Calibration Plots Research Articles

Construction and validation of a readmission risk prediction model for elderly patients with coronary heart disease

BackgroundTo investigate the risk factors for readmission of elderly patients with coronary artery disease, and to construct and validate a predictive model for readmission risk of elderly patients with coronary artery disease within 3 years by applying machine learning method.MethodsWe selected 575 elderly patients with CHD admitted to the Affiliated Lu’an Hospital of Anhui Medical University from January 2020 to January 2023. Based on whether patients were readmitted within 3 years, they were divided into two groups: those readmitted within 3 years (215 patients) and those not readmitted within 3 years (360 patients). Lasso regression and multivariate logistic regression were used to compare the predictive value of these models. XGBoost, LR, RF, KNN and DT algorithms were used to build prediction models for readmission risk. ROC curves and calibration plots were used to evaluate the prediction performance of the model. For external validation, 143 patients who were admitted between February and June 2023 from a different associated hospital in Lu'an City were also used.ResultsThe XGBoost model demonstrated the most accurate prediction performance out of the five machine learning techniques. Diabetes, Red blood cell distribution width (RDW), and Triglyceride glucose-body mass index (TyG-BMI), as determined by Lasso regression and multivariate logistic regression. Calibration plot analysis demonstrated that the XGBoost model maintained strong calibration performance across both training and testing datasets, with calibration curves closely aligning with the ideal curve. This alignment signifies a high level of concordance between predicted probabilities and observed event rates. Additionally, decision curve analysis highlighted that both decision trees and XGBoost models achieved higher net benefits within the majority of threshold ranges, emphasizing their significant potential in clinical decision-making processes. The XGBoost model's area under the ROC curve (AUC) reached 0.903, while the external validation dataset yielded an AUC of 0.891, further validating the model's predictive accuracy and its ability to generalize across different datasets.ConclusionTyG-BMI, RDW, and diabetes mellitus at the time of admission are the factors affecting readmission of elderly patients with coronary artery disease, and the model constructed based on the XGBoost algorithm for readmission risk prediction has good predictive efficacy, which can provide guidance for identifying high-risk patients and timely intervention strategies.

Machine Learning-Based Prediction for In-Hospital Mortality After Acute Intracerebral Hemorrhage Using Real-World Clinical and Image Data.

Machine learning (ML) techniques are widely employed across various domains to achieve accurate predictions. This study assessed the effectiveness of ML in predicting early mortality risk among patients with acute intracerebral hemorrhage (ICH) in real-world settings. ML-based models were developed to predict in-hospital mortality in 527 patients with ICH using raw brain imaging data from brain computed tomography and clinical data. The models' performances were evaluated using the area under the receiver operating characteristic curves and calibration plots, comparing them with traditional risk scores such as the ICH score and ICH grading scale. Kaplan-Meier curves were used to examine the post-ICH survival rates, stratified by ML-based risk assessment. The net benefit of ML-based models was evaluated using decision curve analysis. The area under the receiver operating characteristic curves were 0.91 (95% CI, 0.86-0.95) for the ICH score, 0.93 (95% CI, 0.89-0.97) for the ICH grading scale, 0.83 (95% CI, 0.71-0.91) for the ML-based model fitted with raw image data only, and 0.87 (95% CI, 0.76-0.93) for the ML-based model fitted using clinical data without specialist expertise. The area under the receiver operating characteristic curve increased significantly to 0.97 (95% CI, 0.94-0.99) when the ML model was fitted using clinical and image data assessed by specialists. All ML-based models demonstrated good calibration, and the survival rates showed significant differences between risk groups. Decision curve analysis indicated the highest net benefit when utilizing the findings assessed by specialists. ML-based prediction models exhibit satisfactory performance in predicting post-ICH in-hospital mortality when utilizing raw imaging data or nonspecialist input. Nevertheless, incorporating specialist expertise notably improves performance.

Identification of Key Risk Factors for Rupture in Small Intracranial Aneurysms: A Multicenter Study.

