Validation Set Research Articles

Entropy generation analysis of microrotating Casson’s nanofluid with Darcy–Forchheimer porous media using a neural computing based on Levenberg–Marquardt algorithm

Purpose The purpose of this paper is to showcase the utilization of the magnetohydrodynamics-microrotating Casson’s nanofluid flow model (MHD-MRCNFM) in examining the impact of an inclined magnetic field within a porous medium on a nonlinear stretching plate. This investigation is conducted by using neural networking techniques, specifically using neural networks-backpropagated with the Levenberg–Marquardt scheme (NN-BLMS). Design/methodology/approach The initial nonlinear coupled PDEs system that represented the MRCNFM is transformed into an analogous nonlinear ODEs system by the adoption of similarity variables. The reference data set is created by varying important MHD-MRCNFM parameters using the renowned Lobatto IIIA solver. The numerical reference data are used in validation, testing and training sets to locate and analyze the estimated outcome of the created NN-LMA and its comparison with the corresponding reference solution. With mean squared error curves, error histogram analysis and a regression index, better performance is consistently demonstrated. Mu is a controller that controls the complete training process, and the NN-BLMS mainly concentrates on the higher precision of nonlinear systems. Findings The peculiar behavior of the appropriate physical parameters on nondimensional shapes is demonstrated and explored via sketches and tables. For escalating amounts of inclination angle and Brinkman number, a viable entropy profile is accomplished. The angular velocity curve grows as the rotation viscosity and surface condition factors rise. The dominance of friction-induced irreversibility is observed in the vicinity of the sheet, whereas in the farthest region, the situation is reversed with heat transfer playing a more significant role in causing irreversibilities. Originality/value To improve the efficiency of any thermodynamic system, it is essential to identify and track the sources of irreversible heat losses. Therefore, the authors analyze both flow phenomena and heat transport, with a particular focus on evaluating the generation of entropy within the system.

Keratoconus Progression Determined at the First Visit: A Deep Learning Approach With Fusion of Imaging and Numerical Clinical Data.

Multiple clinical visits are necessary to determine progression of keratoconus before offering corneal cross-linking. The purpose of this study was to develop a neural network that can potentially predict progression during the initial visit using tomography images and other clinical risk factors. The neural network's development depended on data from 570 keratoconus eyes. During the initial visit, numerical risk factors and posterior elevation maps from Scheimpflug imaging were collected. Increase of steepest keratometry of 1 diopter during follow-up was used as the progression criterion. The data were partitioned into training, validation, and test sets. The first two were used for training, and the latter for performance statistics. The impact of individual risk factors and images was assessed using ablation studies and class activation maps. The most accurate prediction of progression during the initial visit was obtained by using a combination of MobileNet and a multilayer perceptron with an accuracy of 0.83. Using numerical risk factors alone resulted in an accuracy of 0.82. The use of only images had an accuracy of 0.77. The most influential risk factors in the ablation study were age and posterior elevation. The greatest activation in the class activation maps was seen at the highest posterior elevation where there was significant deviation from the best fit sphere. The neural network has exhibited good performance in predicting potential future progression during the initial visit. The developed neural network could be of clinical significance for keratoconus patients by identifying individuals at risk of progression.

Development and external validation of a multidimensional deep learning model to dynamically predict kidney outcomes in IgA nephropathy.

Accurately predicting kidney outcomes in IgA nephropathy is crucial for clinical decision making. Insufficient use of longitudinal data in previous studies has limited the accuracy and interpretability of prediction models for failing to reflect the chronic nature of IgA nephropathy. This study aimed at establishing a multivariable dynamic deep learning model using comprehensive longitudinal data for the prediction of kidney outcomes in IgA nephropathy. In this retrospective cohort study of 2,056 IgA nephropathy patients at 18 kidney centers, a total of 28,317 data points were collected by the sliding window method. Among them, 15,462 windows in a single center were randomly assigned to training (80%) and validation (20%) sets while 8797 windows in 18 kidney centers were assigned to an independently test set. Interpretable Multi-Variable Long Short-Term Memory (IMV-LSTM), a deep learning model, was implemented to predict kidney outcomes (kidney failure or 50% decline in kidney function) based on time-invariant variables measured at biopsy and time-variant variables measured during follow-up. Risk performance was evaluated using Kaplan-Meier analysis and the C statistic. Trajectory analysis was performed to assess the various trends of clinical variables during follow-up. The model achieved a higher C statistic (0.93; 95% CI, 0.92-0.95) on the test set than the XGBoost prediction model that we developed in a previous study using only baseline information (C statistic, 0.84; 95% CI, 0.80-0.88). Kaplan-Meier analysis showed that groups with lower predicted risks from the full model survived longer than groups with higher risks. Time-variant variables demonstrated higher importance scores than time-invariant variables. Within time-variant variables, more recent measurements showed higher importance scores. Further interpretation showed that certain trajectory groups of time-variant variables such as serum creatinine and urine protein were associated with elevated risks of adverse outcomes. In IgA nephropathy, a deep learning model can be used to accurately and dynamically predict kidney prognosis based on longitudinal data, and time-variant variables show strong ability to predict kidney outcome.

