Training Set Research Articles

Assessment of gully influencing factors and susceptibility using remote sensing-based frequency ratio method in Sunshui River Basin, Southwest China.

Gully erosion is a serious global environmental problem associated with land degradation and ecosystem security. Examining the influencing factors of gullies and determining susceptibility hold significance in environmental sustainability. The study evaluates the spatial distribution, influencing factors, and susceptibility of gullies in the Sunshui River Basin in Sichuan Province, Southwest China. The frequency ratio method supported by satellite images and the gully inventory dataset (1614 gully head points) with different influencing factors were applied to assess the distribution and susceptibility of gullies. Additionally, gully head points were grouped into a training set (70%, 1130 points) and a test set (30%, 484 points). Spatial distribution results indicated that most gullies are located in the middle and upper part of the basin, characterized by moderate elevation (2100-3300m), steep slopes (11.63-27.34°), abandoned farmland, and Cambisols soil, and fewer gullies are located in lower part characterized by lower elevation, gentle slopes, and low vegetation coverage. Land use and land cover influence on susceptibility is significantly greater than other factors with a prediction rate of 33.9, especially farmland abandonment, while the occurrence of gullies is also more often on southwest-orientated slopes. Gully susceptibility highlighted that the study area affected by the very low, low, moderate, high, and very high susceptibilities to these gullies covered an area of about 16%, 23%, 32%, 26%, and 3% of the total basin respectively, which indicates 61% of the study area is susceptible to gully erosion. Moderate to high susceptibility is situated in the upper and middle part, consistent with the spatial distribution of gullies in the basin, and very high susceptibility (3%) is distributed in both the lower and upper parts of the basin. These results have important implications for soil loss control, land planning, and integrated watershed management in the mountainous areas of Southwest China.

Domain adaptation using AdaBN and AdaIN for high-resolution IVD mesh reconstruction from clinical MRI.

Deep learning has firmly established its dominance in medical imaging applications. However, careful consideration must be exercised when transitioning a trained source model to adapt to an entirely distinct environment that deviates significantly from the training set. The majority of the efforts to mitigate this issue have predominantly focused on classification and segmentation tasks. In this work, we perform a domain adaptation of a trained source model to reconstruct high-resolution intervertebral disc meshes from low-resolution MRI. To address the outlined challenges, we use MRI2Mesh as the shape reconstruction network. It incorporates three major modules: image encoder, mesh deformation, and cross-level feature fusion. This feature fusion module is used to encapsulate local and global disc features. We evaluate two major domain adaptation techniques: adaptive batch normalization (AdaBN) and adaptive instance normalization (AdaIN) for the task of shape reconstruction. Experiments conducted on distinct datasets, including data from different populations, machines, and test sites demonstrate the effectiveness of MRI2Mesh for domain adaptation. MRI2Mesh achieved up to a 14% decrease in Hausdorff distance (HD) and a 19% decrease in the point-to-surface (P2S) metric for both AdaBN and AdaIN experiments, indicating improved performance. MRI2Mesh has demonstrated consistent superiority to the state-of-the-art Voxel2Mesh network across a diverse range of datasets, populations, and scanning protocols, highlighting its versatility. Additionally, AdaBN has emerged as a robust method compared to the AdaIN technique. Further experiments show that MRI2Mesh, when combined with AdaBN, holds immense promise for enhancing the precision of anatomical shape reconstruction in domain adaptation.

A Novel Approach to Detect Drones Using Deep Convolutional Neural Network Architecture

Over the past decades, drones have become more attainable by the public due to their widespread availability at affordable prices. Nevertheless, this situation sparks serious concerns in both the cyber and physical security domains, as drones can be employed for malicious activities with public safety threats. However, detecting drones instantly and efficiently is a very difficult task due to their tiny size and swift flights. This paper presents a novel drone detection method using deep convolutional learning and deep transfer learning. The proposed algorithm employs a new feature extraction network, which is added to the modified YOU ONLY LOOK ONCE version2 (YOLOv2) network. The feature extraction model uses bypass connections to learn features from the training sets and solves the “vanishing gradient” problem caused by the increasing depth of the network. The structure of YOLOv2 is modified by replacing the rectified linear unit (relu) with a leaky-relu activation function and adding an extra convolutional layer with a stride of 2 to improve the small object detection accuracy. Using leaky-relu solves the “dying relu” problem. The additional convolution layer with a stride of 2 reduces the spatial dimensions of the feature maps and helps the network to focus on larger contextual information while still preserving the ability to detect small objects. The model is trained with a custom dataset that contains various types of drones, airplanes, birds, and helicopters under various weather conditions. The proposed model demonstrates a notable performance, achieving an accuracy of 77% on the test images with only 5 million learnable parameters in contrast to the Darknet53 + YOLOv3 model, which exhibits a 54% accuracy on the same test set despite employing 62 million learnable parameters.

