Risk Prediction Model For Patients Research Articles

Accuracy of death risk prediction models for acute coronary syndrome patients: a systematic review and meta-analysis.

This study systematically evaluates the accuracy of several death risk prediction models for patients with acute coronary syndrome (ACS) through evidence-based methods. We identify the most accurate and effective ACS death risk prediction model and provide an evidence-based basis for clinical healthcare personnel to evaluate their choice of death risk prediction model for ACS patients. An evidence-based approach was used to study the current death risk prediction model for ACS. First, a literature search was carried out using computer-based and manual searching. The literature databases searched include Cochrane Library, MEDLINE, EMBASE, PubMed, Web of Science, WanFang Data, CNKI, VPCS, and SinoMed. The search period was limited to 2009 to 2022. Screening, quality evaluation and data extraction were carried out for the included articles. The PROBAST was used to conduct a migration risk assessment. RevMan 5.3 and Meta-DiSc 1.4 were used in combination to determine the model effect sizes. A descriptive analysis was conducted for the data that could not be meta-analyzed. A total of 8277 articles were initially included in this study. After screening, 25 articles were finally included, involving 11 different risk prediction models. A total of 306,390 patients with ACS were included of which 158,080 (51.6%) were male and 147,793 (48.4%) were female. The patients stemmed from 11 different countries (e.g., China, the USA, Spain, the UK, etc.). The total number of deaths was 23,601. The sensitivity of the GRACE risk prediction model was 0.78, with a specificity of 0.76 and an AUC value of 0.86. The sensitivity of the CAMI risk prediction model was 0.78, with a specificity of 0.70 and an AUC value of 0.85. The sensitivity of the TIMI risk prediction model was 0.51, with a specificity of 0.81, and an AUC value of 0.64. The sensitivity of the REMS risk prediction model was 0.78, with a specificity of 0.46 and an AUC value of 0.41. Eight different risk prediction models (EPICOR, CRUSADE, SAMI, GWTG, LNS, SYNTAX II, APACHE II) that could not be combined with the effect size were also included, with sensitivities ranging from 0.77-0.95, specificities ranging from 0.22-0.99, and AUC values ranging from 0.71-0.92. The GRACE and CAMI risk prediction models demonstrate good accuracy for evaluating the death risk of ACS patients. The accuracy of the TIMI risk prediction model is similar to that of the REMS risk prediction model. The APACHE II, SYNTAX II, EPICOR, and CAMI risk prediction models also show good accuracy for estimating the risk of death in ACS patients, although further validation is needed due to limited evidence. For improved predictive accuracy and to help advance medical interventions, the author recommends that clinical medical staff use the GRACE model to predict the death risk of ACS patients.

Construction of a mortality risk prediction model for patients with acute diquat poisoning based on clinically accessible data

BackgroundTo examine the risk factors associated with mortality in individuals suffering from acute diquat poisoning and to develop an effective prediction model using clinical data.MethodsA retrospective review was conducted on the clinical records of 107 individuals who were hospitalized for acute diquat poisoning at a tertiary hospital in Sichuan Province between January 2017 and September 30, 2023, and further categorized into survivor and nonsurvivor groups based on their mortality status within 30 days of poisoning. The patient’s demographic information, symptoms within 24 h of admission, and details of the initial clinical ancillary examination, as well as the APACHE II score, were documented. The model was developed using backward stepwise logistic regression, and its performance was assessed using receiver operating characteristic curves, calibration curves, Brier scores, decision curve analysis curves, and bootstrap replicates for internal validation.ResultsMultifactorial logistic regression analysis revealed that blood pressure (hypertension, OR 19.73, 95% CI 5.71–68.16; hypotension, OR 61.38, 95% CI 7.40–509.51), white blood count (OR 1.35, 95% CI 1.20–1.52), red cell distribution width-standard deviation (OR 1.22, 95% CI 1.08–1.38), and glomerular filtration rate (OR 0.96, 95% CI 0.94–0.97) were identified as independent risk factors for mortality in patients with diquat. Subsequently, a nomogram with an area under the curve of 0.97 (95% CI: 0.93–1) was developed. Internal bootstrap resampling (1000 repetitions) confirmed the model’s adequate discriminatory power, with an area under the curve of 0.97. Decision curve analysis demonstrated greater net gains for the nomogram, while the clinical impact curves indicated greater predictive validity.ConclusionThe nomogram model developed in this study using available clinical data enhances the prediction of risk for DQ patients and has the potential to provide valuable clinical insights to guide patient treatment decisions.

