Risk Discrimination Research Articles

U.S. payer budget impact of using an AI-augmented cancer risk discrimination digital histopathology platform to identify high-risk of recurrence in women with early-stage invasive breast cancer

Aims Use of gene expression signatures to predict adjuvant chemotherapy benefit in women with early-stage breast cancer is increasing. However, high cost, limited access, and eligibility for these tests results in the adoption of less precise assessment approaches. This study evaluates the cost impact of PreciseDx Breast (PDxBr), an AI-augmented histopathology platform that assesses the 6-year risk of recurrence in early-stage invasive breast cancer patients to help improve informed use of adjuvant chemotherapy. Materials and methods A decision-tree Markov model was developed to compare the costs of treatment guided by standard of care (SOC) risk assessment (i.e. clinical diagnostic workup with or without Oncotype DX) versus PDxBr with SOC in a hypothetical cohort of U.S. women with early-stage invasive breast cancer. A commercial payer perspective compares costs of testing, adjuvant therapy, recurrence, adverse events, surveillance, and end-of-life care. Results PDxBr use in prognostic evaluation resulted in savings of $4 million (M) in year one compared to current SOC in 1 M females members. Over 6-years, savings increased to $12.5 M. The per-treated patient costs in year one amounted to $19.5 thousand (K) for SOC and $16.9K for PDxBr. Limitations For simplicity, recurrence was not specified. We performed scenario analyses to account for variations in rates for local, regional, and distant recurrence. Second, a recurrent patient incurs the total cost of treated recurrence in the first year and goes back to remission or death. Third, CDK4/6i treatment is only incorporated in the recurrence costs but not in the first line of treatment for early-stage breast cancer due to limited data. Conclusions Sensitivity analyses demonstrated robust overall savings to changes in all variables in the model. The use of PDxBr to assess breast cancer recurrence risk has the potential to fill gaps in care and reduce costs when gene expression signatures are not available.

Prognostic Value of Integrated Assessment of Cardiac Magnetic Resonance-Derived Global Coronary Flow Reserve and Cardiopulmonary Exercise Testing-Derived Peak Oxygen Consumption in Patients With Acute Myocardial Infarction.

Background: This study investigated the prognostic value of cardiovascular magnetic resonance (CMR)-derived global coronary flow reserve (G-CFR) in addition to cardiopulmonary exercise testing (CPET) variables in patients with acute myocardial infarction (AMI). Methods and Results: We investigated 127 patients with AMI who underwent primary or urgent percutaneous coronary intervention (PCI) and post-intervention CMR and CPET. The incidence of major cardiac and cerebrovascular events (MACCE), defined as all-cause death, recurrent non-fatal myocardial infarction, re-hospitalization due to congestive heart failure, and stroke, was evaluated (median follow-up, 2.8 years). Patients with MACCE (n=14) had lower ejection fraction (EF) (50 [43-59] vs. 58 [51-63]%; P=0.014), lower G-CFR (1.74 [1.19-2.20] vs. 2.40 [1.61-3.66]; P=0.008), and lower peak oxygen consumption (V̇O2) (15.16±2.64 vs. 17.19±3.70 mL/kg/min; P=0.049) than patients without MACCE. G-CFR<2.33 and peak V̇O2 <15.65 mL/kg/min (cut-off values derived from receiver operating characteristic curve analyses) were significantly associated with the incidence of MACCE (log-rank test, P=0.01). The combination of low G-CFR and low peak V̇O2 improved risk discrimination for MACCE when added to the reference clinical model including age, male sex, post-PCI peak creatine kinase, EF, and left anterior descending artery culprit lesion. Conclusions: G-CFR and peak V̇O2 showed incremental prognostic information compared with the reference model using historically important clinical risk factors, indicating that this approach may help identify high-risk patients who suffer subsequent adverse events.

Cardiac Mechanics and the Risk of Atrial Fibrillation in a Community-Based Cohort of Older Adults.

