Large Data Collections Research Articles

Precision medicine in complex diseases-Molecular subgrouping for improved prediction and treatment stratification.

Complex diseases are caused by a combination of genetic, lifestyle, and environmental factors and comprise common noncommunicable diseases, including allergies, cardiovascular disease, and psychiatric and metabolic disorders. More than 25% of Europeans suffer from a complex disease, and together these diseases account for 70% of all deaths. The use of genomic, molecular, or imaging data to develop accurate diagnostic tools for treatment recommendations and preventive strategies, and for disease prognosis and prediction, is an important step toward precision medicine. However, for complex diseases, precision medicine is associated with several challenges. There is a significant heterogeneity between patients of a specific disease-both with regards to symptoms and underlying causal mechanisms-and the number of underlying genetic and nongenetic risk factors is often high. Here, we summarize precision medicine approaches for complex diseases and highlight the current breakthroughs as well as the challenges. We conclude that genomic-based precision medicine has been used mainly for patients with highly penetrant monogenic disease forms, such as cardiomyopathies. However, for most complex diseases-including psychiatric disorders and allergies-available polygenic risk scores are more probabilistic than deterministic and have not yet been validated for clinical utility. However, subclassifying patients of a specific disease into discrete homogenous subtypes based on molecular or phenotypic data is a promising strategy for improving diagnosis, prediction, treatment, prevention, and prognosis. The availability of high-throughput molecular technologies, together with large collections of health data and novel data-driven approaches, offers promise toward improved individual health through precision medicine.

Deep learning health management diagnostics applied to the NIST smoke experiments

Fire is one of the most important hazards that must be considered in advanced nuclear power plant safety assessments. The Nuclear Regulatory Commission (NRC) has developed a large collection of experimental data and associated analyses related to the study of fire safety. In fact, computational fire models are based on quantitative comparisons to those experimental data. During the modeling process, it is important to develop diagnostic health management systems to check the equipment status in fire processes. For example, a fire sensor does not directly provide accurate and complex information that nuclear power plants (NPPs) require. With the assistance of the machine learning method, NPP operators can directly get information on local, ignition, fire material of an NPP fire, instead of temperature, smoke obscuration, gas concentration, and alarm signals. In order to improve the predictive capabilities, this work demonstrates how the deep learning classification method can be used as a diagnostic tool in a specific set of fire experiments. Through a single input from a sensor, the deep learning tool can predict the location and type of fire. This tool also has the capability to provide automatic signals to potential passive fire safety systems. In this work, test data are taken from a specific set of the National Institute of Standards and Technology (NIST) fire experiments in a residential home and analyzed by using the machine learning classification models. The networks chosen for comparison and evaluation are the dense neural networks, convolutional neural networks, long short-term memory networks, and decision trees. The dense neural network and long short-term memory network produce similar levels of accuracy, but the convolutional neural network produces the highest accuracy.

Weather forecasting using big data

The use of big data in weather forecasting is examined in this article. Large and complicated data collections that can be examined to find patterns, trends, and relationships are referred to as "big data." Big data has become more crucial to weather forecasting in recent years since it can offer insightful information about weather trends and boost forecasting precision. The difficulties of using large data for weather forecasting are discussed in the article along with the methods for processing and analyzing it. It also offers case studies that show how big data has increased the precision of weather forecasts. The paper concludes by highlighting the potential advantages of big data in weather forecasting and by discussing its future applications. Big data can be used to improve weather predictions.

NbThermo: a new thermostability database for nanobodies.

We present NbThermo-a first-in-class database that collects melting temperatures (Tm), amino acid sequences and several other categories of useful data for hundreds of nanobodies (Nbs), compiled from an extensive literature search. This so-far unique database currently contains up-to-date, manually curated data for 564 Nbs. It represents a contribution to efforts aimed at developing new algorithms for reliable Tm prediction to assist Nb engineering for a wide range of applications of these unique biomolecules. Nbs from the two most common source organisms-llama and camel-show similar distributions of melting temperatures. A first exploratory research that takes advantage of this large data collection evidences that understanding the structural bases of Nb thermostability is a complex task, since there are no apparent differences in sequence patterns between the frameworks of Nbs with lower and higher melting temperatures, indicating that the highly variable loops play a relevant role in defining Nb thermostability. Database URL https://valdes-tresanco-ms.github.io/NbThermo.

