Test Set Research Articles

Deep learning based ultra-low dose fan-beam computed tomography image enhancement algorithm: Feasibility study in image quality for radiotherapy.

We investigated the feasibility of deep learning-based ultra-low dose kV-fan-beam computed tomography (kV-FBCT) image enhancement algorithm for clinical application in abdominal and pelvic tumor radiotherapy. A total of 76 patients of abdominal and pelvic tumors were prospectively selected. The Catphan504 was acquired with the same conditions as the standard phantom test set. We used a CycleGAN-based model for image enhancement. Normal dose CT (NDCT), ultra-low dose CT (LDCT) and deep learning enhanced CT (DLR) were evaluated by subjective and objective analyses in terms of imaging quality, HU accuracy, and image signal-to-noise ratio (SNR). The image noise of DLR was significantly reduced, and the contrast-to-noise ratio (CNR) was significantly improved compared to the LDCT. The most significant improvement was the acrylic which represented soft tissue in CNR from 1.89 to 3.37, improving by 76%, nearly approaching the NDCT, and in low-density resolution from 7.64 to 12.6, improving by 64%. The spatial frequencies of MTF10 and MTF50 in DLR were 4.28 and 2.35 cycles/mm in DLR, respectively, which are higher than LDCT 3.87 and 2.12 cycles/mm, and even slightly higher than NDCT 4.15 and 2.28 cycles/mm. The accuracy and stability of HU values of DLR were similar to NDCT. The image quality evaluation of the two doctors agreed well with DLR and NDCT. A two-by-two comparison between groups showed that the differences in image scores of LDCT compared with NDCT and DLR were all statistically significant (p<0.05), and the subjective scores of DLR were close to NDCT. The image quality of DLR was close to NDCT with reduced radiation dose, which can fully meet the needs of conventional image-guided adaptive radiotherapy (ART) and achieve the quality requirements of clinical radiotherapy. The proposed method provided a technical basis for LDCT-guided ART.

Automatic localization and deep convolutional generative adversarial network-based classification of focal liver lesions in computed tomography images: A preliminary study.

Computed tomography of the abdomen exhibits subtle and complex features of liver lesions, subjectively interpreted by physicians. We developed a deep learning-based localization and classification (DLLC) system for focal liver lesions (FLLs) in computed tomography imaging that could assist physicians in more robust clinical decision-making. We conducted a retrospective study (approval no. EMRP-109-058) on 1589 patients with 17335 slices with 3195 FLLs using data from January 2004 to December 2020. The training set included 1272 patients (male: 776, mean age 62±10.9), and the test set included 317 patients (male: 228, mean age 57±11.8). The slices were annotated by annotators with different experience levels, and the DLLC system was developed using generative adversarial networks for data augmentation. A comparative analysis was performed for the DLLC system versus physicians using external data. Our DLLC system demonstrated mean average precision at 0.81 for localization. The system's overall accuracy for multiclass classifications was 0.97 (95% confidence interval [CI]: 0.95-0.99). Considering FLLs≤3cm, the system achieved an accuracy of 0.83 (95% CI: 0.68-0.98), and for size>3cm, the accuracy was 0.87 (95% CI: 0.77-0.97) for localization. Furthermore, during classification, the accuracy was 0.95 (95% CI: 0.92-0.98) for FLLs≤3cm and 0.97 (95% CI: 0.94-1.00) for FLLs>3cm. This system can provide an accurate and non-invasive method for diagnosing liver conditions, making it a valuable tool for hepatologists and radiologists.

Application of Machine Learning to Predict the Capacity of Fractured Horizontal Wells in Shale Reservoirs

Shale oil wells typically have numerous volume fracturing segments in their horizontal sections, resulting in significant variability in productivity across these segments. Conventional productivity prediction and fracturing effect evaluation methods are challenging to apply effectively. Establishing a stable and efficient intelligent productivity prediction method using machine learning is a promising approach for the effective development of shale oil reservoirs. This study is based on geological data, fracturing records, and a production database of 91 production wells in a shale oil reservoir in a specific area. Fourteen key parameters affecting productivity were selected from geological and engineering perspectives, and the recursive feature elimination method based on support vector machines identified five optimal main controlling factors. Three machine learning methods—decision tree, random forest, and gradient boosting decision tree (GBDT)—were used to model productivity prediction, with root mean square error (RMSE) employed to evaluate model performance. The study results indicate that formation coefficient, cluster spacing, treatment volume, sand volume, and fracturing segment length are the main controlling factors influencing productivity in fractured horizontal wells. Among the models, the random forest algorithm with bootstrap sampling produced the most stable prediction results, achieving a prediction accuracy of 94% and an RMSE of 0.934 on the test set, outperforming the decision tree and GBDT models in terms of minimum RMSE on the test set.