Development and validation of a risk prediction model for motoric cognitive risk syndrome in older adults

ObjectiveThe objective of this study was to develop a risk prediction model for motoric cognitive risk syndrome (MCR) in older adults.MethodsParticipants were selected from the 2015 China Health and Retirement Longitudinal Study database and randomly assigned to the training group and the validation group, with proportions of 70% and 30%, respectively. LASSO regression analysis was used to screen the predictors. Then, identified predictors were included in multivariate logistic regression analysis and used to construct model nomogram. The performance of the model was evaluated by area under the receiver operating characteristic (ROC) curve (AUC), calibration curves and decision curve analysis (DCA).Results528 out of 3962 participants (13.3%) developed MCR. Multivariate logistic regression analysis showed that weakness, chronic pain, limb dysfunction score, visual acuity score and Five-Times-Sit-To-Stand test were predictors of MCR in older adults. Using these factors, a nomogram model was constructed. The AUC values for the training and validation sets of the predictive model were 0.735 (95% CI = 0.708–0.763) and 0.745 (95% CI = 0.705–0.785), respectively.ConclusionThe nomogram constructed in this study is a useful tool for assessing the risk of MCR in older adults, which can help clinicians identify individuals at high risk.

Artificial intelligence for automatic detection and segmentation of nasal polyposis: a pilot study.

Accurate diagnosis and quantification of polyps and symptoms are pivotal for planning the therapeutic strategy of Chronic rhinosinusitis with nasal polyposis (CRSwNP). This pilot study aimed to develop an artificial intelligence (AI)-based image analysis system capable of segmenting nasal polyps from nasal endoscopy videos. Recorded nasal videoendoscopies from 52 patients diagnosed with CRSwNP between 2019 and 2022 were retrospectively analyzed. Images extracted were manually segmented on the web application Roboflow. A dataset of 342 images was generated and divided into training (80%), validation (10%), and testing (10%) sets. The Ultralytics YOLOv8.0.28 model was employed for automated segmentation. The YOLOv8s-seg model consisted of 195 layers and required 42.4 GFLOPs for operation. When tested against the validation set, the algorithm achieved a precision of 0.91, recall of 0.839, and mean average precision at 50% IoU (mAP50) of 0.949. For the segmentation task, similar metrics were observed, including a mAP ranging from 0.675 to 0.679 for IoUs between 50% and 95%. The study shows that a carefully trained AI algorithm can effectively identify and delineate nasal polyps in patients with CRSwNP. Despite certain limitations like the focus on CRSwNP-specific samples, the algorithm presents a promising complementary tool to existing diagnostic methods.

Predicting the 28-day prognosis of acute-on-chronic liver failure patients based on machine learning

BackgroundWe aimed to establish a prognostic predictive model based on machine learning (ML) methods to predict the 28-day mortality of acute-on-chronic liver failure (ACLF) patients, and to evaluate treatment effectiveness. MethodsACLF patients from six tertiary hospitals were included for analysis. Features for ML models’ development were selected by LASSO regression. Models’ performance was evaluated by area under the curve (AUC) and accuracy. Shapley additive explanation was used to explain the ML model. ResultsOf the 736 included patients, 587 were assigned to a training set and 149 to an external validation set. Features selected included age, hepatic encephalopathy, total bilirubin, PTA, and creatinine. The eXtreme Gradient Boosting (XGB) model outperformed other ML models in the prognostic prediction of ACLF patients, with the highest AUC and accuracy. Delong's test demonstrated that the XGB model outperformed Child-Pugh score, MELD score, CLIF-SOFA, CLIF-C OF, and CLIF-C ACLF. Sequential assessments at baseline, day 3, day 7, and day 14 improved the predictive performance of the XGB-ML model and can help clinicians evaluate the effectiveness of medical treatment. ConclusionsWe established an XGB-ML model to predict the 28-day mortality of ACLF patients as well as to evaluate the treatment effectiveness.