Analysis and Forecasting of Energy Data and GDP Based on Pearson Correlation Analysis-Random Forest Algorithm

The relationship between energy data and GDP is an important economic issue because energy is the foundation that supports modern economic development. This paper examines the relationship between energy data and GDP and uses Pearson correlation analysis to calculate the relationship between each variable in energy data and annual GDP for 52 regions. The results show that total electricity consumption is the factor with the highest degree of influence on GDP, followed by natural gas consumption, biomass consumption, hydroelectricity consumption, LPG consumption and geothermal energy consumption. This indicates that there is an extremely strong correlation between local energy data and GDP. To further explore this correlation, this paper attempts to predict the GDP of the locality based on the local energy data using a machine learning approach.The Random Forest algorithm is chosen as the machine learning model, and the training, validation and test sets are divided according to the ratio of 6:2:2. By using MSE, RMSE, MAE, MAPE and R to evaluate the model, it is found that the random forest machine learning algorithm can predict the local GDP well.The predicted value of GDP and the actual value of GDP are very close to each other, meanwhile, the value of MSE is 62.779.These findings show that the local energy data are closely related to economic development. The impact of energy factors on the economy should be taken into account when formulating economic policies. In addition, machine learning algorithms can provide strong support for economic forecasting and provide more accurate information for decision makers.

Development and Validation of an Automated, Real-Time Predictive Model for Postpartum Hemorrhage

OBJECTIVE: To develop and validate a predictive model for postpartum hemorrhage that can be deployed in clinical care using automated, real-time electronic health record (EHR) data and to compare performance of the model with a nationally published risk prediction tool. METHODS: A multivariable logistic regression model was developed from retrospective EHR data from 21,108 patients delivering at a quaternary medical center between January 1, 2018, and April 30, 2022. Deliveries were divided into derivation and validation sets based on an 80/20 split by date of delivery. Postpartum hemorrhage was defined as blood loss of 1,000 mL or more in addition to postpartum transfusion of 1 or more units of packed red blood cells. Model performance was evaluated by the area under the receiver operating characteristic curve (AUC) and was compared with a postpartum hemorrhage risk assessment tool published by the CMQCC (California Maternal Quality Care Collaborative). The model was then programmed into the EHR and again validated with prospectively collected data from 928 patients between November 7, 2023, and January 31, 2024. RESULTS: Postpartum hemorrhage occurred in 235 of 16,862 patients (1.4%) in the derivation cohort. The predictive model included 21 risk factors and demonstrated an AUC of 0.81 (95% CI, 0.79–0.84) and calibration slope of 1.0 (Brier score 0.013). During external temporal validation, the model maintained discrimination (AUC 0.80, 95% CI, 0.72–0.84) and calibration (calibration slope 0.95, Brier score 0.014). This was superior to the CMQCC tool (AUC 0.69 [95% CI, 0.67–0.70], P<.001). The model maintained performance in prospective, automated data collected with the predictive model in real time (AUC 0.82 [95% CI, 0.73–0.91]). CONCLUSION: We created and temporally validated a postpartum hemorrhage prediction model, demonstrated its superior performance over a commonly used risk prediction tool, successfully coded the model into the EHR, and prospectively validated the model using risk factor data collected in real time. Future work should evaluate external generalizability and effects on patient outcomes; to facilitate this work, we have included the model coefficients and examples of EHR integration in the article.