Predicting rupture risk in small intracranial aneurysms (IAs) < 5 mm is crucial for guiding clinical decisions. This study aims to identify key clinical and morphological risk factors associated with rupture in small IAs, providing better insight for decision-making. A retrospective analysis was performed on patients with small IAs from one center, with external validation data from another center. Logistic regression identified significant risk factors for aneurysm rupture, which were incorporated into a predictive model. The model's performance was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC), calibration plots, and the Hosmer-Lemeshow (H-L) goodness-of-fit test. Clinical utility was assessed via decision curve analysis (DCA). The training cohort consisted of 226 patients (ruptured, n = 181; unruptured, n = 92), while 136 patients (ruptured, n = 100; unruptured, n = 59) were used for external validation. Significant risk factors included hypertension, smoking, anterior communicating artery aneurysms (AcomA), daughter sacs, aspect ratio (AR), and size ratio (SR). The model demonstrated strong predictive ability with AUCs of 0.969 and 0.967 in the training and validation cohorts, respectively. Calibration plots indicated a good agreement between predicted and observed rupture risks, while DCA highlighted the model's clinical relevance. This study identifies and validates critical risk factors associated with small IA rupture and presents a clinically useful, high-accuracy predictive model to aid in individualized patient management.

Risk factor analysis and nomogram model establishment for in-hospital death of elderly patients with surgically treated traumatic acute subdural hematoma.

The purpose of this study was to investigate the risk factors for in-hospital death in elderly patients with surgically treated traumatic acute subdural hematoma (ASDH) and to construct a nomogram model for in-hospital death risk prediction. We analyzed 104 elderly patients who underwent decompressive craniotomy (DC) for isolated traumatic ASDH between May 2013 and May 2021 in our department. Independent factors for in-hospital death were identified via univariate and multivariate logistic regression analyses, and a nomogram model was constructed and validated. The overall in-hospital mortality rate was 58.7% (61/104). Sex (odds ratio [OR] = 11.94), dilated pupils (bilateral vs absent; OR = 194.16) and subarachnoid hemorrhage (SAH) (OR = 16.01) were independent risk factors for in-hospital death. A nomogram model for in-hospital death risk prediction was constructed based on these variables. Statistical analysis revealed that this model had good predictive performance, and receiver operating characteristic (ROC) curve analysis revealed that the area under the curve (AUC) of the nomogram model was 0.916 (95% confidence interval [CI] = 0.861-0.970). The calibration plot, which compared the predicted effective rate and observed effective rate, revealed the accurate predictive ability of the model. The model was internally validated via 200 bootstrap samples to calculate the discrimination accuracy, and the concordance index was 0.891. Decision curve analysis (DCA) demonstrated that the nomogram was clinically beneficial. The most important risk factors for in-hospital death in elderly patients with surgically treated traumatic ASDH were sex, dilated pupils, and SAH. The nomogram constructed from these data could be a promising and convenient tool to predict in-hospital death risk, but further external validation is needed.

Bayesian Inference for Post-Processing of Remote-Sensing Image Classification

A key component of remote-sensing image analysis is image classification, which aims to categorize images into different classes using machine-learning methods. In many applications, machine-learning classifiers assign class probabilities to each pixel. These class probabilities serve as input for post-processing techniques that aim to improve the results of machine-learning algorithms. This paper proposes a new post-processing algorithm based on an empirical Bayes approach. We employ non-isotropic neighborhood definitions to capture the impact of borders between land classes in the statistical model. By incorporating expert knowledge, the algorithm improves the consistency of the classified map. This technique has proven its efficacy for large-scale data processing using image time-series analysis. The proposed method is a key component of a time-first, space-based approach for big Earth-observation data processing. It is available as open source as part of the R package sits.

Combined systemic immune-inflammatory index and prognostic nutritional index predicts the efficacy and prognosis of ES-SCLC patients receiving PD-L1 inhibitors combined with first-line chemotherapy.

There is a strong association between inflammation and the formation, progression, and metastasis of malignant tumors, according to earlier studies. Some composite inflammation-nutritional indicators, such as the systemic immune-inflammation index (SII) and the prognostic nutritional index (PNI), have a certain predictive effect on the prognosis of patients with small cell lung cancer (SCLC). However, the relationship between these indicators and the efficacy of immunotherapy in SCLC patients is still not well understood. Therefore, the purpose of this study was to explore how the pre-treatment SII-PNI score can predict the tumor response and prognosis of extensive-stage SCLC patients treated with PD-L1 inhibitors and first-line chemotherapy. This research conducted a retrospective review of 70 ES- SCLC patients from December 2019 to January 2023. According to the SII-PNI score, all patients were categorized into three groups. Overall survival (OS) was assessed by implementing the Kaplan Meier and Cox regression models. In addition, we devised a nomogram and scrutinized its accuracy in prediction through receiver operating characteristic (ROC) curve analysis and visualized it by calibration plots. Subsequently, a risk classification system was established. Patients with higher SII-PNI scores exhibited notably poorer survival outcomes compared to their counterpart with low SII-PNI score (p=0.008), as well as poorer short-term curative effects (p=0.004). The results of the multivariate analysis revealed that the SII-PNI score (p=0.036) had an independent association with a less favorable OS. The nomogram has been demonstrated to be a reliable prognostic tool for ES-SCLC patients. A notable difference was identified between the two different levels of risk. The baseline SII-PNI score can serve as a reliable prognostic indicator for ES-SCLC patients receiving immunotherapy. Higher SII-PNI scores imply a worse prognosis.

