outperforming previous models, including HALT-HCC, deMELD, and MELD-Eq. ConclusionAn urgency-based priority system for patients with HCC, similar to MELD for patients with chronic liver disease, is achievable with a parsimonious model incorporating AFP, MELD 3.0, and tumor size. This approach can be applied to the liver allocation system to prioritize patients with HCC and can inform decision-making regarding urgency weights for exception cases in the upcoming continuous distribution system.

Exploring the Utility of the Reynolds and Framingham Risk Stratification Models in Predicting the Presence and Severity of Coronary Artery Disease in Chinese Patients.

Coronary artery disease (CAD) is one of the leading causes of mortality and morbidity worldwide. Thus, a simple and practical method to identify it is urgently needed. This study aims to explore the correlation between the Reynolds and Framingham risk scores and the Gensini score (GS), along with their utility in predicting the presence and severity of CAD.This research represents a single-center retrospective study. A total of 13,824 Chinese patients were enrolled in our study. GS was used to assess and group the presence and severity of CAD. The Spearman rank test and the logistic regression analysis were then performed to explore the correlation between the Reynolds/Framingham risk scores and the GS. The receiver-operating characteristic curve analysis was used to evaluate the performance of the Reynolds and Framingham risk stratification models.Both the Reynolds and Framingham risk scores showed statistically significant positive correlations with the presence (r (Reynolds): 0.179; r (Framingham): 0.182) and severity (r (Reynolds): 0.232; r (Framingham): 0.259) of CAD. Both scores had statistically significant powers of predicting the presence (cut-off value [Reynolds]: 4.20%; cut-off value [Framingham]: 12.33%) and severity (cut-off value [Reynolds]: 8.94%; cut-off value [Framingham]: 20.59%) of CAD. The Reynolds risk score showed a better performance compared to the Framingham risk score for both the presence (Reynolds area under the curve (AUC): 0.649 versus Framingham AUC: 0.637 P < 0.05) and severity (Reynolds AUC: 0.656 versus Framingham AUC: 0.645 P < 0.05) of CAD.Our study suggests that the Reynolds and Framingham risk scores can be used to predict the presence and severity of CAD in the Chinese population. The Reynolds risk score showed great superiority in the women's group, while the Framingham risk score had a better performance in predicting severity as a whole.

Monetary and Non-Monetary Inequalities in Modern Russian Society: Dynamics of the Recent Decade

The article examines the monetary and non-monetary inequalities dynamics in Russian society over the last decade through the prism of social stratification models using the RLMS HSE data. It is shown that the general configurations of monetary and non-monetary inequalities share similar characteristics and similar trends. As a result, Russian society today is not only a society of dominant middle strata, both in terms of income and quality of life, but is also characterized by a further dynamic of “median averaging” in the mass strata of the population. The middle stratum in terms of quality of life is larger than the median group in terms of income: more than two thirds of the population are now in a very similar position in terms of the qualitative characteristics of their daily lives, regardless of the fact that their income levels may differ. The configuration of non-monetary inequalities is characterized by greater volatility in the shares of the polar groups , which are more responsive to external changes in the socio-economic context, while the configuration of monetary inequality (assessed using the relative approach based on median income), is characterized by greater monotonicity and a slower rate of change over the last 10 years. In the long run, however, the configuration of income inequality has also changed quite significantly: the dominance of the median group became characteristic only in the last decade. At the micro level, the position in the income hierarchy is not strictly linked to the respective position in the quality of life hierarchy. The results show that the task of reducing inequality is not trivial.

Endoplasmic reticulum stress-related signatures: a game-changer in prognostic stratification for hepatocellular carcinoma.

