Risk Prediction Score Research Articles

Validity of mortality risk prediction scores in critically ill patients with secondary pulmonary embolism.

Pulmonary embolism (PE) is a feared complication in the ICU, significantly impacting morbidity and mortality of the patients affected. Herein, we assess the use of the Acute Physiology and Chronic Health Evaluation-IV (APACHE-IV) and PE-specific risk scores to predict mortality among intensive care unit (ICU) patients who developed secondary PE. This retrospective cohort study used information from 208 United States critical care units recorded in the eICU Collaborative Research Database during 2014 and 2015. We calculated APACHE-IV, Pulmonary Embolism Severity Index (PESI), simplified PESI (sPESI), and ICU-sPESI scores and compared their predicting performance using the area under the receiver operating characteristic (AUROC) curve. Of 812 patients included in our study, 150 died (mortality, 18.5% [95% CI, 15.8%-21.1%]). Compared to survivors, non-survivors had higher APACHE-IV (86 vs 52, P<0.001), PESI (170 vs 129, P<0.001), sPESI (2 vs 2, P<0.001), and ICU-sPESI (4 vs 2, P<0.001) scores. AUROCs were 0.790 (APACHE-IV); 0.737 (PESI); 0.726 (ICU-sPESI); and 0.620 (sPESI). APACHE-IV performed significantly better than all 3 PE-specific mortality scores (APACHE-IV vs PESI, P=0.041; APACHE-IV vs sPESI, P=0.001; and APACHE-IV vs ICU-sPESI, P=0.021). Both the PESI and ICU-sPESI outperformed the sPESI (PESI vs sPESI, P=0.001; ICU-sPESI vs sPESI, P<0.001). APACHE-IV score was found to be the best instrument for predicting mortality risk, but PESI and ICU-sPESI scores may be used when APACHE-IV is unavailable. sPESI AUROC suggests absence of sufficient discriminative value to be used as a predictor of mortality in patients with secondary PE.

Risk factors and scores for prediction of coronary artery aneurysms in Kawasaki disease: a European monocentric study

BackgroundJapanese Kawasaki disease (KD) risk scores cannot be adopted in non-Japanese patients. In North American populations a baseline coronary artery Z-score > 2 and the Son score are associated with coronary artery aneurysms (CAAs) at 4 and 8 weeks from disease onset. In European populations, the Kawanet and Kawanet-echo scores are associated with intravenous immunoglobulin resistance. This study aims to evaluate the association between KD risk scores and baseline coronary artery Z-scores with CAAs at one, two, and six months in a European population.MethodsHistorical cohort study of all the children diagnosed with KD in a tertiary care hospital in Milan, Italy, between 1st January 2015 and 31st May 2021. Univariate and multivariate (adjusting for age and corticosteroid therapy) logistic regression analyses were used to study the association between the risk scores, a baseline Z-score ≥ 2 and ≥ 2.5 with CAAs.ResultsEighty-nine patients were diagnosed with KD at our Centre, and 12 were excluded based on the exclusion criteria. We included 77 patients, 51 (66%) males, and 26 (34%) females, with a median age at presentation of 27 months (IQR 13–46). A baseline Z-score ≥ 2 was correlated with CAAs at one and two-month follow-ups (odds ratio (OR) 10, 95% confidence interval (CI) 2–72, and OR 18, CI 3-357) but not at six-month follow-up. The Son score showed an association with one and two-month follow-up CAAs (OR 3, CI 1.3-7, and OR 3, CI 1.3-8) but not with a six-month follow-up.ConclusionsPatients with a baseline Z-score ≥ 2 are at higher risk for CAAs in the long term. The Son score should be tested in larger European samples. Further studies should keep the observational periods longer than 8 weeks from KD onset.