Establishment and validation of a nomogram for predicting postoperative intestinal adhesion in children with acute appendicitis.

This study aims to explore the value of multiple indicators in the evaluation of risk factors for intestinal adhesion (IA) after appendectomy in children with acute appendicitis (AA). A retrospective study was conducted on 608 patients who underwent appendectomy in the Department of Pediatric Surgery, Children's Medical Center of Jilin Province from January 2017 to April 2023, with a one-year follow-up period to record the occurrence of IA after appendectomy. Univariate and multivariate analysis were used to screen the risk factors of postoperative IA, and a prediction model was established to predict postoperative IA. There were 527 patients in the non-IA group and 81 patients in the IA group. Binary Logistic regression was used to determine the strength of correlation with postoperative intestinal adhesion. The risk factors identified were as follows: DS ≥ 43h (OR = 3.903, 5points), CRP ≥ 65mg/L (OR = 3.424, 4.5points), PCT ≥ 0.9µg/L (OR = 8.683, 8points), Surgical duration ≥ 100min (OR = 6.457, 7points), Appendiceal perforation (OR = 6.073, 6.5points), Postoperative exhaust time ≥ 55h (OR = 14.483, 10points). After test, the nomogram drawn based on binary logistic regression can obtain good prediction efficiency. In the training set, the area under the curve was 0.960, the sensitivity was 0.898, and the specificity was 0.905. In the test set, the area under the curve was 0.957, the sensitivity was 0.864, and the specificity was 0.906. Postoperative exhaust time ≥ 55h has a high risk of IA after appendicitis surgery in children. Early recovery of intestinal peristalsis function is essential. This scoring model is a novel and promising method for predicting postoperative IA.

Optimizing food waste anaerobic digestion in Kuwait: Experimental insights and empirical modelling using artificial neural networks.

This study investigates, for the first time, the anaerobic digestion of food waste in Kuwait to optimize methane production through a combination of artificial neural network (ANN) modelling and continuous reactor experiments. The ANN model, utilizing eight hidden neurons and a 70-20-10 split for training, validation and testing sets, yielded mean squared error values of 0.0056, 0.0048 and 0.0059 and coefficient of determination (R²) values of 0.9942, 0.9986 and 0.9892, respectively. Methane percentages in biogas were predicted using six parameters: biomass type, pH, organic loading rate (OLR), hydraulic retention time (HRT), temperature and reactor volume. To validate the ANN results, continuous reactor experiments were conducted under an OLR of 3 kg VS m⁻³ d⁻¹ and HRT of 20 days at varying temperatures (35°C, 40°C, 45°C, 50°C and 55°C). The experiments demonstrated optimal methane production in the mesophilic range, with ANN predictions closely aligning with experimental data up to 45°C. However, deviations were observed at higher temperatures, particularly under thermophilic conditions beyond 50°C. This study provides novel insights into waste-to-energy initiatives in Kuwait and highlights the potential of integrating computational models with empirical data to enhance biogas production processes.

Abstract B056: Towards a generalized machine learning model for Raman spectroscopy-based liquid biopsy in cancer screening using self-supervised learning