ASSESSMENT OF CARDIOVASCULAR RISK IN PATIENTS WITH RHEUMATOID ARTHRITIS ACCORDING TO CURRENT HYPERTENSION GUIDELINES

Objective: Patients with rheumatoid arthritis (RA) are at increased risk of cardiovascular disease (CVD) by as much as 50% compared to the general population. Considering that disease-specific calculators have failed to provide more accurate CVD risk stratification in RA, CVD risk calculation in RA patients is challenging, especially for those who are not by definition at high risk based on concomitant established CVD or its equivalents. The presence of an immune-mediated inflammatory disease (e.g., RA) has been considered as a CVD risk modifier by the previous 2018 European Society of Hypertension/European Society of Cardiology (ESH/ESC) guidelines. Nevertheless, current 2023 ESH/ESC guidelines recommend assessment in RA using general CVD risk calculators. Design and method: We aimed to calculate CVD risk in RA patients using the most frequently applied CVD risk calculators in the general population. We only stratified patients free from established CVD (heart disease, stroke) or its equivalents (diabetes mellitus, chronic kidney disease) aged 40-74 years. The following algorithms were applied: (i) SCORE2 (Systemic Coronary Risk Estimation-2), (ii) Framingham Risk Score-Adult Treatment Panel (FRS-ATP) CVD risk calculator, and (iii) the American College of Cardiology/American Heart Association (ACC/AHA) Pooled Cohort Equation. We further correlated the estimated CVD risk by each algorithm with surrogate CVD markers, i.e. arterial stiffness and carotid atherosclerosis. For this purpose, carotid-femoral pulse wave velocity (cfPWV) was measured using applanation tonometry (Sphygmocor ®), and carotid intima-media thickness (cIMT) was estimated using carotid ultrasound. Results: A total of 91 patients aged 60.3±8.1 years were included (78% females). Using the FRS-ATP algorithm, more patients were classified as high risk and fewer as low risk compared to the other calculators (Table 1). Moreover, CVD risk calculated with FRS-ATP correlated stronger with both cfPWV and cIMT, compared to CVD risk calculated with the other algorithms (Table 2). Conclusions: In RA patients without established CVD, diabetes, or chronic kidney disease, the FRS-ATP algorithm may be applied as a useful tool for CVD risk stratification. Prospective, large-scale studies are warranted to determine the most reliable CVD risk prediction model for patients with RA.

Establishment and assessment of mortality risk prediction model in patients with sepsis based on early-stage peripheral lymphocyte subsets.

This study is aimed to explore the value of lymphocyte subsets in evaluating the severity and prognosis of sepsis. The counts of lymphocytes, CD3+ T cells, CD4+ T cells, CD8+ T cells, CD19+ B cells, and NK cells significantly decreased between day 1 and day 3 in both the survivor and the non-survivor groups. The peripheral lymphocyte subsets (PLS) at day 1 were not significantly different between the survivor and the non-survivor groups. However, at day 3, the counts of lymphocytes, CD3+ T cells, CD4+ T cells, and NK cells were remarkably lower in the non-survivor group. No significant differences in CD8+ T cells, or CD19+ B cells were observed. The PLS index was independently and significantly associated with the 28-day mortality risk in septic patients (OR: 3.08, 95% CI: 1.18-9.67). Based on these clinical parameters and the PLS index, we developed a nomograph for evaluating the individual mortality risk in sepsis. The area under the curve of prediction with the PLS index was significantly higher than that from the model with only clinical parameters (0.912 vs. 0.817). Our study suggests that the decline of PLS occurred in the early stage of sepsis. The new novel PLS index can be an independent predictor of 28-day mortality in septic patients. The prediction model based on clinical parameters and the PLS index has relatively high predicting ability.

Risk prediction model based on machine learning for predicting miscarriage among pregnant patients with immune abnormalities.

