Effective Risk Stratification Research Articles

Preoperative identification from occult leiomyosarcomas in laparoscopic hysterectomy and laparoscopic myomectomy: accuracy of the ultrasound scoring system (PRESS-US).

To assess the diagnostic performance and inter-observer agreement of a PREoperative sarcoma scoring based on ultrasound (PRESS-US) in differentiating uterine leiomyosarcoma (uLMS) from leiomyoma (LM). We conducted a retrospective evaluation of patients who underwent surgery and received standardized ultrasound examinations due to the presence of uterine myoma-like masses. Histological diagnosis was used as the reference standard. The masses were analyzed using morphological uterus sonographic assessment criteria, and the diagnostic accuracy of PRESS-US was evaluated using ROC curve analysis. Kappa (κ) statistics were used to assess the inter-observer agreement between a less experienced and an expert radiologist. Among the 646 patients, 632 (97.8%) were diagnosed with LM, and 14 (2.2%) had uLMS. The malignancy rates for low-risk and high-risk patients were 0.35% and 13.48%, respectively. The optimal PRESS-US cutoff was 17.5, resulting in an AUC of 89.7% (95% CI, 0.79-1.00), with a sensitivity of 85.7% and a specificity of 87.8%. The inter-observer agreement between a less experienced and an expert radiologist was excellent (κ = 0.811, P < 0.001). PRESS-US provides effective risk stratification for uLMS for radiologists with different levels of experience, with high reliability. Subgrouping high-risk patients helps in better risk stratification.

Comprehensive strategies for preoperative pulmonary risk evaluation and management.

Postoperative pulmonary complications (PPCs) significantly increase morbidity and mortality in surgical patients, particularly those with pulmonary conditions. The incidence of PPCs varies widely, influenced by surgery type, patient age, smoking status, and comorbidities like chronic obstructive pulmonary disease (COPD) and congestive heart failure. Preoperative pulmonary function tests and chest radiographs, while critical for lung resection surgery, should be selectively used based on individual risk factors. Effective risk stratification models, including ASA classification, Arozullah Respiratory Failure Index, Gupta Calculators, and ARISCAT model, aid in predicting PPCs. Key strategies to reduce PPCs involve preoperative optimization of pulmonary conditions, smoking cessation, and respiratory rehabilitation. In COPD and asthma patients, maintaining optimal disease control through inhaled therapies, systemic corticosteroids, and preoperative respiratory exercises is crucial. Anemia and hypoalbuminemia are notable predictors of PPCs, warranting careful management. The type and duration of anesthesia significantly impact PPC risk, with regional anesthesia preferred over general anesthesia when feasible. Comprehensive preoperative evaluation and tailored interventions are essential to improve surgical outcomes and reduce PPC incidence. Further study involving domestic patients is needed to refine national guidelines for managing patients at risk of PPCs.

Deep Learning Predicts Lymphovascular Invasion Status in Muscle Invasive Bladder Cancer Histopathology.

Lymphovascular invasion (LVI) is linked to poor prognosis in patients with muscle-invasive bladder cancer (MIBC). Accurately identifying the LVI status in MIBC patients is crucial for effective risk stratification and precision treatment. We aim to develop a deep learning model to identify the LVI status in whole-slide images (WSIs) of MIBC patients. A cohort from The Cancer Genome Atlas (TCGA) database was used to train a deep learning model, slide-based lymphovascular invasion predictor (SBLVIP), based on multiple-instance learning. This model was externally validated using the Renmin Hospital of Wuhan University (RHWU) and People's Hospital of Hanchuan City (PHHC) cohorts. Kaplan-Meier curves, along with univariate and multivariate Cox models, were employed to evaluate the association between the LVI status predicted by SBLVIP and the survival outcomes of MIBC patients. In the TCGA cohort, the SBLVIP model achieved an average accuracy of 0.804 [95% confidence interval (CI) 0.712-0.895] and an area under the receiver operating characteristic curve (AUC) of 0.77 (95% CI 0.63-0.84) in the training set. In the internal validation set, the model's average accuracy and AUC were 0.774 (95% CI, 0.701-0.846) and 0.76 (95% CI, 0.60-0.83), respectively. In the RHWU cohort, the SBLVIP model achieved an average accuracy of 0.807 (95% CI 0.734-0.880) and an AUC of 0.74 (95% CI 0.55-0.83). In the PHHC cohort, SBLVIP demonstrated an average accuracy of 0.821 (95% CI 0.737-0.909) and an AUC of 0.74 (95% CI 0.58-0.89). Moreover, the LVI status predicted by SBLVIP showed significant independent prognostic value (P = 1 × 10-6). We developed a deep learning model named SBLVIP to predict the LVI status in routine WSIs of MIBC patients.

