Low False Positive Rate Research Articles

Focal cortical dysplasia lesion segmentation using multiscale transformer

ObjectivesAccurate segmentation of focal cortical dysplasia (FCD) lesions from MR images plays an important role in surgical planning and decision but is still challenging for radiologists and clinicians. In this study, we introduce a novel transformer-based model, designed for the end-to-end segmentation of FCD lesions from multi-channel MR images.MethodsThe core innovation of our proposed model is the integration of a convolutional neural network-based encoder-decoder structure with a multiscale transformer to augment the feature representation of lesions in the global field of view. Transformer pathways, composed of memory- and computation-efficient dual-self-attention modules, leverage feature maps from varying depths of the encoder to discern long-range interdependencies among feature positions and channels, thereby emphasizing areas and channels relevant to lesions. The proposed model was trained and evaluated on a public-open dataset including MR images of 85 patients using both subject-level and voxel-level metrics.ResultsExperimental results indicate that our model offers superior performance both quantitatively and qualitatively. It successfully identified lesions in 82.4% of patients, with a low false-positive lesion cluster rate of 0.176 ± 0.381 per patient. Furthermore, the model achieved an average Dice coefficient of 0.410 ± 0.288, outperforming five established methods.ConclusionIntegration of the transformer could enhance the feature presentation and segmentation performance of FCD lesions. The proposed model has the potential to serve as a valuable assistive tool for physicians, enabling rapid and accurate identification of FCD lesions. The source code and pre-trained model weights are available at https://github.com/zhangxd0530/MS-DSA-NET.Critical relevance statementThis multiscale transformer-based model performs segmentation of focal cortical dysplasia lesions, aiming to help radiologists and clinicians make accurate and efficient preoperative evaluations of focal cortical dysplasia patients from MR images.Key PointsThe first transformer-based model was built to explore focal cortical dysplasia lesion segmentation.Integration of global and local features enhances the segmentation performance of lesions.A valuable benchmark for model development and comparative analyses was provided.Graphical

Design of novel convolution neural network model for lung cancer detection by using sensitivity maps

<p>Despite the existence of numerous models for detecting lung cancer, there is still room for achieving higher levels of accuracy. In this paper, a maximum sensitivity neural network (MSNN) has been proposed. As the name suggests, the model aims to achieve high sensitivity and offers a viable remedy to minimize the number of false positive in oder to improve the overall accuracy for lung cancer detection. The MSNN model is a promising model since it can efficiently interpret grayscale lung computed tomography (CT) scan images as inputs and can be trained using just a few images also. This model has surpassed previous deep learning models by obtaining a remarkable sensitivity of 94.6% and an accuracy of 96.9%. A sensitivity map is created, offering important insights into the critical regions for finding malignant nodules. This innovative method has shown outstanding performance in identifying lung cancer with a low false positive rate which can increase the accuracy of medical diagnoses.</p>

Population screening for cirrhosis.

In response to the growing health crisis of liver-related morbidity and mortality, screening for liver cirrhosis has emerged as a promising strategy for early detection and timely intervention. By identifying individuals with severe fibrosis or compensated cirrhosis, screening holds the promise of enhancing treatment outcomes, delaying disease progression, and ultimately improving the quality of life of affected individuals. Clinical practice guidelines from international scientific societies currently recommend targeted screening strategies, investigating high-risk populations with known risk factors of liver disease. While there is good evidence that screening increases case finding in the population, and a growing number of studies indicate that screening may motivate beneficial lifestyle changes in patients with steatotic liver disease, there are major gaps in knowledge in need of clarification before screening programs of cirrhosis are implemented. Foremost, randomized trials are needed to ensure that screening leads to improved liver-related morbidity and mortality. If not, screening for cirrhosis could be unethical due to overdiagnosis, overtreatment, increased health care costs, negative psychological consequences of screening, and futile invasive investigations. Moreover, the tests used for screening need to be optimized toward lower false positive rates than the currently used FIB-4 while retaining few false negatives. Finally, barriers to adherence to screening and implementation of screening programs need to be elucidated. This review provides a comprehensive overview of the current landscape of screening strategies for liver cirrhosis and the promises and pitfalls of current methods for early cirrhosis detection.