Hepatocellular carcinoma (HCC) has limited therapeutic options and a poor prognosis. The endoplasmic reticulum (ER) plays a crucial role in tumor progression and response to stress, making it a promising target for HCC stratification. This study aimed to develop a risk stratification model using ER stress-related signatures. We utilized transcriptome data from The Cancer Genome Atlas and Gene Expression Omnibus, which encompass whole-genome expression profiles and clinical annotations. Machine learning algorithms, including the least absolute shrinkage and selection operator, random forest, and support vector machine recursive feature elimination, were applied to the key genes associated with HCC prognosis. A prognostic system was developed using univariate Cox hazard analysis and least absolute shrinkage and selection operator Cox regression, followed by validation using Kaplan-Meier analysis and receiver operating characteristic curves. Tumor immune dysfunction and exclusion tools were used to predict immunotherapy responsiveness. Two distinct clusters associated with ER stress were identified in HCC, each exhibiting unique clinical and biological features. Using a computational approach, a prognostic risk model, namely the ER stress-related signature, was formulated, demonstrating enhanced predictive accuracy compared with that of existing prognostic models. An effective clinical nomogram was established by integrating the risk model with clinicopathological factors. Patients with lower risk scores exhibited improved responsiveness to various chemotherapeutic, targeted, and immunotherapeutic agents. The critical role of ER stress in HCC is highlighted. The ER stress-related signature developed in this study is a powerful tool to assess the risk and clinical treatment of HCC.

Development and Validation of a PIVKA-II-Based Model for HCC Risk Stratification in Patients With HCV-Related Cirrhosis Successfully Treated With DAA.

Patients with hepatitis C virus (HCV)-related cirrhosis with sustained virological response (SVR) to direct-acting antivirals (DAA) remain at risk of developing hepatocellular carcinoma (HCC). Recently, serum protein induced by vitamin K absence or antagonist-II (PIVKA-II) has shown promising results as an HCC-predictive biomarker. We aimed to develop and validate a PIVKA-II-based model for HCC risk stratification in cirrhotic patients with SVR to DAA. A total of 1220 consecutive patients (Turin, n = 531; Pisa, n = 335; Milan, n = 354) with HCV-related cirrhosis treated with DAA were included in the study. Patients were retrospectively allocated to the training cohort (Turin+Pisa; median follow-up [FU] 39, 22-55 months; incident HCC: 93 [10.7%]) and validation cohort (Milan; median FU 49.0, 35.0-52.0 months; incident HCC: 19 [5.4%]). Serum PIVKA-II levels were measured using the LumipulseG system (Fujirebio, Japan) at SVR12 (Turin and Pisa cohorts) or the end of treatment (Milan cohort). Using Cox regression analysis, a model including PIVKA-II combined with age, sex, ALT, AST, γGT, platelet count, albumin and total bilirubin was derived from the training cohort (C-index = 0.72). In the validation cohort, the model showed a C-index of 0.71 with an area under the curve of 0.84 for identifying patients who developed HCC during the first 12 months of FU. When patients were grouped into three risk categories, the cumulative incidence of HCC was 2.7%, 4.0% and 14.3% in the low-, medium- and high-risk groups, respectively (p < 0.001). Notably, no HCC occurred within 3 years of FU in the low-risk group. Our PIVKA-II-based model showed satisfactory accuracy for HCC risk stratification and may represent a valuable tool for implementing risk-based surveillance protocols in patients with HCV-related cirrhosis with SVR to DAA.

Preoperative Multivariable Model for Risk Stratification of Hypoxemia During One-Lung Ventilation

