Separate Tests Research Articles

Optimizing Nucleic Acid Delivery Systems through Barcode Technology.

Conventional biological experiments often focus on in vitro assays because of the inherent limitations when handling multiple variables in vivo, including labor-intensive and time-consuming procedures. Often only a subset of samples demonstrating significant efficacy in the in vitro assays can be evaluated in vivo. Nonetheless, because of the low correlation between the in vitro and in vivo tests, evaluation of the variables under examination in vivo and not solely in vitro is critical. An emerging approach to achieve high-throughput in vivo tests involves using a barcode system consisting of various nucleotide combinations. Unique barcodes for each variant enable the simultaneous testing of multiple entities, eliminating the need for separate individual tests. Subsequently, to identify crucial parameters, samples were collected and analyzed using barcode sequencing. This review explores the development of barcode design and its applications, including the evaluation of nucleic acid delivery systems and the optimization of gene expression in vivo.

Machine learning modeling for ultrasonic quality attribute assessment of pharmaceutical tablets for continuous manufacturing and real-time release testing

In in-process quality monitoring for Continuous Manufacturing (CM) and Critical Quality Attributes (CQA) assessment for Real-time Release (RTR) testing, ultrasonic characterization is a critical technology for its direct, non-invasive, rapid, and cost-effective nature. In quality evaluation with ultrasound, relating a pharmaceutical tablet’s ultrasonic response to its defect state and quality parameters is essential. However, ultrasonic CQA characterization requires a robust mathematical model, which cannot be obtained with traditional first principles-based modeling approaches. Machine Learning (ML) using experimental data is emerging as a critical analytical tool for overcoming such modeling challenges. In this work, a novel Deep Neural Network-based ML-driven Non-Destructive Evaluation (ML-NDE) modeling framework is developed, and its effectiveness for extracting and predicting three CQAs, namely defect states, compression force levels, and amounts of disintegrant, is demonstrated. Using a robotic tablet handling experimental rig, each attribute’s distinct waveform dataset was acquired and utilized for training, validating, and testing the respective ML models. This study details an advanced algorithmic quality assessment framework for pharmaceutical CM in which automated RTR testing is expected to be critical in developing cost-effective in-process real-time monitoring systems. The presented ML-NDE approach has demonstrated its effectiveness through evaluations with separate (unused) test datasets.

Analysis of stock forecasting based on LSTM

The use of the long short-term memory (LSTM) machine learning algorithm for stock prediction is widely used contemporarily. This study the feasibility of price prediction based on LSTM. This study first collected extensive data on stock prices, including the closing prices, volumes, and other relevant indicators, for several companies. Then, it implemented an LSTM-based model using this data, which was trained on a dataset containing historical stock price information over a fixed period. The models performance was evaluated using a separate test set. Based on the analysis, LSTM is successful in forecasting stock a remarkable degree of precision, rendering it an invaluable asset for investors aiming to make well-informed investment choices. Its ability to capture long-term dependencies and patterns within time series data makes it an ideal choice for forecasting future trends in financial markets. By leveraging this model, investors can gain valuable insights into potential market movements and adjust their investment strategies accordingly. Overall, the promising results obtained from applying LSTM-based models highlight their potential value in supporting investors' decision-making processes and ultimately improving investment outcomes.

Numerical investigation of carbon dioxide capture using nanofluids via machine learning

Using nanofluids to capture CO2 is a promising method of reducing emissions. The goal of this study was to develop models that could forecast how well water-based nanofluids would absorb CO2. Several machine learning models, such as Decision Tree, Random Forest, eXtreme Gradient Boosting, and K-Nearest Neighbors, underwent training using a total of 1306 experimental datasets. These datasets contained information on the CO2 solubility in aqueous solutions for different types of nanoparticles. In terms of Average Absolute Relative Deviation (AARD%), Mean Absolute Error (MAE), Relative Absolute Error, Mean Squared Error, and Correlation Coefficient, the predictive performance on separate test data was assessed. The XGBoost model demonstrates a higher degree of accuracy in simulating the absorption capacity of aqueous nanofluid compared to other models. This is evident through the AARD value of 2.8%, MSE of 0.00084, MAE of 0.012 and an R value of 0.992. The research provides insight into the utilization of different machine learning algorithms for simulating the absorption of CO2 by nanofluids. By employing accurate data-driven models, the efficiency of nanofluid-based CO2 capture processes can be enhanced through improvements in their design and operating conditions.