Limited Utility of Quantitative Thresholds on 99mTc-Sestamibi Single-Photon Emission Computed Tomography/Computed Tomography for Distinguishing Renal Cell Carcinoma From Oncocytic Renal Masses

Purpose: 99mTc-sestamibi single-photon emission CT/x-ray CT (SPECT/CT) uses a mitochondria-targeting tracer to differentiate renal cell carcinoma from oncocytomas and hybrid oncocytoma/chromophobe tumors. Initial studies support 99mTc-sestamibi SPECT/CT’s accuracy, but we previously found that oncocytomas still account for 20% of lesions with low tracer uptake in qualitatively interpreted scans. Here, we assess performance of 99mTc-sestamibi SPECT/CT utilizing quantitative assessment thresholds, hypothesizing that this may improve test performance. Materials and Methods: All 99mTc-sestamibi SPECT/CT performed for renal mass evaluation between February 2020 and December 2021 was analyzed. A “hot” mass had qualitatively equivalent or higher 99mTc-sestamibi uptake than normal renal parenchyma; a “cold” mass did not. Target-to-background ratios (TBRs) were calculated using tracer counts in the masses vs nearby normal parenchyma. Quantitative “hot”/“cold” determinations were made using published TBR cutoffs. Findings were correlated with histology. Results: Seventy-eight patients underwent 99mTc-sestamibi SPECT/CT for 98 renal masses. For the 52 masses with diagnostic pathology, the negative predictive value (NPV) of qualitatively interpreted 99mTc-sestamibi SPECT/CT for ruling out oncocytoma was 80%, with a 1.9% false-positive rate. A TBR cutoff of 0.46 achieved the highest NPV of 89.3%, with a 23.1% false-positive rate. A TBR cutoff of 0.74 achieved the lowest false-positive rate of 1.9%, with a 78.3% NPV. No TBR cutoff achieved both higher NPV and lower false positives than the qualitatively interpreted scans. Conclusions: Quantitative TBR cutoffs for interpretation of 99mTc-sestamibi SPECT/CT scans for renal masses do not offer meaningful improvements in accuracy over qualitative reads. Additional studies are required to better characterize the utility of 99mTc-sestamibi SPECT/CT in the real-world setting.

Accelerating cavity fault prediction using deep learning at Jefferson Laboratory

Abstract Accelerating cavities are an integral part of the continuous electron beam accelerator facility (CEBAF) at Jefferson Laboratory. When any of the over 400 cavities in CEBAF experiences a fault, it disrupts beam delivery to experimental user halls. In this study, we propose the use of a deep learning model to predict slowly developing cavity faults. By utilizing pre-fault signals, we train a long short-term memory-convolutional neural network binary classifier to distinguish between radio-frequency (RF) signals during normal operation and RF signals indicative of impending faults. We optimize the model by adjusting the fault confidence threshold and implementing a multiple consecutive window criterion to identify fault events, ensuring a low false positive rate. Results obtained from analysis of a real dataset collected from the accelerating cavities simulating a deployed scenario demonstrate the model’s ability to identify normal signals with 99.99% accuracy and correctly predict 80% of slowly developing faults. Notably, these achievements were achieved in the context of a highly imbalanced dataset, and fault predictions were made several hundred milliseconds before the onset of the fault. Anticipating faults enables preemptive measures to improve operational efficiency by preventing or mitigating their occurrence.