Introduction: It is known that patients with immune-abnormal co-pregnancies are at a higher risk of adverse pregnancy outcomes. Traditional pregnancy risk management systems have poor prediction abilities for adverse pregnancy outcomes in such patients, with many limitations in clinical application. In this study, we will use machine learning to screen high-risk factors for miscarriage and develop a miscarriage risk prediction model for patients with immune-abnormal pregnancies. This model aims to provide an adjunctive tool for the clinical identification of patients at high risk of miscarriage and to allow for active intervention to reduce adverse pregnancy outcomes. Methods: Patients with immune-abnormal pregnancies attending Sichuan Provincial People's Hospital were collected through electronic medical records (EMR). The data were divided into a training set and a test set in an 8:2 ratio. Comparisons were made to evaluate the performance of traditional pregnancy risk assessment tools for clinical applications. This analysis involved assessing the cost-benefit of clinical treatment, evaluating the model's performance, and determining its economic value. Data sampling methods, feature screening, and machine learning algorithms were utilized to develop predictive models. These models were internally validated using 10-fold cross-validation for the training set and externally validated using bootstrapping for the test set. Model performance was assessed by the area under the characteristic curve (AUC). Based on the best parameters, a predictive model for miscarriage risk was developed, and the SHapley additive expansion (SHAP) method was used to assess the best model feature contribution. Results: A total of 565 patients were included in this study on machine learning-based models for predicting the risk of miscarriage in patients with immune-abnormal pregnancies. Twenty-eight risk warning models were developed, and the predictive model constructed using XGBoost demonstrated the best performance with an AUC of 0.9209. The SHAP analysis of the best model highlighted the total number of medications, as well as the use of aspirin and low molecular weight heparin, as significant influencing factors. The implementation of the pregnancy risk scoring rules resulted in accuracy, precision, and F1 scores of 0.3009, 0.1663, and 0.2852, respectively. The economic evaluation showed a saving of ¥7,485,865.7 due to the model. Conclusion: The predictive model developed in this study performed well in estimating the risk of miscarriage in patients with immune-abnormal pregnancies. The findings of the model interpretation identified the total number of medications and the use of other medications during pregnancy as key factors in the early warning model for miscarriage risk. This provides an important basis for early risk assessment and intervention in immune-abnormal pregnancies. The predictive model developed in this study demonstrated better risk prediction performance than the Pregnancy Risk Management System (PRMS) and also demonstrated economic value. Therefore, miscarriage risk prediction in patients with immune-abnormal pregnancies may be the most cost-effective management method.

Pretreatment mortality risk prediction model in patients with polymyositis/dermatomyositis-associated interstitial lung disease

ObjectivesRisk prediction for patients with polymyositis/dermatomyositis-associated interstitial lung disease (PM/DM-ILD) is challenging due to heterogeneity in the disease course. We aimed to develop a mortality risk prediction model for PM/DM-ILD.MethodsThis...

Construction and evaluation of short-term and long-term mortality risk prediction model for patients with sepsis based on MIMIC-IV database.

Given the high incidence and mortality rate of sepsis, early identification of high-risk patients and timely intervention are crucial. However, existing mortality risk prediction models still have shortcomings in terms of operation, applicability, and evaluation on long-term prognosis. This study aims to investigate the risk factors for death in patients with sepsis, and to construct the prediction model of short-term and long-term mortality risk. Patients meeting sepsis 3.0 diagnostic criteria were selected from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database and randomly divided into a modeling group and a validation group at a ratio of 7꞉3. Baseline data of patients were analyzed. Univariate Cox regression analysis and full subset regression were used to determine the risk factors of death in patients with sepsis and to screen out the variables to construct the prediction model. The time-dependent area under the curve (AUC), calibration curve, and decision curve were used to evaluate the differentiation, calibration, and clinical practicability of the model. A total of 14 240 patients with sepsis were included in our study. The 28-day and 1-year mortality were 21.45% (3 054 cases) and 36.50% (5 198 cases), respectively. Advanced age, female, high sepsis-related organ failure assessment (SOFA) score, high simplified acute physiology score II (SAPS II), rapid heart rate, rapid respiratory rate, septic shock, congestive heart failure, chronic obstructive pulmonary disease, liver disease, kidney disease, diabetes, malignant tumor, high white blood cell count (WBC), long prothrombin time (PT), and high serum creatinine (SCr) levels were all risk factors for sepsis death (all P<0.05). Eight variables, including PT, respiratory rate, body temperature, malignant tumor, liver disease, septic shock, SAPS II, and age were used to construct the model. The AUCs for 28-day and 1-year survival were 0.717 (95% CI 0.710 to 0.724) and 0.716 (95% CI 0.707 to 0.725), respectively. The calibration curve and decision curve showed that the model had good calibration degree and clinical application value. The short-term and long-term mortality risk prediction models of patients with sepsis based on the MIMIC-IV database have good recognition ability and certain clinical reference significance for prognostic risk assessment and intervention treatment of patients.