Comprehensive functional testing based on physical load with changing power in a closed cycle for students

A large number of studies are devoted to the study of the functional capabilities of pupils and students. The majority of scientists and practitioners evaluate the level of functional capabilities with the help of various test tasks on physical fitness, also use various functional tests and functional testing with the help of dosed physical loads, in isolated cases with the help of maximum loads. In the light of the published data, there is a noticeable controversy of opinions in determining the level of functional capabilities due to certain inaccuracies in obtaining results and inaccuracies in the approaches to finding relevant indicators, which do not take into account the age-related changes occurring in the body of pupils and students. In our opinion, the most accurate, operative and informative is functional testing, in which the power of the physical load changes in a closed cycle. This technique allows to detect not only the indicators of physical performance and the reaction of the cardiovascular system, but also allows to establish the regulatory and energy components of the systemic reaction of the human body. The implementation of such monitoring technology and information program, which provides an automated assessment of the functional capabilities of the human body, and is accurate, informative and physiologically justified, is relevant in our time. In order to optimize the educational and educational process of physical education and obtain more complete information about the level of functional capabilities of students of higher educational institutions, it is advisable to use complex monitoring taking into account the appropriate functional testing and separate tests of physical fitness, which will help specialists in the field of physical education to obtain a more accurate and versatile information about students' functional capabilities, assess their state of health, implement individual and differential approaches in the educational process of physical education based on the received data, make corrections to the educational process in educational institutions.

Abstract 6177: Machine learning enables prediction of ADC targets from whole slide H&E images

Abstract Background: The efficacy of antibody-drug conjugates (ADCs) depends on the expression and specificity of the target antigen by tumor cells. Although H&E-stained slides are routinely collected during cancer care, specialized IHC staining is typically required to ascertain antigen expression. Such stains are not always available or readily deployed. The need to perform separate IHC tests for each candidate ADC may burden clinical labs and can hinder access to care in resource-limited settings. Here we develop an ensemble of machine learning models to accurately predict the expression of 166 distinct ADC targets directly from H&E images. Methods: For each ADC-targeted gene, patients with copy-number amplifications (CNAs) were identified from somatic whole exome sequencing. Genes differentially expressed in patients with CNAs were identified from bulk transcriptomics. For each gene, an expression signature was developed based on the expression levels of differentially upregulated genes. Next, whole-slide, H&E-stained histopathology images were embedded into a lower-dimensional representation via a transformer model trained with self-supervised learning. Neural networks were developed to predict a patient’s probability of having a CNA in an ADC-targeted gene, as indicated by an expression signature exceeding the p90. All evaluation metrics were ascertained by 5-fold cross-validation, with training and evaluation on independent patients. Results: For each of the 166 ADC-targeted genes, a median of 154 patients were found to harbor a CNA, and the expression signature included a median of 180 genes. In all cases, patients with CNAs had significantly higher expression signatures than those without. For predicting likely CNA status directly from H&E histopathology images, the mean AUROC was 0.888 (95% CI, 0.876-0.900) and the mean AUPRC was 0.571 (95% CI, 0.531-0.611). Among the 166 ADC-targeted genes, the AUROC exceeded 0.95 for 31.3%, 0.8 for 80.7%, and 0.725 for 100%. The best-predicted ADC target was SLC7A5 (AUROC: 0.995 [95% CI, 0.994-0.998]; AUPRC: 0.967 [95% CI, 0.963-0.976]). Conclusion: We have developed models that accurately predict the likely expression of ADC targets based solely on H&E images. The ability to accurately discern the presence of ADC antigens from H&E images has numerous potential applications, including cohort refinement, computer-aided diagnosis, and personalized treatment planning. Citation Format: Zachary Ryan McCaw, Anna Shcherbina, Yajas Shah, insitro Research Team, Philip Tagari, Daphne Koller, Christopher Probert. Machine learning enables prediction of ADC targets from whole slide H&E images [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 6177.