BACKGROUND: Hypoxemia occurs with relative frequency during one-lung ventilation (OLV) despite advances in airway management. Lung perfusion scans are thought to be one of the most accurate methods to predict hypoxemia during OLV, but their complexity and costs are well-known limitations. There is a lack of preoperative stratification models to estimate the risk of intraoperative hypoxemia among patients undergoing thoracic surgery. Our primary objective was to develop a risk stratification model for hypoxemia during OLV based on preoperative clinical variables. METHODS: This is a single-center, retrospective cohort study including 3228 patients who underwent lung resections with OLV from 2017 to 2022, at a tertiary academic health care center in the United States. Vital signs and ventilator settings were retrieved minute by minute. Intraoperative hypoxemia was defined as an episode of oxygen desaturation (Spo 2 &lt;90%) for at least 5 minutes. Demographic and clinical characteristics were included in a stepwise logistic regression, which was used for the selection of predictors of the risk score model. All patients included in this cohort underwent elective lung surgery in lateral decubitus position, with double lumen tube and placement confirmation with fiberoptic bronchoscopy. Our model was validated internally using area under the receiver operating curves (AUC) with bootstrapping correction. RESULTS: The incidence of hypoxemia during OLV was 8.9% (95% confidence interval [CI], 8.0–10.0). Multivariable logistic regression identified 9 risk factors with their corresponding scoring: preoperative Spo 2 &lt;92% (15 points), hemoglobin &lt;10 g/dL (6 points), age &gt;60 years old (4 points), male sex (4 points), body mass index &gt;30 kg/m2 (8 points), diabetes mellitus (4 points), congestive heart failure (7 points), hypertension (3 points), and right-sided surgery (3 points). The AUC of the model after bootstrap correction was 0.708 (95% CI, 0.676–0.74). Based on the highest Youden index, the optimal score for predicting intraoperative hypoxemia was 13. The risk of hypoxemia increased from 4.7% in the first quartile of scores (0–13 points), to 32% in the third quartile (27–39 points), and 83.3% in the fourth quartile (&gt;39 points). At scores of 20 or greater, the specificity of the model exceeded 90% and reached a positive predictive value of 80%. CONCLUSIONS: The risk of hypoxemia during OLV can be stratified preoperatively using accessible clinical variables. Our risk model is well calibrated but showed moderate discrimination for predicting intraoperative hypoxemia. The accuracy of preoperative models for risk stratification of hypoxemia during OLV should be explored in prospective studies.

Current Situation, Existing Problems and Prospect of the Study of Social Stratification in Contemporary China

Introduction. Under the backdrop of market economy and social transformation in China, the class structure of society has undergone profound changes, and the traditional class division is no longer relevant. However, there are still some unresolved problems in the study of social strata in China. The lack of diversity and comparability of research methods limits the depth and scope of research. Relatively few studies have been conducted on some emerging classes. Research on the relationship between social class and other social issues is insufficient, such as the relationship between class and education, class and income distribution, etc., are still limited. Methodology and sources. At present, a social classification model has been proposed to study social stratification in China, taking into account the characteristics of China's national conditions. A large number of empirical studies have revealed the evolution and characteristics of China's social class structure. The mechanism of social class formation and the factors influencing them have been studied, which has provided theoretical support for social development. Modern stratification models of Chinese authors have been used for the analysis in comparison with traditional models. Results and discussion. The study of social stratification in China inherited the theoretical framework and empirical research methods of Western social scientists, and there are also attempts to develop its own model of social stratification in combination with the actual situation in China. The structure of social stratification in China is characterized by the need to take into account the state redistribution system and the market economy model. However, there is a consensus that government officials are at the top of the social hierarchy, and the class of peasants and unemployed are at the bottom of society; mental workers (white collars) are higher than manual workers (blue collars). The results of studies on the impact of human capital on social stratification show that gender and educational level have universal significance in society; household registration system and housing type are special independent variables that affect social stratification in China more than in other countries, etc. However, there is a lack of relevant empirical studies that could provide specific quantitative data showing how independent variables affect social stratification in China. Many new social and professional groups have emerged in Chinese society. In recent years, some Chinese scholars have studied such specific social and professional groups, the most widespread and in demand in the labor market in China, taking into account the digitalization processes. Conclusion. It is necessary to further explore the methods and models of social stratification suitable for China's national conditions so as to cover the characteristics of social class diversity. It is necessary to strengthen the research on the relationship between social class and other social issues so as to provide more effective policy recommendations for social development. It is also necessary to strengthen the research on emerging classes, pay attention to their social status, mobility and responsibilities, and provide more effective support and guidance for their development.