3.Y.1. Genomics in EU Health Systems: Navigating the Opportunities and Challenges for Personalized Health

Abstract The rapid advancements in genomics research offer significant promise for revolutionizing healthcare, potentially reshaping how we approach disease prevention, diagnosis, and treatment. However, unlocking the full potential of genomics requires more than just scientific breakthroughs-it necessitates translating these discoveries into clinical practice. This involves bridging the gap between research and healthcare implementation, addressing challenges such as technical infrastructure, ethical and legal frameworks, healthcare professional competencies, and citizen engagement. As we navigate the evolving landscape of individualized patient care, it becomes increasingly crucial to implement effective risk stratification methodologies and personalized preventive measures. Among these methodologies, polygenic risk scores are gaining prominence. However, the adoption of these innovations necessitates careful consideration of their clinical utility, including their feasibility, cost-effectiveness, and acceptability in diverse healthcare settings. Validating these approaches from multiple perspectives is essential to ensure their effectiveness in real-world clinical practice. Integrating genomic sequencing data with health records presents an invaluable resource that can enhance patient outcomes and drive further research. The creation of infrastructures and initiatives such as those carried out by projects like the European Health Data Space and Genomic Data Infrastructure are fundamental to unleash the enormous potential of data-driven innovation. To date, the implementation of genomics in medical practice varies across European countries, with discrepancies in adoption levels across different aspects of healthcare, including prevention, diagnosis, and personalized treatment. Addressing these disparities and promoting standardized approaches to genomic medicine implementation are crucial steps toward ensuring equitable access and maximizing the benefits of genomics for all individuals across Europe. This workshop aims to provide decision-makers, healthcare professionals and researchers with a comprehensive overview of the state-of-the-art for the adoption of personalized approaches, and of the maturity of genomic medicine practices within different healthcare systems as well outlining the benefits of data accessibility for research. The speakers are coordinators and partners of EU projects as B1MG (Beyond One Million Genomes), Prophet (A PeRsOnalized Prevention roadmap for the future Healthcare), EHDS (European Health Data Space), GDI (European Genomic Data Infrastructure), GoE (Genome of Europe) and CanHeal. Key messages • Genomics has the potential to improve health outcomes. • Equal access to genomic medicine critical for personalized health. Ensuring equity, while considering feasibility.

Incidence of acute cardiovascular hospitalizations and association with hemodynamic biomarkers in cancer patients treated with Immune Checkpoint Inhibitor therapy

Abstract Background/Introduction Immune checkpoint inhibitors (ICI) have significantly improved outcomes for several malignancies. Despite these benefits, patients with cancer face an increased risk for the development of cardiovascular disease due to mutual risk factors, similar biological mechanisms, as well as cardiotoxic side effects of therapy. Therefore, there is a pressing need for effective risk stratification strategies. Purpose This study aimed to explore the association between NT-proBNP levels and the risk of acute cardiovascular hospitalizations and death in patients who receive ICI. Methods We used electronic health records of patients treated with ICI who had available baseline NT-proBNP levels at our hospital, a tertiary academic center, between January 2017 and July 2022. The primary outcome of interest was the composite of acute cardiovascular hospitalization or death. The associations between NT-proBNP and outcomes were analyzed using cox regression models adjusted for age, sex, serum creatinine, diabetes, HF, CAD, hypertension, AF, LDL-C, and CRP. Results In total, 550 patients (35% female, median age 65 yrs) were included in the study. The median NT-proBNP levels were 272 pg/mL (IQR 102-742 pg/mL) and 388 (71%) patients had NT-proBNP levels ≥125 pg/mL. During a median FU of 67 weeks, 190 patients (35%) died, and 103 CV hospitalizations occurred in 76 patients (14%). Compared with patients with NT-proBNP concentrations &amp;lt;125, those with NT-proBNP concentrations ≥125 pg/ml had significantly higher event rates of the combined endpoint (12-Month KM event rates: 38% vs 21%, P&amp;lt;0.001). After multivariable adjustment, NT-proBNP remained independently associated with an increased risk of cardiovascular hospitalization and death (Adjusted HR for 1-SD increase in log-transformed biomarker 1.64, 95% CI 1.24 to 2.14; Figure). Conclusion These data highlight NT-proBNP levels as a valuable marker for identifying patients at increased risk of cardiovascular complications during ICI therapy.