Prediction of unplanned cesarean section using measurable maternal and fetal characteristics, Ethiopia, a retrospective cohort study

BackgroundWhen a pregnant woman experiences unusual circumstances during a vaginal delivery, an unplanned cesarean section may be necessary to save her life. It requires knowledge and quick assessment of the risky situation to decide to perform an unplanned cesarean section, which only occurs in specific obstetric situations. This study aimed to develop and validate a risk prediction model for unplanned cesarean sections among laboring women in Ethiopia.MethodA retrospective follow-up study was conducted. The data were extracted using a structured checklist. Analysis was done using STATA version 14 and R version 4.2.2 software. Logistic regression was fitted to determine predictors of unplanned cesarean sections. Significant variables were then used to develop a risk prediction model. Performance was assessed using Area Under the Receiver Operating Curve (AUROC) and calibration plot. Internal validation was performed using the bootstrap technique. The clinical benefit of the model was assessed using decision curve analysis.ResultA total of 1,000 laboring women participated in this study; 28.5% were delivered by unplanned cesarean section. Parity, amniotic fluid status, gestational age, prolonged labor, the onset of labor, amount of amniotic fluid, previous mode of delivery, and abruption remained in the reduced multivariable logistic regression and were used to develop a prediction risk score with a total score of 9. The AUROC was 0.82. The optimal cut-off point for risk categorization as low and high was 6, with a sensitivity (85.2%), specificity (90.1%), and accuracy (73.9%). After internal validation, the optimism coefficient was 0.0089. The model was found to have clinical benefits.ConclusionTo objectively measure the risk of an unplanned Caesarean section, a risk score model based on measurable maternal and fetal attributes has been developed. The score is simple, easy to use, and repeatable in clinical practice.

A Machine Learning Predictive Model of Bloodstream Infection in Hospitalized Patients.

The aim of the study was to build a machine learning-based predictive model to discriminate between hospitalized patients at low risk and high risk of bloodstream infection (BSI). A Data Mart including all patients hospitalized between January 2016 and December 2019 with suspected BSI was built. Multivariate logistic regression was applied to develop a clinically interpretable machine learning predictive model. The model was trained on 2016-2018 data and tested on 2019 data. A feature selection based on a univariate logistic regression first selected candidate predictors of BSI. A multivariate logistic regression with stepwise feature selection in five-fold cross-validation was applied to express the risk of BSI. A total of 5660 hospitalizations (4026 and 1634 in the training and the validation subsets, respectively) were included. Eleven predictors of BSI were identified. The performance of the model in terms of AUROC was 0.74. Based on the interquartile predicted risk score, 508 (31.1%) patients were defined as being at low risk, 776 (47.5%) at medium risk, and 350 (21.4%) at high risk of BSI. Of them, 14.2% (72/508), 30.8% (239/776), and 64% (224/350) had a BSI, respectively. The performance of the predictive model of BSI is promising. Computational infrastructure and machine learning models can help clinicians identify people at low risk for BSI, ultimately supporting an antibiotic stewardship approach.

Integration of risk factor polygenic risk score with disease polygenic risk score for disease prediction

Polygenic risk score (PRS) is useful for capturing an individual’s genetic susceptibility. However, previous studies have not fully exploited the potential of the risk factor PRS (RFPRS) for disease prediction. We explored the potential of integrating disease-related RFPRSs with disease PRS to enhance disease prediction performance. We constructed 112 RFPRSs and analyzed the association of RFPRSs with diseases to identify disease-related RFPRSs in 700 diseases, using the UK Biobank dataset. We uncovered 6157 statistically significant associations between 247 diseases and 109 RFPRSs. We estimated the disease PRSs of 70 diseases that exhibited statistically significant heritability, to generate RFDiseasemetaPRS—a combined PRS integrating RFPRSs and disease PRS—and compare the prediction performance metrics between RFDiseasemetaPRS and disease PRS. RFDiseasemetaPRS showed better performance for Nagelkerke’s pseudo-R2, odds ratio (OR) per 1 SD, net reclassification improvement (NRI) values and difference of R2 considered by variance of R2 in 31 out of 70 diseases. Additionally, we assessed risk classification between two models by examining OR between the top 10% and remaining 90% individuals for the 31 diseases; RFDiseasemetaPRS exhibited better R2, NRI and OR than disease PRS. These findings highlight the importance of utilizing RFDiseasemetaPRS, which can provide personalized healthcare and tailored prevention strategies.

A novel cardiovascular disease risk score for prediction of atherosclerotic disease events in men with prostate cancer.