Abstract 7286: Optimizing prediction of metastatic castration-resistant prostate cancer: Multimodal fusion of clinicopathological and genomic features with machine learning

Abstract Background: Transitioning from metastatic castration-sensitive prostate cancer (mCSPC) to its resistant variant poses risks of intensified medication, toxic side effects, and financial burdens for men undergoing treatment. Our study proposes a multimodal approach that integrates clinical, pathological, and genomic features to optimize prediction of metastatic castration-resistant prostate cancer (mCRPC) events. By applying machine learning (MML) techniques to multimodal data, we aim to stratify these patients based on the risk of developing mCRPC, contributing to the development of safer and personalized treatment strategies. Methods: We analyzed a large cohort of patients with mCSPC (n=399) with a minimum of 36 month follow-up, annotated with clinical, pathological, and genomic features, encompassing relevant variables such as disease volume, PSA, metastases timing, variant classification, Grade Group, fraction of genome altered, MSI score, mutation counts, karyotypes, tumor mutational burden, and purity. Using a multimodal machine learning framework, we extracted informative features and employed eight distinct machine learning algorithms: K-Nearest Neighbor, Support Vector Machine, Decision Tree, and Logistic Regression, Support Vector Machine with RBF Kernel, Random Forest, and Gradient Boosting, in addition to a Deep Neural Networks architecture for building predictive models in supervised binary classification experiments. The models' performance was evaluated on separate training (80%) and testing sets (20%), and standard evaluation metrics, such as the area under the receiver operating characteristic curve (AUROC), and accuracy, were computed. Correlations were utilized to explore the relationships between features, and permutation analysis was employed to determine the importance of predictors. All raw data included in the analysis are available on cBioPortal database. The study is supported by the NIH-NCI-T32 for Next Generation Pathologists Program at our institution. Results: Of the 399 mCSPC patients, 56% developed castration resistance, 50% had Grade Group 5 disease, and 69% exhibited missense mutations. In a series of 8 experiments, the Support Vector Machine with RBF Kernel ensemble model and SVC exhibited the highest performance with an AUROC score of 0.77, while the remaining models tested in the study demonstrated AUROC scores ranging from 0.62 to 0.75. Notably, the fraction of altered genome emerged as the top-ranked predictor, displaying the highest importance score. Conclusions: Our study demonstrates the strong predictive performance of MML models in accurately identifying mCRPC events by leveraging routine clinical, pathological, and genomic data, offering valuable guidance for optimizing patient stratification and tailoring personalized therapeutic interventions. Citation Format: Mohammad K. Alexanderani, Francesca Khani, Matthew Greenblatt, Brian Robinson, Massimo Loda, Luigi Marchionni. Optimizing prediction of metastatic castration-resistant prostate cancer: Multimodal fusion of clinicopathological and genomic features with machine learning [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 7286.

Abstract 1065: Two-step method for early detection of ovarian cancer with high specificity via platelet RNA

