An agentic AI marketplace for prelitigation analyses with ZKP-integrated ethical verifications

Deep-learning (DL) methods have recently been introduced for seismic signal processing. Using DL methods, many researchers have adopted these novel techniques in an attempt to construct a DL model for seismic data reconstruction. The performance of DL-based methods depends heavily on what is learned from the training data. We focus on constructing the DL model that well reflect the features of target data sets. The main goal is to integrate DL with an intuitive data analysis approach that compares similar patterns prior to the DL training stage. We have developed a two-sequential method consisting of two stages: (1) analyzing training and target data sets simultaneously for determining the target-informed training set and (2) training the DL model with this training data set to effectively interpolate the seismic data. Here, we introduce the convolutional autoencoder t-distributed stochastic neighbor embedding (CAE t-SNE) analysis that can provide the insight into the results of interpolation through the analysis of training and target data sets prior to DL model training. Our method was tested with synthetic and field data. Dense seismic gathers (e.g., common-shot gathers) were used as a labeled training data set, and relatively sparse seismic gathers (e.g., common-receiver gathers [CRGs]) were reconstructed in both cases. The reconstructed results and signal-to-noise ratios demonstrated that the training data can be efficiently selected using CAE t-SNE analysis, and the spatial aliasing of CRGs was successfully alleviated by the trained DL model with this training data, which contain target features. These results imply that the data analysis for selecting target-informed training set is very important for successful DL interpolation. In addition, our analysis method can also be applied to investigate the similarities between training and target data sets for other DL-based seismic data reconstruction tasks.

1594 Background: Over the past decade, the U.S. Food and Drug Administration (FDA) has leveraged regulations and guidance documents to accelerate improvements in demographic reporting and encourage adequate representation of minorities in clinical trials. This cross-sectional study aims to assess the impact of these interventions by characterizing demographic data reporting and representation by sex, age, and racial and ethnic identity in pivotal trials supporting novel cancer therapeutics approved by the FDA from 2012 through 2021. Methods: Study demographic data were abstracted from FDA drug approval packages and US cancer population demographic data was abstracted from US Cancer Statistics. The percentages of trials reporting sex, age, racial and ethnic identity of participants in drug approval packages were calculated and participation to prevalence ratios (PPRs) were calculated by dividing the percentage of participants in each demographic by the percentage of the US cancer population in each group. PPRs were constructed for each pivotal trial by cancer type. Adequate representation was defined as PPR 0.8-1.2 and the proportion of trials which were adequately representative of each demographic was calculated and trended over time. Results: From 2012 through 2021, the FDA approved 118 cancer therapeutics, based on 131 pivotal trials. For drugs approved 2012-2016, the majority of associated pivotal trials reported participation based on sex (100% of trials), age (100%) and White (98%), Black (75%) or Asian (84%) racial identity, but not American Indian or Alaskan Native racial identity (18%) or Hispanic ethnic identity (41%). For drugs approved 2017-2021, there were no significant improvements in demographic data reporting, although there was a trend towards increased reporting on Hispanic ethnic identity from 2012-2016 (41%) to 2017-2021 (65%) (p= 0.06). For drugs approved 2012-2016, most pivotal trials adequately represented female participants (78% of trials) and participants identifying as White (87%), but few pivotal trials adequately represented older adults (7%), participants identifying as Black (11%), American Indian or Alaskan Native (0%), Asian (18%) or Hispanic (5%). Representation in pivotal trials did not significantly improve for any demographic for drugs approved 2017-2021 (p>0.05). Conclusions: This study found that the last decade’s efforts to improve demographic data transparency and representation in clinical trials have not yet borne fruit for novel cancer therapeutics. More consequential FDA regulations may be necessary. Beyond the FDA, demographic data transparency and adequate minority representation in oncology clinical trials is an all-stakeholder responsibility. A more just clinical trial infrastructure requires greater collaboration between the FDA, sponsors, enrollers, contract research organizations and cooperative groups.