314 Background: Prostate cancer patients (PC) face an elevated risk of both developing atherosclerotic cardiovascular disease (ASCVD). The American College of Cardiology Pooled Cohort Equations (PCE) for ASCVD predictions may lack accuracy. Methods: Males ≥18 years, diagnosed with PC between 2005-2012 at a hybrid academic-community practice were included. Using XGBoost algorithm we developed using a training subset of the cohort (50% train + 25% test), ranked 33 covariates (including demographic, treatment-related and social determinants of health (SDOH) information) for ASCVD prediction using SHAP (Shapley additive explanations) values. The top 10 predictors were transformed in a predictive equation using logistic regression models. This equation was tested in the cohort validation subset (25%), and subsequently compared to the PCE risk score. Results: We included 1,506 patients, with a median age of 67 (IQR 60-74) years, 13.8% had advanced stage disease (TNM III-IV), 1.5% had high risk PC (Gleason 8-10), and 20.5% received androgen deprivation therapy (ADT). Of those, 10.4% had a 10-year ASCVD risk. The PCE had an area under the curve (AUC)=0.61 and underestimated ASCVD in 0.9% (mean risk=20.1% [95% CI 17.2-23.0] vs. mean predicted risk=19.2% [95% CI 18.6-19.8]). The equation pooled from the top-10 predictors of the ML algorithm (C-index=0.78 [95% CI 0.75-0.81]) achieved an AUC=0.71 (Table). Conclusions: Conventional PCE tend to underestimate ASCVD risk in males with PC. A cancer-specific model inclusive of SDOH exhibits good performance for predicting ASCVD risk in this population. [Table: see text]

GlioPredictor: a deep learning model for identification of high-risk adult IDH-mutant glioma towards adjuvant treatment planning

Identification of isocitrate dehydrogenase (IDH)-mutant glioma patients at high risk of early progression is critical for radiotherapy treatment planning. Currently tools to stratify risk of early progression are lacking. We sought to identify a combination of molecular markers that could be used to identify patients who may have a greater need for adjuvant radiation therapy machine learning technology. 507 WHO Grade 2 and 3 glioma cases from The Cancer Genome Atlas, and 1309 cases from AACR GENIE v13.0 datasets were studied for genetic disparities between IDH1-wildtype and IDH1-mutant cohorts, and between different age groups. Genetic features such as mutations and copy number variations (CNVs) correlated with IDH1 mutation status were selected as potential inputs to train artificial neural networks (ANNs) to predict IDH1 mutation status. Grade 2 and 3 glioma cases from the Memorial Sloan Kettering dataset (n = 404) and Grade 3 glioma cases with subtotal resection (STR) from Northwestern University (NU) (n = 21) were used to further evaluate the best performing ANN model as independent datasets. IDH1 mutation is associated with decreased CNVs of EGFR (21% vs. 3%), CDKN2A (20% vs. 6%), PTEN (14% vs. 1.7%), and increased percentage of mutations for TP53 (15% vs. 63%), and ATRX (10% vs. 54%), which were all statistically significant (p < 0.001). Age > 40 was unable to identify high-risk IDH1-mutant with early progression. A glioma early progression risk prediction (GlioPredictor) score generated from the best performing ANN model (6/6/6/6/2/1) with 6 inputs, including CNVs of EGFR, PTEN and CDKN2A, mutation status of TP53 and ATRX, patient’s age can predict IDH1 mutation status with over 90% accuracy. The GlioPredictor score identified a subgroup of high-risk IDH1-mutant in TCGA and NU datasets with early disease progression (p = 0.0019, 0.0238, respectively). The GlioPredictor that integrates age at diagnosis, CNVs of EGFR, CDKN2A, PTEN and mutation status of TP53, and ATRX can identify a small cohort of IDH-mutant with high risk of early progression. The current version of GlioPredictor mainly incorporated clinically often tested genetic biomarkers. Considering complexity of clinical and genetic features that correlate with glioma progression, future derivatives of GlioPredictor incorporating more inputs can be a potential supplement for adjuvant radiotherapy patient selection of IDH-mutant glioma patients.