Makeup-Invariant Faces Recognition Using a Pre-Trained Neural Network, Grasshopper Optimization Algorithm, and Random Forest

Makeup-Invariant Face Recognition is a critical area of research that aims to identify and classify manipulated or forged face images in the field of face recognition systems. Advances in deep learning techniques, such as pre-trained neural networks, have shown promising results in this domain. In this paper, a novel approach for detecting manipulated faces is proposed, combining the strengths of pre-trained neural networks, the Grasshopper Optimization (GOA) Algorithm, and Random Forest classifier. The proposed method utilizes the powerful feature extraction capabilities of pre-trained deep neural networks to capture intricate details and patterns in face images. Subsequently, the GOA algorithm is employed to select optimal features. Additionally, the Random Forest classifier is utilized for effective classification of face images and identifying different individuals based on the selected features. By integrating these three algorithms, the proposed approach demonstrates significant improvements in detecting manipulated faces, achieving higher detection rates and lower false positive rates compared to existing state of the art methods. Simulation results on data from 25 different individuals with manipulated face images show an average accuracy of 97.23%, which represents an enhancement over the compared methods.

A novel methodology for anomaly detection in smart home networks via Fractional Stochastic Gradient Descent

With the rising integration of IoT devices within smart home environments, securing these interconnected systems against unauthorized access and cyber threats has become increasingly critical. This study introduces a novel methodology utilizing an advanced Artificial Neural Network (ANN) frame-work to enhance attack and anomaly detection capabilities within smart home networks. The objective is to develop a robust model that outperforms traditional detection methods and provides high accuracy and low false positive rates in identifying potential security threats. The research employs a pioneering approach to train the ANN by incorporating a Fractional Stochastic Gradient Descent optimizer grounded in Grunwald–Letnikov fractional calculus. This method was chosen for its potential to refine learning processes and improve detection accuracy over standard optimizers. The evaluation of the model was performed using the DS2OS traffic traces dataset, applying precision, sensitivity (recall), and specificity metrics to assess performance. The proposed model demonstrated exceptional performance with an accuracy of 0.9951. It significantly surpassed traditional methods like Logistic Regression and Support Vector Machines. The precision achieved was high, indicating a low rate of false positives, while the sensitivity and specificity values underscore the model’s ability to identify both typical and unconventional behaviours within the network accurately. This study introduces a robust and efficient ANN-based methodology for enhancing security in smart home IoT networks. Using a fractional stochastic gradient descent optimizer has proven effective in improving the model’s accuracy and reliability in detecting anomalies and attacks. The findings suggest significant implications for the future of IoT security, highlighting the potential for broader applications of fractional calculus in machine learning to enhance cybersecurity measures in various domains.

Curvature analysis of CI electrode arrays: a novel approach to categorize perimodiolar positions without anatomical landmarks.

Perimodiolar electrode arrays may be positioned regular, over-inserted or under-inserted into the cochlea depending on the cochlear size and shape. The study aimed to examine whether there are differences between these groups in the local curvature along the intracochlear array. Individual curvature variables were developed to categorize the groups and the relationship between the curvature and the angular insertion depth at the electrode tip was analyzed. The curvature along the intracochlear array was measured in the CBCT image of 85 perimodiolar electrodes of a single type. The mean curvature and the ratio of the mean curvature at contacts E14-16 to the mean curvature at E7-8 (bowing ratio) were calculated across the array, and its true positive rate (TPR) and false positive rate (FPR) were calculated to establish optimal threshold values to categorize the groups. 68.2% of the cases were categorized as regular positioned, 22.4% had an over-insertion and 9.4% had an under-insertion. The mean curvature was significantly weaker with under-insertion (< 342°) than with normal insertion depth (≥ 342°). With an over-insertion, the bowing ratio was < 1 and otherwise > 1. Both the mean curvature and bowing ratio were found to have an optimal threshold value with high TPR (= 1.00) and low FPR (≤ 0.06) for categorizing under-insertion and over-insertion, respectively. Curvature analysis is a useful tool to assess if a perimodiolar electrode array has been inserted deep enough into the cochlea. Independent of critical anatomical landmarks, over-inserted arrays and under-inserted arrays could be well categorized by using individual curvature variables. The results need to be validated using additional data sets.