Abstract Head and neck cancers, which encompass a range of malignancies affecting the oral cavity, pharynx, and larynx, are critical to address due to their high morbidity and impact on quality of life. This underscores the need for effective and non-invasive diagnostic tools. Raman spectroscopy-based liquid biopsy detects cancers by analyzing intrinsic Raman fingerprints in biofluids without the need for molecular labels, making it a promising point-of-care screening method. However, Raman scattering is weak, and interpreting spectra from biological samples is challenging due to overlapping peaks, fluorescence background, cosmic rays, and instrument noise, which obscure the signal. Extensive preprocessing and advanced analytical techniques are usually needed to isolate the true Raman signal. While machine learning models have shown promise in classifying cancer status from Raman spectra, variations in Raman systems, lack of standardized protocols, and small patient cohorts limit their clinical utility. Our goal is to develop a model for Raman spectroscopy-based liquid biopsy that generalizes across different measurement conditions and clinical indications. A key challenge is the high cost of acquiring extensive labeled training data. To overcome this, we use a Siamese-based, self-supervised model trained on unlabeled spectral data. The model generates synthetic spectra that mimic real variations across Raman systems and measurement protocols by preprocessing the input and adding simulated factors like fluorescence background, noise, and cosmic rays. By maximizing the cosine similarity between the embeddings of the generated spectra and their originals, the model learns meaningful features of the Raman spectra. This approach not only expands the training set but also enhances the model’s stability across different instruments. In our preliminary study, we analyzed thousands of Raman spectra measured on liquid biopsy specimens (blood plasma and saliva) collected from a cohort of 71 head and neck cancer patients (spread across early and late-stage disease) and 44 non-cancerous controls. Spectra were divided into training and test sets with an 80:20 ratio. Each specimen was drop cast onto a quartz substrate and 25 repeated Raman point scans were performed in a grid over the dried spot. We augmented the training set to reach 9,200 spectra, and t-SNE plots of the embeddings of the test set (1,150 spectra) showed clear clustering separated by sample type, with distinct clusters for healthy individuals and cancer patients. Despite the excellent performance for cancer vs control, separation among cancer patients at different stages remains limited, but will be the target of future work building on this study. These results suggest that our label-free approach can effectively distinguish between healthy and cancerous samples using unlabeled data, advancing the potential for the widespread clinical application of Raman-based liquid biopsy powered by machine learning. Citation Format: Yifei Gu, Kwan Lun Chiu, Andrés Muñoz-Jaramillo, Andrew C. Birkeland, Maria Navas-Moreno, Randy Carney. Towards a generalized machine learning model for Raman spectroscopy-based liquid biopsy in cancer screening using self-supervised learning [abstract]. In: Proceedings of the AACR Special Conference: Liquid Biopsy: From Discovery to Clinical Implementation; 2024 Nov 13-16; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(21_Suppl):Abstract nr B056.

Deep learning-based automated measurement of hip key angles and auxiliary diagnosis of developmental dysplasia of the hip.

Anteroposterior pelvic radiographs remains the most widely employed method for diagnosing developmental dysplasia of the hip. This study aims to evaluate the accuracy of an artificial intelligence model in measuring angles in pelvic radiographs of the hip. The assessment seeks to demonstrate the efficacy of the artificial intelligence model in diagnosing both developmental dysplasia of the hip and borderline developmental dysplasia of the hip through the analysis of pelvic radiographs. A total of 1,029 patients, including 273 men and 757 women, were retrospectively included in this study. The anteroposterior pelvic radiographs were randomly divided into three sets: the training set (720 cases), the validation set (103 cases), and the test set (206 cases). Key anatomical points on the anteroposterior pelvic radiographs were identified. The Sharp, Tönnis, and Center Edge angles were calculated automatically based on the corresponding criteria. The hip development status was compared between measurements obtained from the artificial intelligence model and those defined manually by two radiologists. The area under the receiver operating characteristic curve was utilized to assess the diagnostic performance of the artificial intelligence model. The results obtained from both manual measurements and the artificial intelligence model demonstrated no significant differences in the Sharp, Tönnis, and Center edge angles (all p > 0.05). The intra-class correlation coefficients and correlation coefficient r values exceeded 0.75, indicating that both the artificial intelligence model and manual measurements exhibited good repeatability and a positive correlation. Notably, the artificial intelligence model provided measurements more faster than those conducted by radiologists (p = 0.001). The artificial intelligence model also demonstrated high diagnostic accuracy, sensitivity, and specificity for developmental dysplasia of the hip. The performance of the artificial intelligence model in diagnosing developmental dysplasia of the hip was robust. Additionally, the results from the artificial intelligence model and manual measurements were largely consistent with clinical diagnosis results (p = 0.01). The artificial intelligence model can effectively evaluate hip conditions by measuring the Sharp, Tönnis, and Center edge angles, which are consistent closely with clinical diagnosis results. The results of the artificial intelligence model measurements demonstrate a high degree of consistency with those obtained through manual measurements. The angles of Sharp, Tönnis, and Center edge, as evaluated by the deep learning-based convolutional neural network model, exhibit robust diagnostic performance in identifying both developmental dysplasia of the hip and borderline developmental dysplasia of the hip. Consequently, the artificial intelligence model has the potential to fully replace manual measurements of these critical hip angles, providing a more efficient and precise alternative for diagnosing both conditions of the hip.