Method for Automatic Selection of Parameters in Normal Tissue Complication Probability Modeling

Stratifying the Utility of Transthoracic Echocardiography for Ischemic Stroke Using a Risk Score

Due to the mismatch of statistical distributions of acoustic speech between training and testing sets, the performance of spoken language identification (SLID) could be drastically degraded. In this paper, we propose an unsupervised neural adaptation model to deal with the distribution mismatch problem for SLID. In our model, we explicitly formulate the adaptation as to reduce the distribution discrepancy on both feature and classifier for training and testing data sets. Moreover, inspired by the strong power of the optimal transport (OT) to measure distribution discrepancy, a Wasserstein distance metric is designed in the adaptation loss. By minimizing the classification loss on the training data set with the adaptation loss on both training and testing data sets, the statistical distribution difference between training and testing domains is reduced. We carried out SLID experiments on the oriental language recognition (OLR) challenge data corpus where the training and testing data sets were collected from different conditions. Our results showed that significant improvements were achieved on the cross domain test tasks.

Purpose The purpose of this study was to establish a combined model based on T1WI, T2WI, FLAIR images and clinical parameters to predict the prognosis of hypoxic-ischemic encephalopathy (HIE) in full-term newborns. Methods Based on the results of cognitive scores and motor function scores at 12 months post-birth, the patients were classified into two groups: Group B for those with good prognosis (n = 84) and Group W for those with poor prognosis (n = 96). A total of 180 patients were retrospectively evaluated and assigned to either the training data set (n = 126) or the testing data set (n = 54). The clinical characteristics of both groups were compared first. Then, a clinical model, a radiomics model, and a combined model were developed. Finally, we evaluated the performance of the three constructed models using the receiver operating characteristic (ROC) curve and the area under the curve (AUC). Results The Apgar scores at 1 minute, 5 minutes, and 10 minutes were all higher in Group B compared to Group W, with P < 0.05 indicating a statistically significant difference. The clinical model showed that the Apgar score at 10 minutes was the most effective factor, with an AUC of 0.857 in the training data set and an AUC of 0.737 in the testing data set. For the radiomics model, 9 radiomics features were found to be significantly related to predicting the prognosis of HIE, with AUCs of 0.916 and 0.770 in the training and testing data sets, respectively. For the combined model, 7 radiomics features, Apgar scores at 5 minutes, and Apgar scores at 10 minutes were independent predictors for predicting the prognosis of HIE, with AUCs of 0.952 and 0.823 in the training and testing data sets, respectively. The combined model demonstrates better performance than both the clinical and radiomics models. Conclusions The combined model, which incorporates MR-based radiomics signatures, and clinical factors, is effective in predicting the prognosis of HIE.

Although rare, the incidence of venous thromboembolism (VTE) in pediatric trauma patients is increasing, and the consequences of VTE in children are significant. Studies have demonstrated increasing VTE risk in older pediatric trauma patients and improved VTE rates with institutional interventions. While national evidence-based guidelines for VTE screening and prevention are in place for adults, none exist for pediatric patients, to our knowledge. To develop a risk prediction calculator for VTE in children admitted to the hospital after traumatic injury to assist efforts in developing screening and prophylaxis guidelines for this population. Retrospective review of 536,423 pediatric patients 0 to 17 years old using the National Trauma Data Bank from January 1, 2007, to December 31, 2012. Five mixed-effects logistic regression models of varying complexity were fit on a training data set. Model validity was determined by comparison of the area under the receiver operating characteristic curve (AUROC) for the training and validation data sets from the original model fit. A clinical tool to predict the risk of VTE based on individual patient clinical characteristics was developed from the optimal model. Diagnosis of VTE during hospital admission. Venous thromboembolism was diagnosed in 1141 of 536,423 children (overall rate, 0.2%). The AUROCs in the training data set were high (range, 0.873-0.946) for each model, with minimal AUROC attenuation in the validation data set. A prediction tool was developed from a model that achieved a balance of high performance (AUROCs, 0.945 and 0.932 in the training and validation data sets, respectively; P = .048) and parsimony. Points are assigned to each variable considered (Glasgow Coma Scale score, age, sex, intensive care unit admission, intubation, transfusion of blood products, central venous catheter placement, presence of pelvic or lower extremity fractures, and major surgery), and the points total is converted to a VTE risk score. The predicted risk of VTE ranged from 0.0% to 14.4%. We developed a simple clinical tool to predict the risk of developing VTE in pediatric trauma patients. It is based on a model created using a large national database and was internally validated. The clinical tool requires external validation but provides an initial step toward the development of the specific VTE protocols for pediatric trauma patients.