Artificial intelligence based diagnosis of sulcus: assesment of videostroboscopy via deep learning.

To develop a convolutional neural network (CNN)-based model for classifying videostroboscopic images of patients with sulcus, benign vocal fold (VF) lesions, and healthy VFs to improve clinicians' accuracy in diagnosis during videostroboscopies when evaluating sulcus. Videostroboscopies of 433 individuals who were diagnosed with sulcus (91), who were diagnosed with benign VF diseases (i.e., polyp, nodule, papilloma, cyst, or pseudocyst [311]), or who were healthy (33) were analyzed. After extracting 91,159 frames from videostroboscopies, a CNN-based model was created and tested. The healthy and sulcus groups underwent binary classification. In the second phase of the study, benign VF lesions were added to the training set, and multiclassification was executed across all groups. The proposed CNN-based model results were compared with five laryngology experts' assessments. In the binary classification phase, the CNN-based model achieved 98% accuracy, 98% recall, 97% precision, and a 97% F1 score for classifying sulcus and healthy VFs. During the multiclassification phase, when evaluated on a subset of frames encompassing all included groups, the CNN-based model demonstrated greater accuracy when compared with that of the five laryngologists (%76 versus 72%, 68%, 72%, 63%, and 72%). The utilization of a CNN-based model serves as a significant aid in the diagnosis of sulcus, a VF disease that presents notable challenges in the diagnostic process. Further research could be undertaken to assess the practicality of implementing this approach in real-time application in clinical practice.

Implementation and evaluation of a mentorship program in clinical master in family medicine during the COVID-19 pandemic at the Arabian Gulf University: a longitudinal study

BackgroundWe implemented a contextualized innovative mentorship program in the Clinical Master in Family Medicine (CMFM) program established in April 2020 at Arabian Gulf University. In this paper, we describe the process of this program and derive the major challenges faced by trainees and related corrective actions and their outcomes on high-risk trainees for optimal performance.MethodsWe conducted a mixed-method longitudinal study of 80 trainees, analyzing information extracted from the Moodle learning platform about five key performance indicators as well as the contents (quantitative and qualitative) of mentoring meeting reports submitted through a validated online form between 2020 and 2022. We analyzed frequencies and themes of challenges and compared trainees' performance according to time and level of risk.ResultsThe follow-up of all 80 trainees in two cohorts (40 for each cohort) shows that most are female (93.75%) and the mean age is 30.00 ± 2.19 years with a ratio of mentors to mentees of 1 to 5. Meetings are conducted through phone calls, virtually, and face-to-face in 62%, 29%, and 8.3% respectively. The mean number and duration of meetings are 30.88 ± 2.31 and 20.08 ± 9.50 min respectively. Time management is the most reported challenge (41.3%), followed by health, social, and psychological-related issues in 7.6%, 4.6%, and 3% respectively. We extracted four main themes related to trainees, settings of training, e-Portfolio, and the COVID-19 pandemic. The mentorship program captured 12 trainees at high risk for low academic progress (12%) of whom six graduated on time and the remaining had to repeat a few courses the following terms. The performance of the program is stable over time (mean GPA of 3.30 (SE = 0.03), versus 3.34 (SE = 0.05) for cohorts 1 and 2 in the two years respectively, (P = 0.33). However, it is slightly lower among high-risk trainees compared to the remaining (GPA = 3.35 (SE = 0.03) versus 3.14 (SE = 0.08), P = 0.043) though above the minimum of the threshold of 3 out of 4, required for the master's degree.ConclusionThe mentorship program captured the struggling trainees and permitted to implement pertinent corrective actions timely, particularly in the context of a two-year intensive CMFM program during the COVID-19 pandemic.

Correlation inference attacks against machine learning models.

Despite machine learning models being widely used today, the relationship between a model and its training dataset is not well understood. We explore correlation inference attacks, whether and when a model leaks information about the correlations between the input variables of its training dataset. We first propose a model-less attack, where an adversary exploits the spherical parameterization of correlation matrices alone to make an informed guess. Second, we propose a model-based attack, where an adversary exploits black-box model access to infer the correlations using minimal and realistic assumptions. Third, we evaluate our attacks against logistic regression and multilayer perceptron models on three tabular datasets and show the models to leak correlations. We lastly show how extracted correlations can be used as building blocks for attribute inference attacks and enable weaker adversaries. Our results raise fundamental questions on what a model does and should remember from its training set.