Development and validation of a prediction model for self-reported hypoglycemia risk in patients with type 2 diabetes: A longitudinal cohort study.

To develop and validate a simple prediction model for hypoglycemia risk in patients with type 2 diabetes. We prospectively analyzed the data of 1,303 subjects in a third-class hospital in Tianjin and followed up their hypoglycemia events at 3 and 6 months. The hypoglycemia risk prediction models for 3 and 6 months were developed and the model performance was evaluated. A total of 340 (28.4%) patients experienced hypoglycemia within 3 months and 462 (37.2%) within 6 months during the follow-up period. Age, central obesity, intensive insulin therapy, frequency of hypoglycemia in the past year, and hypoglycemia prevention education entered both model3month and model6month. The area under the receiver operating characteristic curve of model3month and model6month were 0.711 and 0.723, respectively. The Youden index was 0.315 and 0.361, while the sensitivities were 0.615 and 0.714, and the specificities were 0.717 and 0.631. The calibration curves showed that the models were similar to reality. The decision curves implied that the clinical net benefit of the model was clear. The study developed 3 and 6 month hypoglycemia risk prediction models for patients with type 2 diabetes. The discrimination and calibration of the two prediction models were good, and might help to improve clinical decision-making and guide patients to more reasonable self-care and hypoglycemia prevention at home.

Hypertension risk prediction models for patients with diabetes based on machine learning approaches

Hypertension risk prediction models for patients with diabetes based on machine learning approaches

Derivation and Internal Validation of a Disease-Specific Cardiovascular Risk Prediction Model for Patients With Psoriatic Arthritis and Psoriasis.

To address suboptimal cardiovascular risk prediction in patients with psoriatic disease (PsD), we developed and internally validated a five-year disease-specific cardiovascular risk prediction model. We analyzed data from a prospective cohort of participants with PsD without a history of cardiovascular events. Traditional cardiovascular risk factors and PsD-related measures of disease activity were considered as potential predictors. The study outcome included nonfatal and fatal cardiovascular events. A base prediction model included 10 traditional cardiovascular risk factors. Eight PsD-related factors were assessed by adding them to the base model to create expanded models, which were controlled for PsD therapies. Variable selection was performed using Least Absolute Shrinkage and Selection Operator (LASSO) penalized regression with 10-fold cross-validation. Model performance was assessed using measures of discrimination and calibration and measures of sensitivity and specificity. Between 1992 and 2020, 85 of 1,336 participants developed cardiovascular events. Discrimination of the base model (with traditional cardiovascular risk factors alone) was excellent, with an area under the receiver operator characteristic curve (AUC) of 85.5 (95% confidence interval [CI] 81.9-89.1). Optimal models did not select any of the tested disease-specific factors. In a sensitivity analysis, which excluded lipid lowering and antihypertensive treatments, the number of damaged joints was selected in the expanded model. However, this model did not improve risk discrimination compared to the base model (AUC 85.5, 95% CI 82.0-89.1). Traditional cardiovascular risk factors alone are effective in predicting cardiovascular risk in patients with PsD. A risk score based on these factors performed well, indicating excellent discrimination and calibration.

Cardiovascular risk assessment in patients with antiphospholipid syndrome: a cross-sectional performance analysis of nine clinical risk prediction tools

ObjectivesThis study aimed to assess the performance of cardiovascular risk (CVR) prediction models reported by European Alliance of Associations for Rheumatology and European Society of Cardiology recommendations to identify high-atherosclerotic...

Prediction of respiratory failure risk in patients with pneumonia in the ICU using ensemble learning models.