Abstract Owing to lack of disease-specific symptoms and screening methods, most of patients with ovarian cancer are diagnosed at an advanced stage. Recent technology based on platelet RNA aids in detection of tumors at the early stages. Also, for population screening of low-prevalence diseases like cancer, accurate detection with high specificity is essential to improve diagnostic methods. Thus, we proposed platelet RNA-based early ovarian cancer detection with great specificity. It is a two-step method for detecting ovarian tumors with more than 99% specificity using exon-exon junction features and sampling invariant normalization and finding their malignancy with more than 99% negative predictive value using exon-exon junction and hematology parameters. First, we downloaded public platelet transcriptome data of gynecological cancer including ovarian cancer (n=151), benign tumor (n=30), and healthy counterparts (n=218) from GEO (GSE158508, 89843, and 183635). Second, we prospectively enrolled patients with gynecological cancer (n=31), benign tumors (n=20), and healthy women (n=18) at Seoul National University Hospital (SNUH) and Boaz Medical Center and obtained platelet transcriptome data (FMH data). Feature selection and model development were conducted using public training set (n=243), public validation set (n=156), and FMH training/validation set (n=47). The batch-invariant normalization was performed, and 198 splice junctions were selected as features from training/validation set for the bootstrap aggregation of the SVM model diagnosing the existence of an ovarian tumor. The model performance was assessed from a separate test set only composed of FMH data (n=22). Our model that demonstrated 96.8% sensitivity, 100.0% specificity, with a predetermined cut-off value. Next, FMH training/validation set was used for model development of following malignancy test. 10 splice junctions and 19 hematology parameters were selected and SVM models were separately developed for splice junctions and hematology parameters using 5-fold cross validation. The predictions were combined using a logical OR operation to obtain the final prediction result. The result showed its diagnostic performance with 100% sensitivity or NPV, and 50.0% specificity in the test data set with a predetermined cut-off value. We proposed a two-step method to operationally improve the existing protocol for ovarian cancer screening. Our model initially excludes most healthy individuals who do not have ovarian tumors and excludes patients with benign ovarian tumors who do not necessitate medical testing. To conclude, our model allows physicians to identify a subset of ovarian tumor patients with a higher risk of malignancy even at early stages; it exhibits potential in enhancing early diagnosis of ovarian cancer, leading to increase of treatment effectiveness and ultimately augmenting the survival of patients with ovarian cancer. Citation Format: Eunyong Ahn, Se Ik Kim, Sungmin Park, Sarah Kim, Yeochan Kim, Eunchong Huang, Suyeon Lee, Dong Won Hwang, Heeyeon Kim, HyunA Jo, Untack Cho, Juwon Lee, TaeJin Ahn, Yong-Sang Song. Two-step method for early detection of ovarian cancer with high specificity via platelet RNA [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 1065.

Abstract P287: Incorporating Behavioral and Social Determinants of Health Variables Into a Machine Learning Model Predicting Cardiometabolic Disease

Introduction: Machine learning models hold potential for improved cardiometabolic disease prediction and more efficacious prevention and intervention efforts. Current models are limited by use of cross-sectional datasets and variables (features) consisting of diagnostic criteria (such as blood glucose or hemoglobin A1c in type 2 diabetes models) and overlook health behaviors and social determinants of health (HB-SDH). Hypothesis: Machine learning models built with HB-SDH variables will accurately predict type 2 diabetes. Methods: We used data from 2,493 participants without diabetes in the Adolescent to Adult Health study (mean age = 15.5 years at baseline (1994), 40.9% male) who contributed blood samples and anthropometric measures in wave 4 (2008) or 5 (2016-2018). We used an 80/20 split to form separate training and test datasets; the training dataset was used to build random forest and XGBoost models, and performance with respect to classifying diabetes was evaluated in the test dataset. We first built a model using 15 demographic and biomarker features as a comparator for our second model, which included 34 HB-SDH features measured during adulthood but no biomarkers. Results: Five-hundred sixteen participants developed type 2 diabetes. In XGBoost, the comparator model was found to predict diabetes with 92.6% accuracy (95% CI: 89.8%, 94.8%) and area under the curve (AUC) = 0.8165. The HB-SDH model had 88.7% accuracy (95% CI: 85.4, 91.4%) and AUC = 0.7631. Using random forest, the comparator model had 93.0% accuracy (95% CI: 90.3, 95.2%) and AUC = 0.8376, while the HB-SDH model had 89.8% (95% CI: 88.6, 92.4%) accuracy and AUC = 0.7650. The top 10 variables in ascertaining classifications in the random forest model included self-reported general health, waist circumference, self-reported anxiety diagnosis, self-reported hypertension diagnosis, income, BMI, education level, change in weight, financial scarcity, and experienced stigma, while in the XGBoost model these were self-reported general health, experienced stigma, financial scarcity, self-reported anxiety diagnosis, experienced weight stigma, waist circumference, income, self-reported hypertension diagnosis, sugar-sweetened beverage intake, and BMI. Conclusions: Machine learning models built with behavioral and social determinants of health variables perform comparably to models with biomarkers and identify salient features for diabetes risk. The features that factored into classification performance were similar between random forest and XGBoost models. In this population, HB-SDH of relevance included socioeconomic indicators, sugary beverages, anxiety, and experiencing stigma, in addition to adiposity and hypertension. This finding needs to be replicated in diverse cohorts that may experience different HB-SDH.