Machine Learning For Risk Prediction After Heart Failure Emergency Department Visit or Hospital Admission Using Administrative Health Data.

Patients visiting the emergency department (ED) or hospitalized for heart failure (HF) are at increased risk for subsequent adverse outcomes, however effective risk stratification remains challenging. We utilized a machine-learning (ML)-based approach to identify HF patients at risk of adverse outcomes after an ED visit or hospitalization using a large regional administrative healthcare data system. Patients visiting the ED or hospitalized with HF between 2002-2016 in Alberta, Canada were included. Outcomes of interest were 30-day and 1-year HF-related ED visits, HF hospital readmission or all-cause mortality. We applied a feature extraction method using deep feature synthesis from multiple sources of health data and compared performance of a gradient boosting algorithm (CatBoost) with logistic regression modelling. The area under receiver operating characteristic curve (AUC-ROC) was used to assess model performance. We included 50,630 patients with 93,552 HF ED visits/hospitalizations. At 30-day follow-up in the holdout validation cohort, the AUC-ROC for the combined endpoint of HF ED visit, HF hospital readmission or death for the Catboost and logistic regression models was 74.16 (73.18-75.11) versus 62.25 (61.25-63.18), respectively. At 1-year follow-up corresponding values were 76.80 (76.1-77.47) versus 69.52 (68.77-70.26), respectively. AUC-ROC values for the endpoint of all-cause death alone at 30-days and 1-year follow-up were 83.21 (81.83-84.41) versus 69.53 (67.98-71.18), and 85.73 (85.14-86.29) versus 69.40 (68.57-70.26), for the CatBoost and logistic regression models, respectively. ML-based modelling with deep feature synthesis provided superior risk stratification for HF patients at 30-days and 1-year follow-up after an ED visit or hospitalization using data from a large administrative regional healthcare system.

Distinct Phenotypic Groups and Related Clinical Outcomes in Patients With Hypertrophic Cardiomyopathy.

Hypertrophic cardiomyopathy (HCM) is a heterogeneous disorder with varying risks of clinical outcomes, including sudden cardiac death (SCD). We aimed to identify distinct phenotypes among patients with HCM in relation to SCD risk factors, interpret their clinical characteristics, and examine their outcomes. This retrospective study analyzed 1231 consecutive patients with HCM from 2 tertiary hospitals. We performed latent class analysis to categorize patients into phenotypic groups. Three distinct phenotypic groups were identified using latent class analysis. Group 1 (n=554) consisted of young patients with HCM with minimal SCD risk factors and favorable cardiac remodeling. Group 2 (n=114) comprised young patients with HCM and a high prevalence of SCD risk factors, whereas Group 3 (n=563) included older patients (median age, 68 years). Over a median 6.5-year follow-up, 34 SCD-related events, 131 cardiovascular events, 133 all-cause mortality events, and 70 noncardiovascular mortality events were observed. Group 2 exhibited the highest rate of SCD-related events (5-year SCD rate: Group 1 versus 2 versus 3: 0.8% versus 8.2% versus 4.0%, respectively, P<0.001), and cardiovascular events were more frequent in Groups 2 and 3 compared with Group 1. All-cause and noncardiovascular mortality were the most frequent in Group 3. A simplified decision tree was developed for the straightforward assignment of phenotypic group membership, demonstrating fair concordance. This study identified 3 distinct clinical phenotypes in patients with HCM, each associated with different SCD risks and outcomes. Data-driven phenotyping of patients with HCM offers effective risk stratification and may optimize patient management.

How Morphology Shapes Survival in Invasive Squamous Cell Carcinoma of the Lung.