Assessment of cardiac structure and function improves risk prediction of new-onset atrial fibrillation (AF) in different populations. We aimed to comprehensively compare standard and newer measures of cardiac structure and function in improving prediction of AF in a cohort of older adults without history of AF and stroke. We included 5050 participants without prevalent AF and stroke (mean age 75 ± 5 years, 59% women and 22% Black) from the Atherosclerosis Risk in Communities (ARIC) study who underwent complete 2-dimensional echocardiography, including speckle-tracking analysis of the left ventricle (LV) and left atrium (LA). We assessed the association of cardiac measures with incident AF (including atrial flutter) and quantified the extent to which these measures improved model discrimination and risk classification of AF compared with the CHARGE-AF score. Over a median follow-up time of 7 years, 676 participants developed AF (incidence rate, 2.13 per 100 person-years). LV mass index and wall thickness, E/e' and measures of LA structure and function, but not LV systolic function, were associated with incident AF, after accounting for confounders. Above all, LA reservoir strain, contraction strain, and LA minimal volume index (C-statistics [95%Confidence interval]: 0.73 [0.70,0.75], 0.72 [0.70,0.75] and 0.72 [0.69,0.75], respectively) significantly improved the risk discrimination of the CHARGE-AF score (baseline C-statistic: 0.68 [0.65,0.70]) and achieved the highest category-based net reclassification improvement (29%, 24% and 20%, respectively). In a large cohort of older adults without prevalent AF and stroke, measures of LA function improved the prediction of AF more than other conventional cardiac measures.

Quantitative Integrative Survival Prediction in Multiple Myeloma Patients Treated With Bortezomib-Based Induction, High-Dose Therapy and Autologous Stem Cell Transplantation.

Given the high heterogeneity in survival for patients with multiple myeloma, it would be clinically useful to quantitatively predict the individual survival instead of attributing patients to two to four risk groups as in current models, for example, revised International Staging System (R-ISS), R2-ISS, or Mayo-2022-score. Our aim was to develop a quantitative prediction tool for individual patient's 3-/5-year overall survival (OS) probability. We integrated established clinical and molecular risk factors into a comprehensive prognostic model and evaluated and validated its risk discrimination capabilities versus R-ISS, R2-ISS, and Mayo-2022-score. A nomogram for estimating OS probabilities was built on the basis of a Cox regression model. It allows one to translate the individual risk profile of a patient into 3-/5-year OS probabilities by attributing points to each prognostic factor and summing up all points. The nomogram was externally validated regarding discrimination and calibration. There was no obvious bias or overfitting of the prognostic index on the validation cohort. Resampling-based and external evaluation showed good calibration. The c-index of the model was similar on the training (0.76) and validation cohort (0.75) and significantly higher than for the R-ISS (P < .001) or R2-ISS (P < .01). In summary, we developed and validated individual quantitative nomogram-based OS prediction. Continuous risk assessment integrating molecular prognostic factors is superior to R-ISS, R2-ISS, or Mayo-2022-score alone.

Credit Risk Assessment Using a Combined Approach of Supervised and Unsupervised Learning

In the financial industry, credit scoring is a crucial tool for assessing credit risk. The study aims to enhance the accuracy and reliability of credit scoring by combining supervised and unsupervised learning methods. We propose an integrated model that combines Kohonen's Self-Organizing Maps (SOM) with the Random Forest algorithm to provide a more comprehensive analysis of credit card user data. Key features for model training were identified through feature selection and extraction. Experimental results show that the integrated model improved the AUC from 0.82 to 0.89, increased user satisfaction from a score of 3.8 to 4.35, and boosted usage rates by 12.5%. Additionally, the integrated model significantly enhanced the discrimination and prediction accuracy of user credit risk. These findings indicate that the combination of unsupervised learning with Kohonen's Self-Organizing Maps and supervised learning with Random Forest can effectively improve the accuracy of credit scoring, providing financial institutions with a more reliable tool for credit risk assessment.

Associations of Cardiometabolic Indices With Peptides Related to Hypertensive Disorders of Pregnancy in Adult Men.