BackgroundLower-grade glioma (LGG) is one of the prevalent malignancies threatening human health, with considerable intrinsic heterogeneities in their biological behavior. Previous studies have revealed that the immune component is a key factor influencing the formation and development of malignancies. In this study, we aim to use a novel approach to develop a prognostic signature of immune-related gene pairs (IRGPs) to determine the survival outcome of patients with LGG.MethodsTranscriptomic profiles and clinical data for LGG were obtained from The Cancer Genome Atlas (TCGA) and Chinese Glioma Genome Atlas (CGGA) databases, and used as training and validation data sets, respectively. IRGPs influencing the overall survival (OS) of patients with LGG in the training data set were screened by performing univariate Cox regression analysis. Next, a prognostic IRGPs signature was constructed using least absolute shrinkage and selection operator (LASSO) regression. Finally, we cross-validated the two databases to verify the stability of the prognostic signature.ResultsA total of 33 IRGPs influencing prognosis of LGG in the training data set were included in the prognostic signature. Patients with high risk scores (RSs) in the training and validation data sets had a poorer OS than those with low RSs. Moreover, significant differences were observed in tumor-infiltrating immune cells (TICs) between high- and low-RS groups. Functional enrichment analyses results revealed that genes in the high-RS group were enriched in the immune-related activities and developmental processes.ConclusionThe prognostic signature containing 33 IRGPs has a significant correlation with OS and relative levels of immune cells associated with LGG. The results of the present study provide new insights into the prediction of survival outcome and therapeutic response of LGG.

The development of Artificial Intelligence (AI), especially Machine Learning (ML) technology, has injected new vitality into the geospatial domain. Training Data (TD) plays a fundamental role in geospatial AI/ML. They are key items for training, validating, and testing AI/ML models. At present, open access Training Datasets (TDS) are usually packaged into public or personal file repository, without a standardized method to express its metadata and data content, making it difficult to be found, accessed, interoperated, and reused.Therefore, based on the Open Geospatial Consortium (OGC) standards baseline, the OGC Training Data Markup Language for AI (TrainingDML-AI) Standard Working Group (SWG) tried to develop the TD model and encoding methods to exchange and retrieve TD in the Web environment. The scope includes: how TD are prepared, how to specify different metadata used for different AI/ML tasks, how to differentiate the high-level TD information model and extended information models specific to various AI/ML applications. The work will describe the latest progress and status of the standard development.The TrainingDML-AI conceptual model includes the most relevant entities of the TD covering from dataset to individual training samples and labels. It specifies how and into which parts of the TD should be decomposed and classified. The core concepts include: AI_TrainingDataset, which represents a collection of training samples; AI_TrainingData, which is an individual training sample in a TDS; AI_Task, which identifies what task the TDS is used for; AI_Label, which represents the label semantics for TD; AI_Labeling, which provides the provenance for the TD; AI_TDChangeset, which records TD changes between two TDS versions; DataQuality, which can be associated with the TDS to document its quality.The TrainingDML-AI content model focuses on implementations with basic attributes defined for off-the-shelf deployment. Concepts related to the EO AI/ML applications are defined as additional elements. Six key components are highlighted:Training Dataset/Data. AI_AbstractTrainingDataset indicates the TDS, while each training sample is represented as AI_AbstractTrainingData. AI_EOTrainingDataset and AI_EOTrainingData are defined to convey attributes specific to EO domain. AI_EOTask is proposed by extending AI_AbstractTask to represent specific AI/ML tasks in the EO domain. The task type can refer to a particular type defined by an external category. Labels for each individual training sample can be represented using features, coverages, or semantic classes. The AI_AbstractLabel is extended to specify AI_SceneLabel, AI_ObjectLabel, and AI_PixelLabel respectively. AI_Labeling records basic provenance information on how to create the TDS. It includes the labeler and labeling procedure, which can be mapped to the agent and activity respectively in W3C PROV. DataQuality and QualityElements defined in the ISO 19157-1 are used to align with the existing efforts on geographic data quality. Change procedures of the TDS are documented in the AI_TDChangeset, which composes of changed training samples in the collection level. Finally, use case scenarios and best practices are provided to illustrate intended use and benefits of TrainingDML-AI for EO AI/ML applications. Totally five different tasks are provided, covering scene classification, object detection, semantic segmentation, change detection and 3D model reconstruction. Some software implementations including pyTDML and LuojiaSet are also presented.