Squamous cell carcinoma (SQCC) represents a significant proportion of human malignancies affecting various anatomical sites, including the lung. Understanding the prognostic factors is crucial for establishing effective risk stratification in these patients, as multiple critical aspects significantly impact overall survival. A retrospective study was conducted on 99 patients with operable lung SQCC treated at a tertiary center. The exclusion criteria included patients under 18, those with in situ or metastatic SQCC, and those who received neoadjuvant therapy. The surgical specimens were re-analyzed, and data were collected on multiple variables, including pTNM staging, tumor characteristics, and overall survival (OS). The Kaplan-Meier survival analysis and Cox regression models were used to identify significant prognostic factors. The Kaplan-Meier analysis showed a median survival of 36 months with a 65.65% mortality rate. Significant factors influencing survival included keratinization, histological grading, tumor size and stage, pleural invasion, tumor cell arrangement, tumor budding, spread through air space (STAS), and mitotic index. A multiple Cox regression highlighted the nonkeratinizing tumors, advanced pT stages, single-cell invasion, and high mitotic index as key predictors of poorer outcomes. The nonkeratinizing tumors showed higher mortality and shorter median survival rates compared to keratinizing tumors. The tumor staging, cell arrangement, and tumor budding significantly impacted the survival curves. The study underscores the importance of detailed histopathological evaluations in lung SQCC. The nonkeratinizing tumors, advanced pT stage, single-cell invasion, and high mitotic index were associated with higher hazard rates, emphasizing the need for a comprehensive grading system incorporating these factors to improve prognostic accuracy and guide treatment strategies.

Polygenic risk and rare variant gene clustering enhance cancer risk stratification for breast and prostate cancers

Polygenic risk score (PRS) and rare monogenic variant screening are valuable tools for predicting cancer risk and identifying individuals at high risk. Integrating both common and rare genetic variants is crucial for accurate risk assessment. However, estimating the impacts of rare variants on cancer and combining them with PRS remains challenging. Here, we analyze 454,711 exome sequencing and 487,409 array UK Biobank samples, focusing on breast and prostate cancers. We introduce an expanded PRS (EPRS) approach, yielding a systematic model for more effective risk stratification. By prioritizing and clustering genes with cancer-specific rare variants based on odds ratios and population-attributable fraction, we refine risk stratification by combining both monogenic and polygenic effects. Individuals in high-PRS groups with rare high-impact gene variants show up to 15- and 22-fold higher risk for breast and prostate cancers, respectively, compared to those in the intermediate-PRS groups without rare variants. Combined risk profiles vary across distinct rare variant clusters within the same PRS group for both cancers. Our EPRS approach enhances risk stratification for breast and prostate cancers, offering important insights for future research and potential applications to other cancer types.

Early prediction of mortality and morbidities in VLBW preterm neonates using machine learning.

Predicting mortality and specific morbidities before they occur may allow for interventions that may improve health trajectories. Integrating key maternal and postnatal infant variables in the first 2 weeks of age into machine learning (ML) algorithms will reliably predict survival and specific morbidities in VLBW preterm infants. ML algorithms were developed to integrate 47 features for predicting mortality, bronchopulmonary dysplasia (BPD), neonatal sepsis, necrotizing enterocolitis (NEC), intraventricular hemorrhage (IVH), cystic periventricular leukomalacia (PVL), and retinopathy of prematurity (ROP). A retrospective cohort (n = 3341) was used to train and validate the models with a repeated 10-fold cross-validation strategy. These models were then tested on a separate cohort (n = 447) to evaluate the final model performance. Among the seven ML algorithms employed, tree-based ensemble models, specifically Random Forest (RF) and XGBoost, had the best performance metrics. The area under the receiver operating characteristic curve (AUROC) of sepsis with or without meningitis (0.73), NEC (0.73), BPD (0.71), and mortality (0.74) exceeded 0.7, while the area under Precision-Recall curve (AUPRC) for all outcomes was greater than the prevalence, demonstrating effective risk stratification in VLBW preterm infants. Our study demonstrates the potential of predictive analytics leveraging ML techniques in advancing precision medicine. Reliable prediction of adverse outcomes before they occur has the potential to institute interventions and possibly improve health trajectories in VLBW preterm infants. We used machine learning to develop and test predictive models for mortality and five major morbidities in VLBW preterm infants. Individualized prediction of outcomes and individualized interventions will advance Precision Medicine in Neonatology.

Development of a Mitochondrial Membrane Permeability Transition Prognosis System in Colon Adenocarcinoma: Risk Stratification and Therapeutic Target Identification.

