We aimed to compare the performance of risk prediction scores for CVD (i.e., coronary heart disease and stroke), and a broader definition of CVD including atrial fibrillation and heart failure (CVD+), in individuals with type 2 diabetes.
Scores were identified through a literature review and were included irrespective of the type of predicted cardiovascular outcome or the inclusion of individuals with type 2 diabetes. Performance was assessed in a contemporary, representative sample of 168,871 UK-based individuals with type 2 diabetes (age ≥18 years without pre-existing CVD+). Missing observations were addressed using multiple imputation.
We evaluated 22 scores: 13 derived in the general population and nine in individuals with type 2 diabetes. The Systemic Coronary Risk Evaluation (SCORE) CVD rule derived in the general population performed best for both CVD (C statistic 0.67 [95% CI 0.67, 0.67]) and CVD+ (C statistic 0.69 [95% CI 0.69, 0.70]). The C statistic of the remaining scores ranged from 0.62 to 0.67 for CVD, and from 0.64 to 0.69 for CVD+. Calibration slopes (1 indicates perfect calibration) ranged from 0.38 (95% CI 0.37, 0.39) to 0.74 (95% CI 0.72, 0.76) for CVD, and from 0.41 (95% CI 0.40, 0.42) to 0.88 (95% CI 0.86, 0.90) for CVD+. A simple recalibration process considerably improved the performance of the scores, with calibration slopes now ranging between 0.96 and 1.04 for CVD. Scores with more predictors did not outperform scores with fewer predictors: for CVD+, QRISK3 (19 variables) had a C statistic of 0.68 (95% CI 0.68, 0.69), compared with SCORE CVD (six variables) which had a C statistic of 0.69 (95% CI 0.69, 0.70). Scores specific to individuals with diabetes did not discriminate better than scores derived in the general population: the UK Prospective Diabetes Study (UKPDS) scores performed significantly worse than SCORE CVD (p value <0.001).
CVD risk prediction scores could not accurately identify individuals with type 2 diabetes who experienced a CVD event in the 10 years of follow-up. All 22 evaluated models had a comparable and modest discriminative ability.
Introduction:Acute kidney injury (AKI) after cardiac surgery is independently associated with a prolonged hospital stay, increased cost of care, and increased post-operative mortality. Delayed elevation of serum creatinine (SCr) levels requires novel biomarkers to provide a prediction of AKI after cardiac surgery. Our objective was to find a novel blood biomarkers combination to construct a model for predicting AKI after cardiac surgery and risk stratification.Methods:This was a case-control study. Weighted Gene Co-expression Network Analysis (WGCNA) was applied to Gene Expression Omnibus (GEO) dataset GSE30718 to seek potential biomarkers associated with AKI. We measured biomarker levels in venous blood samples of 67 patients with AKI after cardiac surgery and 59 control patients in two cohorts. Clinical data were collected. We developed a multi-biomarker model for predicting cardiac-surgery-associated AKI and compared it with a traditional clinical-factor-based model.Results:From bioinformatics analysis and previous articles, we found 6 potential plasma biomarkers for the prediction of AKI. Among them, 3 biomarkers, such as growth differentiation factor 15 (GDF15), soluble suppression of tumorigenicity 2 (ST2, IL1RL1), and soluble urokinase plasminogen activator receptor (uPAR) were found to have prediction ability for AKI (area under the curve [AUC] > 0.6) in patients undergoing cardiac surgery. They were then incorporated into a multi-biomarker model for predicting AKI (C-statistic: 0.84, Brier 0.15) which outperformed the traditional clinical-factor-based model (C-statistic: 0.73, Brier 0.16).Conclusion:Our research validated a promising plasma multi-biomarker model for predicting AKI after cardiac surgery.
Predictive models are currently used for early intervention to help identify patients with a high risk of adverse events. Assessing the accuracy of such models is a crucial part of the development process. To measure the predictive performance of a scoring model, quantitative indices such as the K-S statistic and C-statistic are used. This paper discusses the relationship between Gini coefficients and event prevalence rates. The main contribution of the paper is the theoretical proof of the relationship between the Gini coefficient and event prevalence rate.