Campus Network Traffic Prediction and Anomaly Detection Based on Deep Learning

This paper proposes an intelligent solution for network traffic prediction and anomaly detection in campus networks, addressing the increasingly severe network security challenges. The proposed approach innovatively integrates Convolutional Neural Networks (CNN) and Long Short-Term Memory networks (LSTM) to simultaneously extract local features and capture dynamic temporal dependencies of network traffic, significantly improving prediction accuracy. Based on this, an adaptive threshold anomaly detection algorithm is designed to automatically adjust detection sensitivity according to traffic variations, achieving a better balance between accuracy and recall rates. Additionally, an anomaly visualization scheme is presented, intuitively displaying the spatiotemporal distribution of network anomalies through heatmaps, assisting administrators in decision-making. Large-scale experiments demonstrate that this approach can effectively identify various security threats such as DDoS attacks, scanning probes, and botnets, with an overall detection rate exceeding 90% while maintaining a low false positive rate. Compared to traditional statistical and machine learning methods, the proposed approach exhibits stronger adaptability and generalization capabilities, providing crucial support for building an intelligent, precise, and reliable campus network security protection system. Future work will focus on further improving the real-time performance and robustness of the solution, expanding its application in new network scenarios such as IoT and edge computing.

Anomaly detection for multivariate time series in IoT using discrete wavelet decomposition and dual graph attention networks

Effective anomaly detection in multivariate time series data is critical to ensuring the security of Internet of Things (IoT) devices and systems. However, building a high precision and low false positive rate anomaly detection model for the complex and volatile IoT environment is a challenging task. This is often due to issues such as a lack of anomaly labeling, high data volatility, and the complexity of device mechanisms. Traditional machine learning algorithms and sequence models frequently fail to account for feature correlation and temporal dependency in anomaly detection. Although deep learning-based anomaly detection methods have progressed, there is still room for improvement in precision, recall, and generalization ability. In this paper, we propose an anomaly detection model called Meta-MWDG to address these issues. The model is based on a multi-scale discrete wavelet decomposition and a dual graph attention network, which can effectively extract feature correlation and temporal dependency in multivariate time series data. Additionally, model-agnostic meta-learning (MAML) is introduced to improve the model’s generalization performance, enabling it to perform well on new tasks even with a few samples. A gated recurrent unit (GRU) is combined with a multi-head self-attention network to output both prediction and reconstruction results in a joint optimization strategy, improving the precision of anomaly detection. Extensive experimental studies demonstrate that Meta-MWDG outperforms the state-of-the-art methods in anomaly detection.

An Anti-Forensics Video Forgery Detection Method Based on Noise Transfer Matrix Analysis.

The dispute over the authenticity of video has become a hot topic in judicial practice in recent years. Despite detection methods being updated rapidly, methods for determining authenticity have limitations, especially against high-level forgery. Deleting the integral group of pictures (GOP) length in static scenes could remove key information in the video, leading to unjust sentencing. Anyone can conduct such an operation using publicly available software, thus escaping state-of-the-art detection methods. In this paper, we propose a detection method based on noise transfer matrix analysis. A pyramid structure and a weight learning module are adopted to improve the detection rate and reduce the false positive rate. In total, 80 videos were examined through delicate anti-forensic forgery operations to verify the detection performance of the proposed method and three previously reported methods against anti-forensic forgery operations. In addition, two of the latest learning-based methods were included in our experiments to evaluate the proposed method. The experimental results show that the proposed method significantly improves the detection of frame deletion points compared with traditional and learning-based methods, especially in low false positive rate (FPR) intervals, which is meaningful in forensic science.

Weakly-supervised learning-based pathology detection and localization in 3D chest CT scans.