The implementation of equal opportunity policies across governmental bureaucracies has not uniformly advanced the interests of men, women and minorities therein. This paper examines this common occurrence of the unequal outcomes associated with equal opportunity policies. Political scientists have an abiding interest in equal employment opportunity and affirmative action policies and procedures in governmental agencies because these are a principal means of achieving demographic and substantive representation in government. We find the prevailing approach to analyzing these equal opportunity policies rather inadequate–and, indeed, perhaps even part of the larger problem. We propose a new conceptual framework, one that moves beyond conventional demographic (passive) representation to a consideration of substantive (active) representation. The constraints of moving from demographic representational bureaucracy to substantive representational bureaucracy are examined as we integrate institutional an...

Fly-rock induced by blasting is an inevitable phenomenon in quarry mining, which can give rise to severe hazards, for example, causing damage to buildings and human life. Thus, successfully estimating fly-rock distance is crucial. Many researchers attempt to develop empirical, statistical, or machine learning models to accurately predict fly-rock distance. However, for most previous research, a worrying drawback is that the amount of data related to fly-rock distance prediction is insufficient. This is because the measurement work of fly-rock distance is costly for manpower and material resources. To deal with the problem of data shortage, we first separated the original data set that was collected from four granite quarry sites in Malaysia into two parts, i.e., the training and testing sets, and then adopted a data augmentation technique termed tabular variational autoencoder (TVAE) to augment the amount of the training (true) data, so as to generate a fresh synthetic data set. Subsequently, we utilized several statistical visualization methods, such as the boxplot, kernel density estimation, cumulative distribution function, and heatmap, to testify to the effectiveness of the synthetic data generated by the TVAE model. Lastly, several commonly used machine learning models were developed to verify whether the mixed data set—which is obtained by merging the training and synthetic data sets—can benefit from the addition of the synthetic data. The verification work is implemented on the testing data set. The results demonstrate that the size of the training data set has increased from the initial 131 to 1000 to obtain a synthetic data set, and the statistical methods proved that the synthetic data set not only preserves the inner characteristics of the training data set but also generalizes more diversities compared with the training data set. Further, by comparing the performance of five machine learning models on three data sets (i.e., the training, synthetic, and mixed data sets), it can be concluded that the overall performance of all machine learning models on the mixed data set outperforms that on the training and synthetic data sets. Consequently, it can be asserted that the application of the data augmentation technique on the fly-rock distance issue is fruitful in the present study and has profound engineering application value.KeywordsFly-rock distance predictionData augmentationTabular variational autoencoderMachine learning prediction models

A Validated Model to Predict Postoperative Symptom Severity After Mandibular Third Molar Removal

This paper introduces a framework for how to appropriately adopt and adjust machine learning (ML) techniques used to construct electrocardiogram (ECG)-based biometric authentication schemes. The proposed framework can help investigators and developers on ECG-based biometric authentication mechanisms define the boundaries of required datasets and get training data with good quality. To determine the boundaries of datasets, use case analysis is adopted. Based on various application scenarios on ECG-based authentication, three distinct use cases (or authentication categories) are developed. With more qualified training data given to corresponding machine learning schemes, the precision on ML-based ECG biometric authentication mechanisms are increased in consequence. The ECG time slicing technique with the R-peak anchoring is utilized in this framework to acquire ML training data with good quality. In the proposed framework four new measure metrics are introduced to evaluate the quality of the ML training and testing data. In addition, a Matlab toolbox, containing all proposed mechanisms, metrics, and sample data with demonstrations using various ML techniques, is developed and made publicly available for further investigation. For developing ML-based ECG biometric authentication, the proposed framework can guide researchers to prepare the proper ML setups and the ML training datasets along with three identified user case scenarios. For researchers adopting ML techniques to design new schemes in other research domains, the proposed framework is still useful for generating the ML-based training and testing datasets with good quality and utilizing new measure metrics.

