Explore the vast range of titles available.

Background：The currently available polysomnography （PSG） equipments and operating personnel are facing increasing pressure,such situation may result in the problem that a large number of obstructive sleep apnea （OSA） patients cannot receive timely diagnosis and treatment,we sought to develop a nomogram quantifying the risk of OSA for a better decision of using PSG,based on the clinical syndromes and the demographic and anthropometric characteristics.Methods：The nomogram was constructed through an ordinal logistic regression procedure.Predictive accuracy and performance characteristics were assessed with the area under the curve （AUC） of the receiver operating characteristics and calibration plots,respectively.Decision curve analyses were applied to assess the net benefit of the nomogram.Results：Among the 401 patients,73 （18.2%） were diagnosed and grouped as the none OSA （apnea-hypopnea index [AHI] 〈5）,67 （16.7%） the mild OSA （5 ≤ AHI 〈 15）,82 （20.4%） the moderate OSA （15 ≤ AHI 〈 30）,and 179 （44.6%） the severe OSA （AHI ≥ 30）.The multivariable analysis suggested the significant factors were duration of disease,smoking status,difficulty of falling asleep,lack of energy,and waist circumference.A nomogram was created for the prediction of OSA using these clinical parameters and was internally validated using bootstrapping method.The discrimination accuracies of the nomogram for any OSA,moderate-severe OSA,and severe OSA were 83.8%,79.9%,and 80.5%,respectively,which indicated good calibration.Decision curve analysis showed that using nomogram could reduce the unnecessary polysomnography （PSG） by 10% without increasing the false negatives.Conclusions：The established clinical nomogram provides high accuracy in predicting the individual risk of OSA.This tool may help physicians better make decisions on PSG arrangement for the patients referred to sleep centers.

Calibrated risk models are vital for valid decision support. We define four levels of calibration and describe implications for model development and external validation of predictions. We present results based on simulated data sets. A common definition of calibration is “having an event rate of R% among patients with a predicted risk of R%,” which we refer to as “moderate calibration.” Weaker forms of calibration only require the average predicted risk (mean calibration) or the average prediction effects (weak calibration) to be correct. “Strong calibration” requires that the event rate equals the predicted risk for every covariate pattern. This implies that the model is fully correct for the validation setting. We argue that this is unrealistic: the model type may be incorrect, the linear predictor is only asymptotically unbiased, and all nonlinear and interaction effects should be correctly modeled. In addition, we prove that moderate calibration guarantees nonharmful decision making. Finally, results indicate that a flexible assessment of calibration in small validation data sets is problematic. Strong calibration is desirable for individualized decision support but unrealistic and counter productive by stimulating the development of overly complex models. Model development and external validation should focus on moderate calibration.

Background Development of emergency department (ED) triage systems that accurately differentiate and prioritize critically ill from stable patients remains challenging. We used machine learning models to predict clinical outcomes, and then compared their performance with that of a conventional approach—the Emergency Severity Index (ESI). Methods Using National Hospital and Ambulatory Medical Care Survey (NHAMCS) ED data, from 2007 through 2015, we identified all adult patients (aged ≥ 18 years). In the randomly sampled training set (70%), using routinely available triage data as predictors (e.g., demographics, triage vital signs, chief complaints, comorbidities), we developed four machine learning models: Lasso regression, random forest, gradient boosted decision tree, and deep neural network. As the reference model, we constructed a logistic regression model using the five-level ESI data. The clinical outcomes were critical care (admission to intensive care unit or in-hospital death) and hospitalization (direct hospital admission or transfer). In the test set (the remaining 30%), we measured the predictive performance, including area under the receiver-operating-characteristics curve (AUC) and net benefit (decision curves) for each model. Results Of 135,470 eligible ED visits, 2.1% had critical care outcome and 16.2% had hospitalization outcome. In the critical care outcome prediction, all four machine learning models outperformed the reference model (e.g., AUC, 0.86 [95%CI 0.85–0.87] in the deep neural network vs 0.74 [95%CI 0.72–0.75] in the reference model), with less under-triaged patients in ESI triage levels 3 to 5 (urgent to non-urgent). Likewise, in the hospitalization outcome prediction, all machine learning models outperformed the reference model (e.g., AUC, 0.82 [95%CI 0.82–0.83] in the deep neural network vs 0.69 [95%CI 0.68–0.69] in the reference model) with less over-triages in ESI triage levels 1 to 3 (immediate to urgent). In the decision curve analysis, all machine learning models consistently achieved a greater net benefit—a larger number of appropriate triages considering a trade-off with over-triages—across the range of clinical thresholds. Conclusions Compared to the conventional approach, the machine learning models demonstrated a superior performance to predict critical care and hospitalization outcomes. The application of modern machine learning models may enhance clinicians’ triage decision making, thereby achieving better clinical care and optimal resource utilization.