Seven peptides with low molecular weights in blood have been identified as possible biomarkers of hypertensive disorders of pregnancy (HDP). A history of HDP is known to be associated with a high risk of cardiovascular disease in the later life of women with HDP. However, it remains to be determined whether HDP-related peptides are useful biomarkers of cardiovascular disease in the general population. The purpose of this study was to determine the relationships between these peptides and cardiometabolic risk in adult men. We investigated the relationships between HDP-related peptides and two recent indices of cardiometabolic risk, hematometabolic index (HMI)and lipid accumulation product (LAP), in male workers aged 35 to 69 years. Concentrations of the HDP-related seven peptides with mass/charge ratios (m/z) of 2081 (P-2081), 2091 (P-2091), 2127 (P-2127), 2209 (P-2209), 2378 (P-2378), 2858 (P-2858), and 3156 (P-3156) were measured simultaneously by using a mass spectrometer. Standardized partial regression coefficients (β) were obtained in multivariable linear regression analysis, and mean levels of the log-transformed HMI and LAP were compared in tertile groups of each peptide in the analysis of covariance with adjustment for age, habits of smoking and alcohol drinking, history of diabetes, and medication therapy for dyslipidemia. There was a significant positive correlation between the HMI and the serum level of P-2378 (β= 0.310), a fragment of complement component 4, while a significant inverse correlation (β= -0.389) was obtained between the LAP and the serum level of P-3156, a fragment of inter-α-trypsin inhibitor heavy chain H4. Other peptides (P-2081, P-2091, P-2127, P-2209, and P-2858) did not show significant correlations with the HMI or LAP. The log-transformed HMI tended to be higher with an increase in the tertile for P-2378. The mean level of log-transformed LAP in the first tertile group of P-3156 was significantly higher than those in the second and third tertile groups of P-3156. The HDP-related peptides with m/z of 2378 and m/z of 3156 were shown to be associated with the HMI and LAP, respectively, which are recent indices reflecting cardiometabolic risk. Therefore, the peptides with m/z of 2378 and m/z of 3156 were thought to be potential biomarkers for discrimination of cardiovascular risk in adult men. Further studies on the relationships between the peptides and cardiovascular risk factors in non-pregnant women are needed to confirm the findings of this study.

Proteomic analysis of cardiorespiratory fitness for prediction of mortality and multisystem disease risks

Despite the wide effects of cardiorespiratory fitness (CRF) on metabolic, cardiovascular, pulmonary and neurological health, challenges in the feasibility and reproducibility of CRF measurements have impeded its use for clinical decision-making. Here we link proteomic profiles to CRF in 14,145 individuals across four international cohorts with diverse CRF ascertainment methods to establish, validate and characterize a proteomic CRF score. In a cohort of around 22,000 individuals in the UK Biobank, a proteomic CRF score was associated with a reduced risk of all-cause mortality (unadjusted hazard ratio 0.50 (95% confidence interval 0.48–0.52) per 1 s.d. increase). The proteomic CRF score was also associated with multisystem disease risk and provided risk reclassification and discrimination beyond clinical risk factors, as well as modulating high polygenic risk of certain diseases. Finally, we observed dynamicity of the proteomic CRF score in individuals who undertook a 20-week exercise training program and an association of the score with the degree of the effect of training on CRF, suggesting potential use of the score for personalization of exercise recommendations. These results indicate that population-based proteomics provides biologically relevant molecular readouts of CRF that are additive to genetic risk, potentially modifiable and clinically translatable.

Performance of contemporary cardiovascular risk stratification scores in Brazil: an evaluation in the ELSA-Brasil study

AimsDespite notable population differences in high-income and low- and middle-income countries (LMICs), national guidelines in LMICs often recommend using US-based cardiovascular disease (CVD) risk scores for treatment decisions. We examined...

Blood-based DNA methylation markers for lung cancer prediction

ObjectiveScreening high-risk individuals with low-dose CT reduces mortality from lung cancer, but many lung cancers occur in individuals who are not eligible for screening. Risk biomarkers may be useful to...