Recent advancements in anomaly detection have paved the way for novel radiological reading assistance tools that support the identification of findings, aimed at saving time. The clinical adoption of such applications requires a low rate of false positives while maintaining high sensitivity. In light of recent interest and development in multi pathology identification, we present a novel method, based on a recent contrastive self-supervised approach, for multiple chest-related abnormality identification including low lung density area ("LLDA"), consolidation ("CONS"), nodules ("NOD") and interstitial pattern ("IP"). Our approach alerts radiologists about abnormal regions within a computed tomography (CT) scan by providing 3Dlocalization. We introduce a new method for the classification and localization of multiple chest pathologies in 3D Chest CT scans. Our goal is to distinguish four common chest-related abnormalities: "LLDA", "CONS", "NOD", "IP" and "NORMAL". This method is based on a 3D patch-based classifier with a Resnet backbone encoder pretrained leveraging recent contrastive self supervised approach and a fine-tuned classification head. We leverage the SimCLR contrastive framework for pretraining on an unannotated dataset of randomly selected patches and we then fine-tune it on a labeled dataset. During inference, this classifier generates probability maps for each abnormality across the CT volume, which are aggregated to produce a multi-label patient-level prediction. We compare different training strategies, including random initialization, ImageNet weight initialization, frozen SimCLR pretrained weights and fine-tuned SimCLR pretrained weights. Each training strategy is evaluated on a validation set for hyperparameter selection and tested on a test set. Additionally, we explore the fine-tuned SimCLR pretrained classifier for 3D pathology localization and conduct qualitativeevaluation. Validated on 111 chest scans for hyperparameter selection and subsequently tested on 251 chest scans with multi-abnormalities, our method achieves an AUROC of 0.931 (95% confidence interval [CI]: [0.9034, 0.9557], -value < 0.001) and 0.963 (95% CI: [0.952, 0.976], -value < 0.001) in the multi-label and binary (i.e., normal versus abnormal) settings, respectively. Notably, our method surpasses the area under the receiver operating characteristic (AUROC) threshold of 0.9 for two abnormalities: IP (0.974) and LLDA (0.952), while achieving values of 0.853 and 0.791 for NOD and CONS, respectively. Furthermore, our results highlight the superiority of incorporating contrastive pretraining within the patch classifier, outperforming Imagenet pretraining weights and non-pretrained counterparts with uninitialized weights (F1 score = 0.943, 0.792, and 0.677 respectively). Qualitatively, the method achieved a satisfactory 88.8% completeness rate in localization and maintained an 88.3% accuracy rate against falsepositives. The proposed method integrates self-supervised learning algorithms for pretraining, utilizes a patch-based approach for 3D pathology localization and develops an aggregation method for multi-label prediction at patient-level. It shows promise in efficiently detecting and localizing multiple anomalies within a singlescan.

Convolutional Neural Networks Based Detection System for Cyber-attacks in Industrial Control Systems

Convolutional Neural Networks (CNNs) have emerged as a powerful tool for various pattern recognition tasks, including the detection of cyber-attacks in Industrial Control Systems (ICS). This paper presents a CNN-based detection system specifically designed to safeguard ICS from sophisticated cyber threats. The proposed system leverages the capability of CNNs to automatically learn and extract high-level features from raw data, enabling it to identify anomalies indicative of cyber-attacks with high accuracy. Utilizing a comprehensive cyber-attack dataset containing 59 different types of attacks, the system is trained to distinguish between normal and malicious traffic effectively. Based on the extensive dataset, this study demonstrates that the CNN-based detection system achieves a detection rate of 98.5% and a false-positive rate of 1.2%, significantly outperforming traditional methods. The high detection rate indicates the system's ability to accurately identify a wide range of attack types, while the low false-positive rate ensures minimal disruption to normal operations due to incorrect alerts. These results underscore the system's robustness and reliability in identifying subtle and complex attack patterns. Moreover, the CNN-based system is designed to adapt to new types of attacks as it continues to learn from updated datasets, making it a scalable and future-proof solution. Implementing this system can significantly enhance the cybersecurity posture of industrial environments by providing real-time monitoring and rapid response capabilities. The CNN-based detection system offers a significant advancement in ICS cybersecurity. Effectively identifying and mitigating cyber-attacks contributes to the resilience and reliability of critical infrastructure. The proposed approach improves security measures and ensures industrial processes' continuous and safe operation, which is vital for economic stability and public safety.