Objective Regret is a powerful motivating factor in medical decision making among patients and surgeons. Regret can be particularly important for surgical decisions, which often carry significant risk and may have uncertain outcomes. We performed a systematic review of the literature focused on patient and physician regret in the surgical setting. Methods A search of the English literature between 1986 and 2016 that examined patient and physician self-reported decisional regret was carried out using the MEDLINE/PubMed and Web of Science databases. Clinical studies performed in patients and physicians participating in elective surgical treatment were included. Results Of 889 studies identified, 73 patient studies and 6 physician studies met inclusion criteria. Among the 73 patient studies, 57.5% examined patients with a cancer diagnosis, with breast (26.0%) and prostate (28.8%) cancers being most common. Interestingly, self-reported patient regret was relatively uncommon with an average prevalence across studies of 14.4%. Factors most often associated with regret included type of surgery, disease-specific quality of life, and shared decision making. Only 6 studies were identified that focused on physician regret; 2 pertained to surgical decision making. These studies primarily measured regret of omission and commission using hypothetical case scenarios and used the results to develop decision curve analysis tools. Conclusion Self-reported decisional regret was present in about 1 in 7 surgical patients. Factors associated with regret were both patient- and procedure related. While most studies focused on patient regret, little data exist on how physician regret affects shared decision making.

Backgroud The current diagnostic criteria for refractory Mycoplasma pneumoniae pneumonia (RMPP) among Mycoplasma pneumoniae Pneumonia (MPP) are insufficient for early identification, and potentially delayed appropriate treatment. This study aimed to develop an effective individualized diagnostic prediction nomogram for pediatric RMPP. Methods A total of 517 hospitalized children with MPP, including 131 with RMPP and 386 without RMPP (non-RMPP), treated at Lianyungang Maternal and Child Health Care Hospital from January 2018 to December 2021 were retrospectively enrolled as a development (modeling) cohort to construct an RMPP prediction nomogram. Additionally, 322 pediatric patients with MPP (64 with RMPP and 258 with non-RMPP, who were treated at the Affiliated Hospital of Xuzhou Medical University from June 2020 to May 2022 were retrospectively enrolled as a validation cohort to assess the prediction accuracy of model. Univariable and multivariable logistic regression analyses were used to identify RMPP risk factors among patients with MPP. Nomogram were generated based on these risk factors using the rms package of R, and the predictive performance was evaluated based on receiver operating characteristic (ROC) curves and using decision curve analysis (DCA). Results Multivariate analysis revealed five significant independent predictors of RMPP among patients with MPP: age (hazard ratio [ HR ] 1.16, 95% confidence interval [ CI ] 1.08–1.33, P  = 0.038), fever duration ( HR 1.34, 95% CI 1.20–1.50, P  < 0.001), lymphocyte count ( HR 0.45, 95% CI 0.23–0.89, P  = 0.021), serum D-dimer (D-d) level ( HR 1.70, 95% CI 1.16–2.49, P  = 0.006), and pulmonary imaging score ( HR 5.16, 95% CI 2.38–11.21, P  < 0.001). The area under the ROC curve was 90.7% for the development cohort and 96.36% for the validation cohort. The internal and external verification calibration curves were almost linear with slopes of 1, and the DCA curve revealed a net benefit with the final predictive nomogram. Conclusion This study proposes a predictive nomogram only based on five variables. The nomogram can be used for early identification of RMPP among pediatric patients with MPP, thereby facilitating more timely and effective intervention.

Background For patients with breast cancer undergoing neoadjuvant chemotherapy (NACT), most of the existing prediction models of pathologic complete response (pCR) using clinicopathological features were based on standard statistical models like logistic regression, while models based on machine learning mostly utilized imaging data and/or gene expression data. This study aims to develop a robust and accessible machine learning model to predict pCR using clinicopathological features alone, which can be used to facilitate clinical decision-making in diverse settings. Methods The model was developed and validated within the National Cancer Data Base (NCDB, 2018–2020) and an external cohort at the University of Chicago (2010–2020). We compared logistic regression and machine learning models, and examined whether incorporating quantitative clinicopathological features improved model performance. Decision curve analysis was conducted to assess the model’s clinical utility. Results We identified 56,209 NCDB patients receiving NACT (pCR rate: 34.0%). The machine learning model incorporating quantitative clinicopathological features showed the best discrimination performance among all the fitted models [area under the receiver operating characteristic curve (AUC): 0.785, 95% confidence interval (CI): 0.778–0.792], along with outstanding calibration performance. The model performed best among patients with hormone receptor positive/human epidermal growth factor receptor 2 negative (HR+/HER2-) breast cancer (AUC: 0.817, 95% CI: 0.802–0.832); and by adopting a 7% prediction threshold, the model achieved 90.5% sensitivity and 48.8% specificity, with decision curve analysis finding a 23.1% net reduction in chemotherapy use. In the external testing set of 584 patients (pCR rate: 33.4%), the model maintained robust performance both overall (AUC: 0.711, 95% CI: 0.668–0.753) and in the HR+/HER2- subgroup (AUC: 0.810, 95% CI: 0.742–0.878). Conclusions The study developed a machine learning model ( https://huolab.cri.uchicago.edu/sample-apps/pcrmodel ) to predict pCR in breast cancer patients undergoing NACT that demonstrated robust discrimination and calibration performance. The model performed particularly well among patients with HR+/HER2- breast cancer, having the potential to identify patients who are less likely to achieve pCR and can consider alternative treatment strategies over chemotherapy. The model can also serve as a robust baseline model that can be integrated with smaller datasets containing additional granular features in future research.