Evaluation of Polygenic Risk Scores for Prediction of Coronary Artery Disease in a Greek Case-Control Study.

Coronary artery disease (CAD) stands as the most predominant type of cardiovascular disease (CVD). Polygenic risk scores (PRSs) have become essential tools for quantifying genetic susceptibility, and researchers endeavor to improve their predictive precision. The aim of the present work is to assess the performance and the relative contribution of PRSs developed for CVD or CAD within a Greek population. The sample under study comprised 924 Greek individuals (390 cases with CAD and 534 controls) from the THISEAS study. Nine PRSs drawn from the PGS catalog were replicated and tested for CAD risk prediction. PRSs computations were performed in the R language, and snpStats was used to process genotypic data. Descriptive characteristics of the study were analyzed using the statistical software IBM SPSS Statistics v21.0. The effectiveness of each PRS was assessed using the PRS R2 metric provided by PRSice2. Among nine PRSs, PGS000747 greatly increased the predictive value of primary CAD risk factors by 21.6% (p-value = 2.63 × 10-25). PGS000012 was associated with a modest increase in CAD risk by 2.2% (p-value = 9.58 × 10-4). The remarkable risk discrimination capability of PGS000747 stands out as the most noteworthy outcome of our study.

#559 Validation of the Kidney Failure Risk Equation (KFRE) in individuals with chronic kidney disease and multimorbidity

Abstract Background and Aims Increasing numbers of individuals with chronic kidney disease (CKD) experience multiple long-term conditions (multimorbidity). Clinical guidance recommends the use of validated risk prediction equations, such as the kidney failure risk equation (KFRE), to guide referral to specialist kidney care services. However, multimorbidity may impact the accuracy of creatinine-based eGFR and bias the prognostic utility of KFRE. Equations with alternative filtration markers, such as Cystatin C eGFR (eGFRcys) or the combined creatinine and Cystatin C eGFR (eGFRcrcys), may improve KFRE's risk stratification and discrimination of future kidney failure risks. This study aimed to validate the four-variable KFRE in individuals with CKD, with and without multimorbidity in a research-based cohort (UK Biobank) and a population-based cohort (Stockholm Creatinine Measurements project (SCREAM)). The study also assessed the performance of KFRE when using eGFRcr, eGFRcys and eGFRcrcys. Method Individuals from both cohorts were included if they had CKD, defined as eGFR&amp;lt;60 mL/min/1.73 m2 by any of the three eGFR equations (eGFRcr, eGFRcys and eGFRcrcys), and had available proteinuria measurement at time of testing or within the previous 12 months. Multimorbidity was defined as the presence of two or more long-term conditions in addition to CKD and was grouped into multimorbidity clusters based on previous research. The outcome was kidney failure, defined as the need for long-term dialysis or kidney transplantation. KFRE performance at 2- and 5-years was assessed using the area under the receiver operating characteristic curve and c-index for discrimination and calibration curves for calibration. Results We included 24 489 individuals from UK Biobank and 42 902 individuals from SCREAM (mean age 62.8 (SD 5.6) and 70.1 (SD14.1), 54% and 66% female, respectively). In UK biobank, 14 998 individuals had multimorbidity, of which 5 375 had cardiometabolic multimorbidity. In SCREAM, 30 147 had multimorbidity and 17 854 cardiometabolic multimorbidity. Overall, there were 252 and 312 kidney failure events and 1 108 and 1 471 death events in UK Biobank and 918 and 1 098 kidney failure events and 8 785 and 10 152 death events in SCREAM within 2- and 5-years respectively. Model performance was consistent across both cohorts. Discrimination power of KFRE was good in individuals with and without multimorbidity and across the 2-year and 5-year models (Table 1). Calibration plots revealed over-estimation of risk at 2-years in both cohorts and under-estimation of risk at 5-years in patients with multimorbidity in UK Biobank. There was no improvement in model performance when using eGFRcys or eGFRcrcys compared to eGFRCr. There was a higher cumulative incidence of both kidney failure and death in the multimorbidity group, with a prominent increase in risk of death over time compared to the no multimorbidity group. This was most evident in the SCREAM cohort (Fig. 1). Conclusion KFRE adequately predicts kidney failure in individuals with multimorbidity and either creatinine or cystatin C can be used. Given the high rates of mortality amongst people with multimorbidity, exploration of models that account for the competing risk of death is warranted.