Deep learning-based end-to-end scan-type classification, pre-processing, and segmentation of clinical neuro-oncology studies.

Modern neuro-oncology workflows are driven by large collections of high-dimensional MRI data obtained using varying acquisition protocols. The concomitant heterogeneity of this data makes extensive manual curation and pre-processing imperative prior to algorithmic use. The limited efforts invested towards automating this curation and processing are fragmented, do not encompass the entire workflow, or still require significant manual intervention. In this work, we propose an artificial intelligence-driven solution for transforming multi-modal raw neuro-oncology MRI Digital Imaging and Communications in Medicine (DICOM) data into quantitative tumor measurements. Our end-to-end framework classifies MRI scans into different structural sequence types, preprocesses the data, and uses convolutional neural networks to segment tumor tissue subtypes. Moreover, it adopts an expert-in-the-loop approach, where segmentation results may be manually refined by radiologists. This framework was implemented as Docker Containers (for command line usage and within the eXtensible Neuroimaging Archive Toolkit [XNAT]) and validated on a retrospective glioma dataset (n = 155) collected from the Washington University School of Medicine, comprising preoperative MRI scans from patients with histopathologically confirmed gliomas. Segmentation results were refined by a neuroradiologist, and performance was quantified using Dice Similarity Coefficient to compare predicted and expert-refined tumor masks. The scan-type classifier yielded a 99.71% accuracy across all sequence types. The segmentation model achieved mean Dice scores of 0.894 (± 0.225) for whole tumor segmentation. The proposed framework can automate tumor segmentation and characterization - thus streamlining workflows in a clinical setting as well as expediting standardized curation of large-scale neuro-oncology datasets in a research setting.

Commercializing Personal Health Information: A Critical Qualitative Content Analysis of Documents Describing Proprietary Primary Care Databases in Canada.

Commercial data brokers have amassed large collections of primary care patient data in proprietary databases. Our study objective was to critically analyze how entities involved in the collection and use of these records construct the value of these proprietary databases. We also discuss the implications of the collection and use of these databases. We conducted a critical qualitative content analysis using publicly available documents describing the creation and use of proprietary databases containing Canadian primary care patient data. We identified relevant commercial data brokers, as well as entities involved in collecting data or in using data from these databases. We sampled documents associated with these entities that described any aspect of the collection, processing, and use of the proprietary databases. We extracted data from each document using a structured data tool. We conducted an interpretive thematic content analysis by inductively coding documents and the extracted data. We analyzed 25 documents produced between 2013 and 2021. These documents were largely directed at the pharmaceutical industry, as well as shareholders, academics, and governments. The documents constructed the value of the proprietary databases by describing extensive, intimate, detailed patient-level data holdings. They provided examples of how the databases could be used by pharmaceutical companies for regulatory approval, marketing and understanding physician behaviour. The documents constructed the value of these data more broadly by claiming to improve health for patients, while also addressing risks to privacy. Some documents referred to the trade-offs between patient privacy and data utility, which suggests these considerations may be in tension. Documents in our analysis positioned the proprietary databases as socially legitimate and valuable, particularly to pharmaceutical companies. The databases, however, may pose risks to patient privacy and contribute to problematic drug promotion. Solutions include expanding public data repositories with appropriate governance and external regulatory oversight.

Form data as a resource in architectural analysis: an architectural distant reading of wooden churches from the Carpathian Mountain regions of Eastern Europe

ABSTRACT Recent research into architectural form analysis using deep learning (DL) methods has shown potential to identify features from large collections of building data, shedding new light into formal aspects of our built environment. As these methods begin to enter architectural, urban, and policy design contexts, it becomes important to develop critical approaches to employing them. In this paper, we document and reflect upon our efforts to create a custom dataset of 3-D models of 331 wooden churches located within the Carpathian Mountains of Eastern Europe, and to use DL methods to explore this dataset with the goal of revealing unexpected formal traits and advancing architectural scholarship on this subject. While existing scholarship groups them into four distinct stylistic categories, our analysis reveals stylistic overlaps, previously undetected micro styles, and shared architectural features. We posit the resulting analyses as an example of an ‘architectural distant reading’ that enriches our understanding of this architectural typology through an unprecedentedly detailed portrait of its formal characteristics based on a large architectural dataset. Crucially, drawing on recent developments in critical data and algorithm studies, we show how the dataset construction and subsequent analyses, and their results, were shaped by slow, manual data curation processes, methodological constraints, subjective decisions, and engagements with archives, domain experts. We thus illustrate how DL techniques might be contextualized for architectural studies in relation to other modes of knowledge and labour, and offer a detailed case study of state-of-the-art computational methods enriching established approaches to architectural form and historical analysis.