Background The absence of distinct symptoms in the majority of individuals with metabolic dysfunction-associated fatty liver disease (MAFLD) poses challenges in identifying those at high risk, so we need simple, efficient and cost-effective noninvasive scores to aid healthcare professionals in patient identification. While most noninvasive scores were developed for the diagnosis of nonalcoholic fatty liver disease (NAFLD), consequently, the objective of this study was to systematically assess the diagnostic ability of 12 noninvasive scores (METS-IR/TyG/TyG-WC/TyG-BMI/TyG-WtHR/VAI/HSI/FLI/ZJU/FSI/K-NAFLD) for MAFLD. Methods The study recruited eligible participants from two sources: the National Health and Nutrition Examination Survey (NHANES) 2017-2020.3 cycle and the database of the West China Hospital Health Management Center. The performance of the model was assessed using various metrics, including area under the receiver operating characteristic curve (AUC), net reclassification index (NRI), integrated discrimination improvement (IDI), decision curve analysis (DCA), and subgroup analysis. Results A total of 7398 participants from the NHANES cohort and 4880 patients from the Western China cohort were included. TyG-WC had the best predictive power for MAFLD risk in the NHANES cohort (AUC 0.863, 95% CI 0.855–0.871), while TyG-BMI had the best predictive ability in the Western China cohort (AUC 0.903, 95% CI 0.895–0.911), outperforming other models, and in terms of IDI, NRI, DCA, and subgroup analysis combined, TyG-WC remained superior in the NAHANES cohort and TyG-BMI in the Western China cohort. Conclusions TyG-BMI demonstrated satisfactory diagnostic efficacy in identifying individuals at a heightened risk of MAFLD in Western China. Conversely, TyG-WC exhibited the best diagnostic performance for MAFLD risk recognition in the United States population. These findings suggest the necessity of selecting the most suitable predictive models based on regional and ethnic variations.

In recent years, machine learning (ML)-based models have been widely used in clinical domains to predict clinical risk events. However, in production, the performances of such models heavily rely on changes in the system and data. The dynamic nature of the system environment, characterized by continuous changes, has significant implications for prediction models, leading to performance degradation and reduced clinical efficacy. Thus, monitoring model shifts and evaluating their impact on prediction models are of utmost importance. This study aimed to assess the impact of a model shift on ML-based prediction models by evaluating 3 different use cases-delirium, sepsis, and acute kidney injury (AKI)-from 2 hospitals (M and H) with different patient populations and investigate potential model deterioration during the COVID-19 pandemic period. We trained prediction models using retrospective data from earlier years and examined the presence of a model shift using data from more recent years. We used the area under the receiver operating characteristic curve (AUROC) to evaluate model performance and analyzed the calibration curves over time. We also assessed the influence on clinical decisions by evaluating the alert rate, the rates of over- and underdiagnosis, and the decision curve. The 2 data sets used in this study contained 189,775 and 180,976 medical cases for hospitals M and H, respectively. Statistical analyses (Z test) revealed no significant difference (P>.05) between the AUROCs from the different years for all use cases and hospitals. For example, in hospital M, AKI did not show a significant difference between 2020 (AUROC=0.898) and 2021 (AUROC=0.907, Z=-1.171, P=.242). Similar results were observed in both hospitals and for all use cases (sepsis and delirium) when comparing all the different years. However, when evaluating the calibration curves at the 2 hospitals, model shifts were observed for the delirium and sepsis use cases but not for AKI. Additionally, to investigate the clinical utility of our models, we performed decision curve analysis (DCA) and compared the results across the different years. A pairwise nonparametric statistical comparison showed no differences in the net benefit at the probability thresholds of interest (P>.05). The comprehensive evaluations performed in this study ensured robust model performance of all the investigated models across the years. Moreover, neither performance deteriorations nor alert surges were observed during the COVID-19 pandemic period. Clinical risk prediction models were affected by the dynamic and continuous evolution of clinical practices and workflows. The performance of the models evaluated in this study appeared stable when assessed using AUROCs, showing no significant variations over the years. Additional model shift investigations suggested that a calibration shift was present for certain use cases (delirium and sepsis). However, these changes did not have any impact on the clinical utility of the models based on DCA. Consequently, it is crucial to closely monitor data changes and detect possible model shifts, along with their potential influence on clinical decision-making.

