Clinical use of polygenic risk scores for detection of peripheral artery disease and cardiovascular events.

We have previously shown that polygenic risk scores (PRS) can improve risk stratification of peripheral artery disease (PAD) in a large, retrospective cohort. Here, we evaluate the potential of PRS in improving the detection of PAD and prediction of major adverse cardiovascular and cerebrovascular events (MACCE) and adverse events (AE) in an institutional patient cohort. We created a cohort of 278 patients (52 cases and 226 controls) and fit a PAD-specific PRS based on the weighted sum of risk alleles. We built traditional clinical risk models and machine learning (ML) models using clinical and genetic variables to detect PAD, MACCE, and AE. The models' performances were measured using the area under the curve (AUC), net reclassification index (NRI), integrated discrimination improvement (IDI), and Brier score. We also evaluated the clinical utility of our PAD model using decision curve analysis (DCA). We found a modest, but not statistically significant improvement in the PAD detection model's performance with the inclusion of PRS from 0.902 (95% CI: 0.846-0.957) (clinical variables only) to 0.909 (95% CI: 0.856-0.961) (clinical variables with PRS). The PRS inclusion significantly improved risk re-classification of PAD with an NRI of 0.07 (95% CI: 0.002-0.137), p = 0.04. For our ML model predicting MACCE, the addition of PRS did not significantly improve the AUC, however, NRI analysis demonstrated significant improvement in risk re-classification (p = 2e-05). Decision curve analysis showed higher net benefit of our combined PRS-clinical model across all thresholds of PAD detection. Including PRS to a clinical PAD-risk model was associated with improvement in risk stratification and clinical utility, although we did not see a significant change in AUC. This result underscores the potential clinical utility of incorporating PRS data into clinical risk models for prevalent PAD and the need for use of evaluation metrics that can discern the clinical impact of using new biomarkers in smaller populations.

Early predictors of severe left main and/or three-vessel disease in patients with non-ST-segment elevation myocardial infarction: A dual-center retrospective study.

BACKGROUND: Early detection of patients concomitant with left main and/or three-vessel disease (LM/3VD) and high SYNTAX score (SS) is crucial for determining the most effective revascularization options regarding the use of antiplatelet medications and prognosis risk stratification. However, there is a lack of study for predictors of LM/3VD with SS in patients with non-ST-segment elevation myocardial infarction (NSTEMI). We aimed to identify potential factors that could predict LM/3VD with high SS (SS > 22) in patients with NSTEMI. METHODS: This dual-center retrospective study included a total of 481 patients diagnosed with NSTEMI who performed coronary angiography procedures. Clinical factors on admission were collected. The patients were divided into non-LM/3VD, Nonsevere LM/3VD (SS ≤ 22), and Severe LM/3VD (SS > 22) groups. To identify independent predictors, Univariate and logistic regression analyses were conducted on the clinical parameters. RESULTS: A total of 481 patients were included, with an average age of 60.9 years and 75.9% being male. Among these patients, 108 individuals had severe LM/3VD. Based on the findings of a multivariate logistic regression analysis, the extent of ST-segment elevation observed in lead aVR (OR: 7.431, 95% CI: 3.862-14.301, p < .001) and age (OR: 1.050, 95% CI: 1.029-1.071, p < .001) were identified as independent predictors of severe LM/3VD. CONCLUSION: This study indicated that the age of patients and the extent of ST-segment elevation observed in lead aVR on initial electrocardiogram were the independent predictive factors of LM/3VD with high SS in patients with NSTEMI.

Antithrombotic Treatment and Clinical Outcomes After Intracerebral Hemorrhage: A Retrospective Cohort Study from the Swedish Stroke Register.