Association of plasma ceramide with decline in kidney function in patients with type 2 diabetes

Circulating ceramide levels are dysregulated in kidney disease. However, their associations with rapid decline in kidney function (RDKF) and end-stage kidney disease (ESKD) in patients with type 2 diabetes (T2D) are unknown. In this prospective study of 1746 T2D participants, we examined the association of plasma ceramide Cer16:0, Cer18:0, Cer24:0, and Cer24:1 with RDKF, defined as an estimated glomerular filtration rate (eGFR) decline of 5 ml/min/1.73 m2 per year or greater, and ESKD defined as eGFR <15/min/1.73 m2 for at least 3 months, on dialysis or renal death at follow-up. During a median follow-up period of 7.7 years, 197 patients experienced RDKF. Ceramide Cer24:0 (odds ratio [OR] = 0.71, 95% CI 0.56–0.90) and ratios Cer16:0/Cer24:0 (OR = 3.54 [1.70–7.35]), Cer18:0/Cer24:0 (OR = 1.89 [1.10–3.25]), and Cer24:1/Cer24:0 (OR = 4.01 [1.93–8.31]) significantly associated with RDKF in multivariable analysis; 124 patients developed ESKD. The ratios Cer16:0/Cer24:0 (hazard ratio [HR] = 3.10 [1.44–6.64]) and Cer24:1/Cer24:0 (HR = 4.66 [1.93–11.24]) significantly associated with a higher risk of ESKD. The Cer24:1/Cer24:0 ratio improved risk discrimination for ESKD beyond traditional risk factors by small but statistically significant margin (Harrell C-index difference: 0.01; P = 0.022). A high ceramide risk score also associated with RDKF (OR = 2.28 [1.26–4.13]) compared to lower risk score. In conclusion, specific ceramide levels and their ratios are associated with RDKF and conferred an increased risk of ESKD, independently of traditional risk factors, including baseline renal functions in patients with T2D.

Association of Life’s Essential 8 and Simple 7 Scores With Mortality: Comparison With Pooled Cohort Equation

BackgroundIn 2022, the Life’s Simple 7 (LS7) score was replaced with the Life’s Essential 8 (LE8) score as a tool to measure cardiovascular health. The risk prediction values of LE8 and LS7 scores for mortality have not been compared. Additionally, the risk prediction value of these scores has not been compared with the pooled cohort equations (PCE) in individuals aged 40 to 79 years. ObjectivesThis study compared the risk prediction value of the: 1) LE8 and LS7 scores in the overall population; and 2) LE8 score, LS7 score, and PCE in the 40- to 79-year-old age group for all-cause and cardiovascular mortality in a nationally representative US population. MethodsThe LS7 and LE8 scores and the PCE were calculated in the National Health and Nutrition Examination Survey cycles 2007 to 2018. All-cause and cardiovascular mortality were identified by linking the participants to the National Death Index. The C-statistics of the respective weighted Cox models were used to compare the risk prediction value of the standardized scores. ResultsAmong 21,721 individuals included, the C-statistics for all-cause mortality were 0.823 (95% CI: 0.803-0.843) and 0.819 (95% CI: 0.799-0.838) in the LE8 and LS7 score-based models, respectively. The C-statistics for cardiovascular mortality were 0.887 (95% CI: 0.857-0.905) for the LE8 score-based model and 0.883 (95% CI: 0.861-0.905) for the LS7 score-based model. Among 12,943 individuals aged 40 to 79 years, the C-statistics for the outcome of all-cause mortality were 0.756 (95% CI: 0.732-0.779), 0.674 (95% CI: 0.646-0.701), and 0.681 (95% CI: 0.656-0.706) for the PCE, LS7 score, and LE8 score-based models, respectively. ConclusionsThe LS7 and LE8 scores had similar risk prediction values for all-cause and cardiovascular mortality. Among 40- to 79-year-old individuals, the PCE had better risk discrimination in the LE8 and LS7 scores in predicting all-cause mortality.