The aim of this study was to develop early prediction models for respiratory failure risk in patients with severe pneumonia using four ensemble learning algorithms: LightGBM, XGBoost, CatBoost, and random forest, and to compare the predictive performance of each model. In this study, we used the eICU Collaborative Research Database (eICU-CRD) for sample extraction, built a respiratory failure risk prediction model for patients with severe pneumonia based on four ensemble learning algorithms, and developed compact models corresponding to the four complete models to improve clinical practicality. The average area under receiver operating curve (AUROC) of the models on the test sets after ten random divisions of the dataset and the average accuracy at the best threshold were used as the evaluation metrics of the model performance. Finally, feature importance and Shapley additive explanation values were introduced to improve the interpretability of the model. A total of 1676 patients with pneumonia were analyzed in this study, of whom 297 developed respiratory failure one hour after admission to the intensive care unit (ICU). Both complete and compact CatBoost models had the highest average AUROC (0.858 and 0.857, respectively). The average accuracies at the best threshold were 75.19% and 77.33%, respectively. According to the feature importance bars and summary plot of the predictor variables, activetx (indicates whether the patient received active treatment), standard deviation of prothrombin time-international normalized ratio, Glasgow Coma Scale verbal score, age, and minimum oxygen saturation and respiratory rate were important. Compared with other ensemble learning models, the complete and compact CatBoost models have significantly higher average area under the curve values on the 10 randomly divided test sets. Additionally, the standard deviation (SD) of the compact CatBoost model is relatively small (SD:0.050), indicating that the performance of the compact CatBoost model is stable among these four ensemble learning models. The machine learning predictive models built in this study will help in early prediction and intervention of respiratory failure risk in patients with pneumonia in the ICU.

Cuproptosis-related LINC02454 as a biomarker for laryngeal squamous cell carcinoma based on a novel risk model and in vitro and in vivo analyses.

Laryngeal squamous cell carcinomas (LSCCs) are aggressive tumors with the second-highest morbidity rate in patients with head and neck squamous cell carcinoma. Cuproptosis is a type of programmed cell death that impacts tumor malignancy and progression. Thepurposeofthisstudy was to investigate the relationship between cuproptosis-related long non-coding RNAs (crlncRNAs) and the tumor immune microenvironment and chemotherapeutic drug sensitivity in LSCC, and crlncRNA impact on LSCC malignancy. Clinical and RNA-sequencing data from patients with LSCC were retrieved from the Cancer Genome Atlas. Differentially expressed prognosis-related crlncRNAs were identified based on univariate Cox regression analysis, a crlncRNA signature for LSCC was developed and validated using LASSO Cox regression. Finally, the effect of LINC02454, the core signature crlncRNA, on LSCC malignancy progression was evaluated in vitro and in vivo. We identified a four-crlncRNA signature (LINC02454, AC026310.1, AC090517.2, and AC000123.1), according to which we divided the patients into high- and low-risk groups. The crlncRNA signature risk score was an independent prognostic indicator for overall and progression-free survival, and displayed high predictive accuracy. Patients with a higher abundance of infiltrating dendritic cells, M0 macrophages, and neutrophils had worse prognoses and those in the high-risk group were highly sensitive to multiple chemotherapeutic drugs. Knockdown of LINC02454 caused tumor suppression, via cuproptosis induction. A novel signature of four crlncRNAs was found to be highly accurate as a risk prediction model for patients with LSCC and to have potential for improving the diagnosis, prognosis, and treatment of LSCC.

Development and validation of an in-hospital mortality risk prediction model for patients with severe community-acquired pneumonia in the intensive care unit

BackgroundA high mortality rate has always been observed in patients with severe community-acquired pneumonia (SCAP) admitted to the intensive care unit (ICU); however, there are few reported predictive models regarding the prognosis of this group of patients. This study aimed to screen for risk factors and assign a useful nomogram to predict mortality in these patients.MethodsAs a developmental cohort, we used 455 patients with SCAP admitted to ICU. Logistic regression analyses were used to identify independent risk factors for death. A mortality prediction model was built based on statistically significant risk factors. Furthermore, the model was visualized using a nomogram. As a validation cohort, we used 88 patients with SCAP admitted to ICU of another hospital. The performance of the nomogram was evaluated by analysis of the area under the receiver operating characteristic (ROC) curve (AUC), calibration curve analysis, and decision curve analysis (DCA).ResultsLymphocytes, PaO2/FiO2, shock, and APACHE II score were independent risk factors for in-hospital mortality in the development cohort. External validation results showed a C-index of 0.903 (95% CI 0.838–0.968). The AUC of model for the development cohort was 0.85, which was better than APACHE II score 0.795 and SOFA score 0.69. The AUC for the validation cohort was 0.893, which was better than APACHE II score 0.746 and SOFA score 0.742. Calibration curves for both cohorts showed agreement between predicted and actual probabilities. The results of the DCA curves for both cohorts indicated that the model had a high clinical application in comparison to APACHE II and SOFA scoring systems.ConclusionsWe developed a predictive model based on lymphocytes, PaO2/FiO2, shock, and APACHE II scores to predict in-hospital mortality in patients with SCAP admitted to the ICU. The model has the potential to help physicians assess the prognosis of this group of patients.