A two-stage deep-learning model for determination of the contact of mandibular third molars with the mandibular canal on panoramic radiographs.

This study aimed to assess the accuracy of a two-stage deep learning (DL) model for (1)detecting mandibular third molars (MTMs) and the mandibular canal (MC), and (2)classifying the anatomical relationship between these structures (contact/no contact) on panoramic radiographs. MTMs and MCs were labeled on panoramic radiographs by a calibrated examiner using bounding boxes. Each bounding box contained MTM and MC on one side. The relationship of MTMs with the MC was assessed on CBCT scans by two independent examiners without the knowledge of the condition of MTM and MC on the corresponding panoramic image, and dichotomized as contact/no contact. Data were split into training, validation, and testing sets with a ratio of 80:10:10. Faster R-CNN was used for detecting MTMs and MCs and ResNeXt for classifying their relationship. AP50 and AP75 were used as outcomes for detecting MTMs and MCs, and accuracy, precision, recall, F1-score, and the area-under-the-receiver-operating-characteristics curve (AUROC) were used to assess classification performance. The training and validation of the models were conducted using the Python programming language with the PyTorch framework. Three hundred eighty-seven panoramic radiographs were evaluated. MTMs were present bilaterally on 232 and unilaterally on 155 radiographs. In total, 619 images were collected which included MTMs and MCs. AP50 and AP75 indicating accuracy for detecting MTMs and MCs were 0.99 and 0.90 respectively. Classification accuracy, recall, specificity, F1-score, precision, and AUROC values were 0.85, 0.85, 0.93, 0.84, 0.86, and 0.91, respectively. DL can detect MTMs and MCs and accurately assess their anatomical relationship on panoramic radiographs.

Prediction Model for the Chloride Ion Permeability Resistance of Recycled Aggregate Concrete Based on Machine Learning

The chloride ion permeability resistance of recycled aggregate concrete (RAC) is influenced by multiple factors, and the prediction model for this resistance based on machine learning is still limited. In the paper, six impact factors (IFs), including the carbonation of recycled coarse aggregates (YN), the replacement ratio of recycled coarse aggregates (r), the bending load level (L), the carbonation time (t) and temperature (T) of RAC, and the replacement ratio of carbonated recycled fine aggregates (f), were considered to conduct a chloride penetration test on RAC. Based on the experimental data, four algorithms, including artificial neural network (ANN), support vector machine (SVM), random forest (RF) and extreme gradient boosting (XGBoost), were adopted to establish the machine learning prediction models and study the relationships between the electric flux of RAC and the IFs. The results showed that the predicted values of all four models were in good agreement with the experimental values, and the XGBoost model had the best prediction performance on the testing set. Based on the XGBoost model, the LIME method was adopted to solve the interpretability problem in the prediction process. The importance ranking of IFs on the electric flux was r &gt; t &gt; f &gt; T &gt; L &gt; YN. A graphical user interface (GUI) was developed based on Python 3.8 software to facilitate the use of machine learning models for the chloride ion permeability resistance of RAC. The research results can provide an accurate prediction of the electric flux of RAC.

Design of judicial public opinion supervision and intelligent decision-making model based on Bi-LSTM

Fuzzy preference modeling in intelligent decision support systems aims to improve the efficiency and accuracy of decision-making processes by incorporating fuzzy logic and preference modeling techniques. While network public opinion (NPO) has the potential to drive judicial reform and progress, it also poses challenges to the independence of the judiciary due to the negative impact of malicious public opinion. To tackle this issue within the context of intelligent decision support systems, this study provides an insightful overview of current NPO monitoring technologies. Recognizing the complexities associated with handling large-scale NPO data and mitigating significant interference, a novel judicial domain NPO monitoring model is proposed, which centers around semantic feature analysis. This model takes into account time series characteristics, binary semantic fitting, and public sentiment intensity. Notably, it leverages a bidirectional long short-term memory (Bi-LSTM) network (S-Bi-LSTM) to construct a judicial domain semantic similarity calculation model. The semantic similarity values between sentences are obtained through the utilization of a fully connected layer. Empirical evaluations demonstrate the remarkable performance of the proposed model, achieving an accuracy rate of 85.9% and an F1 value of 87.1 on the test set, surpassing existing sentence semantic similarity models. Ultimately, the proposed model significantly enhances the monitoring capabilities of judicial authorities over NPO, thereby alleviating the burden on public relations faced by judicial institutions and fostering a more equitable execution of judicial power.