A nomogram for predicting pathologic node negativity after neoadjuvant chemotherapy in breast cancer patients: a nationwide, multicenter retrospective cohort study (CSBrS-012)

PurposeThis study aimed to investigate the factors associated with pathologic node-negativity (ypN0) in patients who received neoadjuvant chemotherapy (NAC) to develop and validate an accurate prediction nomogram.MethodsThe CSBrS-012 study (2010–2020) included female patients with primary breast cancer treated with NAC followed by breast and axillary surgery in 20 hospitals across China. In the present study, 7,711 eligible patients were included, comprising 6,428 patients in the primary cohort from 15 hospitals and 1,283 patients in the external validation cohort from five hospitals. The hospitals were randomly assigned. The primary cohort was randomized at a 3:1 ratio and divided into a training set and an internal validation set. Univariate and multivariate logistic regression analyses were performed on the training set, after which a nomogram was constructed and validated both internally and externally.ResultsIn total, 3,560 patients (46.2%) achieved ypN0, and 1,558 patients (20.3%) achieved pathologic complete response in the breast (bpCR). A nomogram was constructed based on the clinical nodal stage before NAC (cN), ER, PR, HER2, Ki67, NAC treatment cycle, and bpCR, which were independently associated with ypN0. The area under the receiver operating characteristic curve (AUC) for the training set was 0.80. The internal and external validation demonstrated good discrimination, with AUCs of 0.79 and 0.76, respectively.ConclusionWe present a real-world study based on nationwide large-sample data that can be used to effectively screen for ypN0 to provide better advice for the management of residual axillary disease in breast cancer patients undergoing NAC.

“Image-Spectral” fusion monitoring of small cotton samples nitrogen content based on improved deep forest

Accurate monitoring of nitrogen nutrition is crucial for improving cotton yield and quality, as well as the ecological environment. The mainstream method for monitoring nutrition is to establish traditional machine learning (ML) models using a single data source. However, this approach has limitations such as limited access to feature information, model-fitting problems, and limited generalization. Deep learning (DL), on the other hand, has shown promise in complex nonlinear modeling tasks due to its flexible structure. However, it has its limitations, such as the fact that agronomic sample collection and testing are usually labor- and material-intensive, resulting in sample sizes that are too small to meet its training conditions. Therefore, there is an urgent need for DL models that can effectively integrate features from multiple data sources and accurately monitor crop nitrogen content, especially in scenarios with small samples. In this study, we conducted indoor pot experiments using the cotton variety Xinluzao 53 and subjected it to six nitrogen treatments. The data sources for our analysis included hyperspectral and digital images of the cotton leaves. To enhance representation learning capabilities, we enriched the multi-class base learners within each layer of the deep forest (DF) model and introduced skip connections. These enhancements improved the quality of inversion for both hyperspectral and digital image datasets. We then developed image-spectral fusion models, which combined the DF structure with stacking ensemble learning. Our focus was on three levels of fusion: feature-level fusion, decision-level fusion, and secondary decision-level fusion. This approach aimed to further enhance the accuracy and stability of nitrogen content inversion. The DF model satisfied the training condition for small samples. Compared to traditional ML algorithms and the original DF algorithm, the improved DF model achieved an increase in validation set R2 of 13.4–28.5% and 10.9–14.9%, respectively. These findings highlight the enhanced accuracy and stability of the improved DF model. Additionally, compared to the optimal inversion model using two single data sources, the “Image-Spectral” three-level fusion models exhibited improvements in validation set R2 of 8.6–9.3%, 10.5–11.2%, and 11.8–12.5% for feature-level, decision-level, and secondary decision-level fusion, respectively. The improved DF and three-level fusion model collectively contributed to the increased accuracy of cotton nitrogen content inversion. Among these models, the secondary decision-level fusion model demonstrated the most marked improvement. This methodology provides valuable insights into monitoring crop phenotypic parameters in situations with limited sample sizes.

Machine learning-based prediction models affecting the recovery of postoperative bowel function for patients undergoing colorectal surgeries