External validation of venous thromboembolism risk prediction models in patients with multiple myeloma in a community setting: A retrospective cohort study.

e20027 Background: Newly diagnosed Multiple Myeloma (MM) patients have a 10 to 20 times higher risk of developing venous thromboembolism (VTE) than the general population. Three risk prediction models have been recently established to ascertain the degree of VTE risk: SAVED (Surgery, Asian race, VTE history, Elderly and Dexamethasone), IMPEDE VTE (Immunomodulatory drugs (IMiD), BMI, Pelvic fracture, Erythropoietin stimulating agent, Dexamethasone/Doxorubicin, Asian Ethnicity, VTE history, Tunneled line, Existing thromboprophylaxis) and PRISM scores (Prior VTE, Race, IMiD, Surgery, Metaphase Cytogenetics). Our primary objective was to assess the external validity of three VTE risk prediction models in a community hospital setting. Methods: All consecutive newly diagnosed MM treated at Saint Vincent Hospital from 1/1/2012 to 12/22/2022 were included in our analysis. Patients receiving therapeutic anticoagulation for other indications or a diagnosis of VTE within 6 months prior to MM diagnosis were excluded. Variables were collected by retrospective chart review at the time of MM treatment initiation. Model discrimination was assessed by calculating the area under the receiver operating characteristic curve (AUROC). Logistic regression was used to calculate the odds ratio (OR) of VTE occurrence with candidate variables in the risk prediction model. Results: The 160 patients with newly diagnosed MM and available data on VTE occurrence were included. The median age of our cohort at treatment initiation was 74 years (range 31-96); 55% were male, and 75% were Caucasians. IMiD-based induction regimen was used in 68.1 % of patients. The median SAVED score was 1 (IQR:0-2), IMPEDE VTE was 4 (IQR: 2-6), and PRISM score was 2 (IQR: 0-2). The most common thromboprophylactic agent used was aspirin (53.8%). The median time to VTE from induction was 4.8 months. The cumulative incidence of VTE at 12 months was 13.1%. Each 1-point increase in the score was associated with a significantly higher chance of VTE occurrence across all three models (Table). Factors significantly associated with the development of VTE were prior VTE history (OR:2.28, 95% CI:1.31-3.97,p = 0.003) and age greater than 80 years (OR:4.03, 95% CI:1.47-11.02,p = 0.006). Conclusions: Our findings suggest that all three PRISM (AUROC = 0.70), SAVED (AUROC = 0.72), and IMPEDE VTE (AUROC = 0.73) scores could statistically predict VTE outcomes in our patient population. The inclusion of more parameters in the IMPEDE VTE score may have led to its outperformance in risk stratification. [Table: see text]

Development of cardiac risk prediction model in patients with HER-2 positive breast cancer on trastuzumab therapy

Background25% of all breast cancer patients have HER-2 overexpression. Breast Cancer patients with HER-2 overexpression are typically treated with HER-2 inhibitors such as Trastuzumab. Trastuzumab is known to cause a decrease in left ventricular ejection fraction. The aim of this study is to create a cardiac risk prediction tool among women with Her-2 positive breast cancer to predict cardiotoxicity.MethodUsing a split sample design, we created a risk prediction tool using patient level data from electronic medical records. The study included women 18 years of age and older diagnosed with HER-2 positive breast cancer who received Trastuzumab. Outcome measure was defined as a drop in LVEF by more than 10% to less than 53% at any time in the 1-year study period. Logistic regression was used to test predictors.ResultsThe cumulative incidence of cardiac dysfunction in our study was 9.4%. The sensitivity and specificity of the model are 46% and 84%, respectively. Given a cumulative incidence of cardiotoxicity of 9%, the negative predictive value of the test was 94%. This suggests that in a low-risk population, the interval of screening for cardiotoxicity may be performed less frequently.ConclusionCardiac risk prediction tool can be used to identify Her-2 positive breast cancer patients at risk of developing cardiac dysfunction. Also, test characteristics in addition to disease prevalence may inform a rational strategy in performing cardiac ultrasound in Her-2 breast cancer patients. We have developed a cardiac risk prediction model with high NPV in a low-risk population which has an appealing cost-effectiveness profile.