Early screening and accurately identifying Acute Appendicitis (AA) among patients with undifferentiated symptoms associated with appendicitis during their emergency visit will improve patient safety and health care quality. The aim of the study was to compare models that predict AA among patients with undifferentiated symptoms at emergency visits using both structured data and free-text data from a national survey.
We performed a secondary data analysis on the 2005-2017 United States National Hospital Ambulatory Medical Care Survey (NHAMCS) data to estimate the association between emergency department (ED) patients with the diagnosis of AA, and the demographic and clinical factors present at ED visits during a patient’s ED stay. We used binary logistic regression (LR) and random forest (RF) models incorporating natural language processing (NLP) to predict AA diagnosis among patients with undifferentiated symptoms.
Among the 40,441 ED patients with assigned International Classification of Diseases (ICD) codes of AA and appendicitis-related symptoms between 2005 and 2017, 655 adults (2.3%) and 256 children (2.2%) had AA. For the LR model identifying AA diagnosis among adult ED patients, the c-statistic was 0.72 (95% CI: 0.69–0.75) for structured variables only, 0.72 (95% CI: 0.69–0.75) for unstructured variables only, and 0.78 (95% CI: 0.76–0.80) when including both structured and unstructured variables. For the LR model identifying AA diagnosis among pediatric ED patients, the c-statistic was 0.84 (95% CI: 0.79–0.89) for including structured variables only, 0.78 (95% CI: 0.72–0.84) for unstructured variables, and 0.87 (95% CI: 0.83–0.91) when including both structured and unstructured variables. The RF method showed similar c-statistic to the corresponding LR model.
We developed predictive models that can predict the AA diagnosis for adult and pediatric ED patients, and the predictive accuracy was improved with the inclusion of NLP elements and approaches.
AbstractIt is essential to identify high risk transient ischemic attack (TIA) patients. The previous study reported that the CSR (comprehensive stroke recurrence) model, a neuroimaging model, had a high predictive ability of recurrent stroke. The aims of this study were to validate the predictive value of CSR model in TIA patients and compare the predictive ability with ABCD3-I score. Data were analyzed from the prospective hospital-based database of patients with TIA which defined by the World Health Organization time-based criteria. The predictive outcome was stroke occurrence at 90 days. The receiver-operating characteristic (ROC) curves were plotted and the C statistics were calculated as a measure of predictive ability. Among 1186 eligible patients, the mean age was 57.28 ± 12.17 years, and 474 (40.0%) patients had positive diffusion-weighted imaging (DWI). There were 118 (9.9%) patients who had stroke within 90 days. In 1186 TIA patients, The C statistic of CSR model (0.754; 95% confidence interval [CI] 0.729–0.778) was similar with that of ABCD3-I score (0.717; 95% CI 0.691–0.743; Z = 1.400; P = 0.1616). In 474 TIA patients with positive DWI, C statistic of CSR model (0.725; 95% CI 0.683–0.765) was statistically higher than that of ABCD3-I score (0.626; 95% CI 0.581–0.670; Z = 2.294; P = 0.0245). The CSR model had good predictive value for assessing stroke risk after TIA, and it had a higher predictive value than ABCD3-I score for assessing stroke risk for TIA patients with positive DWI.
Limited and conflicting evidence is available regarding the predictive value of adding adverse pregnancy outcomes (APOs) to established cardiovascular disease (CVD) risk factors. Hence, the objective of this study was to determine whether adding APOs to the Framingham risk score improves the prediction of CVD events in women.