Prediction of tissue outcome in acute ischemic stroke based on single-phase CT angiography at admission.

In acute ischemic stroke, prediction of the tissue outcome after reperfusion can be used to identify patients that might benefit from mechanical thrombectomy (MT). The aim of this work was to develop a deep learning model that can predict the follow-up infarct location and extent exclusively based on acute single-phase computed tomography angiography (CTA) datasets. In comparison to CT perfusion (CTP), CTA imaging is more widely available, less prone to artifacts, and the established standard of care in acute stroke imaging protocols. Furthermore, recent RCTs have shown that also patients with large established infarctions benefit from MT, which might not have been selected for MT based on CTP core/penumbra mismatch analysis. All patients with acute large vessel occlusion of the anterior circulation treated at our institution between 12/2015 and 12/2020 were screened (N = 404) and 238 patients undergoing MT with successful reperfusion were included for final analysis. Ground truth infarct lesions were segmented on 24 h follow-up CT scans. Pre-processed CTA images were used as input for a U-Net-based convolutional neural network trained for lesion prediction, enhanced with a spatial and channel-wise squeeze-and-excitation block. Post-processing was applied to remove small predicted lesion components. The model was evaluated using a 5-fold cross-validation and a separate test set with Dice similarity coefficient (DSC) as the primary metric and average volume error as the secondary metric. The mean ± standard deviation test set DSC over all folds after post-processing was 0.35 ± 0.2 and the mean test set average volume error was 11.5 mL. The performance was relatively uniform across models with the best model according to the DSC achieved a score of 0.37 ± 0.2 after post-processing and the best model in terms of average volume error yielded 3.9 mL. 24 h follow-up infarct prediction using acute CTA imaging exclusively is feasible with DSC measures comparable to results of CTP-based algorithms reported in other studies. The proposed method might pave the way to a wider acceptance, feasibility, and applicability of follow-up infarct prediction based on artificial intelligence.

Absorption Distribution Metabolism Excretion and Toxicity Property Prediction Utilizing a Pre-Trained Natural Language Processing Model and Its Applications in Early-Stage Drug Development.

Machine learning techniques are extensively employed in drug discovery, with a significant focus on developing QSAR models that interpret the structural information of potential drugs. In this study, the pre-trained natural language processing (NLP) model, ChemBERTa, was utilized in the drug discovery process. We proposed and evaluated four core model architectures as follows: deep neural network (DNN), encoder, concatenation (concat), and pipe. The DNN model processes physicochemical properties as input, while the encoder model leverages the simplified molecular input line entry system (SMILES) along with NLP techniques. The latter two models, concat and pipe, incorporate both SMILES and physicochemical properties, operating in parallel and with sequential manners, respectively. We collected 5238 entries from DrugBank, including their physicochemical properties and absorption, distribution, metabolism, excretion, and toxicity (ADMET) features. The models' performance was assessed by the area under the receiver operating characteristic curve (AUROC), with the DNN, encoder, concat, and pipe models achieved 62.4%, 76.0%, 74.9%, and 68.2%, respectively. In a separate test with 84 experimental microsomal stability datasets, the AUROC scores for external data were 78% for DNN, 44% for the encoder, and 50% for concat, indicating that the DNN model had superior predictive capabilities for new data. This suggests that models based on structural information may require further optimization or alternative tokenization strategies. The application of natural language processing techniques to pharmaceutical challenges has demonstrated promising results, highlighting the need for more extensive data to enhance model generalization.