BACKGROUND: A rapid shift has occurred from vitamin K antagonists toward direct oral anticoagulants, which have a lower risk of intracerebral hemorrhage (ICH). However, effects on clinical outcomes after ICH are understudied. We aimed to describe the prevalence of antithrombotic drugs and to study the prognosis among prestroke functionally independent Swedish patients with ICH. METHODS AND RESULTS: We identified all patients diagnosed with nontraumatic ICH in 2017 to 2021 from the Swedish Stroke Register (n=13 155) and assessed death and functional outcome at 3 months after ICH in prestroke functionally independent patients (n=10 014). Functional outcome was estimated among 3-month survivors on the basis of self-reported activities of daily living scores. Risks of outcomes were estimated using Poisson regression. In 13 155 patients, 14.5% used direct oral anticoagulant, 10.1% vitamin K antagonists, and 21.6% antiplatelets at ICH onset. Among 10 014 pre-stroke activities of daily living-independent patients, oral anticoagulants and antiplatelets were associated with increased mortality risk (adjusted risk ratio, 1.27 [95% CI, 1.13-1.43]; P<0.001; and adjusted risk ratio, 1.23 [95% CI, 1.13-1.34]; P<0.001 respectively). Mortality risk did not statistically differ between antiplatelets and oral anticoagulants nor between direct oral anticoagulant and vitamin K antagonists. Among 5126 patients with nonmissing functional outcome (69.1% of survivors), antiplatelets (adjusted risk ratio, 1.06 [95% CI, 0.99-1.13]; P=0.100) and oral anticoagulants (adjusted risk ratio, 1.01 [95% CI, 0.92-1.12]; P=0.768) were not statistically significantly associated with functional dependence. CONCLUSIONS: There was no statistically significant difference in mortality risk between direct oral anticoagulant and vitamin K antagonists in prestroke functionally independent patients (unadjusted for oral anticoagulant class indication). Furthermore, mortality risk in antiplatelet and oral anticoagulant users might differ less than previously suggested.

Five-Year Cumulative Cardiovascular Health and Clinical Events in Patients With Chronic Kidney Disease: The CRIC Study.

BACKGROUND: Higher cardiovascular health (CVH) score is associated with lower risks of cardiovascular disease (CVD) and mortality in the general population. However, it is unclear whether cumulative CVH is associated with CVD, end-stage kidney disease (ESKD), and death in patients with chronic kidney disease. METHODS AND RESULTS: Among individuals from the prospective CRIC (Chronic Renal Insufficiency Cohort) Study, we used the percentage of the maximum possible CVH score attained from baseline to the year 5 visit to calculate cumulative CVH score. Multivariable-adjusted Cox proportional hazards regression was used to investigate the associations of cumulative CVH with risks of adjudicated CVD (myocardial infarction, stroke, and heart failure), ESKD, and all-cause mortality. A total of 3939 participants (mean age, 57.7 years; 54.9% men) were included. The mean (SD) cumulative CVH score attained during 5 years was 55.5% (12.3%). Over a subsequent median 10.2-year follow-up, 597 participants developed CVD, 656 had ESKD, and 1324 died. A higher cumulative CVH score was significantly associated with lower risks of CVD, ESKD, and mortality, independent of the CVH score at year 5. Multivariable-adjusted hazard ratios and 95% CIs per 10% higher cumulative CVH score during 5 years were 0.81 (0.69-0.95) for CVD, 0.82 (0.70-0.97) for ESKD, and 0.80 (0.72-0.89) for mortality. CONCLUSIONS: Among patients with chronic kidney disease stages 2 to 4, a better CVH status maintained throughout 5 years is associated with lower risks of CVD, ESKD, and all-cause mortality. The findings support the need for interventions to maintain ideal CVH status for prevention of adverse outcomes in the population with chronic kidney disease.

Impact of valvular surgery according to frailty risk in patients with infective endocarditis.

BACKGROUND: Observational studies suggest that valvular surgery can reduce mortality in selected patients with infective endocarditis (IE). However, the benefit of this intervention according to frailty levels remains unclear. Our study aims to assess the effect of valvular surgery according to frailty status in this population. METHODS: We performed a retrospective study using the 2016-2019 National Inpatient Sample database. Adult patients with a primary diagnosis of IE were included. Frailty was assessed using the Hospital Frailty Risk Score. Inverse probability of treatment weighting (IPTW) was used to balance baseline differences between groups. RESULTS: A total of 53,275 patients with IE were included, with 18.3% underwent valvular surgery. The median age was 52 (34-68) years, with 41% females. Overall, 42.7% had low risk of frailty, 53.1% intermediate risk, and 4.2% high risk. After IPTW adjustment, in-hospital mortality was similar both for the entire cohort between valvular and non-valvular surgery groups (3.7% vs. 4.1%, p = .483), and low (1% vs. 0.9%, p = .952) or moderate (5.4% vs. 6%, p = .548) risk of frailty. However, patients at high risk of frailty had significantly lower in-hospital mortality in the valvular surgery group (4.6% vs. 13.9%, p = .016). Renal replacement therapy was similar between groups across frailty status. In contrast, surgery was associated with increased use of mechanical circulatory support and pacemaker implantation. CONCLUSIONS: Our findings suggest that there was no difference in survival between valve surgery and medical management in patients at low/intermediate frailty risk, but not for high-risk individuals.