The role of serum magnesium in the prediction of acute kidney injury after total aortic arch replacement: A prospective observational study.

Considerable morbidity and death are associated with acute kidney damage (AKI) following total aortic arch replacement (TAAR). The relationship between AKI following TAAR and serum magnesium levels remains unknown. The intention of this research was to access the predictive value of serum magnesium levels on admission to the Cardiovascular Surgical Intensive Care Unit (CSICU) for AKI in patients receiving TAAR. From May 2018 to January 2020, a prospective, observational study was performed in the Guangdong Provincial People's Hospital CSICU. Patients accepting TAAR admitted to the CSICU were studied. The Kidney Disease: Improving Global Outcomes (KDIGO) definition of serum creatinine was used to define AKI, and KDIGO stages two or three were used to characterize severe AKI. Multivariable logistic regression and area under the curve receiver-operator characteristic curve (AUC-ROC) analysis were conducted to assess the predictive capability of the serum magnesium for AKI detection. Finally, the prediction model for AKI was established and internally validated. Of the 396 enrolled patients, AKI occurred in 315 (79.5%) patients, including 154 (38.8%) patients with severe AKI. Serum magnesium levels were independently related to the postoperative AKI and severe AKI (both, P < 0.001), and AUC-ROCs for predicting AKI and severe AKI were 0.707 and 0.695, respectively. Across increasing quartiles of serum magnesium, the multivariable-adjusted odds ratios (95% confidence intervals) of postoperative AKI were 1.00 (reference), 1.04 (0.50-2.82), 1.20 (0.56-2.56), and 6.19 (2.02-23.91) (P for Trend < 0.001). When serum magnesium was included to a baseline model with established risk factors, AUC-ROC (0.833 vs 0.808, P = 0.050), reclassification (P < 0.001), and discrimination (P = 0.002) were further improved. Serum magnesium levels on admission are an independent predictor of AKI. In TAAR patients, elevated serum magnesium levels were linked to an increased risk of AKI. In addition, the established risk factor model for AKI can be considerably improved by the addition of serum magnesium in TAAR patients hospitalized in the CSICU.

Hemodynamic gain index and risk of ventricular arrhythmias: a prospective cohort study.

Objectives: Hemodynamic gain index (HGI), a novel hemodynamic index obtained from cardiopulmonary exercise testing (CPX), is associated with adverse cardiovascular outcomes. However, its specific relationship with ventricular arrhythmias (VAs) is unknown. We aimed to assess the association of HGI with risk of VAs in a prospective study. Design: Hemodynamic gain index was estimated using heart rate and systolic blood pressure (SBP) responses ascertained in 1945 men aged 42-61 years during CPX from rest to maximum exercise, using the formula: [(Heart ratemax x SBPmax) - (Heart raterest x SBPrest)]/(Heart raterest x SBPrest). Cardiorespiratory fitness (CRF) was measured using respiratory gas exchange analysis. Hazard ratios (HRs) (95% confidence intervals, CIs) were estimated for VAs. Results: Over a median follow-up duration of 28.2 years, 75 cases of VA were recorded. In analysis adjusted for established risk factors, a unit (bpm/mmHg) higher HGI was associated with a decreased risk of VA (HR 0.72, 95% CI: 0.55-0.95). The results remained consistent on adjustment for lifestyle factors and comorbidities (HR 0.72, 95% CI: 0.55-0.93). Comparing the top versus bottom tertiles of HGI, the corresponding adjusted HRs (95% CIs) were 0.51 (0.27-0.96) and 0.52 (0.28-0.94), respectively. The associations were attenuated on addition of CRF to the model. HGI improved risk discrimination beyond established risk factors but not CRF. Conclusions: Higher HGI is associated with a reduced risk of VAs in middle-aged and older Caucasian men, but dependent on CRF levels. Furthermore, HGI improves the prediction of the long-term risk for VAs beyond established risk factors but not CRF.