Derivation and validation of a machine learning-based risk prediction model in patients with acute heart failure

BackgroundRisk stratification is important in patients with acute heart failure (AHF), and a simple risk score that accurately predicts mortality is needed. The aim of this study is to develop a user-friendly risk-prediction model using a machine-learning method. MethodsA machine-learning-based risk model using least absolute shrinkage and selection operator (LASSO) regression was developed by identifying predictors of in-hospital mortality in the derivation cohort (REALITY-AHF), and its performance was externally validated in the validation cohort (NARA-HF) and compared with two pre-existing risk models: the Get With The Guidelines risk score incorporating brain natriuretic peptide and hypochloremia (GWTG-BNP-Cl-RS) and the acute decompensated heart failure national registry risk (ADHERE). ResultsIn-hospital deaths in the derivation and validation cohorts were 76 (5.1 %) and 61 (4.9 %), respectively. The risk score comprised four variables (systolic blood pressure, blood urea nitrogen, serum chloride, and C-reactive protein) and was developed according to the results of the LASSO regression weighting the coefficient for selected variables using a logistic regression model (4 V-RS). Even though 4 V-RS comprised fewer variables, in the validation cohort, it showed a higher area under the receiver operating characteristic curve (AUC) than the ADHERE risk model (AUC, 0.783 vs. 0.740; p = 0.059) and a significant improvement in net reclassification (0.359; 95 % CI, 0.10–0.67; p = 0.006). 4 V-RS performed similarly to GWTG-BNP-Cl-RS in terms of discrimination (AUC, 0.783 vs. 0.759; p = 0.426) and net reclassification (0.176; 95 % CI, −0.08–0.43; p = 0.178). ConclusionsThe 4 V-RS model comprising only four readily available data points at the time of admission performed similarly to the more complex pre-existing risk model in patients with AHF.

ESKD Risk Prediction Model in a Multicenter Chronic Kidney Disease Cohort in China: A Derivation, Validation, and Comparison Study

In light of the growing burden of chronic kidney disease (CKD), it is of particular importance to create disease prediction models that can assist healthcare providers in identifying cases of CKD individual risk and integrate risk-based care for disease progress management. The objective of this study was to develop and validate a new pragmatic end-stage kidney disease (ESKD) risk prediction utilizing the Cox proportional hazards model (Cox) and machine learning (ML). The Chinese Cohort Study of Chronic Kidney Disease (C-STRIDE), a multicenter CKD cohort in China, was employed as the model's training and testing datasets, with a split ratio of 7:3. A cohort from Peking University First Hospital (PKUFH cohort) served as the external validation dataset. The participants' laboratory tests in those cohorts were conducted at PKUFH. We included individuals with CKD stages 1~4 at baseline. The incidence of kidney replacement therapy (KRT) was defined as the outcome. We constructed the Peking University-CKD (PKU-CKD) risk prediction model employing the Cox and ML methods, which include extreme gradient boosting (XGBoost) and survival support vector machine (SSVM). These models discriminate metrics by applying Harrell's concordance index (Harrell's C-index) and Uno's concordance (Uno's C). The calibration performance was measured by the Brier score and plots. Of the 3216 C-STRIDE and 342 PKUFH participants, 411 (12.8%) and 25 (7.3%) experienced KRT with mean follow-up periods of 4.45 and 3.37 years, respectively. The features included in the PKU-CKD model were age, gender, estimated glomerular filtration rate (eGFR), urinary albumin-creatinine ratio (UACR), albumin, hemoglobin, medical history of type 2 diabetes mellitus (T2DM), and hypertension. In the test dataset, the values of the Cox model for Harrell's C-index, Uno's C-index, and Brier score were 0.834, 0.833, and 0.065, respectively. The XGBoost algorithm values for these metrics were 0.826, 0.825, and 0.066, respectively. The SSVM model yielded values of 0.748, 0.747, and 0.070, respectively, for the above parameters. The comparative analysis revealed no significant difference between XGBoost and Cox, in terms of Harrell's C, Uno's C, and the Brier score (p = 0.186, 0.213, and 0.41, respectively) in the test dataset. The SSVM model was significantly inferior to the previous two models (p < 0.001), in terms of discrimination and calibration. The validation dataset showed that XGBoost was superior to Cox, regarding Harrell's C, Uno's C, and the Brier score (p = 0.003, 0.027, and 0.032, respectively), while Cox and SSVM were almost identical concerning these three parameters (p = 0.102, 0.092, and 0.048, respectively). We developed and validated a new ESKD risk prediction model for patients with CKD, employing commonly measured indicators in clinical practice, and its overall performance was satisfactory. The conventional Cox regression and certain ML models exhibited equal accuracy in predicting the course of CKD.