Sex differences in brain MRI using deep learning toward fairer healthcare outcomes

This study leverages deep learning to analyze sex differences in brain MRI data, aiming to further advance fairness in medical imaging. We employed 3D T1-weighted Magnetic Resonance images from four diverse datasets: Calgary-Campinas-359, OASIS-3, Alzheimer's Disease Neuroimaging Initiative, and Cambridge Center for Aging and Neuroscience, ensuring a balanced representation of sexes and a broad demographic scope. Our methodology focused on minimal preprocessing to preserve the integrity of brain structures, utilizing a Convolutional Neural Network model for sex classification. The model achieved an accuracy of 87% on the test set without employing total intracranial volume (TIV) adjustment techniques. We observed that while the model exhibited biases at extreme brain sizes, it performed with less bias when the TIV distributions overlapped more. Saliency maps were used to identify brain regions significant in sex differentiation, revealing that certain supratentorial and infratentorial regions were important for predictions. Furthermore, our interdisciplinary team, comprising machine learning specialists and a radiologist, ensured diverse perspectives in validating the results. The detailed investigation of sex differences in brain MRI in this study, highlighted by the sex differences map, offers valuable insights into sex-specific aspects of medical imaging and could aid in developing sex-based bias mitigation strategies, contributing to the future development of fair AI algorithms. Awareness of the brain's differences between sexes enables more equitable AI predictions, promoting fairness in healthcare outcomes. Our code and saliency maps are available at https://github.com/mahsadibaji/sex-differences-brain-dl.

Assessing Project Resilience Through Reference Class Forecasting and Radial Basis Function Neural Network

A project needs to be able to anticipate potential threats, respond effectively to adverse events, and adapt to environmental changes. This overall capability is known as project resilience. In order to make efficient project decisions when the project is subjected to disruption, such as adjusting the project budget, reformulating the work plan, and rationalizing the allocation of resources, it is necessary to quantitatively understand the level of project resilience. Therefore, this paper develops a novel approach for forecasting project performance, illustrating the changes in performance levels during the disruption and recovery phases of a project and thus quantitatively assessing project resilience. While there are several methods for assessing project resilience in existing research, the majority of assessment approaches originate from within projects and are highly subjective, which makes it difficult to objectively reflect the level of project resilience. Moreover, the availability of project samples is limited, which makes it difficult to forecast the level of project performance. In view of the fact that the Reference Class Forecasting (RCF) technique avoids subjectivity and the Radial Basis Function (RBF) neural network is known to be better at forecasting small sample datasets, this paper therefore combines the RCF technique and the RBF neural network to construct a model that forecasts the project performance of the current project after experiencing a disruption, further assessing the level of the project resilience. Specifically, this paper first presents a conceptual model of project resilience assessment; subsequently, an RBF neural network model that takes into account project budget, duration, risk level of disruption, and performance before disruption based on the RCF technique is developed to forecast project performance after experiencing disruption; and finally, the level of project resilience is assessed through calculating the ratio of recovery to loss of project performance. The model is trained and validated using 64 completed construction projects with disruptions as the datasets. The results show that the average relative errors between the forecast results of schedule performance index (SPI) and the real values are less than 5%, and the R2 of the training set and the testing set is 0.991 and 0.964, respectively, and the discrepancy between the forecasted and real values of project resilience is less than 10%. These illustrate that the model performs well and is feasible for quantifying the level of project resilience, clarifying its impact on project disruption and recovery situations, and facilitating the decision-makers of the project to make reasonable decisions.