To explore morphology and enhancement features of malignant non-mass enhancement (NME) lesions in contrast-enhanced mammography (CEM), and to develop a multivariable model that can accurately predict the probability of malignancy in NME lesions. A total of 162 patients with 206 NME lesions were enrolled. The ratio of 7:3 was randomly divided into a training data set and a test data set. Differences between benign and malignant NME diseases were compared using statistical analysis in the training data set. A logistic regression analysis was used to develop a multivariable model for predicting the probability of malignancy in the training data set. The predictive value of the model was assessed by calculating the area under the curve (AUC) in both training and test data sets. The incidence of malignancy was higher in cases with malignant microcalcification (32.35%), segmental and linear distribution (55.88%), clumped and clustered ring enhancement pattern (70.59%), and Type III curve (64.71%) (all p < 0.002). The sensitivity, specificity, and AUC of the multivariable model in the training data set and the test data set were 79.41-80.77%, 94.44-97.37%, and 0.920-0.946, respectively. When combining microcalcification and enhancement features, the multivariable model for CEM demonstrated acceptable sensitivity and high specificity in predicting malignant NME lesions. Question CEM has gained momentum as an innovative and clinically useful method, but it has not been identified for the discrimination efficacy of NME lesions. Findings The multivariable model of CEM can improve the diagnostic efficiency of breast malignancy NME lesions, with acceptable sensitivity and high specificity. Clinical relevance CEM is an innovative advancement in breast imaging technology. This multivariable model of CEM integrates factors such as microcalcifications, enhancement morphological distribution, internal enhancement patterns, and time-signal intensity curves, thereby enabling accurate diagnosis of NME lesions.

Financial institutions have a large amount of data on their borrowers, which can be used to predict the probability of borrowers defaulting their loan or not. Some of the models that have been used to predict individual loan defaults include linear discriminant analysis models and extreme value theory models. These models are parametric in nature since they assume that the response being investigated takes a particular functional form. However, there is a possibility that the functional form used to estimate the response is very different from the actual functional form of the response. The purpose of this research was to analyze individual loan defaults in Kenya using the logistic regression model. The data used in this study was obtained from equity bank of Kenya for the period between 2006 to 2016. A random sample of 1000 loan applicants whose loans had been approved by equity bank of Kenya during this period was obtained. Data obtained was on the credit history, purpose of the loan, loan amount, nature of the saving account, employment status, sex of the applicant, age of the applicant, security used when acquiring the loan and the area of residence of the applicant (rural or urban). This study employed a quantitative research design, it deals with individual loans defaults as group characteristics of a borrower. The data was pre-processed by seeding using R- Software and then split into training dataset and test data set. The train data was used to train the logistic regression model by employing Supervised machine learning approach. The R-statistical software was used for the analysis of the data. The test data set was used to do cross-validation of the developed logistic model which later was used for analysis prediction of individual loan defaults. This study focused on the analysis of individual loan defaults in Kenya using the logistic regression model in Machine learning. The logistic regression model predicted 303 defaults from train data set, 122 non-defaults and misclassified loans were 56 and 69. The model had an accuracy of 0.7727 with the train data and 0.7333 with the test data. The logistic regression model showed a precision of 0.8440 and 0.8244 with the train and test data respectively. The performance of the model with both the train and test data was illustrated using a plot of train errors and test errors against sample size on the same axes. The plot showed that the performance of the model increases with an increase in sample size. The study recommended the use of logistic regression in conjunction with supervised machine learning approach in loan default prediction in financial institutions and also more research should be carried out on ensemble methods of loan defaults prediction in order to increase the prediction accuracy.