PurposeThe debate surrounding factors influencing postoperative flatus and defecation in patients undergoing colorectal resection prompted this study. Our objective was to identify independent risk factors and develop prediction models for postoperative bowel function in patients undergoing colorectal surgeries.MethodsA retrospective analysis of medical records was conducted for patients who undergoing colorectal surgeries at Peking University People’s Hospital from January 2015 to October 2021. Machine learning algorithms were employed to identify risk factors and construct prediction models for the time of the first postoperative flatus and defecation. The prediction models were evaluated using sensitivity, specificity, the Youden index, and the area under the receiver operating characteristic curve (AUC) through logistic regression, random forest, Naïve Bayes, and extreme gradient boosting algorithms.ResultsThe study included 1358 patients for postoperative flatus timing analysis and 1430 patients for postoperative defecation timing analysis between January 2015 and December 2020 as part of the training phase. Additionally, a validation set comprised 200 patients who undergoing colorectal surgeries from January to October 2021. The logistic regression prediction model exhibited the highest AUC (0.78) for predicting the timing of the first postoperative flatus. Identified independent risk factors influencing the time of first postoperative flatus were Age (p < 0.01), oral laxatives for bowel preparation (p = 0.01), probiotics (p = 0.02), oral antibiotics for bowel preparation (p = 0.02), duration of operation (p = 0.02), postoperative fortified antibiotics (p = 0.02), and time of first postoperative feeding (p < 0.01). Furthermore, logistic regression achieved an AUC of 0.72 for predicting the time of first postoperative defecation, with age (p < 0.01), oral antibiotics for bowel preparation (p = 0.01), probiotics (p = 0.01), and time of first postoperative feeding (p < 0.01) identified as independent risk factors.ConclusionsThe study suggests that he use of probiotics and early recovery of diet may enhance the recovery of bowel function in patients undergoing colorectal surgeries. Among the various analytical methods used, logistic regression emerged as the most effective approach for predicting the timing of the first postoperative flatus and defecation in this patient population.

A Nomogram Prediction Model for Persistent Pulmonary Hypertension of the Newborn in Neonates Hospitalized for the First Time After Birth.

Persistent pulmonary hypertension of the newborn (PPHN) is one of the critical neonatal diseases associated with high morbidity and mortality. This study attempted to conduct a nomogram prediction model for performing early identification of PPHN and providing effective information for clinical practice. A total of 456 newborns who first admitted to the hospital after birth were included in the analysis, including 138 newborns with PPHN and 318 newborns without PPHN (as controls). The optimal predictive variables selection was performed based on LASSO (least absolute shrinkage and selection operator) regression and multivariate logistic regression. Using the selected variables, a nomogram prediction model was developed. To validate the model, the model was assessed using the receiver operating characteristic curve, calibration plot, and clinical impact curve. Six predictors, namely, gestational age, neonatal respiratory distress syndrome, the levels of hemoglobin and creatine kinase-MB, gestational thyroid dysfunction, and Pao2, were identified by LASSO and multivariate logistic regression analysis from the original 30 variables studied. The constructed model, using these predictors, exhibited favorable predictive ability for PPHN, with an area under the receiver operating characteristic of 0.897 (sensitivity = 0.876, specificity = 0.785) in the training set and 0.871 (sensitivity = 0.902, specificity = 0.695) in the validation set, and was well calibrated, as indicated by the PHosmer-Lemeshow test values of 0.233 and 0.876 for the training and validation sets, respectively. The model included gestational age, neonatal respiratory distress syndrome, the levels of hemoglobin and creatine kinase-MB, gestational thyroid dysfunction, and Pao2 had good prediction performance for predicting PPHN among newborns first admitted to the hospital after birth.

Deep learning-based detection of irreversible pulpitis in primary molars.

Changes in healthy and inflamed pulp on periapical radiographs are traditionally so subtle that they may be imperceptible to human experts, limiting its potential use as an adjunct clinical diagnostic feature. This study aimed to investigate the feasibility of an image-analysis technique based on the convolutional neural network (CNN) to detect irreversible pulpitis in primary molars on periapical radiographs (PRs). This retrospective study was performed in two health centres. Patients who received indirect pulp therapy at Peking University Hospital for Stomatology were retrospectively identified and randomly divided into training and validation sets (8:2). Using PRs as input to an EfficientNet CNN, the model was trained to categorise cases into either the success or failure group and externally tested on patients who presented to our affiliate institution. Model performance was evaluated using sensitivity, specificity, accuracy and F1 score. A total of 348 PRs with deep caries were enrolled from the two centres. The deep learning model achieved the highest accuracy of 0.90 (95% confidence interval: 0.79-0.96) in the internal validation set, with an overall accuracy of 0.85 in the external test set. The mean greyscale value was higher in the failure group than in the success group (p = .013). The deep learning-based model could detect irreversible pulpitis in primary molars with deep caries on PRs. Moreover, this study provides a convenient and complementary method for assessing pulp status.