Metabolomic signatures of ideal cardiovascular health in black adults

Plasma metabolomics profiling is an emerging methodology to identify metabolic pathways underlying cardiovascular health (CVH). The objective of this study was to define metabolomic profiles underlying CVH in a cohort of Black adults, a population that is understudied but suffers from disparate levels of CVD risk factors. The Morehouse-Emory Cardiovascular (MECA) Center for Health Equity study cohort consisted of 375 Black adults (age 53 ± 10, 39% male) without known CVD. CVH was determined by the AHA Life’s Simple 7 (LS7) score, calculated from measured blood pressure, body mass index (BMI), fasting blood glucose and total cholesterol, and self-reported physical activity, diet, and smoking. Plasma metabolites were assessed using untargeted high-resolution metabolomics profiling. A metabolome wide association study (MWAS) identified metabolites associated with LS7 score after adjusting for age and sex. Using Mummichog software, metabolic pathways that were significantly enriched in metabolites associated with LS7 score were identified. Metabolites representative of these pathways were compared across clinical domains of LS7 score and then developed into a metabolomics risk score for prediction of CVH. We identified novel metabolomic signatures and pathways associated with CVH in a cohort of Black adults without known CVD. Representative and highly prevalent metabolites from these pathways included glutamine, glutamate, urate, tyrosine and alanine, the concentrations of which varied with BMI, fasting glucose, and blood pressure levels. When assessed in conjunction, these metabolites were independent predictors of CVH. One SD increase in the novel metabolomics risk score was associated with a 0.88 higher LS7 score, which translates to a 10.4% lower incident CVD risk. We identified novel metabolomic signatures of ideal CVH in a cohort of Black Americans, showing that a core group of metabolites central to nitrogen balance, bioenergetics, gluconeogenesis, and nucleotide synthesis were associated with CVH in this population.

Unplanned cesarean sections in advanced maternal age: Apredictive model.

As maternal age during pregnancy is rising all over the world, there is a growing need for prognostic factors that determine maternal and perinatal outcomes in older women. This study is a retrospective cohort study of women aged 40 years or older at the time of delivery in four Santeon hospitals across the Netherlands between January 2016 and December 2019. Outcomes were compared between women of 40-44 years (advanced maternal age) and 45 years and older (very advanced maternal age). Primary outcome was unplanned cesarean section, secondary outcomes included postpartum hemorrhage and neonatal outcomes. Multivariate regression analysis was performed to analyze predictive factors for unplanned cesarean sections in women who attempted vaginal delivery. Subsequently, a predictive model and risk scores were constructed to predict unplanned cesarean section. A cohort of 1660 women was analyzed; mean maternal age was 41.4 years, 4.8% of the women were 45 years and older. In both groups, more than half of the women had not delivered vaginally before. Unplanned cesarean sections were performed in 21.1% of the deliveries in advanced maternal age and in 29.1% in very advanced maternal age. Four predictive factors were significantly correlated with unplanned cesarean sections: higher body mass index (BMI), no previous vaginal delivery, spontaneous start of delivery and number of days needed for cervical priming. A predictive model was constructed from these factors with an area under the curve of 0.75 (95% confidence interval 0.72-0.78). A sensitivity analysis in nulliparous women proved that BMI, days of cervical priming, age, and gestational age were risk factors, whereas spontaneous start of delivery and induction were protective factors. There was one occurrence of neonatal death. Women of advanced maternal age and those of very advanced maternal age have a higher chance of having an unplanned cesarean section compared to the general obstetric population in the Netherlands. Unplanned cesarean sections can be predicted through use of our predictive model. Risk increases with higher BMI, no previous vaginal delivery, and increasing number of days needed for cervical priming, whereas spontaneous start of labor lowers the risk. In nulliparous women, age and gestational age also increase risk, but induction lowers the risk of having an unplanned cesarean section.