Nomogram for predicting diabetes insipidus following endoscopic transsphenoidal surgery in pituitary adenomas.

Postoperative diabetes insipidus (DI) frequently complicates endoscopic transsphenoidal surgery (TSS) in pituitary adenoma (PA) patients, yet reliable predictive methods for DI risk remain lacking. This study aims to identify risk factors associated with DI following endoscopic transsphenoidal resection of PA and to develop a predictive nomogram for assessing postoperative DI risk. This study involved 600 PA patients underwent endoscopic TSS at Shandong Provincial Hospital from 2021 to 2023. Among these patients, 82 developed postoperative DI while 518 did not. The cohort was randomly divided into training (n = 360) and validation (n = 240) groups at 6:4 ratios by R software. Clinical parameters and radiographic features were evaluated using univariable and multivariable logistic regression to construct a predictive nomogram for post-endoscopic TSS DI risk. Model performance was assessed using ROC curves, calibration plots, and decision curve analysis. Subgroup analysis was used to evaluate the model's ability to discriminate between transient and permanent DI. Univariable and multivariable logistic regression analyses on the training group identified several independent risk factors for post-endoscopic TSS DI, including maximum tumor diameter, Knosp grade, Esposito grade, recurrent PA, and pituitary stalk deviation angle. A nomogram was developed based on these factors, demonstrating robust predictive accuracy with ROC areas under curve of 0.840 for the training group and 0.815 for the validation group. Calibration plots indicated excellent agreement between predicted and observed probabilities of postoperative DI. DCA curves highlighted the nomogram's efficacy in guiding clinical decision-making. Subgroup analysis showed that the model was able to discriminate between transient and permanent DI, and the AUC was 0.652 (95% CI 0.525-0.794). This study presents a nomogram designed to predict postoperative DI risk in patients undergoing endoscopic TSS for PA. Internal and external validations underscored the model's high accuracy, calibration, and clinical utility. Simultaneously, the model can also assess the development risk of permanent DI. This predictive tool offers clinicians valuable support in identifying high-risk DI patients, optimizing postoperative care strategies, and tailoring treatment plans to improve patient outcomes.

Development and validation of a prediction model for the prognosis of renal cell carcinoma with liver metastases: a population-based cohort study.

Current studies on the establishment of prognostic model for renal cell carcinoma (RCC) with liver metastases (LM) were scarce. This study aimed to develop nomograms to predict the prognosis of RCC with LM. Patients diagnosed with RCC between 2010 and 2021 from the Surveillance, Epidemiology, and End Results (SEER) database were selected. The eXtreme Gradient Boosting (XGBoost) and Random Forest (RF) machine learning algorithms were used to screen for the most influential factors affecting prognosis, and the Venn diagram method was employed for further refinement. Subsequently, a nomogram related to brain metastases was constructed. The performance of the nomograms was evaluated through receiver operating characteristics (ROC) curves, calibration plots, C-index, time-dependent C-index, and decision curve analysis (DCA). Kaplan-Meier (K-M) survival curves were used to provide additional verification of the clinical efficacy of the nomogram. This research comprised 2,395 RCC patients with LM. The Venn diagram demonstrated that age, histological type, grade, AJCC T stage, AJCC N stage, surgery, chemotherapy, marital status, and lung metastasis were highly relevant variables to patients with LM. The AUC, C-index, calibration curves, and DCA curves showed excellent performance of the nomogram. Additionally, the prognostic nomogram accurately classified RCC with LM patients into low- and high-risk groups for mortality. This study developed a novel nomogram to predict the prognostic factors of RCC with LM, providing a valuable reference for making accurate clinical decisions.

Predicting epidermal growth factor receptor (EGFR) mutation status in non-small cell lung cancer (NSCLC) patients through logistic regression: a model incorporating clinical characteristics, computed tomography (CT) imaging features, and tumor marker levels.