Gridded Severe Hail Nowcasting Using 3D U-Nets, Lightning Observations, and the Warn-on-Forecast System

Abstract Hailstorms cause billions of dollars in damage across the United States each year. Part of this cost could be reduced by increasing warning lead times. To contribute to this effort, we developed a nowcasting machine learning model that uses a 3D U-Net to produce gridded severe hail nowcasts for up to 40 minutes in advance. The three U-Net dimensions uniquely incorporate one temporal and two spatial dimensions. Our predictors consist of a combination of output from the National Severe Storms Laboratory Warn-on-Forecast System (WoFS) numerical weather prediction ensemble and remote sensing observations from Vaisala’s National Lightning Detection Network (NLDN). Ground truth for prediction was derived from the Maximum Expected Size of Hail calculated from the gridded NEXRAD WSR-88D radar (GridRad) dataset. Our U-Net was evaluated by comparing its test set performance against rigorous hail nowcasting baselines. These baselines included WoFS ensemble HAILCAST and a logistic regression model trained on WoFS 2-5 km updraft helicity. The 3D U-Net outperformed both these baselines for all forecast period timesteps. Its predictions yielded a neighborhooded maximum critical success index (max CSI) of ~0.48 and ~0.30 at forecast minutes 20 and 40, respectively. These max CSIs exceeded the ensemble HAILCAST max CSIs by as much as ~0.35. The NLDN observations were found to increase the U-Net performance by more than a factor of 4 at some timesteps. This system has shown success when nowcasting hail during complex severe weather events, and if used in an operational environment, may prove valuable.

Preoperative Computed Tomography Radiomics-Based Models for Predicting Microvascular Invasion of Intrahepatic Mass-Forming Cholangiocarcinoma

Objectives The aim of the study is to investigate the ability of preoperative CT (Computed Tomography)-based radiomics signature to predict microvascular invasion (MVI) of intrahepatic mass-forming cholangiocarcinoma (IMCC) and develop radiomics-based prediction models. Materials and Methods Preoperative clinical data, basic CT features, and radiomics features of 121 IMCC patients (44 with MVI and 77 without MVI) were retrospectively reviewed. The loading and display of CT images, delineation of the volume of interest, and feature extraction were performed using 3D Slicer. Radiomics features were selected by the LASSO logistic regression model. Multivariate logistic regression analysis was used to establish the radiomics model, radiologic model, and combined model in the training set (n = 85) to predict the MVI of IMCC, and then verified in the validation set (n = 36). Results Among the 3948 radiomics features extracted from multiphase dynamic enhanced CT imaging, 16 most stable features were selected. The AUC of the radiomics model for predicting MVI in the training set and validation set were 0.935 and 0.749, respectively. The AUC of the radiologic model for predicting MVI in the training set and validation set were 0.827 and 0.796, respectively. When radiomics and radiologic models are combined, the predictive performance of the combined model (constructed with shape, intratumoral vessels, portal venous phase tumor-liver CT ratio, and radscore) is optimal, with an AUC of 0.958 in the training set and 0.829 in the test set for predicting MVI. Conclusions CT radiomics signature is a powerful predictor for predicting MVI. The preoperative combined model (constructed with shape, intratumoral vessels, portal venous phase tumor-liver CT ratio, and radscore) performed well in predicting the MVI.

Abstract A051: Identifying patterns of cell-free DNA associated with elevated risk of diffuse large B-cell lymphoma in adult dogs