Predictive Performance of Machine Learning–Based Models for Poststroke Clinical Outcomes in Comparison With Conventional Prognostic Scores: Multicenter, Hospital-Based Observational Study

Background Although machine learning is a promising tool for making prognoses, the performance of machine learning in predicting outcomes after stroke remains to be examined. Objective This study aims to examine how much data-driven models with machine learning improve predictive performance for poststroke outcomes compared with conventional stroke prognostic scores and to elucidate how explanatory variables in machine learning–based models differ from the items of the stroke prognostic scores. Methods We used data from 10,513 patients who were registered in a multicenter prospective stroke registry in Japan between 2007 and 2017. The outcomes were poor functional outcome (modified Rankin Scale score &gt;2) and death at 3 months after stroke. Machine learning–based models were developed using all variables with regularization methods, random forests, or boosted trees. We selected 3 stroke prognostic scores, namely, ASTRAL (Acute Stroke Registry and Analysis of Lausanne), PLAN (preadmission comorbidities, level of consciousness, age, neurologic deficit), and iScore (Ischemic Stroke Predictive Risk Score) for comparison. Item-based regression models were developed using the items of these 3 scores. The model performance was assessed in terms of discrimination and calibration. To compare the predictive performance of the data-driven model with that of the item-based model, we performed internal validation after random splits of identical populations into 80% of patients as a training set and 20% of patients as a test set; the models were developed in the training set and were validated in the test set. We evaluated the contribution of each variable to the models and compared the predictors used in the machine learning–based models with the items of the stroke prognostic scores. Results The mean age of the study patients was 73.0 (SD 12.5) years, and 59.1% (6209/10,513) of them were men. The area under the receiver operating characteristic curves and the area under the precision-recall curves for predicting poststroke outcomes were higher for machine learning–based models than for item-based models in identical populations after random splits. Machine learning–based models also performed better than item-based models in terms of the Brier score. Machine learning–based models used different explanatory variables, such as laboratory data, from the items of the conventional stroke prognostic scores. Including these data in the machine learning–based models as explanatory variables improved performance in predicting outcomes after stroke, especially poststroke death. Conclusions Machine learning–based models performed better in predicting poststroke outcomes than regression models using the items of conventional stroke prognostic scores, although they required additional variables, such as laboratory data, to attain improved performance. Further studies are warranted to validate the usefulness of machine learning in clinical settings.

Construction of a 12-gene prognostic model for colorectal cancer based on heat shock protein-related genes

Some heat shock proteins (HSPs) have been shown to influence tumor prognosis, but their prognostic significance in colorectal cancer (CRC) remains unclear. This study explored the prognostic significance of HSP-related genes in CRC. Transcriptional data and clinical information of CRC patients were obtained from The Cancer Genome Atlas (TCGA) database, and a literature search was conducted to identify HSP-related genes. Using Least Absolute Selection and Shrinkage Operator (LASSO) regression and univariate/multivariate Cox regression analyses, 12 HSP-related genes demonstrating significant associations with CRC survival were successfully identified and employed to formulate a predictive risk score model. The efficacy and precision of this model were validated utilizing TCGA and Gene Expression Omnibus (GEO) datasets, demonstrating its reliability in CRC prognosis prediction. gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses revealed significant disparities between high- and low-risk groups in chromatin remodeling biological functions and neutrophil extracellular trap formation pathways. Single sample gene set enrichment analysis (ssGSEA) further revealed differences in immune cell types and immune functional status between the two risk groups. Differential analysis showed higher expression of immune checkpoints within the low-risk group, while the high-risk group exhibited notably higher Tumor Immune Dysfunction and Exclusion (TIDE) scores. Additionally, we predicted the sensitivity of different prognosis risk patients to various drugs, providing potential drug choices for tailored treatment. Combined, our study successfully crafted a novel CRC prognostic model that can effectively predict patient survival, immune landscape, and treatment response, providing important support and guidance for CRC patient prognosis.