Identifying psychological predictors of SARS-CoV-2 vaccination: A machine learning study

BackgroundMajor barriers to addressing SARS-CoV-2 vaccine hesitancy include limited knowledge of what causes delay/refusal of SARS-CoV-2 vaccination and limited ability to predict who will remain unvaccinated over significant time periods despite vaccine availability. The present study begins to address these barriers by developing a machine learning model that prospectively predicts who will persist in not vaccinating against SARS-CoV-2. MethodUnvaccinated individuals (n = 325) who completed a baseline survey were followed over the six-month period when vaccines against SARS-CoV-2 were first widely available (April–October 2021). A random forest model was used to predict who would remain unvaccinated against SARS-CoV-2 from their baseline measures, including demographic information (e.g., age), medical history (e.g., of influenza vaccination), Health-Belief Model constructs (e.g., perceived vaccine dangerousness), conspiracist ideation, and task-based metrics of vulnerability to conspiracist ideation (e.g., tendency toward illusory pattern perception). ResultsThe resulting model significantly predicted vaccination status (AUC-PR = 0.77, 95%CI [0.56 0.90]). At the optimal probability threshold determined by the Generalized Threshold Shifting Protocol, the model was moderately precise (0.83) when identifying individuals who remained unvaccinated (n = 80), and had a very low rate (0.04) of false-positives (incorrectly suggesting that individuals remained unvaccinated). Permutational importance tests suggested that baseline SARS-CoV-2 vaccine intentions conveyed the most information about future SARS-CoV-2 vaccination status. Conspiracist ideation was the second most informative predictor, suggesting that misinformation influences vaccination behavior. Other important predictors included perceived vaccine dangerousness, as expected under the Health Belief Model, and influenza vaccination history. ConclusionsThe model we developed can accurately and prospectively identify individuals who remain unvaccinated against SARS-CoV-2. It could therefore facilitate empirically-informed allocation of interventions that encourage vaccine uptake. The predictive value of conspiracist ideation, perceived vaccine dangerousness, and vaccine intentions in our model is consistent with potential causal relations between these variables and SARS-CoV-2 vaccine uptake.

Modeling Radiologists' Assessments to Explore Pairing Strategies for Optimized Double Reading of Screening Mammograms.

To develop a model that simulates radiologist assessments and use it to explore whether pairing readers based on their individual performance characteristics could optimize screening performance. Logistic regression models were designed and used to model individual radiologist assessments. For model evaluation, model-predicted individual performance metrics and paired disagreement rates were compared against the observed data using Pearson correlation coefficients. The logistic regression models were subsequently used to simulate different screening programs with reader pairing based on individual true-positive rates (TPR) and/or false-positive rates (FPR). For this, retrospective results from breast cancer screening programs employing double reading in Sweden, England, and Norway were used. Outcomes of random pairing were compared against those composed of readers with similar and opposite TPRs/FPRs, with positive assessments defined by either reader flagging an examination as abnormal. The analysis data sets consisted of 936,621 (Sweden), 435,281 (England), and 1,820,053 (Norway) examinations. There was good agreement between the model-predicted and observed radiologists' TPR and FPR (r ≥ 0.969). Model-predicted negative-case disagreement rates showed high correlations (r ≥ 0.709), whereas positive-case disagreement rates had lower correlation levels due to sparse data (r ≥ 0.532). Pairing radiologists with similar FPR characteristics (Sweden: 4.50% [95% confidence interval: 4.46%-4.54%], England: 5.51% [5.47%-5.56%], Norway: 8.03% [7.99%-8.07%]) resulted in significantly lower FPR than with random pairing (Sweden: 4.74% [4.70%-4.78%], England: 5.76% [5.71%-5.80%], Norway: 8.30% [8.26%-8.34%]), reducing examinations sent to consensus/arbitration while the TPR did not change significantly. Other pairing strategies resulted in equal or worse performance than random pairing. Logistic regression models accurately predicted screening mammography assessments and helped explore different radiologist pairing strategies. Pairing readers with similar modeled FPR characteristics reduced the number of examinations unnecessarily sent to consensus/arbitration without significantly compromising the TPR. A logistic-regression model can be derived that accurately predicts individual and paired reader performance during mammography screening reading.Pairing screening mammography radiologists with similar false-positive characteristics reduced false-positive rates with no significant loss in true positives and may reduce the number of examinations unnecessarily sent to consensus/arbitration.

