Machine Learning Prediction Model for Acute Renal Failure After Acute Aortic Syndrome Surgery

BackgroundAcute renal failure (ARF) is the most common major complication following cardiac surgery for acute aortic syndrome (AAS) and worsens the postoperative prognosis. Our aim was to establish a machine learning prediction model for ARF occurrence in AAS patients.MethodsWe included AAS patient data from nine medical centers (n = 1,637) and analyzed the incidence of ARF and the risk factors for postoperative ARF. We used data from six medical centers to compare the performance of four machine learning models and performed internal validation to identify AAS patients who developed postoperative ARF. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve was used to compare the performance of the predictive models. We compared the performance of the optimal machine learning prediction model with that of traditional prediction models. Data from three medical centers were used for external validation.ResultsThe eXtreme Gradient Boosting (XGBoost) algorithm performed best in the internal validation process (AUC = 0.82), which was better than both the logistic regression (LR) prediction model (AUC = 0.77, p < 0.001) and the traditional scoring systems. Upon external validation, the XGBoost prediction model (AUC =0.81) also performed better than both the LR prediction model (AUC = 0.75, p = 0.03) and the traditional scoring systems. We created an online application based on the XGBoost prediction model.ConclusionsWe have developed a machine learning model that has better predictive performance than traditional LR prediction models as well as other existing risk scoring systems for postoperative ARF. This model can be utilized to provide early warnings when high-risk patients are found, enabling clinicians to take prompt measures.

Development of a radiomics model to diagnose pheochromocytoma preoperatively: a multicenter study with prospective validation

Background Preoperative diagnosis of pheochromocytoma (PHEO) accurately impacts preoperative preparation and surgical outcome in PHEO patients. Highly reliable model to diagnose PHEO is lacking. We aimed to develop a magnetic resonance imaging (MRI)-based radiomic-clinical model to distinguish PHEO from adrenal lesions. Methods In total, 305 patients with 309 adrenal lesions were included and divided into different sets. The least absolute shrinkage and selection operator (LASSO) regression model was used for data dimension reduction, feature selection, and radiomics signature building. In addition, a nomogram incorporating the obtained radiomics signature and selected clinical predictors was developed by using multivariable logistic regression analysis. The performance of the radiomic-clinical model was assessed with respect to its discrimination, calibration, and clinical usefulness. Results Seven radiomics features were selected among the 1301 features obtained as they could differentiate PHEOs from other adrenal lesions in the training (area under the curve [AUC], 0.887), internal validation (AUC, 0.880), and external validation cohorts (AUC, 0.807). Predictors contained in the individualized prediction nomogram included the radiomics signature and symptom number (symptoms include headache, palpitation, and diaphoresis). The training set yielded an AUC of 0.893 for the nomogram, which was confirmed in the internal and external validation sets with AUCs of 0.906 and 0.844, respectively. Decision curve analyses indicated the nomogram was clinically useful. In addition, 25 patients with 25 lesions were recruited for prospective validation, which yielded an AUC of 0.917 for the nomogram. Conclusion We propose a radiomic-based nomogram incorporating clinically useful signatures as an easy-to-use, predictive and individualized tool for PHEO diagnosis.

Discontinuation of Azathioprine could be considered in pediatric patients with Crohn’s disease who have sustained clinical and deep remission

Few studies have demonstrated treatment strategies about the duration and cessation of medications in patients with Crohn’s disease (CD). We investigated factors affecting clinical relapse after infliximab (IFX) or azathioprine (AZA) withdrawal in pediatric patients with CD on combination therapy. Pediatric patients with moderate-to-severe CD receiving combination therapy were analyzed retrospectively and factors associated with clinical relapse were investigated. Discontinuation of IFX or AZA was performed in patients who sustained clinical remission (CR) for at least two years and achieved deep remission. A total of 75 patients were included. Forty-four patients (58.7%) continued with combination therapy and 31 patients (41.3%) discontinued AZA or IFX (AZA withdrawal 10, IFX withdrawal 15, both withdrawal 6). Cox proportional-hazards regression and statistical internal validation identified three factors associated with clinical relapse: IFX cessation (hazard ratio; HR 2.982, P = 0.0081), IFX TLs during maintenance therapy (HR 0.581, P = 0.003), 6-thioguanine nucleotide (6-TGN) level (HR 0.978, P < 0.001). However, AZA cessation was not associated with clinical relapse (P = 0.9021). Even when applied in pediatric patients who met stringent criteria, IFX cessation increased the relapse risk. However, withdrawal of AZA could be contemplated in pediatric patients with CD who have sustained CR for at least 2 years and achieved deep remission.