Perfusion quality odds (PEQUOD) trial: validation of the multifactorial dynamic perfusion index as a predictor of cardiac surgery-associated acute kidney injury.

The multifactorial dynamic perfusion index was recently introduced as a predictor of cardiac surgery-associated acute kidney injury. The multifactorial dynamic perfusion index was developed based on retrospective data retrieved from the patient files. The present study aims to prospectively validate this index in an external series of patients, through an on-line measure of its various components. Inclusion criteria were adult patients undergoing cardiac surgery with cardiopulmonary bypass. Data collection included preoperative factors and cardiopulmonary bypass-related factors. These were collected on-line using a dedicated monitor. Factors composing the multifactorial dynamic perfusion index are the nadir haematocrit, the nadir oxygen delivery, the time of exposure to a low oxygen delivery, the nadir mean arterial pressure, cardiopulmonary bypass duration, the use of red blood cell transfusions and the peak arterial lactates. Two hundred adult patients were investigated. The multifactorial dynamic perfusion index had a good (c-statistics 0.81) discrimination for cardiac surgery-associated acute kidney injury (any stage) and an excellent (c-statistics 0.93) discrimination for severe patterns (stage 2-3). Calibration was modest for cardiac surgery-associated acute kidney injury (any stage) and good for stage 2-3. The use of vasoconstrictors was an additional factor associated with cardiac surgery-associated acute kidney injury. The multifactorial dynamic perfusion index is validated for discrimination of cardiac surgery-associated acute kidney injury risk. It incorporates modifiable risk factors, and may help in reducing the occurrence of cardiac surgery-associated acute kidney injury.

Prognostic performance of soluble urokinase plasminogen activator receptor for heart failure or mortality in Western and Asian patients with acute breathlessness

AimsThe performance of circulating soluble urokinase plasminogen activator receptor (suPAR) for predicting the composite endpoint of subsequent heart failure (HF) hospitalisation and/or death at 1 year was assessed in (i) patients with undifferentiated breathlessness, and generalisability was compared in (ii) disparate Western versus Asian sub-cohorts, and in (iii) the sub-cohort adjudicated with HF. Methods and resultsPatients with acute breathlessness were recruited from the emergency departments in New Zealand (NZ, n = 612) and Singapore (n = 483). suPAR measured in the presentation samples was higher in patients incurring the endpoint (n = 281) compared with survivors (5.2 ng/mL vs 3.1 ng/mL, P < 0.0001). The discriminative power of suPAR for endpoint prediction was c-statistic of 0.77 in the combined population, but was superior in Singapore than NZ (c-statistic: 0.83 vs 0.71, P < 0.0001). Although the highest suPAR tertile (>4.37 ng/mL) was associated with risks of >4-fold in NZ, >20-fold in Singapore, and ≥3-fold in HF for incurring the outcome, there was no interaction between country and suPAR levels after adjustment. Multivariable analysis indicated suPAR to be robust in predicting HF/death at 1-year [hazard ratio: 1.9 (95% CI:1.7 to 2.0) per SD increase] and improved risk discrimination for outcome prediction in HF (∆0.06) and for those with NT-proBNP >1000 pg/mL (∆0.02). ConclusionsuPAR is a strong independent predictor of HF and/or death at 1 year in acutely breathless patients, in both Asian and Western cohorts, and in HF. suPAR may improve stratification of acutely breathless patients, and in acute HF, for risk of later onset of heart failure or mortality.