Methods and Results
Out of 5413 women who participated in the Tehran Lipid and Glucose Study, 4013 women met the eligibility criteria included for the present study. The exposure and the outcome variables were collected based on the standard protocol. Cox proportional hazard model was used to evaluate the association of APOs and CVDs. The variant of C‐statistic for survivals and reclassification of subjects into Framingham risk score categories after adding APOs was reported. Out of the 4013 eligible subjects, a total of 1484 (36.98%) women reported 1 APO, while 395 (9.84%) of the cases reported multiple APOs. Univariate proportional hazard Cox models showed the significant relations between CVD events and APOs. The enhanced model had a higher C‐statistic indicating more acceptable discrimination as well as a slight improvement in discrimination (C‐statistic differences: 0.0053). Moreover, we observed a greater risk of experiencing a CVD event in women with a history of multiple APOs compared with cases with only 1 APO (1 APO: hazard ratio [HR] = 1.22; 2 APOs: HR; 1.94; ≥3 APOs: HR = 2.48).
Beyond the established risk factors, re‐estimated CVDs risk by adding APOs to the Framingham risk score may improve the accurate risk estimation of CVD. Further observational studies are needed to confirm our findings.
In acute myeloid leukemia (AML), measurable residual disease (MRD) before or after allogeneic hematopoietic cell transplantation (HCT) is an established, independent indicator of poor outcome. To address how peri-HCT MRD dynamics could refine risk assessment across different conditioning intensities, we analyzed 810 adults transplanted in remission after myeloablative conditioning (MAC; n=515) or non-MAC (n=295) who underwent multiparameter flow cytometry-based MRD testing before and 20-40 days after allografting. Patients without pre- and post-HCT MRD (MRDneg/MRDneg) had the lowest risks of relapse and highest relapse-free survival (RFS) and overall survival (OS). Relative to those patients, outcomes for MRDpos/MRDpos and MRDneg/MRDpos patients were poor regardless of conditioning intensity. Outcomes for MRDpos/MRDneg patients were intermediate. Among 161 patients with MRD before HCT, MRD was cleared more commonly with a MAC (85/104 [81.7%]) than non-MAC (33/57 [57.9%]) regimen (P=0.002). Although non-MAC regimens were less likely to clear MRD, if they did the impact on outcome was greater. Thus, there was a significant interaction between conditioning intensity and "MRD conversion" for relapse (P=0.020), RFS (P=0.002), and OS (P=0.001). Similar findings were obtained in the subset of 590 patients receiving HLA-matched allografts. C-statistic values were higher (indicating higher predictive accuracy) for peri-HCT MRD dynamics compared to the isolated use of pre-HCT MRD status and post-HCT MRD status for prediction of relapse, RFS, and OS. Across conditioning intensities, peri-HCT MRD dynamics improve risk assessment over isolated pre- or post-HCT MRD assessments.
The disease burden from ischaemic heart disease remains heavy in the Chinese population. Traditional risk scores for estimating long-term mortality in patients with acute myocardial infarction (AMI) have been developed without sufficiently considering advances in interventional procedures and medication. The goal of this study was to develop a risk score comprising clinical parameters and intervention advances at hospital admission to assess 5-year mortality in AMI patients in a Chinese population.
We performed a retrospective observational study on 2,722 AMI patients between January 2013 and December 2017. Of these patients, 1,471 patients from Changsha city, Hunan Province, China were assigned to the development cohort, and 1,251 patients from Xiangtan city, Hunan Province, China, were assigned to the validation cohort. Forty-five candidate variables assessed at admission were screened using least absolute shrinkage and selection operator, stepwise backward regression, and Cox regression methods to construct the C2ABS2-GLPK score, which was graded and stratified using a nomogram and X-tile. The score was internally and externally validated. The C-statistic and Hosmer-Lemeshow test were used to assess discrimination and calibration, respectively.
From the 45 candidate variables obtained at admission, 10 potential predictors, namely, including Creatinine, experience of Cardiac arrest, Age, N-terminal Pro-Brain Natriuretic Peptide, a history of Stroke, Statins therapy, fasting blood Glucose, Left ventricular end-diastolic diameter, Percutaneous coronary intervention and Killip classification were identified as having a close association with 5-year mortality in patients with AMI and collectively termed the C2ABS2-GLPK score. The score had good discrimination (C-statistic = 0.811, 95% confidence intervals (CI) [0.786–0.836]) and calibration (calibration slope = 0.988) in the development cohort. In the external validation cohort, the score performed well in both discrimination (C-statistic = 0.787, 95% CI [0.756–0.818]) and calibration (calibration slope = 0.976). The patients were stratified into low- (≤148), medium- (149 to 218) and high-risk (≥219) categories according to the C2ABS2-GLPK score. The predictive performance of the score was also validated in all subpopulations of both cohorts.