Artificial Intelligence and Sensor Technologies the Future of Special Education for Students with Intellectual and Developmental Disabilities

Learning environments such as classrooms and online systems for students with developmental or intellectual disabilities are typically dynamic, multisensory, and make use of top-down attention and working memory mechanisms to promote sense making by the student. This is specifically true when the student with intellectual disabilities is mainstreamed into a general education classroom. The complex interactions between the classroom, the student, and the content creates serious difficulty in assessing a student’s understanding, particularly for students who are non-verbal or have deficits in communication. However, the last five years have ushered a revolution in computational power, brain mapping, wearable sensors use, large scale data collection, generative artificial intelligence, and physiological signal processing techniques e.g., the 4th industrial revolution

Early detection of student degree-level academic performance using educational data mining.

Higher educational institutes generate massive amounts of student data. This data needs to be explored in depth to better understand various facets of student learning behavior. The educational data mining approach has given provisions to extract useful and non-trivial knowledge from large collections of student data. Using the educational data mining method of classification, this research analyzes data of 291 university students in an attempt to predict student performance at the end of a 4-year degree program. A student segmentation framework has also been proposed to identify students at various levels of academic performance. Coupled with the prediction model, the proposed segmentation framework provides a useful mechanism for devising pedagogical policies to increase the quality of education by mitigating academic failure and encouraging higher performance. The experimental results indicate the effectiveness of the proposed framework and the applicability of classifying students into multiple performance levels using a small subset of courses being taught in the initial two years of the 4-year degree program.

Does regular physical activity generally reduce basal energy expenditure? Arguments against an alleged paradigm change. A short report

Careau et al. (5) recently published a paper entitled “Energy compensation and adiposity in humans“ in the journal Current Biology. They evaluated measurements of total energy expenditure (TEE), basal energy expenditure (BEE) and activity energy expenditure (AEE) saved in a large data collection. Based on an overall negative correlation between BEE and AEE in a large group of subjects varying in sex, age and body mass they suggest that intense physical activity generally reduces BEE. There was “controlling for sex, age, and body composition“. But surprisingly the authors do not present values per kg body mass despite comparing subjects with a large variation in this quantity. Data published in former publications by one of the coauthors allow calculating daily kcal/kg from means. This indicates that low BEE accompanied by high AEE was caused by a smaller body mass in physically active subjects.

A granular physics-based model for sediment dispersion

Current models of dispersion in marine sediments include losses due to fluid viscosity and shearing at grain-grain contacts. An additional loss mechanism, which is well established in granular physics but is not included in existing models, is the inelasticity of normal compression at grain-grain contacts. Additionally, force-bearing contact networks, often called “force chains,” involve primarily normal compressive forces. These “force chains” are known to play a dominant role in force transmission in granular materials, including wave propagation. Using theoretical analysis of a 1D model “force chain” as well as DEM simulations in higher spatial dimension, we show that this granular mechanics perspective, where forces are transmitted along lossy force chains, may be able to explain salient features of the acoustic properties of marine sediments. In particular, the low and high-frequency behavior of the attenuation coefficient match a large collection of experimental data. [This was supported by the Office of Naval Research.]

Coarse Closed-Loop Trajectory Design of Multiple UAVs for Parallel Data Collection

Multiple unmanned aerial vehicles (UAVs) are able to accelerate the large area data collection procedure by using a parallel manner. Due to the UAV flying ability differentiation and the communication equipment (CE) distribution, the optimal trajectory that minimizes the data collection completion time is difficult to achieve. This paper aims at minimizing the multi-UAV parallel data collection completion time in a wide area without precise CE location information. Different with the existing works, we propose a coarse multi-UAV trajectory design solution without repeated edges, in which each UAV follows a closed-loop trajectory to reduce the data collection time. To facilitate the UAV control and guarantee the data collection of edge CEs, four flight rules are set up. Then a division unit structure with four stay points is proposed to partition the wide area. We prove that a closed-loop trajectory exists for any area that consists of division units with the proposed structure. In the high signal to noise ratio case, the optimal area partition that minimizes the data collection time is obtained. The closed-loop trajectory for each UAV is constructed to minimize the data collection completion time. Simulation results show that the proposed coarse closed-loop trajectory design method is approaching the lower bound of the data collection completion time with a loss less than 10%.