A machine learning algorithm based on circulating metabolic biomarkers offers improved predictions of neurological diseases

Background and aimsA machine learning algorithm based on circulating metabolic biomarkers for the predictions of neurological diseases (NLDs) is lacking. To develop a machine learning algorithm to compare the performance of a metabolic biomarker-based model with that of a clinical model based on conventional risk factors for predicting three NLDs: dementia, Parkinson’s disease (PD), and Alzheimer’s disease (AD). Materials and methodsThe eXtreme Gradient Boosting (XGBoost) algorithm was used to construct a metabolic biomarker-based model (metabolic model), a clinical risk factor-based model (clinical model), and a combined model for the prediction of the three NLDs. Risk discrimination (c-statistic), net reclassification improvement (NRI) index, and integrated discrimination improvement (IDI) index values were determined for each model. ResultsThe results indicate that incorporation of metabolic biomarkers into the clinical model afforded a model with improved performance in the prediction of dementia, AD, and PD, as demonstrated by NRI values of 0.159 (0.039–0.279), 0.113 (0.005–0.176), and 0.201 (−0.021–0.423), respectively; and IDI values of 0.098 (0.073–0.122), 0.070 (0.049–0.090), and 0.085 (0.068–0.101), respectively. ConclusionThe performance of the model based on circulating NMR spectroscopy-detected metabolic biomarkers was better than that of the clinical model in the prediction of dementia, AD, and PD.

Unpacking gender-specific risk and protective factors for mental health status among Congolese refugees in Uganda

ABSTRACT Background: Research indicates refugees from the Democratic Republic of Congo (DRC), particularly females, have a higher incidence of mental health problems compared to the global norm for conflict-affected populations. Objective: This study aimed to unpack gender differences in the mental health of Congolese refugees by examining specific risk (trauma exposure, adaptation challenges, and discrimination) and protective factors (marital status, literacy, and social resources) in relation to posttraumatic stress symptoms (PTSS) and depression. Method: Utilizing systematic random sampling, we surveyed 667 adult refugees (370 females, 297 males) in the Kyaka II refugee settlement in Western Uganda. A multi-group path analysis was conducted, initially allowing for variance between genders and subsequently comparing a constrained model, where paths were set equal across groups. Results: The unconstrained model presented an excellent fit to the data. When paths were set to be equal across groups, the decline in model fit, confirmed by a chi-square difference test, indicated differences in the model for males and females. A series of Z-tests were used to compare individual paths. Experiencing discrimination was a stronger risk factor for depression among men, whereas a history of rape was more strongly associated with depression for females. Being literate and a member of a social group in the settlement were stronger protective factors for depression among men, whereas living with a partner and a felt sense of connection to their community was more important for women. Associations between risk and protective factors and PTSS were more similar across groups, only membership in a group was significantly moderated by gender; with group membership being more impactful for males. Conclusion: The results highlight similarities and differences in predictors of distress for male and female Congolese refugees and point to potential avenues for tailoring programming to be gender sensitive.

Discrimination and net-reclassification of cardiovascular disease risk with Lipoprotein(a) levels: The ATTICA study (2002–2022)

Lipoprotein(a) [Lp(a)] is a recognized as risk factor for atherosclerotic cardiovascular disease (ASCVD). However, its influence on clinical risk evaluations remains unclear. This study aimed to determine whether Lp(a) improves CVD risk prediction among apparently healthy adults from the general population. In 2002, n = 3,042 adults free of CVD, residing in Athens metropolitan area, in Greece, were recruited. A 20-year follow-up was conducted in 2022, comprising n = 2,169 participants, of which n = 1,988 had complete data for CVD incidence. Lp(a) levels were significantly associated with 20-year ASCVD incidence in the crude model (Hazard Ratio per 1 mg/dL: 1.004, p = 0.048), but not in multi-adjusted models considering demographic, lifestyle, and clinical factors. Adding Lp(a) to the Reynolds Risk Score (RRS) and Framingham Risk Score (FRS) variables resulted in positive Net Reclassification Improvement (NRI) values (0.159 and 0.160 respectively), indicating improved risk classification. Mediation analysis suggested that C-reactive protein, Interleukin-6, and Fibrinogen mediate the relationship between Lp(a) and ASCVD. No significant interaction was observed between Lp(a) and potential moderators. Lp(a) levels can predict 20-year CVD outcomes and improve CVD risk prediction within the general population, possibly via the intricate relationship between Lp(a), systemic inflammation, atherothrombosis.