The C2ABS2-GLPK score is a Chinese population-based risk assessment tool to predict 5-year mortality in AMI patients based on 10 variables that are routinely assessed at admission. This score can assist physicians in stratifying high-risk patients and optimizing emergency medical interventions to improve long-term survival in patients with AMI.
Objective: Freezing of gait (FOG) is a disabling complication in Parkinson's disease (PD). Yet, studies on a validated model for the onset of FOG based on longitudinal observation are absent. This study aims to develop a risk prediction model to predict the probability of future onset of FOG from a multicenter cohort of Chinese patients with PD.Methods: A total of 350 patients with PD without FOG were prospectively monitored for ~2 years. Demographic and clinical data were investigated. The multivariable logistic regression analysis was conducted to develop a risk prediction model for FOG.Results: Overall, FOG was observed in 132 patients (37.70%) during the study period. At baseline, longer disease duration [odds ratio (OR) = 1.214, p = 0.008], higher total levodopa equivalent daily dose (LEDD) (OR = 1.440, p < 0.001), and higher severity of depressive symptoms (OR = 1.907, p = 0.028) were the strongest predictors of future onset of FOG in the final multivariable model. The model performed well in the development dataset (with a C-statistic = 0.820, 95% CI: 0.771–0.865), showed acceptable discrimination and calibration in internal validation, and remained stable in 5-fold cross-validation.Conclusion: A new prediction model that quantifies the risk of future onset of FOG has been developed. It is based on clinical variables that are readily available in clinical practice and could serve as a small tool for risk counseling.
ObjectivesLiver dysfunction is prevalent in patients with heart failure (HF) and can lead to poor prognosis. The albumin-bilirubin (ALBI) score is considered as an effective and convenient scoring system for assessing liver function. We analysed the correlation between ALBI and in-hospital mortality in patients with HF.DesignA retrospective cohort study.Setting and participantsA total of 9749 patients with HF (from January 2013 to December 2018) was enrolled and retrospectively analysed.Main outcome measuresThe main outcome is in-hospital mortality.ResultsALBI score was calculated using the formula (log10 bilirubin [umol/L] * 0.66) + (albumin [g/L] * −0.085), and analysed as a continuous variable as well as according to three categories. Following adjustment for multivariate analysis, patients which occurred in-hospital death was remarkably elevated in tertile 3 group (ALBI ≥2.27) (OR 1.671, 95% CI 1.228 to 2.274, p=0.001), relative to the other two groups (tertile 1: ≤2.59; tertile 2: −2.59 to −2.27). Considering ALBI score as a continuous variable, the in-hospital mortality among patients with HF increased by 8.2% for every 0.1-point increase in ALBI score (OR 1.082; 95% CI 1.052 to 1.114; p<0.001). The ALBI score for predicting in-hospital mortality under C-statistic was 0.650 (95% CI 0.641 to 0.660, p<0.001) and the cut-off value of ALBI score was −2.32 with a specificity of 0.630 and a sensitivity of 0.632. Moreover, ALBI score can enhance the predictive potential of NT-pro-BNP (NT-pro-BNP +ALBI vs NT-pro-BNP: C-statistic: z=1.990, p=0.0467; net reclassification improvement=0.4012, p<0.001; integrated discrimination improvement=0.0082, p<0.001).ConclusionsIn patients with HF, the ALBI score was an independent prognosticator of in-hospital mortality. The predictive significance of NT-proBNP +ALBI score was superior to NT-proBNP, and ALBI score can enhance the predictive potential of NT-proBNP.