Evaluating increases in sensitivity from NORDIC for diverse fMRI acquisition strategies

As the neuroimaging field moves towards detecting smaller effects at higher spatial resolutions, and faster sampling rates, there is increased attention given to the deleterious contribution of unstructured, thermal noise. Here, we critically evaluate the performance of a recently developed reconstruction method, termed NORDIC, for suppressing thermal noise using datasets acquired with various field strengths, voxel sizes, sampling rates, and task designs.Following minimal preprocessing, statistical activation (t-values) of NORDIC processed data was compared to the results obtained with alternative denoising methods. Additionally, we examined the consistency of the estimates of task responses at the single-voxel, single run level, using a finite impulse response (FIR) model. To examine the potential impact on effective image resolution, the overall smoothness of the data processed with different methods was estimated. Finally, to determine if NORDIC alters or removes temporal information important for modeling responses, we employed an exhaustive leave-p-out cross validation approach, using FIR task responses to predict held out timeseries, quantified using R2.After NORDIC, the t-values are increased, an improvement comparable to what could be achieved by 1.5 voxels smoothing, and task events are clearly visible and have less cross-run error. These advantages are achieved with smoothness estimates increasing by less than 4%, while 1.5 voxel smoothing is associated with increases of over 140%. Cross-validated R2s based on the FIR models show that NORDIC is not measurably distorting the temporal structure of the data under this approach and is the best predictor of non-denoised time courses. The results demonstrate that analyzing 1 run of data after NORDIC produces results equivalent to using 2 to 3 original runs and that NORDIC performs equally well across a diverse array of functional imaging protocols.Significance Statement: For functional neuroimaging, the increasing availability of higher field strengths and ever higher spatiotemporal resolutions has led to concomitant increase in concerns about the deleterious effects of thermal noise. Historically this noise source was suppressed using methods that reduce spatial precision such as image blurring or averaging over a large number of trials or sessions, which necessitates large data collection efforts. Here, we critically evaluate the performance of a recently developed reconstruction method, termed NORDIC, which suppresses thermal noise. Across datasets varying in field strength, voxel sizes, sampling rates, and task designs, NORDIC produces substantial gains in data quality. Both conventional t-statistics derived from general linear models and coefficients of determination for predicting unseen data are improved. These gains match or even exceed those associated with 1 voxel Full Width Half Max image smoothing, however, even such small amounts of smoothing are associated with a 52% reduction in estimates of spatial precision, whereas the measurable difference in spatial precision is less than 4% following NORDIC.

The Transcriptomic Response of the Boll Weevil, Anthonomus grandis grandis Boheman (Coleoptera: Curculionidae), following Exposure to the Organophosphate Insecticide Malathion.

Insecticide tolerance and resistance have evolved countless times in insect systems. Molecular drivers of resistance include mutations in the insecticide target site and/or gene duplication, and increased gene expression of detoxification enzymes. The boll weevil, Anthonomus grandis grandis Boheman (Coleoptera: Curculionidae), is a pest of commercial cotton and has developed resistance in the field to several insecticides; however, the current organophosphate insecticide, malathion, used by USA eradication programs remains effective despite its long-term use. Here, we present findings from an RNA-seq experiment documenting gene expression post-exposure to field-relevant concentrations of malathion, which was used to provide insight on the boll weevil's continued susceptibility to this insecticide. Additionally, we incorporated a large collection of boll weevil whole-genome resequencing data from nearly 200 individuals collected from three geographically distinct areas to determine SNP allele frequency of the malathion target site, as a proxy for directional selection in response to malathion exposure. No evidence was found in the gene expression data or SNP data consistent with a mechanism of enhanced tolerance or resistance adaptation to malathion in the boll weevil. Although this suggests continued effectiveness of malathion in the field, we identified important temporal and qualitative differences in gene expression between weevils exposed to two different concentrations of malathion. We also identified several tandem isoforms of the detoxifying esterase B1 and glutathione S-transferases, which are putatively associated with organophosphate resistance.