Development and validation of a predictive model for the risk of sarcopenia in the older adults in China

BackgroundSarcopenia is a progressive age-related disease that can cause a range of adverse health outcomes in older adults, and older adults with severe sarcopenia are also at increased short-term mortality risk. The aim of this study was to construct and validate a risk prediction model for sarcopenia in Chinese older adults.MethodsThis study used data from the 2015 China Health and Retirement Longitudinal Study (CHARLS), a high-quality micro-level data representative of households and individuals aged 45 years and older adults in China. The study analyzed 65 indicators, including sociodemographic indicators, health-related indicators, and biochemical indicators.Results3454 older adults enrolled in the CHARLS database in 2015 were included in the final analysis. A total of 997 (28.8%) had phenotypes of sarcopenia. Multivariate logistic regression analysis showed that sex, Body Mass Index (BMI), Mean Systolic Blood Pressure (MSBP), Mean Diastolic Blood Pressure (MDBP) and pain were predictive factors for sarcopenia in older adults. These factors were used to construct a nomogram model, which showed good consistency and accuracy. The AUC value of the prediction model in the training set was 0.77 (95% CI = 0.75–0.79); the AUC value in the validation set was 0.76 (95% CI = 0.73–0.79). Hosmer–Lemeshow test values were P = 0.5041 and P = 0.2668 (both P > 0.05). Calibration curves showed significant agreement between the nomogram model and actual observations. ROC and DCA showed that the nomograms had good predictive properties.ConclusionsThe constructed sarcopenia risk prediction model, incorporating factors such as sex, BMI, MSBP, MDBP, and pain, demonstrates promising predictive capabilities. This model offers valuable insights for clinical practitioners, aiding in early screening and targeted interventions for sarcopenia in Chinese older adults.

Adaptation of state-of-the-art neural network architectures to interference fringe reduction in absorption spectroscopy

State-of-the-art neural network architectures in image classification and natural language processing were applied to interference fringe reduction in absorption spectroscopy by interpreting the data structure accordingly. A model was designed for temporal interpolation of background spectra and a different model was created for gas concentration fitting. The networks were trained on experimental data provided by a wavelength modulation spectroscopy instrument and the best performing architectures were analyzed further to evaluate generalization performance, robustness and transferability. A BERT-styled fitter achieved the best performance on the validation set and reduced the mean squared error of fitted amplitude by 99.5%. However, analysis of the de-noising behavior showed large biases. A U-Net styled convolutional neural network reduced the mean squared error of the interpolation by 93.2%. Evaluation on a test set provided evidence that the combination of model interpolation and linear fitting was robust and the detection limit was improved by 52.4%. Transferring the trained interpolator model to a different spectrometer setup showed no chaotic out-of-distribution effects. Additional fine-tuning further increased the performance. Neural network architectures cannot be generally applied to all absorption spectroscopy tasks. However, given the right task and the data representation, robust performance increase is achievable.

A voltammetric method coupled with chemometrics for determination of a ternary antiparkinson mixture in its dosage form: greenness assessment

An electroanalytical methodology was developed by direct differential pulse voltammetric (DPV) measurement of Levodopa (LD), Carbidopa (CD) and Entacapone (ENT) mixture using bare glassy carbon electrode (GCE) in Britton Robinson (BR) buffer (pH = 2.0). A multivariate calibration model was then applied to the exported preprocessed voltammetric data using partial least square (PLS) as a chemometric tool. Additionally, the model was cross-validated and the number of latent variables (LVs) were determined to produce a reliable model for simultaneous quantitation of the three drugs either in their synthetic mixtures or in their marketed pharmaceutical formulation with high accuracy and precision. Data preprocessing was used to tackle the problem of lacking bi-linearity which is commonly found in electrochemical data. The proposed chemometric model was able to provide fast and reliable technique for quantitative determination of antiparkinson drugs in their dosage forms. This was successfully achieved by utilizing sixteen mixtures as calibration set and nine mixtures as validation set. The percent recoveries for LD, CD and ENT were found to be 100.05% ± 1.28%, 100.04% ± 0.53% and 99.99% ± 1.25%, respectively. The obtained results of the proposed method were statistically compared to those of a previously reported High Performance Liquid Chromatography (HPLC) methodology. Finally, the presented analytical method strongly supports green analytical chemistry regarding the minimization of potentially dangerous chemicals and solvents, as well as reducing energy utilization and waste generation.

MRI-based deep learning and radiomics for prediction of occult cervical lymph node metastasis and prognosis in early-stage oral and oropharyngeal squamous cell carcinoma: a diagnostic study.