Comparison of Mayo And HFA-ICOS Cardiotoxicity Risk Score Validity for Predicting Cardiotoxicity in Anthracycline Chemotherapy Patients

Background: Anthracycline can cause cardiotoxicity. In estimating the risk of cardiotoxicity, various risk prediction scores have been developed. Mayo cardiotoxicity risk score has long been used. The newest protocol is the HFA-ICOS cardiotoxicity risk score. There have been no studies that directly compare the validity of these scores. Objective: This study aims to compare the validity of the Mayo and HFA-ICOS cardiotoxicity risk scores for predicting cardiotoxicity in anthracycline chemotherapy patients. Method: This research was a retrospective cohort. It began by searching for patients who underwent baseline evaluation before anthracycline chemotherapy in a tertiary hospital. Seventy patients who met the criteria were included. Baseline data was used for cardiotoxicity risk score assessment. Cardiotoxicity follow-up was carried out with echocardiography. Statistical analysis was carried out using STATA Se 17.0 statistical software. Result: Twenty of 70 patients (28.6%) experienced cardiotoxicity. The average total dose of doxorubicin used was 433.8 mg/m2. The majority of patients were women. The most common cardiovascular risk factor was hypertension. The AUC for the Mayo cardiotoxicity risk score was 0.695 (sensitivity 65%, specificity 74 %). The HFA-ICOS cardiotoxicity risk score was 0.59 (sensitivity 30 %, specificity 88 %). The Mayo cardiotoxicity risk score is better to role-out cardiotoxicity (NPV 84.1%) compared to the HFA-ICOS cardiotoxicity risk score (NPV 75.9%). Conclusion: There is a difference between Mayo and HFA-ICOS validity for predicting cardiotoxicity. Overall, the Mayo cardiotoxicity risk score is better compared to the HFA-ICOS cardiotoxicity risk score.

Predicting progression of Alzheimer’s disease using new survival analysis approach

It is critical to determine the risk of Alzheimer’s disease (AD) in people with mild cognitive impairment (MCI) to begin treatment early. Its development is affected by many things, but how each effect and how the disease worsens is unclear. Nevertheless, an in-depth examination of these factors may provide a reasonable estimate of how long it will take for patients at various stages of the disease to develop Alzheimer’s. Alzheimer’s disease neuroimaging initiative (ADNI) database had 900 people with 63 features from magnetic resonance imaging (MRI), genetic, cognitive, demographic, and cerebrospinal fluid data. These characteristics are used to track AD progression. A hybrid approach for dynamic prediction in clinical survival analysis has been developed to track progression to AD. The method uses a random forest cox regression approach to figure out how long it will take for MCI to turn into AD. In order to evaluate the result concordance index is used. The concordance index measures the rank correlation between predicted risk scores and observed time points. The concordance index was statistically considerably higher in the suggested work than in previous approaches with a score of 95.3%, which is higher than others.

Prediction of Major Adverse Cardiac Events After Transcatheter Aortic Valve Implantation: A Machine Learning Approach with GRACE Score.

Predictive risk scores have a significant impact on patient selection and assessing the likelihood of complications following interventions in patients with severe aortic stenosis (AS). This study aims to explore the utility of machine learning (ML) techniques in predicting 30-day major adverse cardiac events (MACE) by analyzing parameters, including the Global Registry of Acute Coronary Events (GRACE) score. This retrospective, multi-center, observational study enrolled 453 consecutive patients diagnosed with severe AS who underwent transcatheter aortic valve implantation (TAVI) from April 2020 to January 2023. The primary outcome was defined as a composition of MACE comprising periprocedural myocardial infarction (MI), cerebrovascular events (CVE), and all-cause mortality during the 1-month follow-up period after the procedure. Conventional binomial logistic regression and ML models were utilized and compared for prediction purposes. The study population had a mean age of 76.1, with 40.8% being male. The primary endpoint was observed in 7.5% of cases. Among the individual components of the primary endpoint, the rates of all-cause mortality, MI, and CVE were reported as 4.2%, 2.4%, and 1.9%, respectively. The ML-based Extreme Gradient Boosting (XGBoost) model with the GRACE score demonstrated superior discriminative performance in predicting the primary endpoint, compared to both the ML model without the GRACE score and the conventional regression model [Area Under the Curve (AUC)= 0.98 (0.91-0.99), AUC= 0,87 (0.80-0.98), AUC= 0.84 (0.79-0.96)]. ML techniques hold the potential to enhance outcomes in clinical practice, especially when utilized alongside established clinical tools such as the GRACE score.