Explore the role of mitochondrial membrane permeability transition (MPT) in colon adenocarcinoma (COAD). Further exploration of risk stratification for COAD prognostic assessment has important clinical value. MPT-related pathways play a key role in the pathogenesis of many human diseases, including tumorigenesis. Its impact on COAD is still unknown. Bioinformatics analysis was conducted by analyzing the GEO database and TCGA database, and the bioinformatics results were verified by in vitro experiments. Through the analysis of the transcriptome data of 1008 COAD samples in the GEO database and TCGA database, the differential expressions of MPT-related genes in COAD were explored, followed by molecular subtype analysis based on MPT characteristics by univariate Cox algorithm analysis and the consensus clustering algorithm. The gene signature associated with MPT molecular subtypes was further identified and the MPT scoring system was established by the LASSO-univariate Cox analysis algorithm. After evaluating the prognostic value of the MPT scoring system in COAD patients via nomogram establishment, the clinical value of the MPT scoring system was comprehensively analyzed through somatic mutation characteristics analysis, immunotherapy response analysis, immunoinfiltration analysis, and drug sensitivity analysis. CCK-8, WB, PCR, colony formation method, and Transwell method were used to verify the effect of the screened target on the proliferation and invasion of COAD cells. We successfully established a scoring system related to MPT and validated the prognostic value of COAD patients. The potential clinical value of the MPT scoring system was also analyzed. VSIG4 was selected for further in vitro experiments to verify the effect of the screened targets on the proliferation and invasion ability of COAD cells. We established an MPT scoring system for effective risk stratification of COAD patients, demonstrating the impact of MPT on the development of COAD and its potential value as an intervention factor.

Association between psychopharmacotherapy and postpartum hemorrhage

BackgroundPrior studies evaluating the relationship between psychopharmacotherapy (PPT), and postpartum hemorrhage (PPH) have yielded inconsistent findings. Clarifying this potential relationship is important for effective counseling and risk stratification. ObjectivesOur primary objective was to evaluate the association between prenatal exposure to PPT (any drug class) and the occurrence of PPH requiring transfusion of packed red blood cells (PPH+pRBC) after systematically adjusting for known hemorrhage risk factors at the time of admission for delivery. Secondary objectives were to evaluate the association between individual PPT drug classes and PPH+pRBC, and the association between treatment intensity of mental health condition and PPH+pRBC. Finally, we evaluated the association between PPT and a broader definition of PPH that included deliveries requiring multiple uterotonic drugs. Study designThis is a retrospective cross-sectional study of all pregnancies delivered at 23 weeks of gestational age or greater at seven hospitals within a large academic health system in New York between January 2019 and December 2022. There were no exclusion criteria, as postpartum hemorrhage risk assessment is necessary for all patients admitted for delivery. We assessed exposure to prenatal PPT, including selective serotonin reuptake inhibitors (SSRIs: escitalopram, fluoxetine, sertraline), serotonin-norepinephrine reuptake inhibitors (SNRIs: duloxetine, venlafaxine), dopamine-norepinephrine reuptake inhibitors (DNRIs: buproprion), benzodiazepines (alprazolam, diazepam, lorazepam), and others (buspirone, trazodone, zolpidem). Multivariable logistic regression was performed to evaluate the relationship between PPT and PPH+pRBC, while systematically adjusting for known hemorrhage risk factors at the time of hospital admission. Similar regression analyses were performed to address the secondary objectives. ResultsA total of 107,425 deliveries were included. Non-Hispanic White patients constituted the largest race and ethnicity group (43.4%), followed by Hispanic patients (18.7%), Asian or Pacific Islander patients (13.2%), and non-Hispanic Black patients (12.3%). Prenatal exposure to PPT occurred in 3.6% of pregnancies (n=3,834). The overall rate of PPH+pRBC was 2.9% (n=3,162). PPH+pRBC occurred more frequently in pregnancies exposed to PPT than in pregnancies which were not exposed (5.5% vs. 2.8%, respectively; aOR 2.10, 95% CI: 1.79–2.44). SSRIs and benzodiazepine monotherapy were each associated with higher odds of PPH+pRBC than nonexposure. Compared to patients without a mental health condition, monotherapy was associated with nearly 2-fold increased odds and combination PPT was associated with nearly 4-fold greater odds of PPH+pRBC after adjustment for confounding variables (monotherapy: aOR 1.94, 95% CI: 1.64–2.28; combination PPT: aOR 3.96, 95% CI: 2.61–5.79). Patients with untreated mental health conditions (no PTT) had no increased odds of PPH+pRBC compared to those without mental health conditions. Finally, after adjusting for covariates, a positive association was found between PPT and PPH requiring pRBC transfusion and/or the use of two additional uterotonic agents beyond routine postpartum oxytocin (aOR 1.53, 95% CI: 1.35–1.73). ConclusionsPrenatal PPT exposure is associated with increased odds of clinically significant PPH+pRBC after adjusting for other hemorrhage risk factors. Combination PPT was associated with greater odds of PPH+pRBC than monotherapy.