Interpretable machine learning for the prediction of death risk in patients with acute diquat poisoning

The aim of this study was to develop and validate predictive models for assessing the risk of death in patients with acute diquat (DQ) poisoning using innovative machine learning techniques. Additionally, predictive models were evaluated through the application of SHapley Additive ExPlanations (SHAP). A total of 201 consecutive patients from the emergency departments of the First Hospital and Shengjing Hospital of China Medical University admitted for deliberate oral intake of DQ from February 2018 to August 2023 were analysed. The initial clinical data of the patients with acute DQ poisoning were collected. Machine learning methods such as logistic regression, random forest, support vector machine (SVM), and gradient boosting were applied to build the prediction models. The whole sample was split into a training set and a test set at a ratio of 8:2. The performances of these models were assessed in terms of discrimination, calibration, and clinical decision curve analysis (DCA). We also used the SHAP interpretation tool to provide an intuitive explanation of the risk of death in patients with DQ poisoning. Logistic regression, random forest, SVM, and gradient boosting models were established, and the areas under the receiver operating characteristic curves (AUCs) were 0.91, 0.98, 0.96 and 0.94, respectively. The net benefits were similar across all four models. The four machine learning models can be reliable tools for predicting death risk in patients with acute DQ poisoning. Their combination with SHAP provides explanations for individualized risk prediction, increasing the model transparency.

Predictive Modeling of Long-Term Prognosis After Resection in Typical Pulmonary Carcinoid: A Machine Learning Perspective

Typical Pulmonary Carcinoid (TPC) is defined by its slow growth, frequently necessitating surgical intervention. Despite this, the long-term outcomes following tumor resection are not well understood. This study examined the factors impacting Overall Survival (OS) in patients with TPC, leveraging data from the Surveillance, Epidemiology, and End Results database spanning from 2000 to 2018. We employed Lasso-Cox analysis to identify prognostic features and developed various models using Random Forest, XGBoost, and Cox regression algorithms. Subsequently, we assessed model performance using metrics such as Area Under the Curve (AUC), calibration plot, Brier score, and Decision Curve Analysis (DCA). Among the 2687 patients, we identified five clinical features significantly affecting OS. Notably, the Random Forest model exhibited strong performance, achieving 5- and 7-year AUC values of 0.744/0.757 in the training set and 0.715/0.740 in the validation set, respectively, outperforming other models. Additionally, we developed a web-based platform aimed at facilitating easy access to the model. This study presents a machine learning model and a web-based support system for healthcare professionals, assisting in personalized treatment decisions for patients with TPC post-tumor resection.

Failure evaluation on tailor made aerospace aluminum alloys via underwater friction stir welding employing predictive machine learning technologies

Employing tailor-made alloys with uneven thickness achieves light weighting, a critical issue for reducing emissions, leading to lower aircraft pollutants and fuel costs. The research utilizes advanced machine learning techniques such as Gaussian process regression (GPR), artificial neural networks (ANN) linear regression (LR), and support vector machines (SVM) to predict the ultimate tensile strength of underwater friction stir welding of AA6082-T6 and A2219-T83 tailor-made joints. The models have been evaluated with an assortment of kernel functions, including the polynomial kernel (PK), the radial basis function (RBF), and the Pearson VII universal kernel (PUK). To acquire experimental data, we used a Central Composite Design (CCD) technique, incorporating various factors in the process encompassing tool tilt angle (TA), rotating speed (RS), and welding speed (WS). The SVM radial basis function model (SRBP) had a maximum correlation coefficient of 0.9995 and a minimum root mean square error value (RMSE) of 0.5433 in the training set and 0.6271 in the test set. The ANN model predicted the UTS with an error margin of 0.21%, while the SRBP model showed a 0.52% error, and the LR model exhibited a significantly higher error of 7.73%. A peak tensile strength of 252.98 MPa was recorded in the S20 specimen, accounting for 85.61% of the base metal’s (AA6082 T6) strength. A reduced acute tearing ridge indicates petite, shallow dimples due to the inherent cooling. Through the analysis of metrics and residuals, high accuracy rates were observed when employing the ANN and SRBP models to predict mechanical traits.

Genomic predictions of genetic variances and correlations among traits for breeding crosses in soybean.