The incidence of occult cervical lymph node metastases (OCLNM) is reported to be 20%-30% in early-stage oral cancer and oropharyngeal cancer. There is a lack of an accurate diagnostic method to predict occult lymph node metastasis and to help surgeons make precise treatment decisions. To construct and evaluate a preoperative diagnostic method to predict occult lymph node metastasis (OCLNM) in early-stage oral and oropharyngeal squamous cell carcinoma (OC and OP SCC) based on deep learning features (DLFs) and radiomics features. A total of 319 patients diagnosed with early-stage OC or OP SCC were retrospectively enrolled and divided into training, test and external validation sets. Traditional radiomics features and DLFs were extracted from their MRI images. The least absolute shrinkage and selection operator (LASSO) analysis was employed to identify the most valuable features. Prediction models for OCLNM were developed using radiomics features and DLFs. The effectiveness of the models and their clinical applicability were evaluated using the area under the curve (AUC), decision curve analysis (DCA) and survival analysis. Seventeen prediction models were constructed. The Resnet50 deep learning (DL) model based on the combination of radiomics and DL features achieves the optimal performance, with AUC values of 0.928 (95% CI: 0.881-0.975), 0.878 (95% CI: 0.766-0.990), 0.796 (95% CI: 0.666-0.927) and 0.834 (95% CI: 0.721-0.947) in the training, test, external validation set1 and external validation set2, respectively. Moreover, the Resnet50 model has great prediction value of prognosis in patients with early-stage OC and OP SCC. The proposed MRI-based Resnet50 deep learning model demonstrated high capability in diagnosis of OCLNM and prognosis prediction in the early-stage OC and OP SCC. The Resnet50 model could help refine the clinical diagnosis and treatment of the early-stage OC and OP SCC.

DCGAN-DTA: Predicting drug-target binding affinity with deep convolutional generative adversarial networks

BackgroundIn recent years, there has been a growing interest in utilizing computational approaches to predict drug-target binding affinity, aiming to expedite the early drug discovery process. To address the limitations of experimental methods, such as cost and time, several machine learning-based techniques have been developed. However, these methods encounter certain challenges, including the limited availability of training data, reliance on human intervention for feature selection and engineering, and a lack of validation approaches for robust evaluation in real-life applications.ResultsTo mitigate these limitations, in this study, we propose a method for drug-target binding affinity prediction based on deep convolutional generative adversarial networks. Additionally, we conducted a series of validation experiments and implemented adversarial control experiments using straw models. These experiments serve to demonstrate the robustness and efficacy of our predictive models. We conducted a comprehensive evaluation of our method by comparing it to baselines and state-of-the-art methods. Two recently updated datasets, namely the BindingDB and PDBBind, were used for this purpose. Our findings indicate that our method outperforms the alternative methods in terms of three performance measures when using warm-start data splitting settings. Moreover, when considering physiochemical-based cold-start data splitting settings, our method demonstrates superior predictive performance, particularly in terms of the concordance index.ConclusionThe results of our study affirm the practical value of our method and its superiority over alternative approaches in predicting drug-target binding affinity across multiple validation sets. This highlights the potential of our approach in accelerating drug repurposing efforts, facilitating novel drug discovery, and ultimately enhancing disease treatment. The data and source code for this study were deposited in the GitHub repository, https://github.com/mojtabaze7/DCGAN-DTA. Furthermore, the web server for our method is accessible at https://dcgan.shinyapps.io/bindingaffinity/.

Predictive Models for Suicide Attempts in Major Depressive Disorder and the Contribution of EPHX2: A Pilot Integrative Machine Learning Study

Suicide is a major public health problem caused by a complex interaction of various factors. Major depressive disorder (MDD) is the most prevalent psychiatric disorder associated with suicide; therefore, it is essential to prioritize suicide prediction and prevention within this population. Integrated information from different dimensions, including personality, cognitive function, and social and genetic factors, is necessary to improve the performance of predictive models. Besides, recent studies have indicated the critical roles for EPHX2/P2X2 in the pathophysiology of MDD. Our previous studies found an association of EPHX2 and P2X2 with suicide in MDD. This study is aimed at (1) establishing predictive models with integrated information to distinguish MDD from healthy volunteers, (2) estimating the suicide risk of MDD, and (3) determining the contribution of EPHX2/P2X2. This cross-sectional study was conducted on 472 prospectively collected participants. The machine learning (ML) technique using Extreme Gradient Boosting (XGBoost) classifier was employed to evaluate the performance and relative importance of the extracted characteristics in recognising patients with MDD and depressed suicide attempters (DSA). In independent validation set, the model with clinical and cognitive information could recognise MDD with an area under the receiver operating characteristic curve (AUC) of 0.938 (95% confidence interval (CI), 0.898–0.977), and genetic information did not improve classification performance. The model with clinical, cognitive, and genetic information resulted in a significantly higher AUC of 0.801 (95% CI, 0.719–0.884) for identifying DSA than the model with only clinical information, in which the three single nucleotide polymorphisms of EPHX2 showed important roles. This study successfully established step-by-step predictive ML models to estimate the risk of suicide attempts in MDD. We found that EPHX2 can help improve the performance of suicidal predictive models. This trial is registered with NCT05575713.