Tumour-pleura relationship on computed tomography (CT) provides effective risk stratification for peripheral pulmonary nodules with Lung Imaging Reporting and Data System (Lung-RADS) score of 4X.

Pulmonary nodules with Lung Imaging Reporting and Data System (Lung-RADS) 4X are of greater clinical significance, and accurate differentiation of pathological types and visceral pleural invasion (VPI) of Lung-RADS 4X peripheral pulmonary nodules before treatment can aid in stratification. This study set out to investigate whether the tumour-pleura relationship on computed tomography (CT) can provide effective risk stratification for peripheral pulmonary nodules with Lung-RADS 4X. This was a single institution, retrospective study of 482 consecutive patients with Lung-RADS score 4X, who were pathologically diagnosed with tuberculous granuloma and adenocarcinoma from January 2019 to December 2023. We assessed clinical factors (baseline characteristics and tumour markers) and CT findings. Univariate and multivariate logistic regression analyses were used to determine the classification of pulmonary nodules and predictors of VPI. Multivariate analysis revealed that gender [odds ratio (OR) =0.392; P<0.001], carcinoembryonic antigen (CEA) level (OR =8.331; P<0.001), type of nodules (OR =13.551 and 7.478; P<0.001 and P=0.016) and maximum base width of soft tissue component on the pleura side (OR =0.857; P=0.005) were significant independent factors for distinguishing tuberculous granuloma from adenocarcinoma. And the type of linear connection between lesion and pleura (OR =3.936; P<0.001), and the maximum base width of soft tissue components on the pleura side (OR =1.359; P=0.001) were correlated independently with VPI. The area under the curve (AUC) for predicting pulmonary nodules classification was 82.60% [95% confidence interval (CI): 78.85-86.35%), and the AUC for predicting VPI was 76.10% (95% CI: 69.83-82.38%). The tumour-pleura relationship will be helpful in further risk stratification for peripheral pulmonary nodules with a score of Lung-RADS 4X.

Cardio-oncology: chances and challenges.

Cardio-oncology is an emerging field that aims to ensure optimal cancer treatment while minimising cardiovascular toxicity. The management of cardiovascular toxicity is critical because it can lead to premature discontinuation of treatment, increasing the risk of cancer recurrence and mortality. The 2022 European Society of Cardiology guidelines were a milestone in advocating a patient-centred, multidisciplinary approach. Key components include risk stratification and a standardised criterion for adverse events, incorporating definitions from the International Cardio-Oncology Society. Effective risk stratification, supported by imaging and biomarkers, helps to anticipate cardiovascular problems and implement preventive measures. Future research should focus on understanding mechanisms, developing preventive strategies and implementing personalised medicine. Education and reducing disparities in care are essential to advance cardio-oncology and improve patient outcomes.

Construction of an interpretable model for predicting survival outcomes in patients with middle to advanced hepatocellular carcinoma (≥5cm) using lasso-cox regression.