Parental selection is perhaps the most critical decision a breeder makes, establishing the foundation of the entire program for years to come. Cross selection based on predicted mean and genetic variance can be further expanded to multiple-trait improvement by predicting the genetic correlation ( ) between pairs of traits. Our objective was to empirically assess the ability to predict the family mean, genetic variance, superior progeny mean and genetic correlation through genomic prediction in a soybean population. Data made available through the Soybean Nested Association Mapping project included phenotypic data on seven traits (days to maturity, lodging, oil, plant height, protein, seed size, and seed yield) for 39 families. Training population composition followed a leave-one-family-out cross-validation scheme, with the validation family genetic parameters predicted using the remaining families as the training set. The predictive abilities for family mean and superior progeny mean were significant for all traits while predictive ability of genetic variance was significant for four traits. We were able to validate significant predictive abilities of for 18 out of 21 (86%) pairwise trait combinations (P < 0.05). The findings from this study support the use of genome-wide marker effects for predicting in soybean biparental crosses. If successfully implemented in breeding programs, this methodology could help to increase the rate of genetic gain for multiple correlated traits.

ExpHRD: an individualized, transcriptome-based prediction model for homologous recombination deficiency assessment in cancer

BackgroundHomologous recombination deficiency (HRD) stands as a clinical indicator for discerning responsive outcomes to platinum-based chemotherapy and poly ADP-ribose polymerase (PARP) inhibitors. One of the conventional approaches to HRD prognostication has generally centered on identifying deleterious mutations within the BRCA1/2 genes, along with quantifying the genomic scars, such as Genomic Instability Score (GIS) estimation with scarHRD. However, the scarHRD method has limitations in scenarios involving tumors bereft of corresponding germline data. Although several RNA-seq-based HRD prediction algorithms have been developed, they mainly support cohort-wise classification, thereby yielding HRD status without furnishing an analogous quantitative metric akin to scarHRD. This study introduces the expHRD method, which operates as a novel transcriptome-based framework tailored to n-of-1-style HRD scoring.ResultsThe prediction model has been established using the elastic net regression method in the Cancer Genome Atlas (TCGA) pan-cancer training set. The bootstrap technique derived the HRD geneset for applying the expHRD calculation. The expHRD demonstrated a notable correlation with scarHRD and superior performance in predicting HRD-high samples. We also performed intra- and extra-cohort evaluations for clinical feasibility in the TCGA-OV and the Genomic Data Commons (GDC) ovarian cancer cohort, respectively. The innovative web service designed for ease of use is poised to extend the realms of HRD prediction across diverse malignancies, with ovarian cancer standing as an emblematic example.ConclusionsOur novel approach leverages the transcriptome data, enabling the prediction of HRD status with remarkable precision. This innovative method addresses the challenges associated with limited available data, opening new avenues for utilizing transcriptomics to inform clinical decisions.

Development and Validation of a Prediction Model for Thyroid Dysfunction in Patients During Immunotherapy

ObjectiveThis study was designed to develop and validate a predictive model for assessing the risk of thyroid toxicity following treatment with immune checkpoint inhibitors (ICIs). MethodsA retrospective analysis was conducted on a cohort of 586 patients diagnosed with malignant tumors who received programmed cell death 1 (PD-1)/programmed death-ligand 1 (PD-L1) inhibitors. The patients were randomly divided into training and validation cohorts in a 7:3 ratio. Logistic regression analyses were performed on the training set to identify risk factors of thyroid dysfunction, and a nomogram was developed based on these findings. Internal validation was performed using K-fold cross-validation on the validation set. The performance of the nomogram was assessed in terms of discrimination and calibration. Additionally, decision curve analysis (DCA) was utilized to demonstrate the decision efficiency of the model. ResultsOur clinical prediction model consisted of four independent predictors of thyroid immune-related adverse events (irAEs), namely baseline thyrotropin (TSH, OR=1.427, 95%CI:1.163-1.876), baseline thyroglobulin antibody (TgAb, OR=1.105, 95%CI:1.035-1.180), baseline thyroid peroxidase antibody (TPOAb, OR=1.172, 95%CI:1.110-1.237), and baseline platelet count (PLT, OR=1.004, 95%CI:1.000-1.007). The developed nomogram achieved excellent discrimination with an area under the curve (AUC) of 0.863 (95%CI: 0.817-0.909) and 0.885 (95%CI: 0.827-0.944) in the training and internal validation cohorts respectively. Calibration curves exhibited a good fit, and the decision curve indicated favorable clinical benefits. ConclusionThe proposed nomogram serves as an effective and intuitive tool for predicting the risk of thyroid irAEs, facilitating clinicians making individualized decisions based on patient-specific information.