Cardiovascular Risk Estimation Is Suboptimal in People With HIV.

BACKGROUND: Established cardiovascular disease (CVD) risk prediction functions may not accurately predict CVD risk in people with HIV. We assessed the performance of 3 CVD risk prediction functions in 2 HIV cohorts. METHODS AND RESULTS: CVD risk scores were calculated in the Mass General Brigham and Kaiser Permanente Northern California HIV cohorts, using the American College of Cardiology/American Heart Association atherosclerotic CVD function, the FHS (Framingham Heart Study) hard coronary heart disease function and the Framingham Heart Study hard CVD function. Outcomes were myocardial infarction or coronary death for FHS hard coronary heart disease function; and myocardial infarction, stroke, or coronary death for American College of Cardiology/American Heart Association and FHS hard CVD function. We calculated regression coefficients and assessed discrimination and calibration by sex; predicted to observed risk of outcome was also compared. In the combined cohort of 9412, 158 (1.7%) had a coronary heart disease event, and 309 (3.3%) had a CVD event. Among women, CVD risk was generally underestimated by all 3 risk functions. Among men, CVD risk was underestimated by the American College of Cardiology/American Heart Association and FHS hard CVD function, but overestimated by the FHS hard coronary heart disease function. Calibration was poor for women using the FHS hard CVD function and for men using all functions. Discrimination in all functions was good for women (c-statistics ranging from 0.78 to 0.90) and moderate for men (c-statistics ranging from 0.71 to 0.72). CONCLUSIONS: Established CVD risk prediction functions generally underestimate risk in people with HIV. Differences in model performance by sex underscore the need for both HIV-specific and sex-specific functions. Development of CVD risk prediction models tailored to HIV will enhance care for aging people with HIV.

Long-Term Mortality Predictors Using a Machine-Learning Approach in Patients With Chronic Limb-Threatening Ischemia After Peripheral Vascular Intervention.

BACKGROUND: Patients with chronic limb-threatening ischemia (CLTI) face a high long-term mortality risk. Identifying novel mortality predictors and risk profiles would enable individual health care plan design and improved survival. We aimed to leverage a random survival forest machine-learning algorithm to identify long-term all-cause mortality predictors in patients with CLTI undergoing peripheral vascular intervention. METHODS AND RESULTS: Patients with CLTI undergoing peripheral vascular intervention from 2017 to 2018 were derived from the Medicare-linked VQI (Vascular Quality Initiative) registry. We constructed a random survival forest to rank 66 preprocedural variables according to their relative importance and mean minimal depth for 3-year all-cause mortality. A random survival forest of 2000 trees was built using a training sample (80% of the cohort). Accuracy was assessed in a testing sample (20%) using continuous ranked probability score, Harrell C-index, and out-of-bag error rate. A total of 10 114 patients were included (mean±SD age, 72.0±11.0 years; 59% men). The 3-year mortality rate was 39.1%, with a median survival of 1.4 years (interquartile range, 0.7-2.0 years). The most predictive variables were chronic kidney disease, age, congestive heart failure, dementia, arrhythmias, requiring assisted care, living at home, and body mass index. A total of 41 variables spanning all domains of the biopsychosocial model were ranked as mortality predictors. The accuracy of the model was excellent (continuous ranked probability score, 0.172; Harrell C-index, 0.70; out-of-bag error rate, 29.7%). CONCLUSIONS: Our random survival forest accurately predicts long-term CLTI mortality, which is driven by demographic, functional, behavioral, and medical comorbidities. Broadening frameworks of risk and refining health care plans to include multidimensional risk factors could improve individualized care for CLTI.

Assessing Glycosylated Hemoglobin Thresholds for Development of Cardiovascular Disease by Racial and Ethnic Groups.