Full-scale tests of deicing with seawater

Sea-spray icing is one of the major hazards for small- and medium-sized vessels in polar regions. Predominant anti- and deicing measures include prevention by heeding the weather forecasts and avoiding high-risk situations, protection by enclosing exposed and high-priority areas, manual ice removal by personnel, heat tracing and surplus heat. Energy is in limited supply on vessels, and alternative ways of ice protection are sought after. Seawater is readily available, and as evident from wave-washing, either naturally occurring or increased by provocative maneuvering, seawater can hold an efficient deicing capacity. This study contains knowledge gained from four separate full-scale deicing tests. Deicing is achieved during the field tests by utilizing the vessel's external fire sprinkler systems and in one case a fire hose. To the author's knowledge, no recent tests with deicing of vessels using flushing seawater have been performed, and this article is considered a first step towards evaluating the viability of the method. Targeted high-volume, low-pressure systems seem to be an effective method for deicing, particularly combined with favorable design. However, because of the risk of increased icing or freezing run-off the method is suitable for vessels and structures with sufficient run-off capabilities. Vessel safety can be improved by incorporating the proposed method.

Orientation of two-dimensional materials mf-BN in Pebax mixed matrix membranes by magnetic fields for enhancing CO2/N2 separation performance

Two-dimensional materials possess a high aspect ratio and excellent spatial utilization, making them potential filler for the fabrication of mixed matrix membranes (MMMs). However, the disordered arrangement of two-dimensional materials can negatively impact membrane performance. In this study, hexagonal boron nitride (h-BN) two-dimensional material loaded with polyethyleneimine (PEI) and magnetic material Fe3O4 was prepared. The filler (mf-BN) was incorporated into Pebax-1657, and the orientation of mf-BN in the MMM was controlled using a magnetic field. Horizontally and vertically oriented mf-BN/Pebax MMMs were successfully prepared and subjected to gas separation tests. The results demonstrate that oriented MMMs exhibit superior performance compared to non-oriented ones. When the mf-BN loading is 20 wt%, the CO2/N2 selectivity for horizontally and vertically oriented MMMs respectively reaches 83.9 and 76.8. The CO2 permeability increases to 114.7 and 139.8 Barrer, respectively. The magnetic field orientation of filler presents a promising approach for further enhancing the performance of MMMs.

Preoperatively predicting vessels encapsulating tumor clusters in hepatocellular carcinoma: Machine learning model based on contrast-enhanced computed tomography.

Recently, vessels encapsulating tumor clusters (VETC) was considered as a distinct pattern of tumor vascularization which can primarily facilitate the entry of the whole tumor cluster into the bloodstream in an invasion independent manner, and was regarded as an independent risk factor for poor prognosis in hepatocellular carcinoma (HCC). To develop and validate a preoperative nomogram using contrast-enhanced computed tomography (CECT) to predict the presence of VETC+ in HCC. We retrospectively evaluated 190 patients with pathologically confirmed HCC who underwent CECT scanning and immunochemical staining for cluster of differentiation 34 at two medical centers. Radiomics analysis was conducted on intratumoral and peritumoral regions in the portal vein phase. Radiomics features, essential for identifying VETC+ HCC, were extracted and utilized to develop a radiomics model using machine learning algorithms in the training set. The model's performance was validated on two separate test sets. Receiver operating characteristic (ROC) analysis was employed to compare the identified performance of three models in predicting the VETC status of HCC on both training and test sets. The most predictive model was then used to constructed a radiomics nomogram that integrated the independent clinical-radiological features. ROC and decision curve analysis were used to assess the performance characteristics of the clinical-radiological features, the radiomics features and the radiomics nomogram. The study included 190 individuals from two independent centers, with the majority being male (81%) and a median age of 57 years (interquartile range: 51-66). The area under the curve (AUC) for the combined radiomics features selected from the intratumoral and peritumoral areas were 0.825, 0.788, and 0.680 in the training set and the two test sets. A total of 13 features were selected to construct the Rad-score. The nomogram, combining clinical-radiological and combined radiomics features could accurately predict VETC+ in all three sets, with AUC values of 0.859, 0.848 and 0.757. Decision curve analysis revealed that the radiomics nomogram was more clinically useful than both the clinical-radiological feature and the combined radiomics models. This study demonstrates the potential utility of a CECT-based radiomics nomogram, incorporating clinical-radiological features and combined radiomics features, in the identification of VETC+ HCC.