Predictive quantitative multidetector computed tomography models for characterization of renal cell carcinoma subtypes and differentiation from renal oncocytoma: nomogram algorithmic approach analysis

BackgroundOur objective is to develop an algorithmic approach using predictive models to discriminate between common solid renal masses, including renal cell carcinoma [RCC] subtypes and renal oncocytoma [RO], using multiphase computed tomography [CT].MethodsWe retrospectively analyzed a group of solid renal masses between January 2011 and January 2023 regarding the CT attenuation values using a multiphase multidetector CT and clinical parameters. Inclusion criteria included patients who had four phases of CT with a partial or radical nephrectomy. Exclusion criteria were patients with biphasic or one-phase CT, poor imaging quality, patients under surveillance, radiofrequency ablation, or indeterminate pathology findings as oncocytic tumor variants. We divided our cohort into training and internal validation sets.ResultsOur results revealed that a total of 467 cases, 351 patients assigned for the training cohort and 116 cases assigned for validation cohort. There is a significant difference between hypervascular clear RCC [CRCC and RO] and hypovascular chromophobe and papillary [ChRCC and PRCC] masses in both training and validation sets, AUC = 0.95, 0.98, respectively. The predictive model for differentiation between CRCC and RO showed AUC = 0.83, 0.85 in both training and validation sets, respectively. At the same time, the discrimination of ChRCC from PRCC showed AUC = 0.94 in the training set and 0.93 in the validation cohort.ConclusionsUsing the largest sample to our knowledge, we developed a three-phase analytical approach to initiate a practical method to discriminate between different solid renal masses that can be used in daily clinical practice.

Preoperative prediction of histopathological grading in patients with chondrosarcoma using MRI-based radiomics with semantic features

BackgroundDistinguishing high-grade from low-grade chondrosarcoma is extremely vital not only for guiding the development of personalized surgical treatment but also for predicting the prognosis of patients. We aimed to establish and validate a magnetic resonance imaging (MRI)-based nomogram for predicting preoperative grading in patients with chondrosarcoma.MethodsApproximately 114 patients (60 and 54 cases with high-grade and low-grade chondrosarcoma, respectively) were recruited for this retrospective study. All patients were treated via surgery and histopathologically proven, and they were randomly divided into training (n = 80) and validation (n = 34) sets at a ratio of 7:3. Next, radiomics features were extracted from two sequences using the least absolute shrinkage and selection operator (LASSO) algorithms. The rad-scores were calculated and then subjected to logistic regression to develop a radiomics model. A nomogram combining independent predictive semantic features with radiomic by using multivariate logistic regression was established. The performance of each model was assessed by the receiver operating characteristic (ROC) curve analysis and the area under the curve, while clinical efficacy was evaluated via decision curve analysis (DCA).ResultsUltimately, six optimal radiomics signatures were extracted from T1-weighted imaging (T1WI) and T2-weighted imaging with fat suppression (T2WI-FS) sequences to develop the radiomics model. Tumour cartilage abundance, which emerged as an independent predictor, was significantly related to chondrosarcoma grading (p < 0.05). The AUC values of the radiomics model were 0.85 (95% CI, 0.76 to 0.95) in the training sets, and the corresponding AUC values in the validation sets were 0.82 (95% CI, 0.65 to 0.98), which were far superior to the clinical model AUC values of 0.68 (95% CI, 0.58 to 0.79) in the training sets and 0.72 (95% CI, 0.57 to 0.87) in the validation sets. The nomogram demonstrated good performance in the preoperative distinction of chondrosarcoma. The DCA analysis revealed that the nomogram model had a markedly higher clinical usefulness in predicting chondrosarcoma grading preoperatively than either the rad-score or clinical model alone.ConclusionThe nomogram based on MRI radiomics combined with optimal independent factors had better performance for the preoperative differentiation between low-grade and high-grade chondrosarcoma and has potential as a noninvasive preoperative tool for personalizing clinical plans.

CT radiomics combined with clinical and radiological factors predict hematoma expansion in hypertensive intracerebral hemorrhage.