BACKGROUND: Diabetes is the strongest risk factor for cardiovascular disease, and although glycosylated hemoglobin (HbA1c) levels are known to vary by race, no racial and ethnic-specific diagnostic thresholds exist for diabetes in prediction of cardiovascular disease events. The purpose of this study is to determine whether HbA1c thresholds for predicting major adverse cardiovascular events (MACEs) differ among racial and ethnic groups. METHODS AND RESULTS: This is a retrospective cohort study of Kaiser Permanente Northern California adult members (n=309 636) with no history of cardiovascular disease who had HbA1c values and race and ethnicity data available between 2014 and 2019. Multivariable logistic regression was used to evaluate the odds of MACEs by the following racial and ethnic groups: Filipino, South Asian, East Asian, Black, White, and Hispanic. A Youden index was used to calculate HbA1c thresholds for MACE prediction by each racial and ethnic group, stratified by sex. Among studied racial and ethnic groups, South Asian race was associated with the greatest odds of MACEs (1.641 [95% CI, 1.456-1.843]; P<0.0001). HbA1c was a positive predictor for MACEs, with an odds ratio of 1.024 (95% CI, 1.022-1.025) for each 0.1% increment increase in HbA1c. HbA1c values varied between 6.0% and 7.6% in MACE prediction by race and ethnicity and sex. White individuals, South Asian individuals, East Asian women, and Black men had HbA1c thresholds for MACE prediction in the prediabetic range, between 6.0% and 6.2%. Black women, Hispanic men, and East Asian men had HbA1c thresholds of 6.2% to 6.6%, less than the typical threshold of 7.0% that is used as a treatment goal. CONCLUSIONS: Findings suggest that the use of race and ethnic- and sex-specific HbA1c thresholds may need to be considered in treatment goals and cardiovascular disease risk estimation.

Association of Lipoprotein (a) and Standard Modifiable Cardiovascular Risk Factors With Incident Myocardial Infarction: The Mass General Brigham Lp(a) Registry.

BACKGROUND: Lipoprotein (a) [Lp(a)] is a robust predictor of coronary heart disease outcomes, with targeted therapies currently under investigation. We aimed to evaluate the association of high Lp(a) with standard modifiable risk factors (SMuRFs) for incident first acute myocardial infarction (AMI). METHODS AND RESULTS: This retrospective study used the Mass General Brigham Lp(a) Registry, which included patients aged ≥18 years with an Lp(a) measurement between 2000 and 2019. Exclusion criteria were severe kidney dysfunction, malignant neoplasm, and prior known atherosclerotic cardiovascular disease. Diabetes, dyslipidemia, hypertension, and smoking were considered SMuRFs. High Lp(a) was defined as >90th percentile, and low Lp(a) was defined as <50th percentile. The primary outcome was fatal or nonfatal AMI. A combination of natural language processing algorithms, International Classification of Diseases (ICD) codes, and laboratory data was used to identify the outcome and covariates. A total of 6238 patients met the eligibility criteria. The median age was 54 (interquartile range, 43-65) years, and 45% were women. Overall, 23.7% had no SMuRFs, and 17.8% had ≥3 SMuRFs. Over a median follow-up of 8.8 (interquartile range, 4.2-12.8) years, the incidence of AMI increased gradually, with higher number of SMuRFs among patients with high (log-rank P=0.031) and low Lp(a) (log-rank P<0.001). Across all SMuRF subgroups, the incidence of AMI was significantly higher for patients with high Lp(a) versus low Lp(a). The risk of high Lp(a) was similar to having 2 SMuRFs. Following adjustment for confounders and number of SMuRFs, high Lp(a) remained significantly associated with the primary outcome (hazard ratio, 2.9 [95% CI, 2.0-4.3]; P<0.001). CONCLUSIONS: Among patients with no prior atherosclerotic cardiovascular disease, high Lp(a) is associated with significantly higher risk for first AMI regardless of the number of SMuRFs.

Development and Validation of a Nomogram for Predicting Nutritional Risk Based on Frailty Scores in Older Stroke Patients.