Enhancing IoT Routing Security and Efficiency: Towards AI-Enabled RPL Protocol

In the rapidly evolving landscape of the Internet of Things (IoT), the security and efficiency of network routing are paramount. The standard Routing Protocol for Low-Power and Lossy Networks (RPL) faces challenges in the form of various cyber-attacks, impacting its reliability and performance. To address this problem, we propose a Novel Algorithm for Network Traffic Analysis and Response (NANTAR), a novel algorithm that optimizes the security and efficiency of RPL routing using AI-based techniques. Through evaluation against traditional RPL, NANTAR has demonstrated remarkable improvements in key performance metrics: a 20% increase in throughput, latency reductions of 20-30%, and more efficient resource utilization. Notably, NANTAR maintains robust network performance with scaling, evidenced by 15-20% lower false positive and negative rates. The algorithm’s efficacy is further highlighted by its high detection rates in the face of diverse attacks and its power consumption efficiency, which is crucial for IoT devices. NANTAR’s adaptability and seamless integration across various IoT platforms affirm its potential as a solution for securing IoT ecosystems, with results indicating significant improvements in key operational metrics.

Optimizing Startup Success Prediction Through SMOTE Oversampling and Classification

Rapid technological advancements have led to a surge in the number of startups competing with innovative ideas. Predicting the chances of a startup's future success becomes crucial for entrepreneurs in making informed decisions and strategizing their growth. This study investigates the effectiveness of the Gradient Boosting classification algorithm in predicting startup success. To address potential class imbalance within the dataset, a pre-processing step utilizing Synthetic Minority Oversampling Technique (SMOTE) was employed. The dataset itself encompassed a wide range of variables related to startup attributes and performance metrics. The F1-score metric was utilized to evaluate the model's accuracy while minimizing false positive predictions that could potentially mislead investors. Gradient Boosting algorithm was employed to analyze the dataset, which was pre-processed using SMOTE to handle potential class imbalance. This technique helps to create synthetic data points for the minority class, resulting in a more balanced dataset for the classification model. The dataset itself encompassed a wide range of variables related to startup attributes and performance. The F1-score metric was utilized to evaluate the model's accuracy while minimizing false positive predictions that could potentially mislead investors. Gradient Boosting algorithm achieved an F1-score of 86% for predicting successful startups and 85% for predicting unsuccessful ones. The low false positive prediction rate of 7.9% on the test data further validates the model's reliability. The findings demonstrate the effectiveness of Gradient Boosting in predicting startup success with high accuracy and minimal false positives

A high-dimensional omnibus test for set-based association analysis.

Set-based association analysis is a valuable tool in studying the etiology of complex diseases in genome-wide association studies, as it allows for the joint testing of variants in a region or group. Two common types of single nucleotide polymorphism (SNP)-disease functional models are recognized when evaluating the joint function of a set of SNP: the cumulative weak signal model, in which multiple functional variants with small effects contribute to disease risk, and the dominating strong signal model, in which a few functional variants with large effects contribute to disease risk. However, existing methods have two main limitations that reduce their power. Firstly, they typically only consider one disease-SNP association model, which can result in significant power loss if the model is misspecified. Secondly, they do not account for the high-dimensional nature of SNPs, leading to low power or high false positives. In this study, we propose a solution to these challenges by using a high-dimensional inference procedure that involves simultaneously fitting many SNPs in a regression model. We also propose an omnibus testing procedure that employs a robust and powerful P-value combination method to enhance the power of SNP-set association. Our results from extensive simulation studies and a real data analysis demonstrate that our set-based high-dimensional inference strategy is both flexible and computationally efficient and can substantially improve the power of SNP-set association analysis. Application to a real dataset further demonstrates the utility of the testing strategy.