This study aimed to establish a hematoma expansion (HE) prediction model for hypertensive intracerebral hemorrhage (HICH) patients by combining CT radiomics, clinical information, and conventional imaging signs. A retrospective continuous collection of HICH patients from three medical centers was divided into a training set (n = 555), a validation set (n = 239), and a test set (n = 77). Extract radiomics features from baseline CT plain scan images and combine them with clinical information and conventional imaging signs to construct radiomics models, clinical imaging sign models, and hybrid models, respectively. The models will be evaluated using the area under the curve (AUC), clinical decision curve analysis (DCA), net reclassification index (NRI), and integrated discrimination improvement (IDI). In the training, validation, and testing sets, the radiomics model predicts an AUC of HE of 0.885, 0.827, and 0.894, respectively, while the clinical imaging sign model predicts an AUC of HE of 0.759, 0.725, and 0.765, respectively. Glasgow coma scale score at admission, first CT hematoma volume, irregular hematoma shape, and radiomics score were used to construct a hybrid model, with AUCs of 0.901, 0.838, and 0.917, respectively. The DCA shows that the hybrid model had the highest net profit rate. Compared with the radiomics model and the clinical imaging sign model, the hybrid model showed an increase in NRI and IDI. The hybrid model based on CT radiomics combined with clinical and radiological factors can effectively individualize the evaluation of the risk of HE in patients with HICH. CT radiomics combined with clinical information and conventional imaging signs can identify HICH patients with a high risk of HE and provide a basis for clinical-targeted treatment. HE is an important prognostic factor in patients with HICH. The hybrid model predicted HE with training, validation, and test AUCs of 0.901, 0.838, and 0.917, respectively. This model provides a tool for a personalized clinical assessment of early HE risk.

A novel predictive model for optimizing diabetes screening in older adults.

The fasting blood glucose test is widely used for diabetes screening. However, it may fail to detect early-stage diabetes characterized by elevated postprandial glucose levels. Hence, we developed and internally validated a nomogram to predict the diabetes risk in older adults with normal fasting glucose levels. This study enrolled 2,235 older adults, dividing them into a Training Set (n = 1,564) and a Validation Set (n = 671) based on a 7:3 ratio. We employed the least absolute shrinkage and selection operator regression to identify predictors for constructing the nomogram. Calibration and discrimination were employed to assess the nomogram's performance, while its clinical utility was evaluated through decision curve analysis. Nine key variables were identified as significant factors: age, gender, body mass index, fasting blood glucose, triglycerides, alanine aminotransferase, the ratio of alanine aminotransferase to aspartate aminotransferase, blood urea nitrogen, and hemoglobin. The nomogram demonstrated good discrimination, with an area under the receiver operating characteristic curve of 0.824 in the Training Set and 0.809 in the Validation Set. Calibration curves for both sets confirmed the model's accuracy in estimating the actual diabetes risk. Decision curve analysis highlighted the model's clinical utility. We provided a dynamic nomogram for identifying older adults at risk of diabetes, potentially enhancing the efficiency of diabetes screening in primary healthcare units.

Efficient Parameterization of Density Functional Tight-Binding for 5f-Elements: A Th-O Case Study.

Density functional tight binding (DFTB) models for f-element species are challenging to parametrize owing to the large number of adjustable parameters. The explicit optimization of the terms entering the semiempirical DFTB Hamiltonian related to f orbitals is crucial to generating a reliable parametrization for f-block elements, because they play import roles in bonding interactions. However, since the number of parameters grows quadratically with the number of orbitals, the computational cost for parameter optimization is much more expensive for the f-elements than for the main group elements. In this work we present a set of efficient approaches for mitigating the hurdle imposed by the large size of the parameter space. A novel group-by-orbital correction functions for two-center bond integrals was developed. With this approach the number of parameters is reduced, and it grows linearly with the number of elements, maintaining the accuracy and the number of parameters, in the case of f elements, by more than 40%. The parameter optimization step was accelerated by means of the mini-batch BFGS method. This method allows parameter optimizations with much larger training sets than other single batch methods. A stochastic optimizer was employed that helped overcome shallow local minima in the objective function. The proposed algorithm was used to parametrize the DFTB Hamiltonian for the Th-O system, which was subsequently applied to the study of ThO2 nanoparticles. The training set consisted of 6322 unique structures, which is barely feasible with conventional optimization methods. The optimized parameter set, LANL-ThO, displays good agreement with DFT-calculated properties such as energies, forces, and structures for both clusters and bulk ThO2. Benefiting from the fewer number of parameters and lower computational costs for objective function evaluations, this new approach shows its potential applications in DFTB parametrization for elements with high angular momentum, which present a challenge to conventional methods.