Approximately 60% of Asian populations with non-small cell lung cancer (NSCLC) harbor epidermal growth factor receptor (EGFR) gene mutations, marking it as a pivotal target for genotype-directed therapies. Currently, determining EGFR mutation status relies on DNA sequencing of histological or cytological specimens. This study presents a predictive model integrating clinical parameters, computed tomography (CT) characteristics, and serum tumor markers to forecast EGFR mutation status in NSCLC patients. Retrospective data collection was conducted on NSCLC patients diagnosed between January 2018 and June 2019 at the First Affiliated Hospital of Zhengzhou University, with available molecular pathology results. Clinical information, CT imaging features, and serum tumor marker levels were compiled. Four distinct models were employed in constructing the diagnostic model. Model diagnostic efficacy was assessed through receiver operating characteristic (ROC) area under the curve (AUC) values and calibration curves. DeLong's test was administered to validate model robustness. Our study encompassed 748 participants. Logistic regression modeling, trained with the aforementioned variables, demonstrated remarkable predictive capability, achieving an AUC of 0.805 (95% confidence interval (CI) [0.766-0.844]) in the primary cohort and 0.753 (95% CI [0.687-0.818]) in the validation cohort. Calibration plots suggested a favorable fit of the model to the data. The developed logistic regression model emerges as a promising tool for forecasting EGFR mutation status. It holds potential to aid clinicians in more precisely identifying patients likely to benefit from EGFR molecular testing and facilitating targeted therapy decision-making, particularly in scenarios where molecular testing is impractical or inaccessible.

Development and Validation of a Survival Prediction Model for Patients with Pancreatic Cancer.

Patients with pancreatic ductal adenocarcinoma (PDAC) face challenging treatment decisions following their diagnosis. We developed and validated a survival prognostication model using routinely available clinical information, patient-reported symptoms, performance status, and initial cancer-directed treatment. This retrospective cohort study included PDAC patients from 2007 to 2020 using linked administrative databases in Ontario, Canada. Patients were randomly selected for model development (75%) and validation (25%). Using the development cohort, a multivariable Cox proportional hazards regression with backward stepwise variable selection was used to predict the probability of survival. Model performance was assessed on the validation cohort using the concordance index and calibration plots. There were 17,450 patients (49% female) with a median age of 72 (IQR 63-81) and a mean survival time of nine months. In the derivation cohort, 1,469 (11%) patients had early stage, 4,202 (32%) had advanced stage disease, and 7,417 (57%) had unknown stage. The following factors were associated with an increased risk of death by more than 10%: tumour in the tail of the pancreas, advanced stage, hospitalization three months prior to diagnosis, congestive heart failure or dementia, low, moderate, or high pain score, moderate or high appetite score, high dyspnea and tiredness score, and a performance status score of 60-70 or lower. The calibration plot indicated good agreement with a C index of 0.76. This model accurately predicted one-year survival for PDAC using clinical factors, symptoms, and performance status. This model may foster shared decision making for patients and their providers.

Construction and Validation of Cardiovascular Disease Prediction Model for Dietary Macronutrients-Data from the China Health and Nutrition Survey.

There are currently many studies on predictive models for cardiovascular disease (CVD) that do not use dietary macronutrients for prediction. This study aims to provide a non-invasive model incorporating dietary information to predict the risk of CVD in adults. The data for this study were obtained from the China Health and Nutrition Survey (CHNS) spanning the years 2004 to 2015. The dataset was divided into training and validation sets at ratio of 7:3. Variables were screened by LASSO, and the Cox proportional hazards regression model was used to construct the 10-year risk prediction model of CVD. The model's performance was assessed using the concordance index (C-index), receiver operating characteristic (ROC) curve, calibration plots, and decision curve analysis (DCA) for discrimination, calibration, and clinical utility. This study included 5,186 individuals, with males accounting for 48.1% and a mean age of 46.39 ± 13.74 years, and females accounting for 51.9% and a mean age of 47.36 ± 13.29 years. The incidence density was 10.84/1000 person years. The model ultimately incorporates 11 non-invasive predictive factors, including dietary-related, demographic indicators, lifestyle behaviors, and disease history. Performance measures for this model were significant (AUC = 0.808 [(95%CI: 0.778-0.837], C-index = 0.797 [0.765-0.829]). After applying the model to internal validation cohorts, the AUC and C-index were 0.799 (0.749-0.838), and 0.788 (0.737-0.838), respectively. The calibration and DCA curves showed that the non-invasive model has relatively high stability, with a good net return. We developed a simple and rapid non-invasive model predictive of CVD for the next 10 years among Chinese adults.