Deep feature selection using adaptive [formula omitted]-Hill Climbing aided whale optimization algorithm for lung and colon cancer detection

One of the most frightening and talked-about diseases in the modern world is cancer. Huge amounts of research are conducted worldwide to make this ailment less fearsome, be it by finding its cure, discovering ways to detect it in much earlier stages to reduce the mortality rate, or identifying precautions for humans to avoid it. The availability of large collections of biomedical and clinical data has ushered in the use of computer vision for cancer detection, especially for two of its most common types, lung and colon carcinomas. In this work, we present a framework wherein both deep learning and meta-heuristic approaches have been used for the prediction of colon or lung cancer, or both, from histopathological images with near-perfect precision. Initially, deep learning models, namely ResNet-18 for 2-class classification and EfficientNet-b4-widese for 3-class and 5-class classification, have been trained on the LC25000 dataset, followed by the extraction of deep features. The feature vector obtained from a deep learning model may have some redundancy. Hence, the selection of the most useful features has been done with the application of our proposed hybrid meta-heuristic optimization algorithm, AdBet-WOA (Whale optimization algorithm with integrated Adaptive β-Hill Climbing local search), utilizing which the Support Vector Machine (SVM) classifier classifies the colon cancer test data, lung cancer test data, and both combined with an accuracy of 99.99%, 99.97%, and 99.96%, respectively, matching the benchmark results comprehensively. For comparison, we have used a few independent as well as hybrid optimization algorithms. Our proposed approach succeeds greatly in reducing the number of features and also leads to better classification performance, as indicated by the obtained results. The relevant codes for our proposed approach are publicly available at: https://github.com/raj-1411/AdBet-WOA

Building a Model for Integrative Computational Social Science Research

Universities are increasingly interested in providing courses that equip students with data science skills and engage experiential learning, particularly in the social sciences. However, these courses can be costly to implement and time-consuming for instructors to develop. This article describes an integrative learning model for teaching computational social science skills to undergraduate students. There are three elements to the model: content delivery through collaborative learning, skill development in an applied lab setting, and student mentorship. I apply this model to an experiential course where undergraduate students learn to create and conduct a national public opinion poll. The model addresses the need for university classes that equip undergraduate students with computational social science skills, and provides a pathway for training student researchers as teaching assistants for future courses. This model builds the research capacity of faculty, graduate assistants, and undergraduates, invests in data science by providing an infrastructure for the collection of large scale data over time, and integrates experiences inside and outside of the classroom. This model is replicable at other institutions and will be of benefit to programs seeking to implement best practices and maximize learning effectiveness through research integration.

A Smartwatch System for Continuous Monitoring of Atrial Fibrillation in Older Adults After Stroke or Transient Ischemic Attack: Application Design Study.

The prevalence of atrial fibrillation (AF) increases with age and can lead to stroke. Therefore, older adults may benefit the most from AF screening. However, older adult populations tend to lag more than younger groups in the adoption of, and comfort with, the use of mobile health (mHealth) apps. Furthermore, although mobile apps that can detect AF are available to the public, most are designed for intermittent AF detection and for younger users. No app designed for long-term AF monitoring has released detailed system design specifications that can handle large data collections, especially in this age group. This study aimed to design an innovative smartwatch-based AF monitoring mHealth solution in collaboration with older adult participants and clinicians. The Pulsewatch system is designed to link smartwatches and smartphone apps, a website for data verification, and user data organization on a cloud server. The smartwatch in the Pulsewatch system is designed to continuously monitor the pulse rate with embedded AF detection algorithms, and the smartphone in the Pulsewatch system is designed to serve as the data-transferring hub to the cloud storage server. We implemented the Pulsewatch system based on the functionality that patients and caregivers recommended. The user interfaces of the smartwatch and smartphone apps were specifically designed for older adults at risk for AF. We improved our Pulsewatch system based on feedback from focus groups consisting of patients with stroke and clinicians. The Pulsewatch system was used by the intervention group for up to 6 weeks in the 2 phases of our randomized clinical trial. At the conclusion of phase 1, 90 trial participants who had used the Pulsewatch app and smartwatch for 14 days completed a System Usability Scale to assess the usability of the Pulsewatch system; of 88 participants, 56 (64%) endorsed that the smartwatch app is "easy to use." For phases 1 and 2 of the study, we collected 9224.4 hours of smartwatch recordings from the participants. The longest recording streak in phase 2 was 21 days of consecutive recordings out of the 30 days of data collection. This is one of the first studies to provide a detailed design for a smartphone-smartwatch dyad for ambulatory AF monitoring. In this paper, we report on the system's usability and opportunities to increase the acceptability of mHealth solutions among older patients with cognitive impairment. ClinicalTrials.gov NCT03761394; https://www.clinicaltrials.gov/ct2/show/NCT03761394. RR2-10.1016/j.cvdhj.2021.07.002.