BACKGROUND: In older stroke patients with frailty, nutritional deficiencies can amplify their susceptibility, delay recovery, and deteriorate prognosis. A precise predictive model is crucial to assess their nutritional risk, enabling targeted interventions for improved clinical outcomes. OBJECTIVE: To develop and externally validate a nutritional risk prediction model integrating general demographics, physical parameters, psychological indicators, and biochemical markers. The aim is to facilitate the early identification of older stroke patients requiring nutritional intervention. METHODS: This was a multicenter cross-sectional study. A total of 570 stroke patients were included, 434 as the modeling set and 136 as the external validation set. The least absolute shrinkage selection operator (LASSO) regression analysis was used to select the predictor variables. Internal validation was performed using Bootstrap resampling (1000 iterations). The nomogram was constructed based on the results of logistic regression. The performance assessment relied on the receiver operating characteristic curve (ROC), Hosmer--Lemeshow test, calibration curves, Brier score, and decision curve analysis (DCA). RESULTS: The predictive nomogram encompassed seven pivotal variables: Activities of Daily Living (ADL), NIHSS score, diabetes, Body Mass Index (BMI), grip strength, serum albumin levels, and depression. Together, these variables comprehensively evaluate the overall health and nutritional status of elderly stroke patients, facilitating accurate assessment of their nutritional risk. The model exhibited excellent accuracy in both the development and external validation sets, evidenced by AUC values of 0.934 and 0.887, respectively. Such performance highlights its efficacy in pinpointing elderly stroke patients who require nutritional intervention. Moreover, the model showed robust goodness of fit and practical applicability, providing essential clinical insights to improve recovery and prognosis for patients prone to malnutrition. CONCLUSIONS: Elderly individuals recovering from stroke often experience significant nutritional deficiencies. The nomogram we devised accurately assesses this risk by combining physiological, psychological, and biochemical metrics. It equips healthcare providers with the means to actively screen for and manage the nutritional care of these patients. This tool is instrumental in swiftly identifying those in urgent need of targeted nutritional support, which is essential for optimizing their recovery and managing their nutrition more effectively.

AI-enhanced integration of genetic and medical imaging data for risk assessment of Type 2 diabetes.

Type 2 diabetes (T2D) presents a formidable global health challenge, highlighted by its escalating prevalence, underscoring the critical need for precision health strategies and early detection initiatives. Leveraging artificial intelligence, particularly eXtreme Gradient Boosting (XGBoost), we devise robust risk assessment models for T2D. Drawing upon comprehensive genetic and medical imaging datasets from 68,911 individuals in the Taiwan Biobank, our models integrate Polygenic Risk Scores (PRS), Multi-image Risk Scores (MRS), and demographic variables, such as age, sex, and T2D family history. Here, we show that our model achieves an Area Under the Receiver Operating Curve (AUC) of 0.94, effectively identifying high-risk T2D subgroups. A streamlined model featuring eight key variables also maintains a high AUC of 0.939. This high accuracy for T2D risk assessment promises to catalyze early detection and preventive strategies. Moreover, we introduce an accessible online risk assessment tool for T2D, facilitating broader applicability and dissemination of our findings.

Machine learning to predict the occurrence of thyroid nodules: towards a quantitative approach for judicious utilization of thyroid ultrasonography.

Introduction: Ultrasound is instrumental in the early detection of thyroid nodules, which is crucial for appropriate management and favorable outcomes. However, there is a lack of clinical guidelines for the judicious use of thyroid ultrasonography in routine screening. Machine learning (ML) has been increasingly used on big data to predict clinical outcomes. This study aims to leverage the ML approach in assessing the risk of thyroid nodules based on common clinical features. Methods: Data were sourced from a Chinese cohort undergoing routine physical examinations including thyroid ultrasonography between 2013 and 2023. Models were established to predict the 3-year risk of thyroid nodules based on patients' baseline characteristics and laboratory tests. Four ML algorithms, including logistic regression, random forest, extreme gradient boosting, and light gradient boosting machine, were trained and tested using fivefold cross-validation. The importance of each feature was measured by the permutation score. A nomogram was established to facilitate risk assessment in the clinical settings. Results: The final dataset comprised 4,386 eligible subjects. Thyroid nodules were detected in 54.8% (n=2,404) individuals within the 3-year observation period. All ML models significantly outperformed the baseline regression model, successfully predicting the occurrence of thyroid nodules in approximately two-thirds of individuals. Age, high-density lipoprotein, fasting blood glucose and creatinine levels exhibited the highest impact on the outcome in these models. The nomogram showed consistency and validity, providing greater net benefits for clinical decision-making than other strategies. Conclusion: This study demonstrates the viability of an ML-based approach in predicting the occurrence of thyroid nodules. The findings highlight the potential of ML models in identifying high-risk individuals for personalized screening, thereby guiding the judicious use of ultrasound in this context.

Increased Risk of New-Onset Rheumatoid Arthritis Among Osteoarthritis Patients Received Total Knee Arthroplasty: a global federated health network analysis.