Compact Viscosity Sensors for Downhole Enhanced Oil Recovery Polymer Fluid Degradation Monitoring

Summary There are currently no technologies available to measure polymer solution viscosities at realistic downhole conditions in a well during enhanced oil recovery (EOR). In this paper, custom-made probes using quartz tuning fork (QTF) resonators are demonstrated for measurements of viscosity of polymer fluids in the laboratory. The electromechanical response of the resonators was calibrated in simple Newtonian fluids and in non-Newtonian polymer fluids at different concentrations. The responses were then used to measure field-collected samples of polymer injection fluids. In the polymer fluids, the measured viscosity values by tuning forks were lower than those measured by the conventional rheometer at 6.8 s−1, closer to the solvent viscosity values. However, the predicted rheometer viscosity vs. QTF-measured viscosity showed a distinct exponential correlation (R2=0.9997), allowing for an empirical calibration between the two viscometers for fluids having the same solvent and polymer compositions. The QTF sensors produced acceptable viscosity measurements of polymer fluids within the required polymer concentration ranges used in the field and predicted field sample viscosities with less than 1–2 cp (or 10–20%) error from the rheometer data. Results were validated based on separate independent tests where the devices were used to measure the viscosity of Newtonian fluids and non-Newtonian polymer fluids in a series of consecutive dip tests, simulating more realistic usage. These devices can be used to measure either the “relative” viscosity changes from a polymer solution prior and post-injection or to measure a “calibrated” viscosity via empirical exponential correlation. The compact QTF sensors developed in this study can be easily integrated into portable systems for laboratory or wellsite deployment as well as logging tools for downhole deployment. This work also demonstrates the ability of these QTF devices to make sensitive viscosity measurements at high-frequencies, opening opportunities for their use in high-frequency rheology studies of EOR fluids.

Application of machine learning algorithms for accurate determination of bilirubin level on in vitro engineered tissue phantom images

Neonatal Jaundice is a common occurrence in neonates. High excess bilirubin would lead to hyperbilirubinemia, leading to irreversible adverse damage such as kernicterus. Therefore, it is necessary and important to monitor neonates’ bilirubin levels in real-time for immediate intervention. However, current screening protocols have their inherent limitations, necessitating more convenient measurements. In this proof-of-concept study, we evaluated the feasibility of using machine learning for the screening of hyperbilirubinemia in neonates from smartphone-acquired photographs. Different machine learning models were compared and evaluated to gain a better understanding of feature selection and model performance in bilirubin determination. An in vitro study was conducted with a bilirubin-containing tissue phantom to identify potential biological and environmental confounding factors. The findings of this study present a systematic characterization of the confounding effect of various factors through separate parametric tests. These tests uncover potential techniques in image pre-processing, highlighting important biological features (light scattering property and skin thickness) and external features (ISO, lighting conditions and white balance), which together contribute to robust model approaches for accurately determining bilirubin concentrations. By obtaining an accuracy of 0.848 in classification and 0.812 in regression, these findings indicate strong potential in aiding in the design of clinical studies using patient-derived images.

A generalized hypothesis test for community structure in networks

AbstractResearchers theorize that many real-world networks exhibit community structure where within-community edges are more likely than between-community edges. While numerous methods exist to cluster nodes into different communities, less work has addressed this question: given some network, does it exhibit statistically meaningful community structure? We answer this question in a principled manner by framing it as a statistical hypothesis test in terms of a general and model-agnostic community structure parameter. Leveraging this parameter, we propose a simple and interpretable test statistic used to formulate two separate hypothesis testing frameworks. The first is an asymptotic test against a baseline value of the parameter while the second tests against a baseline model using bootstrap-based thresholds. We prove theoretical properties of these tests and demonstrate how the proposed method yields rich insights into real-world datasets.