Machine learning models reveal the critical role of nighttime systolic blood pressure in predicting functional outcome for acute ischemic stroke after endovascular thrombectomy

BackgroundBlood pressure (BP) is a key factor for the clinical outcomes of acute ischemic stroke (AIS) receiving endovascular thrombectomy (EVT). However, the effect of the circadian pattern of BP on functional outcome is unclear.MethodsThis multicenter, retrospective, observational study was conducted from 2016 to 2023 at three hospitals in China (ChiCTR2300077202). A total of 407 patients who underwent endovascular thrombectomy (EVT) and continuous 24-h BP monitoring were included. Two hundred forty-one cases from Beijing Hospital were allocated to the development group, while 166 cases from Peking University Shenzhen Hospital and Hainan General Hospital were used for external validation. Postoperative systolic BP (SBP) included daytime SBP, nighttime SBP, and 24-h average SBP. Least absolute shrinkage and selection operator (LASSO), support vector machine-recursive feature elimination (SVM-RFE), Boruta were used to screen for potential features associated with functional dependence defined as 3-month modified Rankin scale (mRS) score ≥ 3. Nine algorithms were applied for model construction and evaluated using area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy.ResultsThree hundred twenty-eight of 407 (80.6%) patients achieved successful recanalization and 182 patients (44.7%) were functional independent. NIHSS at onset, modified cerebral infarction thrombolysis grade, atrial fibrillation, coronary atherosclerotic heart disease, hypertension were identified as prognostic factors by the intersection of three algorithms to construct the baseline model. Compared to daytime SBP and 24-h SBP models, the AUC of baseline + nighttime SBP showed the highest AUC in all algorithms. The XGboost model performed the best among all the algorithms. ROC results showed an AUC of 0.841 in the development set and an AUC of 0.752 in the validation set for the baseline plus nighttime SBP model, with a brier score of 0.198.ConclusionThis study firstly explored the association between circadian BP patterns with functional outcome for AIS. Nighttime SBP may provide more clinical information regarding the prognosis of patients with AIS after EVT.

Radiomics analysis for prediction of lymph node metastasis after neoadjuvant chemotherapy based on pretreatment MRI in patients with locally advanced cervical cancer

BackgroundThis study aims to develop and validate a pretreatment MRI-based radiomics model to predict lymph node metastasis (LNM) following neoadjuvant chemotherapy (NACT) in patients with locally advanced cervical cancer (LACC).MethodsPatients with LACC who underwent NACT from two centers between 2013 and 2022 were enrolled retrospectively. Based on the lymph node (LN) status determined in the pathology reports after radical hysterectomy, patients were categorized as LN positive or negative. The patients from center 1 were assigned as the training set while those from center 2 formed the validation set. Radiomics features were extracted from pretreatment sagittal T2-weighted imaging (Sag-T2WI), axial diffusion-weighted imaging (Ax-DWI), and the delayed phase of dynamic contrast-enhanced sagittal T1-weighted imaging (Sag-T1C) for each patient. The K-best and least absolute shrinkage and selection operator (LASSO) methods were employed to reduce dimensionality, and the radiomics features strongly associated with LNM were selected and used to construct three single-sequence models. Furthermore, clinical variables were incorporated through multivariate regression analysis and fused with the selected radiomics features to construct the clinical-radiomics combined model. The diagnostic performance of the models was assessed using receiver operating characteristic (ROC) curve analysis. The clinical utility of the models was evaluated by the area under the ROC curve (AUC) and decision curve analysis (DCA).ResultsA total of 282 patients were included, comprising 171 patients in the training set, and 111 patients in the validation set. Compared to the Sag-T2WI model (AUC, 95%CI, training set, 0.797, 0.722-0.782; validation set, 0.648, 0.521-0.776) and the Sag-T1C model (AUC, 95%CI, training set, 0.802, 0.723-0.882; validation set, 0.630, 0.505-0.756), the Ax-DWI model exhibited the highest diagnostic performance with AUCs of 0.855 (95%CI, 0.791-0.919) in training set, and 0.753 (95%CI, 0.638-0.867) in validation set, respectively. The combined model, integrating selected features from three sequences and FIGO stage, surpassed predictive ability compared to the single-sequence models, with AUC of 0.889 (95%CI, 0.833-0.945) and 0.859 (95%CI, 0.781-0.936) in the training and validation sets, respectively.ConclusionsThe pretreatment MRI-based radiomics model, integrating radiomics features from three sequences and clinical variables, exhibited superior performance in predicting LNM following NACT in patients with LACC.