Probabilistic regression for autonomous terrain relative navigation via multi-modal feature learning

The extension of human spaceflight across an ever-expanding domain, in conjunction with intricate mission architectures demands a paradigm shift in autonomous navigation algorithms, especially for the powered descent phase of planetary landing. Deep learning architectures have previously been explored to perform low-dimensional localization with limited success. Due to the expectations regarding novel algorithms in the context of real missions, the proposed approaches must be rigorously evaluated in extraneous scenarios and demonstrate sufficient robustness. In the current work, a novel formulation is proposed to train CNN-based Deep Learning (DL) models in a multi-layer cascading architecture and utilize the resulting classification probabilities as regression weights to estimate the position of the lander spacecraft. The approach leverages image intensity and depth data provided by multiple sensors on board to accurately determine the spacecraft’s location relative to the observed terrain at a specific altitude. Navigation performance is validated through Monte Carlo analysis, demonstrating the efficacy of the proposed DL architecture and the subsequent state-estimation framework across several simulated scenarios. It shows tremendous promise in extending the multi-modal feature learning approach to realistic missions.

FIRST-TRIMESTER NUCLEAR MAGNETIC RESONANCE-BASED METABOLOMIC PROFILING INCREASES THE PREDICTION OF GESTATIONAL DIABETES MELLITUS.

To investigate whether nuclear magnetic resonance (NMR)-based metabolomic profiling of maternal blood can be used for first-trimester prediction of gestational diabetes mellitus (GDM). This was a prospective study of 20,000 women attending for routine pregnancy care at 11-13 weeks' gestation. Metabolic profiles were assessed using a high-throughput NMR metabolomics platform. To inform translational applications, we focused on a panel of 34 clinically validated biomarkers for detailed analysis and risk modelling. All biomarkers were used to generate a multivariable logistic regression model to predict GDM. Data were split using random seed into a 70%-30% training and validation set, respectively. Performance of the multivariable models was measured by receiver operating characteristic (ROC) curve analysis and detection rates (DRs) at fixed 10% and 20% false positive rates. Calibration for the combined risk model for all GDM was assessed visually through a figure showing the observed incidence against the predicted risk for GDM. A sensitivity analysis was carried out excluding the 64 women in our cohort who were diagnosed with GDM prior to 20 weeks' gestation. The concentration of several metabolomic biomarkers, including cholesterols, triglycerides, fatty acids, and amino acids, were different in the group that developed GDM, compared to those without GDM. Addition of biomarker profile improved the prediction of GDM provided by maternal demographic characteristics and elements of medical history alone (area under the receiver operating characteristics curve [AUROC] 0.790 and detection rate (DR) of 50%, 95%CI 44.3%-55.7%, at 10% false positive rate (FPR) and 63%, 95%CI 57.4%-68.3%, at 20% FPR, to 0.840, 56%, 95%CI 50.3%-61.6% and 73%, 95%CI 67.7%-77.8%, respectively). The performance of combined testing was better for GDM treated by insulin (ROC AUC 0.905, DR 76%, 95%CI 67.5%-83.2%, at 10% FPR and DR 85%, 95%CI 77.4%-90.9%, at 20%) than GDM treated by diet alone (ROC AUC 0.762, DR 47%, 95%CI 37.7%-56.5%, at 10% FPR and DR 64%, 95%CI 54.5%-72.7%, at 20% FPR). In the calibration plot there was good agreement between the observed incidence of GDM against that predicted from the combined risk model. In the sensitivity analysis excluding the women diagnosed with GDM prior to 20 weeks' gestation, there was a negligible difference in ROC AUC in comparison to the results from the entire cohort combined. Addition of NMR-based metabolomic profiling to risk factors can provide first-trimester prediction of GDM.

Integrating Neutrophil-To-Albumin Ratio and Triglycerides: A Novel Indicator for Predicting Spontaneous Hemorrhagic Transformation in Acute Ischemic Stroke Patients.