Machine Learning applications for Data Quality Monitoring and Data Certification within CMS

The Compact Muon Solenoid (CMS) detector is getting ready for datataking in 2022, after a long shutdown period. LHC Run-3 is expected to deliver an ever-increasing amount of data. To ensure that the recorded data has the best quality possible, the CMS Collaboration has dedicated Data Quality Monitoring (DQM) and Data Certification (DC) working groups. These working groups are made of human shifters and experts who carefully watch and investigate histograms generated from different parts of the detector. However, the current workflow is not granular enough and prone to human errors. On the other hand, several techniques in Machine Learning (ML) can be designed to learn from large collections of data and make predictions for the data quality at an unprecedented speed and granularity. Hence, the data certification process can be considered as a perfect problem for ML techniques to tackle. With the help of ML, we can increase the granularity and speed of the DQM workflow and assist the human shifters and experts in detecting anomalies during data-taking. In this presentation, we present preliminary results from incorporating ML to highly granular DQM information for data certification.

Automatic generation of scientific papers for data augmentation in document layout analysis

Document layout analysis is an important task to extract information from scientific literature. Deep-learning solutions for document layout analysis require large collections of training data that are not always available. We generate a large number of synthetic pages to subsequently train a neural network to perform document object detection. The proposed pipeline allows users to deal with less common layouts for which it is not easy to find large annotated datasets. High-quality annotations for a small collection of papers are obtained through a semi-automatic approach. Then, a generative model, based on LayoutTransformer, is used to generate plausible layouts that are subsequently populated with random information to perform data augmentation. We evaluate the proposed method considering scientific articles with two different types of layouts: double and single columns. For double-column papers, we improve detection by 1% starting from 385 manually annotated scientific articles. For single-column papers, we improve detection by 49% starting from 218 articles.

Machine learning enabled subgroup analysis with real-world data to inform clinical trial eligibility criteria design

Overly restrictive eligibility criteria for clinical trials may limit the generalizability of the trial results to their target real-world patient populations. We developed a novel machine learning approach using large collections of real-world data (RWD) to better inform clinical trial eligibility criteria design. We extracted patients’ clinical events from electronic health records (EHRs), which include demographics, diagnoses, and drugs, and assumed certain compositions of these clinical events within an individual’s EHRs can determine the subphenotypes—homogeneous clusters of patients, where patients within each subgroup share similar clinical characteristics. We introduced an outcome-guided probabilistic model to identify those subphenotypes, such that the patients within the same subgroup not only share similar clinical characteristics but also at similar risk levels of encountering severe adverse events (SAEs). We evaluated our algorithm on two previously conducted clinical trials with EHRs from the OneFlorida+ Clinical Research Consortium. Our model can clearly identify the patient subgroups who are more likely to suffer or not suffer from SAEs as subphenotypes in a transparent and interpretable way. Our approach identified a set of clinical topics and derived novel patient representations based on them. Each clinical topic represents a certain clinical event composition pattern learned from the patient EHRs. Tested on both trials, patient subgroup (#SAE=0) and patient subgroup (#SAE>0) can be well-separated by k-means clustering using the inferred topics. The inferred topics characterized as likely to align with the patient subgroup (#SAE>0) revealed meaningful combinations of clinical features and can provide data-driven recommendations for refining the exclusion criteria of clinical trials. The proposed supervised topic modeling approach can infer the clinical topics from the subphenotypes with or without SAEs. The potential rules for describing the patient subgroups with SAEs can be further derived to inform the design of clinical trial eligibility criteria.