The Diagnostic Value of the CA19-9 and Bilirubin Ratio in Patients with Pancreatic Cancer, Distal Bile Duct Cancer and Benign Periampullary Diseases, a Novel Approach

Distinction of pancreatic ductal adenocarcinoma (PDAC) in the head of the pancreas, distal cholangiocarcinoma (dCCA), and benign periampullary conditions, is complex as they often share similar clinical symptoms. However, these diseases require specific management strategies, urging improvement of non-invasive tools for accurate diagnosis. Recent evidence has shown that the ratio between CA19-9 and bilirubin levels supports diagnostic distinction of benign or malignant hepatopancreaticobiliary diseases. Here, we investigate the diagnostic value of this ratio in PDAC, dCCA and benign diseases of the periampullary region in a novel fashion. To address this aim, we enrolled 265 patients with hepatopancreaticobiliary diseases and constructed four logistic regression models on a subset of patients (n = 232) based on CA19-9, bilirubin and the ratio of both values: CA19-9/(bilirubin−1). Non-linearity was investigated using restricted cubic splines and a final model, the ‘Model Ratio’, based on these three variables was fitted using multivariable fractional polynomials. The performance of this model was consistently superior in terms of discrimination and calibration compared to models based on CA19-9 combined with bilirubin and CA19-9 or bilirubin alone. The ‘Model Ratio’ accurately distinguished between malignant and benign disease (AUC [95% CI], 0.91 [0.86–0.95]), PDAC and benign disease (AUC 0.91 [0.87–0.96]) and PDAC and dCCA (AUC 0.83 [0.74–0.92]) which was confirmed by internal validation using 1000 bootstrap replicates. These findings provide a foundation to improve minimally-invasive diagnostic procedures, ultimately ameliorating effective therapy for PDAC and dCCA.

Impacts of COVID-19 on Electric Vehicle Charging Behavior: Data Analytics, Visualization, and Clustering

COVID-19 pandemic has infected millions and led to a catastrophic loss of lives globally. It has also significantly disrupted the movement of people, businesses, and industries. Additionally, electric vehicle (EV) users have faced challenges in charging their vehicles in public charging locations where there is a risk of COVID-19 exposure. However, a case study of EV charging behavior and its impacts during the SARS-CoV-2 is not addressed in the existing literature. This paper investigates the impacts of COVID-19 on EV charging behavior by analyzing the charging activity during the pandemic using a dataset from a public charging facility in the USA. Data visualization of charging behavior alongside significant timelines of the pandemic was utilized for analysis. Moreover, a cluster analysis using k-means, hierarchical clustering, and Gaussian mixture models was performed to identify common groups of charging behavior based on the vehicle arrival and departure times. Although the number of vehicles using the charging station was reduced significantly due to lockdown restrictions, the charging activity started to pick up again since May 2021 due to an increase in vaccination and easing of public restrictions. However, the charging activity currently still remains around half of the activity pre-pandemic. A noticeable decline in charging session length and an increase in energy consumption can be observed as well. Clustering algorithms identified three groups of charging behavior during the pandemic and their analysis and performance comparison using internal validation measures were also presented.

A Prediction Model for Falls in Community-Dwelling Older Adults in Podiatry Practices

<b><i>Introduction:</i></b> Falls are a worldwide health problem among community-dwelling older adults. Emerging evidence suggests that foot problems increase the risk of falling, so the podiatrist may be crucial in detecting foot-related fall risk. However, there is no screening tool available which can be used in podiatry practice. The predictive value of existing tools is limited, and the implementation is poor. The development of risk models for specific clinical populations might increase the prediction accuracy and implementation. Therefore, the aim of this study was to develop and internally validate an easily applicable clinical prediction model (CPM) that can be used in podiatry practice to predict falls in community-dwelling older adults with foot (-related) problems. <b><i>Methods:</i></b> This was a prospective study including community-dwelling older adults (≥65 years) visiting podiatry practices. General fall-risk variables, and foot-related and function-related variables were considered as predictors for the occurrence of falls during the 12-month follow-up. Logistic regression analysis was used for model building, and internal validation was done by bootstrap resampling. <b><i>Results:</i></b> 407 participants were analyzed; the event rate was 33.4%. The final model included fall history in the previous year, unsteady while standing and walking, plantarflexor strength of the lesser toes, and gait speed. The area under the receiver operating characteristic curve was 0.71 (95% CI: 0.66–0.76) in the sample and estimated as 0.65 after shrinkage. <b><i>Conclusion:</i></b> A CPM based on fall history in the previous year, feeling unsteady while standing and walking, decreased plantarflexor strength of the lesser toes, and reduced gait speed has acceptable accuracy to predict falls in our sample of podiatry community-dwelling older adults and is easily applicable in this setting. The accuracy of the model in clinical practice should be demonstrated through external validation of the model in a next study.