Cardiac Surgery Associated Acute Kidney Injury - Incidence, Risk Factors, Outcomes, and Risk Score Validation from a Single Centre in Bahrain

Background: Cardiac surgery-associated acute kidney injury (CSA-AKI) is a common complication in patients undergoing cardiac surgery. Early prediction of acute kidney injury (AKI) is crucial to estimate and communicate the prognosis and outcome of surgery. This research is particularly significant as it addresses the need for validation of risk scores in non-Caucasian populations with a higher incidence of risk factors, potentially leading to improved patient care and outcomes. Objective: This prospective study aimed to investigate the association between socio-demographic and clinical variables in patients undergoing cardiac surgery in a single center in Bahrain and their correlation with a predictive risk score. Methods: This comprehensive study included 100 patients who underwent cardiac surgery. The distribution of study subjects was meticulously assessed based on the kidney disease: Improving Global Outcomes (KDIGO) classification for AKI. The association of AKI with socio-demographic and clinical variables was rigorously analyzed using chi-square tests and logistic regression analysis and compared to the predicted incidence from the Acute Kidney Injury after Cardiac Surgery (AKICS) score, ensuring the reliability and accuracy of our findings. Results: Among the study subjects, 65% were not affected by acute kidney injury (AKI). In contrast, 19% were classified as having Stage 1 AKI, 8% as Stage 2, and 8% as Stage 3. Additionally, 2% of the patients required dialysis. The findings of our study underscore the significant impact of AKI on hospital stay and the need for dialysis. Female gender, previous myocardial infarction, UF heparin use, and elevated preoperative creatinine levels were significantly associated with AKI. The AKICS score was found to predict AKI in our patients, with a sensitivity of 91% and a specificity of 46.9%. Conclusion: Female gender, previous myocardial infarction, UF heparin use, and elevated preoperative creatinine levels were found to be independent predictors of AKI. We found that patients with AKI had a significantly longer hospital stay duration. The AKICS score has been validated in our local cohort of Middle Eastern patients with high sensitivity. Keywords: Acute kidney injury; Cardiac surgery; Risk factors; Socio-demographic factors; Clinical variables

Improved interpretable machine learning emergency department triage tool addressing class imbalance.

The Score for Emergency Risk Prediction (SERP) is a novel mortality risk prediction score which leverages machine learning in supporting triage decisions. In its derivation study, SERP-2d, SERP-7d and SERP-30d demonstrated good predictive performance for 2-day, 7-day and 30-day mortality. However, the dataset used had significant class imbalance. This study aimed to determine if addressing class imbalance can improve SERP's performance, ultimately improving triage accuracy. The Singapore General Hospital (SGH) emergency department (ED) dataset was used, which contains 1,833,908 ED records between 2008 and 2020. Records between 2008 and 2017 were randomly split into a training set (80%) and validation set (20%). The 2019 and 2020 records were used as test sets. To address class imbalance, we used random oversampling and random undersampling in the AutoScore-Imbalance framework to develop SERP+-2d, SERP+-7d, and SERP+-30d scores. The performance of SERP+, SERP, and the commonly used triage risk scores was compared. The developed SERP+ scores had five to six variables. The AUC of SERP+ scores (0.874 to 0.905) was higher than that of the corresponding SERP scores (0.859 to 0.894) on both test sets. This superior performance was statistically significant for SERP+-7d (2019: Z = -5.843, p < 0.001, 2020: Z = -4.548, p < 0.001) and SERP+-30d (2019: Z = -3.063, p = 0.002, 2020: Z = -3.256, p = 0.001). SERP+ outperformed SERP marginally on sensitivity, specificity, balanced accuracy, and positive predictive value measures. Negative predictive value was the same for SERP+ and SERP. Additionally, SERP+ showed better performance compared to the commonly used triage risk scores. Accounting for class imbalance during training improved score performance for SERP+. Better stratification of even a small number of patients can be meaningful in the context of the ED triage. Our findings reiterate the potential of machine learning-based scores like SERP+ in supporting accurate, data-driven triage decisions at the ED.

Cost-effectiveness of applying high-sensitivity troponin I to a score for cardiovascular risk prediction in asymptomatic population.