Hemorrhagic transformation (HT) is a tragic complication of acute ischemic stroke (AIS), with spontaneous HT (sHT) occurring even without reperfusion therapies. Despite evidence suggesting that several inflammation biomarkers are closely related to HT, its utility in sHT risk stratification remains unclear. This study aimed to identify and integrate effective inflammatory biomarkers associated with sHT and to develop a novel nomogram model for the early detection of sHT. We conducted a retrospective observational cohort study of AIS patients receiving conventional medical treatment solely from March 2022 to March 2023, using a prospectively maintained database. All patients underwent CT follow-up within 7 days after admission, with sHT occurrence within this period as the outcome. Data on demographics, clinical information, laboratory results, and imaging were collected. The cohort was divided into training and validation sets (7:3). Least absolute shrinkage and selection operator (LASSO) regression selected inflammatory biomarkers for a novel index. Univariable and multivariable logistic regressions were conducted to identify independent sHT risk factors. Receiver operating characteristic (ROC) analysis determined optimal cut-off values for continuous factors. A nomogram was developed and validated internally and externally. Predictive accuracy was assessed using the area under the ROC curve (AUC) and calibration plots. Decision curve analysis (DCA) evaluated clinical usefulness. Of 803 AIS patients, 325 were included in the final analysis. sHT was found in 9.5% (31 patients). Training (n = 228) and validation (n = 97) cohorts showed no significant demographic or clinical differences. LASSO regression integrated neutrophil-to-albumin ratio (NAR) and triglycerides (TGs) into a novel index-NATG. Independent sHT risk factors included baseline National Institute of Health Stroke Scale (NIHSS) (OR = 1.09, 95% CI (1.02, 1.16), p = 0.0095), NATG (OR = 1534.87, 95% CI (5.02, 469638.44), p = 0.0120), D-dimer (DD) (OR = 1.12, 95% CI (1.01, 1.25), p = 0.0249), and total cholesterol (TC) (OR = 1.01, 95% CI (1.00, 1.01), p = 0.0280), with their respective optimal cut-off values being 13, 0.059, 0.86, and 3.6. These factors were used to develop the nomogram in the training cohort, which achieved an AUC of 0.804 (95% CI, 0.643-0.918) in the training cohort and 0.713 (95% CI, 0.499-0.868) in the validation cohort, demonstrating consistent calibration. DCA confirmed the nomogram's clinical applicability in both cohorts. A novel indicator combining NAR and TG is positively associated with sHT in AIS patients. The constructed nomogram, integrating this novel indicator with other risk factors, provides a valuable tool for identifying sHT risk, aiding in clinical decision-making.

Optimizing prostate biopsy decision-making for patients with Prostate Imaging-Reporting and Data System (PI-RADS) ≥3 lesions: novel magnetic resonance imaging (MRI)-based nomograms.

Current protocols endorse biopsies for men with Prostate Imaging-Reporting and Data System (PI-RADS v2.1) scores ≥3. However, the subjective nature of PI-RADS can lead to increased false positives and unnecessary biopsies. Synthetic magnetic resonance imaging (MRI), which quantifies multiple relaxation parameters, and apparent diffusion coefficient (ADC), which is the most commonly used quantitative metric, have not yet been combined with a predictive tool. This study aimed to develop and validate novel nomograms using multiparametric MRI, including synthetic MRI, to forecast the risk of prostate cancer (PCa) and clinically significant prostate cancer (csPCa), and to assess the potential of these nomograms to reduce unnecessary biopsies in PI-RADS ≥3 cases. Between August 2020 and August 2022, 323 patients suspected of PCa were enrolled from two centers (cohort 1: 243; cohort 2: 80). All participants underwent multiparametric MRI, including synthetic MRI, before targeted biopsy. Univariable and multivariable logistic regression identified risk factors for PCa and csPCa. Internal validation was conducted using bootstrap resampling, and nomogram performance was evaluated through receiver operating characteristic (ROC) curve analysis, calibration plots, and decision curve analysis (DCA). External validation was performed with cohort 2 data. The impact of the nomograms on biopsy decisions was measured by the avoidance rate and the risk of missed diagnoses. The predictive nomogram for PCa incorporated four risk factors: age, quantitative transverse relaxation time (T2 value) from synthetic MRI, ADC value, and PI-RADS score. The csPCa nomogram included age, ADC value, and PI-RADS score. The nomograms showed high diagnostic accuracy with the area under the curves (AUCs) of 0.916 [95% confidence interval (CI): 0.901-0.974] and 0.947 (95% CI: 0.900-0.994) for PCa prediction in training and external datasets, and 0.884 (95% CI: 0.840-0.928) and 0.935 (95% CI: 0.871-0.998) for csPCa. Calibration curves confirmed the accuracy of predictions. DCA indicated that the nomograms possessed significant net benefit. For PCa detection, biopsy strategy combining our nomogram reduced biopsy procedures by 20.2% and 13.8% in the training and external cohorts, respectively, with a PCa miss rate of 4.5% for both cohorts. The csPCa-targeted biopsy strategy also provided clinical benefits, with biopsy avoidance rates of 20.2% and 10.0%, and csPCa miss rates of 4.8% and 1.7% for PI-RADS ≥3 patients in the two cohorts. The nomograms integrating multiparametric MRI and synthetic MRI are highly effective in predicting PCa and csPCa, concurrently, reducing unnecessary biopsies for patients with PI-RADS ≥3 lesion.