Background: Complications of total knee arthroplasty (TKA) had been widely discussed. However, whether TKA influence risk of rheumatoid arthritis (RA) in osteoarthritis patients remained uncertain. We intend to evaluate the risk of RA in osteoarthritis patients underwent TKA. Methods: In this retrospective cohort study, data was retrieved from the US collaborative networks in TriNetX research network. Within the study period between 2005 and 2017, osteoarthritis patients underwent TKA were enrolled as case cohort whereas osteoarthritis patients never underwent TKA were enrolled as control cohort. Covariates were matched via propensity score matching. Risk of RA in TKA patients were valuated under various follow-up time and sensitivity models. Results: Under 1-year, 3-year and 5-year of follow-up, TKA patients were associated with significantly elevated risk of RA, especially under 1-year follow-up (HR=1.74; 95% CI, 1.39-2.18). Subgroup analysis demonstrated a significant increase in the risk of RA following TKA in the female subgroup (HR=1.42; 95% CI, 1.24-1.63), the subgroup aged 18-64 years (HR=1.48; 95% CI, 1.11-1.97), and the subgroup aged greater than 65 years old (HR=1.38; 95% CI, 1.21-1.58) based on 5-year follow-up. Conclusion: Clinicians should be concerned about uncharted association between TKA and RA reported our current study. Additional prospective studies and in-depth mechanistic inquiries were warranted to determine the causation.

Development of a Novel Nomogram to Predict Major Adverse Cardiac Events in Patients with Chronic Total Occlusion.

Objectives: To create a nomogram using single photon emission computed tomography (SPECT) myocardial perfusion imaging and 18F-FDG positron emissions tomography (PET) gated myocardial metabolism imaging to forecast major adverse cardiovascular events (MACE) in chronic total occlusion (CTO) patients treated with optimal medical therapy (OMT). Methods: A total of 257 patients who received OMT between January 2016 and December 2021 were included in this retrospective study. Patients were randomly divided into development (n=179) and validation (n=78) cohorts. A thorough evaluation was conducted, encompassing clinical features and imaging analysis, which involved assessing myocardial perfusion and metabolism. Independent risk factors were identified using least absolute shrinkage and selection operator (LASSO) and multivariate Cox regression analyses. Calibration curves and decision curve analysis (DCA) were used to evaluate the clinical usefulness. Results: In the development cohort, 53 patients (29.6%) experienced MACE out of 179 patients, while in the validation cohort, MACE occurred in 23 (29.5%) patients out of 78. The PET-left ventricular end-systolic volume (P-ESV) (HR 1.01; 95% CI 1.003-1.017; p=0.003), hibernating myocardium / total perfusion defect (HM/TPD) (HR 1.053; 95% CI 1.038-1.069; p<0.001), PET-left ventricular ejection fraction (P-LVEF) (HR 0.862; 95% CI 0.788-0.943; p=0.001), and left anterior descending branch (LAD) (HR 2.303; 95% CI 1.086-4.884; p=0.03) were significantly associated with MACE and were used to develop the nomogram. The nomogram demonstrated excellent discrimination with C-indexes of 0.931 and 0.911 in the development and validation cohorts. DCA determined that the model exhibited a considerably superior net advantage in predicting MACE. Conclusion: A new nomogram integrating clinical factors and imaging features was created to predict the risk of MACE in patients with CTO.

Construction and Validation of Novel Ferroptosis-related Risk Score Signature and Prognostic Prediction Nomogram for Patients with Colorectal Cancer.