Abstract Background: Nonrandom patterns of cell-free DNA (cfDNA) are closely associated with malignancy. We hypothesize that they are also found in the systemic microenvironment that gives rise to cancer, and that such signatures can inform a risk stratification test. To achieve this, we have initiated the Lymphoma Risk Assessment (LyRA) study, using machine learning on a training set of dogs with known health status and a test set of otherwise healthy adult pet dogs to identify cfDNA signatures that are associated with elevated risk of developing diffuse large B- cell lymphoma (DLBCL). We will validate the predictive accuracy of these signatures, including the persistence of the risk environment and the interval between risk detection and development of clinical disease. Since cfDNA is the primary input of the LyRA test, we first performed a pilot study to assess how sample characteristics affect cfDNA quality and subsequent low-pass whole genome sequencing (WGS) data. Methods: Blood samples were collected from pet dogs with the owner’s informed consent. Paired samples were collected into potassium (K3)EDTA tubes and additive-free red top tubes (n = 5 dogs) or K3EDTA tubes and Cell-free DNA BCT® Streck Tubes (n = 6 dogs). Additional serum samples (n=3) were generously provided by the Morris Animal Foundation Golden Retriever Lifetime Study. cfDNA was isolated using the QIAamp® Circulating Nucleic Acid kit. Total cfDNA concentration was measured by PicoGreen™ and fragment distribution by Agilent High Sensitivity D500 ScreenTape® Assay, with comparisons made by starting material (plasma vs. serum) and collection tubes. Results: Serum had both higher total concentrations of cfDNA (PicoGreen™) and calibrated concentrations of long fragment cfDNA (515-658 bp Agilent traces) compared to plasma. In addition, total cfDNA concentrations increased with malignancy, following the pattern: no cancer &amp;lt; cancer &amp;lt; hematological cancer. Median fragment lengths of Agilent peaks also increased with malignancy for short (125-181 bp) and medium (340-425 bp) fragments, in both serum and plasma, but decreased for long fragments. In these pilot data the trends seen were consistent with our hypothesis and with prior studies, although due to sample size, no statistical testing was performed. Conclusions: The pilot study demonstrated that the effects of sample parameters on cfDNA quality are consistent with existing literature, validating our methods and supporting the rationale for the LyRA study. These features may prove valuable when integrated with genomic data to identify high-risk microenvironments. Recent research has shown that a majority of cfDNA in tumor patients originates from non-malignant cells and current methods often overlook potentially important patterns in this so-called 'discard cfDNA.' By focusing on these overlooked patterns, with an emphasis on risk stratification, the LyRA test could shift clinical management to a prevention-focused approach, serving as a model of testing and interception for DLBCL and other cancers in dogs, and potentially in humans. Citation Format: Lauren E Burt, Amy E Treeful, Mitzi Lewellen, Kimberly Demos-Davies, Andrea Chehadeh, Sara Pracht, Ashley J Schulte, Caitlin Feiock, Julia Medland, Davis Seelig, Kelly M Makielski, Ali Khammanivong, Antonella Borgatti, Michael S Henson, Michael Linden, Daniel Vallera, Gary R Cutter, Aaron L Sarver, Jaime F Modiano. Identifying patterns of cell-free DNA associated with elevated risk of diffuse large B-cell lymphoma in adult dogs [abstract]. In: Proceedings of the AACR Special Conference: Liquid Biopsy: From Discovery to Clinical Implementation; 2024 Nov 13-16; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(21_Suppl):Abstract nr A051.

Single Well Production Prediction Model of Gas Reservoir Based on CNN-BILSTM-AM

In the prediction of single-well production in gas reservoirs, the traditional empirical formula of gas reservoirs generally shows poor accuracy. In the process of machine learning training and prediction, the problems of small data volume and dirty data are often encountered. In order to overcome the above problems, a single-well production prediction model of gas reservoirs based on CNN-BILSTM-AM is proposed. The model is built by long-term and short-term memory neural networks, convolutional neural networks and attention modules. The input of the model includes the production of the previous period and its influencing factors. At the same time, the fitting production and error value of the traditional gas reservoir empirical formula are introduced to predict the future production data. The loss function is used to evaluate the deviation between the predicted data and the real data, and the Bayesian hyperparameter optimization algorithm is used to optimize the model structure and comprehensively improve the generalization ability of the model. Three single wells in the Daniudi D28 well area were selected as the database, and the CNN-BILSTM-AM model was used to predict the single-well production. The results show that compared with the prediction results of the convolutional neural network (CNN) model, long short-term memory neural network (LSTM) model and bidirectional long short-term memory neural network (BILSTM) model, the error of the CNN-BILSTM-AM model on the test set of three experimental wells is reduced by 6.2425%, 4.9522% and 3.0750% on average. It shows that on the basis of coupling the empirical formula of traditional gas reservoirs, the CNN-BILSTM-AM model meets the high-precision requirements for the single-well production prediction of gas reservoirs, which is of great significance to guide the efficient development of oil fields and ensure the safety of China’s energy strategy.

Accurate Thermochemistry with Multireference Methods: A Stress Test for Internally Contracted Multireference Coupled-Cluster Theory.