Time-Point Clinical Outcomes in Patients With Acute Myocardial Infarction: One Step for Personalized Medicine

Limited data exist regarding time-point risk stratification models after acute coronary syndrome. This study aimed to investigate time-point mortality rates in patients with acute myocardial infarction, focusing on comparison by type of myocardial infarction, in a real-world cohort. A total of 12,836 patients from a nationwide Korean registry were analyzed. Mortality rates at yearly, monthly, and weekly time points after admission were calculated by dividing the number of deaths during a specific period by the number of patients at risk in the same period for ST-elevation myocardial infarction (STEMI) and non-STEMI (NSTEMI) groups. In the first week after admission, patients with STEMI had a significantly higher mortality rate than patients with NSTEMI (4.62% vs 1.79%, p <0.001). However, this trend was inverted since the second week. The higher mortality rate in patients with STEMI versus NSTEMI was inverted since the second week for male patients but only since the tenth week for female patients. Temporal assessment of correlates of mortality revealed that several baseline variables, including Killip class, systolic blood pressure, total cholesterol, and STEMI diagnosis, had significantly different effects on deaths over time. In conclusion, temporal assessment of time-point outcomes from the Korean registry revealed that an initially higher mortality rate in patients with STEMI versus NSTEMI was inverted in the second week. This outcome assessment could be a step toward developing an advanced risk prediction model for time-course personalized medicine. Further studies are needed to clarify this issue.

Enhancing risk stratification models in localized prostate cancer by novel validated tissue biomarkers.

Localized prostate cancer (PCa) is a largely heterogeneous disease regarding its clinical behavior. Current risk stratification relies on clinicopathological parameters and distinguishing between indolent and aggressive cases remains challenging. To improve risk stratification, we aimed to identify new prognostic markers for PCa. We performed an in silico analysis on publicly available PCa transcriptome datasets. The top 20 prognostic genes were assessed in PCa tissue samples of our institutional cohort (n = 92) using the NanoString nCounter technology. The three most promising candidates were further assessed by immunohistochemistry (IHC) in an institutional (n = 121) and an independent validation cohort from the EMPACT consortium (n = 199). Cancer-specific survival (CSS) and progression-free survival (PFS) were used as endpoints. Our in silico analysis identified 113 prognostic genes. The prognostic values of seven of the top 20 genes were confirmed in our institutional radical prostatectomy (RPE) cohort. Low CENPO, P2RX5, ABCC5 as well as high ASF1B, NCAPH, UBE2C, and ZWINT gene expressions were associated with shorter CSS. IHC analysis confirmed the significant associations between NCAPH and UBE2C staining and worse CSS. In the external validation cohort, higher NCAPH and ZWINT protein expressions were associated with shorter PFS. The combination of the newly identified tissue protein markers improved standard risk stratification models, such as D'Amico, CAPRA, and Cambridge prognostic groups. We identified and validated high tissue levels of NCAPH, UBE2C, and ZWINT as novel prognostic risk factors in clinically localized PCa patients. The use of these markers can improve routinely used risk estimation models.

Abstract 4138334: Identification and Immunological Characterization of Arrhythmia-Related Molecular Clusters in Ischemic Cardiomyopathy

Ischemic cardiomyopathy, a severe cardiac condition resulting from prolonged myocardial ischemia, is characterized by ventricular dilation, dysfunction, and an increased risk of life-threatening arrhythmias. Arrhythmia, a common complication in ischemic cardiomyopathy, is associated with poor clinical outcomes. Recent studies have indicated that the molecular heterogeneity of ischemic cardiomyopathy may contribute to the development of arrhythmias. Therefore, our study aimed to explore arrhythmia-related molecular clusters in ischemic cardiomyopathy and establish a prediction model for risk stratification. Based on gene expression profiles of ischemic cardiomyopathy patients, we analyzed the dysregulation of arrhythmia-associated genes and the associated immune characteristics (Figure 1A-C). Using unsupervised clustering analysis, we identified distinct arrhythmia-related molecular clusters in ischemic cardiomyopathy patients (Figure 1D-F). Cluster-specific differentially expressed genes were further identified using weighted gene co-expression network analysis (WGCNA). Functional enrichment analysis revealed significant differences in biological processes and pathways between the clusters (Figure 1G-H). Subsequently, we developed a prediction model using a random forest algorithm, which showed superior performance in distinguishing patients with different arrhythmia risks (Figure 1I-J). This forest model demonstrated excellent performance in one external validation datasets with AUC values of 0.891. In conclusion, our study provides novel insights into the molecular basis of arrhythmias in ischemic cardiomyopathy and establishes a prediction model with potential clinical utility for risk stratification and targeted therapies. Further investigation into the specific mechanisms underlying the identified molecular clusters may reveal new therapeutic targets for the management of arrhythmias in ischemic cardiomyopathy patients.