Predictive Factors for Major Bleeding in Patients Undergoing Percutaneous Nephrolithotomy: A Clinical Prediction Study.

To evaluate major bleeding risk factors in percutaneous nephrolithotomy (PCNL) for upper urinary tract calculi and validate a prediction model. Analytical study. Place and Duration of the Study: The First Affiliated Hospital of Wannan Medical College, Wuhu, China, from January 2019 to August 2023. Major bleeding was defined as a decrease in haemoglobin of ≥20 g/L compared to preoperative levels. A retrospective analysis of 468 PCNL patients identified risk factors for major bleeding using univariate, LASSO, and logistic regression analyses. Nomogram models were developed using R software, with ROC and calibration plots assessing the model's accuracy. The bootstrap method provided internal validation, and DCA evaluated clinical utility. Independent risk factors included diabetes (OR = 4.17), staghorn calculi (OR = 3.41), operative duration (OR = 1.01), and staged surgery (OR = 2.75). The model showed high discriminative ability (C-statistic: 0.783) and alignment with observed outcomes. Internal validation confirmed robustness (C-statistic: 0.728). The predictive model for major bleeding during and after PCNL, focusing on diabetes, staghorn calculi, operative duration, and staged surgery, is highly accurate, aiding in the PCNL risk assessment. Upper urinary tract calculi, Percutaneous nephrolithotomy, Major bleeding, Risk factors, Prediction model.

Construction, validation, and visualization of a web-based nomogram to predict survival in male breast cancer patients with second primary prostate cancer.

The advancement of early detection and treatment has brought about a significant concern for male breast cancer (MBC) survivors-the emergence of a second primary malignancy (SPM) poses a grave threat to their lives. Among them, second primary prostate cancer (spPCa) holds particular significance. This study aimed to investigate the impact of spPCa on the prognosis of MBC patients. We performed a retrospective analysis using information from the Surveillance, Epidemiology, and End Results (SEER) database to investigate individuals diagnosed with MBC who also experienced an SPM between 2000 and 2020. Propensity score matching (PSM) was employed to balance the baseline characteristics of individuals with spPCa and those with second primary non-prostate cancer (non-PCa). The impact of spPCa on participant survival was assessed using the Kaplan-Meier method. Furthermore, two nomograms were developed, based on univariate and multifactor Cox regression analyses, to predict overall survival (OS) and cancer-specific survival (CSS). The capacity of the nomograms was evaluated using the concordance index (C-index), calibration curve, receiver operating characteristic (ROC) analysis, and decision curve analysis (DCA). Additionally, a risk stratification system was devised, taking into account the cumulative score of each patient in the nomogram. This study enrolled a total of 885 MBC patients who experienced an SPM, of which 265 (29.9%) were diagnosed with spPCa. Through PSM, 257 pairs of eligible participants were selected. Survival analysis revealed that patients with prostate cancer (PCa) as an SPM have longer OS and CSS compared to those with other types of cancer as an SPM. The participants were randomly divided into a training set and a validation set in a ratio of 7:3. The Cox proportional hazards model was utilized to assess the risk factors associated with survival outcomes. Two nomograms were developed to forecast the 3-, 5-, 8-, and 10-year OS and CSS of male patients who had breast cancer and SPM. The two nomograms exhibited excellent performance in terms of the C-index, ROC curves, calibration plots, and DCA curves, demonstrating their exceptional clinical discriminative ability and predictive utility. In the risk stratification system predicated on the total score of the nomogram, patients deemed high-risk exhibited diminished OS and CSS. Additionally, we created user-friendly web applications to enhance the accessibility of the nomogram in clinical practices, which can be accessed at https://mbcpre.shinyapps.io/DynNomapp_OS/ for OS and https://mbcpre.shinyapps.io/DynNomapp_CSS/ for CSS. MBC patients with spPCa exhibit a more favorable prognosis than those with other SPMs. The two nomograms we constructed could accurately forecast the OS and CSS for MBC patients with spPCa. Patients whose nomograms are stratified as high-risk should gain additional attention. Our nomograms may aid clinicians in personalizing treatment strategies and supporting clinical decisions.