Deconstructing the Blueprint for Infringement: Remedying Flawed Interpretations of the § 120(a) Exception to Architecture Copyrights

Deconstructing the Blueprint for Infringement: Remedying Flawed Interpretations of the § 120(a) Exception to Architecture Copyrights

The effects of a nonsteroidal anti-inflammatory drug on the behavioural and physiological parameters of beef cows and calves assisted at calving

Non-steroidal anti-inflammatory drugs (NSAIDs) may be administered to the cow or the calf as a pain mitigation strategy to combat the negative impacts of injury or trauma associated with a difficult calving. However, the effects of NSAIDs on beef cows’ and calves’ behaviour related to pain and cow-calf bonding after an assisted calving have not been studied. Therefore, the objective of this study was to investigate the effects of meloxicam administered to beef cows and calves after an assisted calving by measuring differences in behaviours associated with pain and cow-calf bonding, and physiological parameters associated with pain. Twenty-three cow-calf pairs assisted at calving were randomly allocated to two medication groups, meloxicam (Metacam®, 20 mg/ml, 0.5 mg/kg body weight, Boehringer Ingelheim, Ingelheim, Germany) or placebo (0.025 ml/kg). Cow blood samples for serum haptoglobin concentration and thermal images of the vulva were taken within 10 minutes after calving and 24±1 hours after calving. Calf blood samples for L‐lactate concentration and thermal images of the head were taken at birth and images repeated at 24±1 hours after birth. Blood samples for serum IgG concentration were taken at 24±1 hours after birth. After at-birth sample collection and treatment administration, the cow-calf pairs were placed in separate box stalls, and behaviours were video recorded for 24±1 hours. A human approach test and a separation test were performed after the 24±1 hour period. Descriptive statistics, multivariable linear and logistic regression models, and non-parametric tests were used to analyze the data. There were no significant differences between meloxicam and placebo groups for serum IgG concentration, haptoglobin concentration, or changes in temperature in the cows’ vulva or calves’ head. Additionally, there were no significant differences between meloxicam and placebo groups for the cows’ behaviours (i.e., time spent lying in sternal recumbency, standing, feeding, self-grooming, grooming the calf, and frequency of tail flicking, tail raising, and pressing against the box stall). Calves treated with meloxicam were more active (P=0.04) and played more (P=0.01) than placebo calves. No other behaviours (i.e., time spent lying in sternal recumbency, attempting to stand, standing, walking, being in a nursing position, investigating, and frequency of approaching the cow) were significantly different between calves treated with meloxicam or placebo. No significant difference (P=0.83) in bonding behaviours was identified for cows and calves treated with meloxicam or a placebo. The anti-inflammatory effects of meloxicam in calves after an assisted calving may improve calf welfare.

Automated surgical step recognition in transurethral bladder tumor resection using artificial intelligence: transfer learning across surgical modalities.

Automated surgical step recognition (SSR) using AI has been a catalyst in the "digitization" of surgery. However, progress has been limited to laparoscopy, with relatively few SSR tools in endoscopic surgery. This study aimed to create a SSR model for transurethral resection of bladder tumors (TURBT), leveraging a novel application of transfer learning to reduce video dataset requirements. Retrospective surgical videos of TURBT were manually annotated with the following steps of surgery: primary endoscopic evaluation, resection of bladder tumor, and surface coagulation. Manually annotated videos were then utilized to train a novel AI computer vision algorithm to perform automated video annotation of TURBT surgical video, utilizing a transfer-learning technique to pre-train on laparoscopic procedures. Accuracy of AI SSR was determined by comparison to human annotations as the reference standard. A total of 300 full-length TURBT videos (median 23.96 min; IQR 14.13-41.31 min) were manually annotated with sequential steps of surgery. One hundred and seventy-nine videos served as a training dataset for algorithm development, 44 for internal validation, and 77 as a separate test cohort for evaluating algorithm accuracy. Overall accuracy of AI video analysis was 89.6%. Model accuracy was highest for the primary endoscopic evaluation step (98.2%) and lowest for the surface coagulation step (82.7%). We developed a fully automated computer vision algorithm for high-accuracy annotation of TURBT surgical videos. This represents the first application of transfer-learning from laparoscopy-based computer vision models into surgical endoscopy, demonstrating the promise of this approach in adapting to new procedure types.