Background: Colorectal cancer (CRC) has a high morbidity and mortality. Ferroptosis is a phenomenon in which metabolism and cell death are closely related. The role of ferroptosis-related genes in the progression of CRC is still not clear. Therefore, we screened and validated the ferroptosis-related genes which could determine the prevalence, risk and prognosis of patients with CRC. Methods: We firstly screened differentially expressed ferroptosis-related genes by The Cancer Genome Atlas (TCGA) database. Then, these genes were used to construct a risk-score model using the least absolute shrinkage and selection operator (LASSO) regression algorithm. The function and prognosis of the ferroptosis-related genes were confirmed using multi-omics analysis. The gene expression results were validated using publicly available databases and qPCR. We also used publicly available data and ferroptosis-related genes to construct a prognostic prediction nomogram. Results: A total of 24 differential expressed genes associated with ferroptosis were screened in this study. A three-gene risk score model was then established based on these 24 genes and GPX3, CDKN2A and SLC7A11 were selected. The significant prognostic value of this novel three-gene signature was also assessed. Furthermore, we conducted RT-qPCR analysis on cell lines and tissues, and validated the high expression of CDKN2A, GPX3 and low expression of SLC7A11 in CRC cells. The observed mRNA expression of GPX3, CDKN2A and SLC7A11 was consistent with the predicted outcomes. Besides, eight variables including selected ferroptosis related genes were included to establish the prognostic prediction nomogram for patients with CRC. The calibration plots showed favorable consistency between the prediction of the nomogram and actual observations. Also, the time-dependent AUC (>0.7) indicated satisfactory discriminative ability of the nomogram. Conclusions: The present study constructed and validated a novel ferroptosis-related three-gene risk score signature and a prognostic prediction nomogram for patients with CRC. Also, we screened and validated the ferroptosis-related genes GPX3, CDKN2A, and SLC7A11 which could serve as novel biomarkers for patients with CRC.

Artificial intelligence in detection of small bowel lesions and their bleeding risk: A new step forward.

The present letter to the editor is related to the study with the title "Automatic detection of small bowel (SB) lesions with different bleeding risk based on deep learning models". Capsule endoscopy (CE) is the main tool to assess SB diseases but it is a time-consuming procedure with a significant error rate. The development of artificial intelligence (AI) in CE could simplify physicians' tasks. The novel deep learning model by Zhang et al seems to be able to identify various SB lesions and their bleeding risk, and it could pave the way to next perspective studies to better enhance the diagnostic support of AI in the detection of different types of SB lesions in clinical practice.

FibroScan-aspartate transaminase: A superior non-invasive model for diagnosing high-risk metabolic dysfunction-associated steatohepatitis.

BACKGROUND: Non-alcoholic fatty liver disease (NAFLD) with hepatic histological NAFLD activity score ≥ 4 and fibrosis stage F ≥ 2 is regarded as "at risk" non-alcoholic steatohepatitis (NASH). Based on an international consensus, NAFLD and NASH were renamed as metabolic dysfunction-associated steatotic liver disease (MASLD) and metabolic dysfunction-associated steatohepatitis (MASH), respectively; hence, we introduced the term "high-risk MASH". Diagnostic values of seven non-invasive models, including FibroScan-aspartate transaminase (FAST), fibrosis-4 (FIB-4), aspartate transaminase to platelet ratio index (APRI), etc. for high-risk MASH have rarely been studied and compared in MASLD. AIM: To assess the clinical value of seven non-invasive models as alternatives to liver biopsy for diagnosing high-risk MASH. METHODS: A retrospective analysis was conducted on 309 patients diagnosed with NAFLD via liver biopsy at Beijing Ditan Hospital, between January 2012 and December 2020. After screening for MASLD and the exclusion criteria, 279 patients were included and categorized into high-risk and non-high-risk MASH groups. Utilizing threshold values of each model, sensitivity, specificity, positive predictive value (PPV), and negative predictive values (NPV), were calculated. Receiver operating characteristic curves were constructed to evaluate their diagnostic efficacy based on the area under the curve (AUROC). RESULTS: MASLD diagnostic criteria were met by 99.4% patients with NAFLD. The MASLD population was analyzed in two cohorts: Overall population (279 patients) and the subgroup (117 patients) who underwent liver transient elastography (FibroScan). In the overall population, FIB-4 showed better diagnostic efficacy and higher PPV, with sensitivity, specificity, PPV, NPV, and AUROC of 26.9%, 95.2%, 73.5%, 72.2%, and 0.75. APRI, Forns index, and aspartate transaminase to alanine transaminase ratio (ARR) showed moderate diagnostic efficacy, whereas S index and gamma-glutamyl transpeptidase to platelet ratio (GPR) were relatively weaker. In the subgroup, FAST had the highest diagnostic efficacy, its sensitivity, specificity, PPV, NPV, and AUROC were 44.2%, 92.3%, 82.1%, 67.4%, and 0.82. The FIB-4 AUROC was 0.76. S index and GPR exhibited almost no diagnostic value for high-risk MASH. CONCLUSION: FAST and FIB-4 could replace liver biopsy as more effectively diagnostic methods for high-risk MASH compared to APRI, Forns index, ARR, S index, and GPR; FAST is superior to FIB-4.