Construction and validation of prognostic models for young cervical cancer patients: age stratification based on restricted cubic splines

Cervical cancer (CC) ranks as the second highest cause of morbidity and mortality among young women; however, there are currently no age-specific definitions for young cervical cancer or prognostic models tailored to this demographic. Data on CC diagnosed between 2000 and 2019 were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. Age stratification is based on the relationship between age and cancer-specific mortality, as demonstrated by restricted cubic spline analyses (RCS). Cox proportional hazards regression analyses were employed to identify independent prognostic factors in the young CC group. Two novel nomograms for this population were developed and validated using an external validation cohort obtained from a local hospital database, evaluated with concordance index (C-index) and calibration plots. Receiver operating characteristic (ROC) curves were utilized to compare the accuracy of the established models against the International Federation of Gynaecology and Obstetrics (FIGO) staging system (2018). A total of 27,658 patients from the SEER database were classified into three age groups (<36 years, 36-60 years, >60 years) based on RCS analyses, with 4,990, 16,922, and 5,746 patients in each group, respectively. The independent prognostic factors identified for young CC included stage, tumour size, grade, histologic type, and surgical intervention. The results of the C-index and calibration in both the training and validation sets confirmed that the two nomograms can accurately predict the occurrence and prognosis of young CC patients. The area under the curve (AUC) values indicated that these models demonstrated higher efficacy in predicting overall survival (OS) compared to the FIGO staging system (2018). These models could potentially serve as effective tools for clinicians to estimate the prognosis of young CC patients.

Nomogram Based on HRV for Predicting the Therapeutic Effects of Orthostatic Training in Children with Vasovagal Syncope

Background: This study intended to find out whether the parameters of heart rate variability (HRV) can predict the treatment efficacy of orthostatic training among pediatric cases of vasovagal syncope (VVS). Methods: Patients with VVS who underwent orthostatic training were retrospectively enrolled. Lasso and logistic regression were used to sift through variables and build the model, which is visualized using a nomogram. The model’s performance was evaluated through calibration plots, a receiver operating characteristic (ROC) curve, and decision curve analysis (DCA) for both datasets. Results: In total, 119 participants were included in the analysis, and 73 and 46 were assigned to the training and validation datasets, respectively. Five factors with nonzero coefficients were chosen based on lasso regression: age, the root means square of successive differences between normal sinus beats (rMSSD), standard deviation of the averages normal-to-normal intervals in all 5-min segments, minimum heart rate, and high frequency. Drawing from the logistic regression analysis results, the visual predictive model incorporated two variables, namely age and rMSSD. For the training dataset, the sensitivity was 0.686 and the specificity was 0.868 with an area under the curve (AUC) of 0.81 (95% CI, 0.71–0.91) for the ROC curve. For the validation dataset, the AUC of the ROC was 0.80 (95% CI, 0.66–0.93), while sensitivity and specificity were recorded at 0.625 and 0.909, respectively. In the calibration plots for both datasets, the predicted probabilities correlated well with the actual probabilities. According to the DCA, the visual predictive model gained a significant net benefit across a wide threshold range. Conclusions: Pediatric patients with VVS can benefit from orthostatic training using a visual predictive model comprising age and rMSSD.

The Barts Surgical Infection Risk tool (B-SIR): external validation and comparison with existing tools to predict surgical site infection after cardiac surgery

ObjectiveWe previously developed and internally validated the Barts Surgical Infection Risk (B-SIR). We sought to explore the external validity of the B-SIR tool and compare with the Australian Clinical Risk Index (ACRI) and Brompton and Harefield Infection Score (BHIS). Study design and settingThis multicentre retrospective analysis of prospectively collected local data included adult (≥18years) patients undergoing cardiac surgery between January 2018 and December 2019. Pre-pandemic data was used as a reflection of standard practice. Area under the curve (AUC) was used to validate and compare the predictive power of the scores and calibration was assessed using Hosmer-Lemeshow test and calibration plots. ResultsFrom three centres, 6,022 patients were included in the complete case analysis. The mean age was 66 years, 75% were men and 3.19% developed SSI. The B-SIR has an AUC of 0.686 (95% CI: 0.649 to 0.723) similar to the developmental study (AUC=0.682; 95% CI: 0.652 to 0.713). This is significantly higher than BHIS AUC=0.610 (95% CI: 0.045 to 0.109; p<0.001) and ACRI AUC=0.614 (95% CI: 0.041 to 0.103; p<0.001). After re-calibration using a correction factor, the B-SIR model gave accurate risk predictions (Hosmer-Lemeshow test p=0.423). Multiple imputation result (AUC=0.676; 95%CI: 0.639 to 0.712) is similar to development data and is higher than ACRI and BHIS. ConclusionExternal B-SIR validation indicates B-SIR predicts SSI after cardiac surgery better than ACRI and BHIS risk tools. This suggests B-SIR could be useful to use routinely in practice.