Predicting the risk of autoimmune thyroid disease in patients with vitiligo: Development and assessment of a new predictive nomogram.

This study aimed to develop an autoimmune thyroid disease (AITD) risk prediction model for patients with vitiligo based on readily available characteristics. A retrospective analysis was conducted on the clinical characteristics, demographics, skin lesions, and laboratory test results of patients with vitiligo. To develop a model to predict the risk of AITD, the Least Absolute Shrinkage and Selection Operator (LASSO) method was used to optimize feature selection, and logistic regression analysis was used to select further features. The C-index, Hosmer-Lemeshow test, and decision curve analysis were used to evaluate the calibration, discrimination ability and clinical utility of the model. Internally, the model was verified using bootstrapping; externally, two independent cohorts were used to confirm model accuracy. Sex, vitiligo type, family history of AITD, family history of other autoimmune disease, thyroid nodules or tumors, negative emotions, skin involvement exceeding 5% of body surface area, and positive immune serology (IgA, IgG, IgM, C3, and C4) were predictors of AITD in the prediction nomogram. The model showed good calibration and discrimination (C-index: 0.746; 95% confidence interval: 0.701-0.792). The accuracy of this predictive model was 74.6%.In both internal validation (a C-index of 1000 times) and external validation, the C-index outperformed (0.732, 0.869, and 0.777). The decision curve showed that the AITD nomogram had a good guiding role in clinical practice. The novel AITD nomogram effectively evaluated the risk of AITD in patients with vitiligo.

Construction and validation of the perioral moisture-related skin damage (PMASD) risk prediction model in patients with colorectal cancer.

This study aims to analyse the risk factors of Peristomal Moisture-Associated Skin Damage (PMASD) in colorectal cancer patients, construct a prediction model, and verify its effect. A total of 375 patients who underwent rectal cancer stoma surgery at the Liaoning Cancer Hospital between January and December 2020 were selected according to the inclusion and exclusion criteria. The clinical data were retrospectively analysed for modelling and internal validation (modelling group). According to the same criteria, the clinical data of 242 patients from January and June 2021 were retrospectively analysed for external validation (validation group). Baseline patient data were recorded. Patients in the modelling group were divided into those with and without PMASD based on the occurrence of PMASD during hospitalisation. Logistic regression analysis was used to examine the factors of PMASD and the PMASD nomogram model of colorectal cancer. Internal model validation was performed with the Bootstrap method, using the ROC and H-L goodness of fit test to evaluate the differentiation and calibration of the model. Last, external validation of the model was performed. In the modelling group, 212 patients with colorectal cancer developed PMASD. According to the results of the logistic regression analysis, high fasting plasma glucose and fasting blood glucose (FPG), a history of radiotherapy, the height of the stoma opening (i.e., flat or lower than the skin surface), and skin folds around the stoma are risk factors for PMASD (OR > 1, P < 0.05). The stool shaping and colostomy are protective factors for PMASD in patients with colorectal cancer (OR < 1, P < 0.05). To establish the prediction of colorectal cancer, patient development of PMASD line, graph model, and internal verification was carried out using the Bootstrap method: H-L test P=0.846, area under curve, area under the ROC curve (0 > 0.75, 95% CI: 0.778-0, AUC=0.820). The external validation included the H-L test (P=0.137, AUC [0.862] > 0.75, 95% CI: 0.815-0.909), with the maximum value of the Youden index as the best cut-off value for the model. The ROC curve had a Youden index of 0.559, a sensitivity of 0.877, and a specificity of 0.657. The prompt model area showed good calibration and discrimination. The PMASD in patients with colorectal cancer is affected by defecation traits, the stoma opening height, stoma type, FPG, skin folds around the stoma, and previous radiotherapy history. The nomogram model can provide an effective means to reasonably predict the risk of PMASD in patients with colorectal cancer.