Abstract 4116410: A Novel Deep Learning Approach for Prediction of Right Heart Failure After Left Ventricular Assist Device Implantation using Pulmonary Artery Pressure Tracings

Introduction: Left ventricular assist device (LVAD) offers a lifeline for advanced heart failure patients, but ~30% experience post-operative right heart failure (RHF) with significant morbidity and mortality. Current methods for predicting RHF risk have limited accuracy. This study is the first of its kind to explore the feasibility of using a convolutional neural network (CNN) deep learning model with pulmonary artery pressure (PAP) tracings acquired during pre-operative hemodynamic assessment to identify patients at risk for early RHF. Methods: A CNN model was pre-trained on PAP tracings from the MIMIC-III Waveform Database to leverage transferable knowledge and improve model performance. The model learned general features and temporal relationships in hemodynamic tracing morphology for RHF prediction. It was then adapted for classification by modifying the output layers. Post-LVAD RHF was definitively adjudicated for each instance included from our 246 patient single center LVAD database. RHF was adjudicated using the 2020 Academic Research Consortium defintion. The database included 205 non-RHF instances and 41 RHF instances. We developed a novel signal processing method utilizing computer vision to extract PAP waveform data from pre-operative right heart catheterization reports. Data was reviewed to ensure accurate pressure tracing representation. SMOTE-ENN (synthetic oversampling) and class weighting addressed dataset imbalance during training to enhance model generalizability and RHF prediction accuracy. Results: The model achieved strong performance in classifying RHF from non-RHF outcomes, as evidenced by consistent AUC scores of 0.87 and 0.85 on validation and unseen test data, respectively. These findings indicate the potential for hemodynamic tracings to predict RHF after LVAD implantation. Notably, the model maintained its performance on unseen data, highlighting its generalizability. Conclusions: This study explored the feasibility of using a deep learning model for RHF risk stratification in patients with LVADs. The model, pre-trained on PAP tracings, achieved promising classification performance assessed by AUC. Further validation with larger, more diverse datasets will refine model performance and enhance generalizability for clinical application. Leveraging hemodynamic tracings within a deep learning framework holds promise for improved clinical outcome prediction.

Gold standard nephroureterectomy, chemoprophylaxis and surveillance in upper tract urothelial carcinoma.

The purpose of this review is to summarize the most recent evidence on surgical management, strategies to reduce tumor recurrence, and surveillance regimens in patients diagnosed with upper tract urothelial carcinoma (UTUC) and elected for radical treatment. Minimally invasive surgery is gaining momentum in the surgical management of UTUC. Chemoprophylaxis is still the gold standard to reduce intravesical recurrence after radical nephroureterectomy (RNU). Novel surveillance strategies have been proposed to adapt follow-up regimens to patients' characteristics. Minimally invasive surgery has been associated with comparable oncological outcomes to the open approach while improving postoperative morbidity. In these cases, bladder cuff excision (BCE) is mostly performed by an extravesical approach, that demonstrates a noninferiority compared to the intravesical one in terms of oncological outcomes. Although lymphadenectomy is recommended in patients with high-risk tumors, its benefits are still unclear. Currently, there is a lack of recent prospective trials on chemoprophylaxis to reduce intravesical recurrence post RNU, making single-dose postoperative chemotherapy instillation the standard treatment. Although novel risk stratification models were released by international urological guidelines, their validity is mainly nonevidence-based. Risk-adapted follow-up strategies incorporating cystoscopy and cross-sectional imaging accounting for individual patient factors should be implemented.