In this retrospective study, we aimed to identify key risk factors and establish an interpretable model for HCC with a diameter ≥ 5cm using Lasso regression for effective risk stratification and clinical decision-making. In this study, 843 patients with advanced hepatocellular carcinoma (HCC) and tumor diameter ≥ 5cm were included. Using Lasso regression to screen multiple characteristic variables, cox proportional hazard regression and random survival forest models (RSF) were established. By comparing the area under the curve (AUC), the optimal model was selected. The model was visualized, and the order of interpretable importance was determined. Finally, risk stratification was established to identify patients at high risk. Lasso regression identified 8 factors as characteristic risk factors. Subsequent analysis revealed that the lasso-cox model had AUC values of 0.773, 0.758, and 0.799, while the lasso-RSF model had AUC values of 0.734, 0.695, and 0.741, respectively. Based on these results, the lasso-cox model was chosen as the superior model. Interpretability assessments using SHAP values indicated that the most significant characteristic risk factors, in descending order of importance, were tumor number, BCLC stage, alkaline phosphatase (ALP), ascites, albumin (ALB), and aspartate aminotransferase (AST). Additionally, through risk score stratification and subgroup analysis, it was observed that the median OS of the low-risk group was significantly better than that of the middle- and high-risk groups. We have developed an interpretable predictive model for middle and late HCC with tumor diameter ≥ 5cm using lasso-cox regression analysis. This model demonstrates excellent prediction performance and can be utilized for risk stratification.

Radiomics-Based Computed Tomography Urogram Approach for the Prediction of Survival and Recurrence in Upper Urinary Tract Urothelial Carcinoma.

Upper tract urothelial carcinoma (UTUC) is a rare and aggressive malignancy with a poor prognosis. The accurate prediction of survival and recurrence in UTUC is crucial for effective risk stratification and guiding therapeutic decisions. Models combining radiomics and clinicopathological data features derived from computed tomographic urograms (CTUs) can be a way to predict survival and recurrence in UTUC. Thus, preoperative CTUs and clinical data were analyzed from 106 UTUC patients who underwent radical nephroureterectomy. Radiomics features were extracted from segmented tumors, and the Least Absolute Shrinkage and Selection Operator (LASSO) method was used to select the most relevant features. Multivariable Cox models combining radiomics features and clinical factors were developed to predict the survival and recurrence. Harrell's concordance index (C-index) was applied to evaluate the performance and survival distribution analyses were assessed by a Kaplan-Meier analysis. The significant outcome predictors were identified by multivariable Cox models. The combined model achieved a superior predictive accuracy (C-index: 0.73) and higher recurrence prediction (C-index: 0.84). The Kaplan-Meier analysis showed significant differences in the survival (p < 0.0001) and recurrence (p < 0.002) probabilities for the combined datasets. The CTU-based radiomics models effectively predicted survival and recurrence in the UTUC patients, and enhanced the prognostic performance by combining radiomics features with clinical factors.

Navigating the Maze: A Mini-Guide for the Management and Therapy of Metabolic Dysfunction-associated Steatotic Liver Disease

Metabolic Dysfunction-Associated Steatotic Liver Disease (MASLD), formerly known as Nonalcoholic Fatty Liver Disease (NAFLD), poses a significant global health challenge with a prevalence of 30% worldwide. Alarming projections anticipate a substantial increase in MASLD cases, highlighting the urgent need for preparedness and effective policies. The pathophysiology of MASLD involves a complex interplay of metabolic, genetic and lifestyle factors. Although liver biopsy remains the gold standard for the diagnosis of MASLD, non-invasive methods such as abdominal ultrasound, transient elastography with controlled attenuation parameter, shear wave elastography, and non-invasive serum fibrosis scores have been developed and validated. Effective risk stratification in primary care with non-invasive fibrosis scores, such as fibrosis 4 (FIB-4) index and NAFLD fibrosis score (NFS), optimizes healthcare resource utilization, ensuring appropriate referrals for high-risk patients while minimizing unnecessary referrals. Lifestyle intervention, including diet and physical activity, remains the primary therapy for MASLD. Notably, with the FDA approval of resmetirom, the first authorized medication for fibrotic metabolic dysfunction-associated steatohepatitis (MASH), and several antifibrotic agents under investigation, the therapeutic landscape for MASLD is rapidly evolving. Despite its increasing prevalence, morbidity and mortality, MASLD is frequently underdiagnosed in primary care. In this review, we aim to provide primary care physicians an update on the diagnosis, management and treatment of MASLD.