Risk stratification scores such as the European Systematic COronary Risk Evaluation (SCORE) are used to guide individuals on cardiovascular disease (CVD) prevention. Adding high-sensitivity troponin I (hsTnI) to such risk scores has the potential to improve accuracy of CVD prediction. We investigated how applying hsTnI in addition to SCORE may impact management, outcome, and cost-effectiveness. Characteristics of 72,190 apparently healthy individuals from the Biomarker for Cardiovascular Risk Assessment in Europe (BiomarCaRE) project were included into a discrete-event simulation comparing two strategies for assessing CVD risk. The standard strategy reflecting current practice employed SCORE (SCORE); the alternative strategy involved adding hsTnI information for further stratifying SCORE risk categories (S-SCORE). Individuals were followed over ten years from baseline examination to CVD event, death or end of follow-up. The model tracked the occurrence of events and calculated direct costs of screening, prevention, and treatment from a European health system perspective. Cost-effectiveness was expressed as incremental cost-effectiveness ratio (ICER) in € per quality-adjusted life year (QALYs) gained during 10 years of follow-up. Outputs were validated against observed rates, and results were tested in deterministic and probabilistic sensitivity analyses. S-SCORE yielded a change in management for 10.0% of individuals, and a reduction in CVD events (4.85% vs. 5.38%, p<0.001) and mortality (6.80% vs. 7.04%, p<0.001). S-SCORE led to 23 (95%CI: 20-26) additional event-free years and 7 (95%CI: 5-9) additional QALYs per 1,000 subjects screened, and resulted in a relative risk reduction for CVD of 9.9% (95%CI: 7.3-13.5%) with a number needed to screen to prevent one event of 183 (95%CI: 172 to 203). S-SCORE increased costs per subject by 187€ (95%CI: 177 € to 196 €), leading to an ICER of 27,440€/QALY gained. Sensitivity analysis was performed with eligibility for treatment being the most sensitive. Adding a person's hsTnI value to SCORE can impact clinical decision making and eventually improves QALYs and is cost-effective compared to CVD prevention strategies using SCORE alone. Stratifying SCORE risk classes for hsTnI would likely offer cost-effective alternatives, particularly when targeting higher risk groups.

Exploring the role of underrepresented populations in polygenic risk scores for neurodegenerative disease risk prediction.

Exploring the role of underrepresented populations in polygenic risk scores for neurodegenerative disease risk prediction.

Genome-wide polygenic risk score for rheumatoid arthritis prediction in postmenopausal women.

Rheumatoid arthritis (RA), a common autoimmune disease, exhibits a vital genetic component. Polygenic risk scores (PRS) derived from genome-wide association studies (GWAS) offer potential utility in predicting disease susceptibility. The present study aimed to develop and validate a PRS for predicting RA risk in postmenopausal women. The study developed a novel PRS using 225,000 genetic variants from a GWAS dataset. The PRS was developed in a cohort of 8967 postmenopausal women and validated in an independent cohort of 6269 postmenopausal women. Among the development cohort, approximately 70% were Hispanic and approximately 30% were African American. The testing cohort comprised approximately 50% Hispanic and 50% Caucasian individuals. Stratification according to PRS quintiles revealed a pronounced gradient in RA prevalence and odds ratios. High PRS was significantly associated with increased RA risk in individuals aged 60-70 years, ≥ 70 years, and overweight and obese participants. Furthermore, at age 65 years, individuals in the bottom 5% of the PRS distribution have an absolute risk of RA at 30.6% (95% confidence interval = 18.5%-42.6%). The risk increased to 53.8% (95% confidence interval = 42.8%-64.9%) for those in the top 5% of the PRS distribution. The PRS developed in the present study is significantly associated with RA risk, showing the potential for early screening of RA in postmenopausal women. This work demonstrates the feasibility of personalized medicine in identifying high-risk individuals for RA, indicating the need for further studies to test the utility of PRS in other populations.

A comparison of clinical risk scores for survival prediction after curative-intent resection of colorectal liver metastases

A comparison of clinical risk scores for survival prediction after curative-intent resection of colorectal liver metastases