Advancements in the treatment of autoimmune diseases: Integrating artificial intelligence for personalized medicine

The incorporation of artificial intelligence (AI) into medical practice has considerably improved the treatment of autoimmune disorders, opening new avenues for personalized therapy. This study examines advances in AI-driven therapeutic options for autoimmune illnesses, including both current and developing treatments. Traditional therapies for autoimmune illnesses, such as immunosuppressive therapy and biologics, attempt to alleviate symptoms but frequently fall short of offering personalized care. Emerging approaches, such as precision medicine and artificial intelligence, are altering the landscape by harnessing massive volumes of patient data to better customize therapies. AI holds the ability to transform autoimmune disease therapy by enhancing diagnosis, discovering biomarkers, optimizing drug development, and personalized treatment procedures. Real-world applications and case studies are examined to demonstrate how machine learning algorithms have improved treatment tactics for rheumatoid arthritis, systemic lupus erythematosus, and multiple sclerosis. While AI has many advantages, like enhanced diagnosis accuracy and personalized therapy, it also has drawbacks, such as data privacy, the requirement for vast datasets, algorithmic bias, and a lack of explain ability. This study emphasizes the advantages of AI, such as improved patient stratification and predictive modelling, while also discussing its drawbacks, such as ethical problems and the possibility of data exploitation. AI presents intriguing prospects for treating autoimmune diseases, but more research and cooperation are required to overcome current difficulties and completely integrate AI into clinical practice.

EPCO-12. MENINGIOMA COPY NUMBER ANALYSIS IDENTIFIES OPTIMIZED SIZE THRESHOLDS AND CO-OCCURRENCE MODELS FOR INDIVIDUALIZED RISK-STRATIFICATION

Abstract Arm-level copy number alterations (CNAs) are common in meningiomas and are useful for risk-stratification, but there is no consensus regarding the optimal size threshold to define CNAs for prognostic models. Moreover, the prognostic importance of co-occurring CNA pairs and overall CNA burden in meningiomas remains incompletely understood. To address this, CNAs were analyzed in 691 retrospective meningiomas with clinical data and DNA methylation profiles from 3 international institutions. Arm-level CNAs were defined from DNA methylation profiles using iterative size thresholds ranging from 1-99% of each chromosome arm. The area under the curve (AUC) for 5-year local freedom from recurrence (LFFR) or overall survival (OS) was calculated using CNAs across size thresholds, and AUC standard deviation across thresholds was used as a measure of size-dependence. LASSO and Elastic Net Cox regressions were used to generate multi-CNA models for LFFR or OS and to identify prognostic co-occurring CNA pairs. These analyses identified 13 size-dependent prognostic CNAs in meningiomas, including loss of 1p, 3q, 4p, 4q, 6p, 6q, 9p, 10q, 12q, 14q,18q, and 22q, and gain of 1q. Regression models restricted to size-dependent CNAs improved risk stratification within strata of previously published models (Integrated score, Integrated grade), and identified prognostic CNAs not included in previous models, such as 1q gain, 7p loss, and 12q loss. Ontology analysis of genes in focal prognostic CNAs identified dysregulated STAT signaling and decreased expression of interferon-related genes from matched paired RNA sequencing. Models of size-dependent, prognostic, co-occurring CNA pairs identified 1p/22q codeletion, 1q gain/22q loss, and 9p/18q codeletion as significant predictors of LFFR. Increased CNA burden correlated with higher tumor grade and was significantly associated with worse LFFR and OS. In summary, chromosome-specific size thresholds identify prognostic arm-level CNAs and co-occurring CNA pairs in meningiomas. Thus, granular copy number analysis may improve risk stratification models for meningioma.