The internally contracted multireference coupled-cluster method with single, double and perturbative triple excitations, icMRCCSD(T), was tested for its performance in the context of computational high-accuracy thermochemistry. The results were gauged against the standard single-reference coupled-cluster hierarchy with up to 5-fold excitations. The test set comprised of a selection of first-row dinuclear compounds and the three 3d-transition metal compounds MnH, FeH, and CoH. The results revealed two problems with the current formulation of icMRCCSD(T). First, the choice of the Dyall Hamiltonian as the zeroth-order Hamiltonian, which leads to a biased description of the different orbital subspaces and particularly poor results for the atomic correlation energies, and second, the tendency to overestimate the perturbative correction for triply excited clusters, in particular in the presence of open shells and correspondingly low orbital-energy gaps. The two problems could be solved by resorting to the effective Fock operator as zeroth-order Hamiltonian and by adopting a modified amplitude equation that includes terms quadratic in the pair clusters. A similar modification was recently proposed by Masios et al. (Phys. Rev. Lett. 2023, 131, 186401) in the context of applying single-reference coupled-cluster theory to systems with small or vanishing band gaps and we chose the acronym '(cT*) correction' in analogy to that work. In contrast to the work of Masios et al., additional terms including single excitation clusters were omitted, as these again lead to an overestimation of correlation effects in more difficult cases. We also tested another alternative for the zeroth-order Hamiltonian and additional higher-order corrections for the correlation energy. These extensions did not significantly improve the results and were also computationally more demanding. The improved icMRCCSD(cT*)F method yields very accurate results with errors, relative to accurate benchmarks, better than 2 kJ/mol for total energies and atomization energies for the entire set of examples considered in this work.

Next-visit prediction and prevention of hypertension using large-scale routine health checkup data.

This paper proposes the use of machine learning models to predict one's risk of having hypertension in the future using their routine health checkup data of their current and past visits to a health checkup center. The large-scale and high-dimensional dataset used in this study comes from MJ Health Research Foundation in Taiwan. The training data for models is separated into 5 folds and used to train 5 models in a 5-fold cross validation manner. While predicting the results for the test set, the voted result of 5 models is used as the final prediction. Experimental results show that our models achieve 69.59% of precision, 77.90% of recall, and 73.51% of F1-score, which outperforms a baseline using only the blood pressure of visitors' last visits. Experiments also show that a visitor who performs a health checkup more often can be predicted better, and models trained with selected important factors achieve better results than those trained with Framingham risk score. We also demonstrate the possibility of using our models to suggest visitors for weight control by adding virtual visits that assume their body weight can be reduced in the near future to model input. Experimental results show that around 5.48% of the people who are with high Body Mass Index of the true positive cases are rejudged as negative, and a rising trend appears when adding more virtual visits, which may be used to suggest visitors that controlling their body weight for a longer time lead to lower probability of having hypertension in the future.

Cluster Perturbation Theory for Core Excited States and Core Ionization Potentials Using Core-Valence Separation.

The development of accurate and fast computational procedures for the ab initio calculation of X-ray spectroscopies is paramount to facilitate theoretical analysis of modern X-ray experiments on molecules. Herein, we present the extension of Cluster Perturbation theory to comprehend the calculation of core excited states and core ionization potentials using the core-valence separation approximation, which has seen widespread success for various quantum chemistry methods. We derive the theoretical framework for introducing core-valence separation into Cluster Perturbation series for excitation energies and display the performance of the methodology in S(D) orbital excitation spaces. The obtained core excitation energies on a test set of medium sized organic molecules show that carbon, nitrogen, and oxygen K-edge excitation energies can be determined with errors below 2 eV relative to the CCSD reference results using the developed CPS(D) excitation energy models which can be used for systems way beyond the reach of conventional CCSD.

Frigatebird optimizer: a novel metaheuristic algorithm

Abstract This paper proposes a new swarm intelligence optimization algorithm - the Frigate Bird Optimizer (FBO). The algorithm is inspired by the unique flight and foraging behaviors of frigatebirds. Its optimization process is divided into two stages: The first stage simulates frigatebirds harassing other seabirds to snatch food, and the search direction and radius of individuals have randomness and uncertainty, which is conducive to global exploration; The second stage simulates frigatebirds observing large fish driving small fish to leap out of the water and preying on them, and individuals tend to gather in the optimal search direction. By simulating the behaviors of frigatebirds under different survival strategies, the algorithm achieves extensive global search in the first stage and fine-tuned local optimization by learning information in the second stage. To evaluate its performance, 46 functions in the CEC2014 and CEC2017 benchmark test sets are selected as objective functions and compared with 9 state-of-the-art meta-heuristic algorithms. The results show that the FBO algorithm has higher performance, excellent iterative optimization ability and strong robustness, and can be applied to different optimization domains.