Prediction of clinical deterioration risk at 8 hours after arrival in emergency department in non‐traumatic patients using trends in modified early warning score level

AbstractBackgroundImproving the quality of medical care in hospitals is a major priority for all departments. The early warning score (EWS) trend is an effective early risk stratification tool that reflects the changes in patient condition and allows better assessment of deterioration risk.ObjectiveThe aim of this study was to investigate whether utilizing the trend of the modified early warning score (MEWS) level within 4 h of a patient's arrival in the emergency department (ED) could identify patients at risk of clinical deterioration at 8 h after arrival in the ED.MethodsWe conducted a retrospective observational study of non‐trauma patients who had at least two vital sign measurements (Glasgow Coma Scale score, heart rate, blood pressure, respiratory rate, and body temperature) within 8 h of arriving in the ED. The primary outcome was patients who had MEWS ≥ 4 at 8 h after arrival in the ED. We performed multivariate logistic regression analysis using age, sex, MEWS level at arrival in the ED, MEWS level within 4 h after arrival in the ED, and MEWS level trend over time.ResultsAmong the 5825 patients, 680 (11.7%) were at risk of deterioration at 8 h after arrival in the ED. To predict the risk of deteriorating conditions (MEWS ≥ 4), utilizing the MEWS level trend within 4 h of arrival in the ED was more effective in identifying patients at risk of deterioration after 8 h of arrival in the ED compared to using a single MEWS value during the ED stay. The corresponding areas under the receiver operating characteristic curve were 0.756 (95% confidence interval (CI) 0.734–0.778) and 0.846 (95% CI 0.827–0.865), respectively (p &lt; 0.01).ConclusionsThe proposed trend‐based predictive model for MEWS levels can alert healthcare personnel regarding patients at increased risk of deterioration (MEWS ≥ 4), potentially reducing mortality rates during ED stays.

Identification and validation of basement membrane-related genes predicting prognosis and immune infiltration associated with bladder cancer.

Bladder cancer (BC) is fatal during muscle invasion and treatment progress is limited. In this study, we aimed to construct and validate basement membrane (BM)-associated gene prognosis to predict BC progression and tumor immune infiltration correlation. We choreographed BM-related genes in the Cancer Genome Atlas (TCGA) database using COX regression and least absolute shrinkage and selection operator (LASSO) analysis, and the predictive value of BM-related genes was further validated by the GSE32548, GSE129845, and immunohistochemistry staining. All analyses were performed with R-version 4.2.2, and its appropriate packages. Three genes were identified to construct a gene signature to predictive of BC prognosis. We divided the TCGA database into 2 groups, and patients in the high-risk group had worse overall survival (OS) than those in the low-risk group. In GSE32548, we confirmed that patients in the high-risk group had a poorer prognosis compared to those in the low-risk group in terms of OS. Immunohistochemical staining of EPEMP1, GPC2, and ITGA3 showed significantly higher expression at the protein level in BC tissues than in normal tissues. The Spearman analysis showed risk score was positively correlated with B cell naïve, Macrophages M2, and Mast cells resting. stromal score, immune score, and ESTIMATE scores were significantly higher in the high-risk group. drugs sensitivity analysis showed IC50 of Cisplatin, Gemcitabine, and Methotrexate in the high-risk group was significantly higher than that in the low-risk group. We identified 3 prognostic genes from a novel perspective of BM genes as effective risk stratification tools for BC patients.

Autoencoder to Identify Sex-Specific Sub-phenotypes in Alzheimer's Disease Progression Using Longitudinal Electronic Health Records.

Alzheimer's Disease (AD) is a complex neurodegenerative disorder significantly influenced by sex differences, with approximately two-thirds of AD patients being women. Characterizing the sex-specific AD progression and identifying its progression trajectory is a crucial step to developing effective risk stratification and prevention strategies. In this study, we developed an autoencoder to uncover sex-specific sub-phenotypes in AD progression leveraging longitudinal electronic health record (EHR) data from OneFlorida+ Clinical Research Consortium. Specifically, we first constructed temporal patient representation using longitudinal EHRs from a sex-stratified AD cohort. We used a long short-term memory (LSTM)-based autoencoder to extract and generate latent representation embeddings from sequential clinical records of patients. We then applied hierarchical agglomerative clustering to the learned representations, grouping patients based on their progression sub-phenotypes. The experimental results show we successfully identified five primary sex-based AD sub-phenotypes with corresponding progression pathways with high confidence. These sex-specific sub-phenotypes not only illustrated distinct AD progression patterns but also revealed differences in clinical characteristics and comorbidities between females and males in AD development. These findings could provide valuable insights for advancing personalized AD intervention and treatment strategies.