Pregnancy episodes in All of Us: harnessing multi-source data for pregnancy-related research.

The National Institutes of Health's All of Us Research Program addresses gaps in biomedical research by collecting health data from diverse populations. Pregnant individuals have historically been underrepresented in biomedical research, and pregnancy-related research is often limited by data availability, sample size, and inadequate representation of the diversity of pregnant people. All of Us integrates a wealth of health-related data, providing a unique opportunity to conduct comprehensive pregnancy-related research. We aimed to identify pregnancy episodes with high-quality electronic health record (EHR) data in All of Us Research Program data and evaluate the program's utility for pregnancy-related research. We used a previously published algorithm to identify pregnancy episodes in All of Us EHR data. We described these pregnancies, validated them with All of Us survey data, and compared them to national statistics. Our study identified 18970 pregnancy episodes from 14234 participants; other possible pregnancy episodes had low-quality or insufficient data. Validation against people who reported a current pregnancy on an All of Us survey found low false positive and negative rates. Demographics were similar in some respects to national data; however, Asian-Americans were underrepresented, and older, highly educated pregnant people were overrepresented. Our approach demonstrates the capacity of All of Us to support pregnancy research and reveals the diversity of the pregnancy cohort. However, we noted an underrepresentation among some demographics. Other limitations include measurement error in gestational age and limited data on non-live births. The wide variety of data in the All of Us program, encompassing EHR, survey, genomic, and fitness tracker data, offers a valuable resource for studying pregnancy, yet care must be taken to avoid biases.

A Monte Carlo resampling framework for implementing goodness‐of‐fit tests in spatial capture‐recapture models

Abstract Spatial capture‐recapture (SCR) models provide estimates of animal density from spatially referenced encounter data and has become the most widely adopted approach for estimating density. Despite the rapid growth in the development and application of spatial capture‐recapture methods, approaches for assessing model fit have received very little attention when compared to other classes of hierarchical models in ecology. Here, we develop an approach for testing goodness‐of‐fit (GoF) for frequentist SCR models using Monte Carlo simulations. We derive probability distributions of activity centres from the fitted model. From these, we calculate the expected encounters in the capture history based on the SCR parameter estimates, propagating the uncertainty of the estimates and the activity centre locations via Monte Carlo simulations. Aggregating these test statistics result in count data, allowing us to test fit with Freeman‐Tukey tests. These tests are based on summary statistics of the total encounters of each individual at each trap (FT‐ind‐trap), total encounters of each individual (FT‐individuals) and total encounters at each trap (FT‐traps). We assess the ability of these GoF tests to diagnose lack of fit under a range of assumption violating scenarios. FT‐traps had the strongest response to unmodelled spatial and trap heterogeneity in detection probability (power = 0.53–0.56), while FT‐ind‐traps had the strongest responses to random individual variation in detectability (power = 0.88) and non‐spatial discrete variation in (power = 0.35). The tests, designed to diagnose poor fit in the detection parameters, were insensitive to unmodelled heterogeneity in density (power = &lt;0.001). They also demonstrated low false positive rates (&lt;0.001) when the correct models were fitted; therefore, it is very unlikely that they will provide false indications of poor model fit. We demonstrate that these GoF tests are capable of detecting lack‐of‐fit when unmodelled heterogeneity is present in the detection sub‐model. When used jointly, the combinations of test results are also able to infer the type of lack‐of‐fit in certain cases. Our Monte Carlo sampling methods may be extended to a wider range of GoF tests, thereby providing a platform for developing more GoF methods for SCR.