Longitudinal Prediction of Freezing of Gait in Parkinson's Disease: A Prospective Cohort Study

Objective: Freezing of gait (FOG) is a disabling complication in Parkinson's disease (PD). Yet, studies on a validated model for the onset of FOG based on longitudinal observation are absent. This study aims to develop a risk prediction model to predict the probability of future onset of FOG from a multicenter cohort of Chinese patients with PD.Methods: A total of 350 patients with PD without FOG were prospectively monitored for ~2 years. Demographic and clinical data were investigated. The multivariable logistic regression analysis was conducted to develop a risk prediction model for FOG.Results: Overall, FOG was observed in 132 patients (37.70%) during the study period. At baseline, longer disease duration [odds ratio (OR) = 1.214, p = 0.008], higher total levodopa equivalent daily dose (LEDD) (OR = 1.440, p &lt; 0.001), and higher severity of depressive symptoms (OR = 1.907, p = 0.028) were the strongest predictors of future onset of FOG in the final multivariable model. The model performed well in the development dataset (with a C-statistic = 0.820, 95% CI: 0.771–0.865), showed acceptable discrimination and calibration in internal validation, and remained stable in 5-fold cross-validation.Conclusion: A new prediction model that quantifies the risk of future onset of FOG has been developed. It is based on clinical variables that are readily available in clinical practice and could serve as a small tool for risk counseling.

Survey of Opioid-Induced Respiratory Depression in Critically Ill Patients Without Mechanical Ventilation and Construction of a Risk Nomogram

Objectives To investigate the current status of opioid-induced respiratory depression (OIRD) and potential risk factors in critically ill patients without mechanical ventilation in the intensive care unit (ICU) and to construct a risk nomogram to predict OIRD. Methods A total of 103 patients without (or who were weaned from) mechanical ventilation who had stayed for more than 24 h in the ICU between June 1, 2021 and September 31, 2021, were included. Patient data, including respiratory depression events, were recorded. The least absolute shrinkage and selection operator regression model were used to select features that were then used to construct a prediction model by multivariate logistic regression analysis. A nomogram was established for the risk of respiratory depression events in patients without mechanical ventilation. The discriminatory performance and calibration of the nomogram were assessed with Harrell’s concordance index and a calibration plot, respectively, and a bootstrap procedure was used for internal validation. Results Respiratory depression was diagnosed in 49/103 (47.6%) patients. Factors included in the nomogram were cardiopulmonary disease (odds ratio [OR]=5.569, 95% confidence interval [CI]=0.751–118.083), respiratory disease (OR=32.833, 95% CI=4.189–725.164), sepsis (OR=6.898, 95% CI=1.756–33.000), duration of mechanical ventilation (OR=3.019, 95% CI=0.862–11.322), lack of mechanical ventilation (OR=20.757, 95% CI=2.409–502.222), and oxygenation index (OR=7.350, 95% CI=2.483–24.286). The nomogram showed good performance for predicting respiratory depression events in critically ill patients without mechanical ventilation. Conclusion The nomogram can be used to identify ICU patients without mechanical ventilation who are at risk of opioid-induced respiratory depression and may therefore benefit from early intervention.

Development and internal validation of a clinical prediction model for acute adjacent vertebral fracture after vertebral augmentation

Aims To develop and internally validate a preoperative clinical prediction model for acute adjacent vertebral fracture (AVF) after vertebral augmentation to support preoperative decision-making, named the after vertebral augmentation (AVA) score. Methods In this prognostic study, a multicentre, retrospective single-level vertebral augmentation cohort of 377 patients from six Japanese hospitals was used to derive an AVF prediction model. Backward stepwise selection (p < 0.05) was used to select preoperative clinical and imaging predictors for acute AVF after vertebral augmentation for up to one month, from 14 predictors. We assigned a score to each selected variable based on the regression coefficient and developed the AVA scoring system. We evaluated sensitivity and specificity for each cut-off, area under the curve (AUC), and calibration as diagnostic performance. Internal validation was conducted using bootstrapping to correct the optimism. Results Of the 377 patients used for model derivation, 58 (15%) had an acute AVF postoperatively. The following preoperative measures on multivariable analysis were summarized in the five-point AVA score: intravertebral instability (≥ 5 mm), focal kyphosis (≥ 10°), duration of symptoms (≥ 30 days), intravertebral cleft, and previous history of vertebral fracture. Internal validation showed a mean optimism of 0.019 with a corrected AUC of 0.77. A cut-off of ≤ one point was chosen to classify a low risk of AVF, for which only four of 137 patients (3%) had AVF with 92.5% sensitivity and 45.6% specificity. A cut-off of ≥ four points was chosen to classify a high risk of AVF, for which 22 of 38 (58%) had AVF with 41.5% sensitivity and 94.5% specificity. Conclusion In this study, the AVA score was found to be a simple preoperative method for the identification of patients at low and high risk of postoperative acute AVF. This model could be applied to individual patients and could aid in the decision-making before vertebral augmentation. Cite this article: Bone Joint J 2022;104-B(1):97–102.