Background Sarcopenia is an important prognostic factor of lung cancer. The serum creatinine/cystatin C ratio (CCR) and the sarcopenia index (SI, serum creatinine × cystatin C‐based glomerular filtration rate) are novel screening tools for sarcopenia; however, the diagnostic accuracy of the CCR and SI for detecting sarcopenia remains unknown. We aimed to explore and validate the diagnostic values of the CCR and SI for determining sarcopenia in non‐small cell lung cancer (NSCLC) and to explore their prognostic values for overall survival. Methods We conducted a prospective cohort study of adult patients with stage IIIB or IV NSCLC. Levels of serum creatinine and cystatin C were measured to calculate the CCR and SI. Sarcopenia was defined separately using CCR, SI, and the Asian Working Group for Sarcopenia (AWGS) 2019 criteria. Participants were randomly sampled into derivation and validation sets (6:4 ratio). The cutoff values for diagnosing sarcopenia were determined based on the derivation set. Diagnostic accuracy was analysed in the validation set through receiver operating characteristic (ROC) curves. Cox regression models and survival curves were applied to evaluate the impact of different sarcopenia definitions on survival. Results We included 579 participants (women, 35.4%; mean age, 58.4 ± 8.9 years); AWGS‐defined sarcopenia was found in 19.5% of men and 10.7% of women. Both CCR and SI positively correlated with computed tomography‐derived and bioimpedance‐derived muscle mass and handgrip strength. The optimal cutoff values for CCR and SI were 0.623 and 54.335 in men and 0.600 and 51.742 in women, with areas under the ROC curves of 0.837 [95% confidence interval (CI): 0.770–0.904] and 0.833 (95% CI: 0.765–0.901) in men (P = 0.25), and 0.808 (95% CI: 0.682–0.935) and 0.796 (95% CI: 0.668–0.924) in women (P = 0.11), respectively. The CCR achieved sensitivities and specificities of 73.0% and 93.7% in men and 85.7% and 65.7% in women, respectively; the SI achieved sensitivities and specificities of 75.7% and 86.5% in men and 92.9% and 62.9% in women, respectively. CCR‐defined, SI‐defined, and AWGS‐defined sarcopenia were independently associated with a high mortality risk [hazard ratio (HR) = 1.75, 95% CI: 1.25–2.44; HR = 1.55, 95% CI: 1.11–2.17; and HR = 1.76, 95% CI: 1.22–2.53, respectively]. Conclusions CCR and SI have satisfactory and comparable diagnostic accuracy and prognostic values for sarcopenia in patients with advanced NSCLC. Both may serve as surrogate biomarkers for evaluating sarcopenia in these patients. However, further external validations are required.

Objective To explore the predictive value of vegetation size on the prognosis of pediatric infective endocarditis (IE). Methods A total of 27 children diagnosed with IE who were admitted to Kunming Children’s Hospital from January 2014 to June 2024 were included. The good prognosis group comprised 10 cases, while the bad prognosis group comprised 17 cases. The receiver operating characteristic (ROC) curve, restricted cubic spline model, and decision curve analysis were utilized to assess the predictive value of vegetation size on the prognosis of pediatric IE. Results There were statistically significant differences in vegetation size, hemoglobin, platelet count, and prothrombin time between the two groups ( P  < 0.05). The ROC curve demonstrated that vegetation size had a high predictive accuracy for the prognosis of pediatric IE (AUC = 0.841, 95% CI: 0.775–0.924). Decision curve analysis indicated that vegetation size held substantial clinical value for predicting the prognosis of pediatric IE. The restricted cubic spline analysis revealed a linear dose-response relationship between vegetation size and prognosis of pediatric IE (nonlinear test, P  = 0.084). Conclusion Significant differences were observed in vegetation size, hemoglobin, platelet count, and prothrombin time between different prognosis of pediatric IE. Limited evidence indicates that vegetation size is a critical factor in predicting the prognosis of pediatric IE. However, studies with larger sample sizes are needed to confirm the accuracy of these conclusions.