Clinical Validation of a Machine-Learned, Point-of-Care System to IDENTIFY Functionally Significant Coronary Artery Disease

Many clinical studies have shown wide performance variation in tests to identify coronary artery disease (CAD). Coronary computed tomography angiography (CCTA) has been identified as an effective rule-out test but is not widely available in the USA, particularly so in rural areas. Patients in rural areas are underserved in the healthcare system as compared to urban areas, rendering it a priority population to target with highly accessible diagnostics. We previously developed a machine-learned algorithm to identify the presence of CAD (defined by functional significance) in patients with symptoms without the use of radiation or stress. The algorithm requires 215 s temporally synchronized photoplethysmographic and orthogonal voltage gradient signals acquired at rest. The purpose of the present work is to validate the performance of the algorithm in a frozen state (i.e., no retraining) in a large, blinded dataset from the IDENTIFY trial. IDENTIFY is a multicenter, selectively blinded, non-randomized, prospective, repository study to acquire signals with paired metadata from subjects with symptoms indicative of CAD within seven days prior to either left heart catheterization or CCTA. The algorithm’s sensitivity and specificity were validated using a set of unseen patient signals (n = 1816). Pre-specified endpoints were chosen to demonstrate a rule-out performance comparable to CCTA. The ROC-AUC in the validation set was 0.80 (95% CI: 0.78–0.82). This performance was maintained in both male and female subgroups. At the pre-specified cut point, the sensitivity was 0.85 (95% CI: 0.82–0.88), and the specificity was 0.58 (95% CI: 0.54–0.62), passing the pre-specified endpoints. Assuming a 4% disease prevalence, the NPV was 0.99. Algorithm performance is comparable to tertiary center testing using CCTA. Selection of a suitable cut-point results in the same sensitivity and specificity performance in females as in males. Therefore, a medical device embedding this algorithm may address an unmet need for a non-invasive, front-line point-of-care test for CAD (without any radiation or stress), thus offering significant benefits to the patient, physician, and healthcare system.

Age-Related Macular Degeneration Detection in Retinal Fundus Images by a Deep Convolutional Neural Network

Computer-based pre-diagnosis of diseases through medical imaging is a task worked on for many years. The so-called fundus images stand out since they do not have uniform illumination and are highly sensitive to noise. One of the diseases that can be pre-diagnosed through fundus images is age-related macular degeneration, which initially manifests as the appearance of lesions called drusen. Several ways of pre-diagnosing macular degeneration have been proposed, methods based entirely on the segmentation of drusen with prior image processing have been designed and applied, and methods based on image pre-processing and subsequent conversion to feature vectors, or patterns, to be classified by a Machine-Learning model have also been developed. Finally, in recent years, the use of Deep-Learning models, particularly Convolutional Networks, has been proposed and used in classification problems where the data are only images. The latter has allowed the so-called transfer learning, which consists of using the learning achieved in the solution of one problem to solve another. In this paper, we propose the use of transfer learning through the Xception Deep Convolutional Neural Network to detect age-related macular degeneration in fundus images. The performance of the Xception model was compared against six other state-of-the-art models with a dataset created from images available in public and private datasets, which were divided into training/validation and test; with the training/validation set, the training was made using 10-fold cross-validation. The results show that the Xception neural network obtained a validation accuracy that surpasses other models, such as the VGG-16 or VGG-19 networks, and had an accuracy higher than 80% in the test set. We consider that the contributions of this work include the use of a Convolutional Neural Network model for the detection of age-related macular degeneration through the classification of fundus images in those affected by AMD (drusen) and the images of healthy patients. The performance of this model is compared against other methods featured in the state-of-the-art approaches, and the best model is tested on a test set outside the training and validation set.