Data-driven Studies Research Articles

A Meta-Analysis Review of Occupant Behaviour Models for Assessing Demand-Side Energy Consumption

Occupant behaviour plays a significant role in shaping the dynamics of energy consumption in buildings, but the complex nature of occupant behaviour has hindered a deeper understanding of its influence. A meta-analysis was conducted on 65 published studies that used data-driven quantitative assessments to assess energy-related occupant behaviour using the Knowledge Discovery and Data Mining (KDD) framework. Hierarchical clustering was utilised to categorise different modelling techniques based on the intended outcomes of the model and the types of parameters used in various models. This study will assist researchers in selecting the most appropriate parameters and methods under various data constraints and research questions. The research revealed two distinct model categories being used to study occupant behaviour-driven energy consumption, namely (i) occupancy status models and (ii) energy-related behaviour models. Multiple studies have identified limitations on data collection and privacy concerns as constraints of modelling occupant behaviour in residential buildings. The “regression model” and its variants were found to be the preferred model types for research that models “energy-related behaviour”, and “classification models” were found to be preferable for modelling “occupancy” status. There were only limited instances of data-driven studies that modelled occupant behaviour in low-income households, and there is a need to generate region-specific models to accurately model energy-related behaviour.

The Marine Biodiversity Observation Network Plankton Workshops: Plankton Ecosystem Function, Biodiversity, and Forecasting—Research Requirements and Applications

The Marine Biodiversity Observation Network Plankton Workshops: Plankton Ecosystem Function, Biodiversity, and Forecasting—Research Requirements and Applications

Identifying Critical Meteorological Elements for Vegetation Coverage Change in China

Intensifying global climate change has a significant influence on the vegetation, which is the basis of most of Earth’s ecosystems. It is urgent to identify the critical meteorological elements of vegetation coverage changes to address the problems induced by climate change. Many studies, ranging from theoretical advances to data-driven analyses, have been devoted to investigating meteorological elements’ roles in changing vegetation coverage. However, little has been considered in the aspect of the meteorological elements’ seasonal scale in data-driven studies. Herein, taking China as an example, we collected satellite-derived vegetation coverage data from 2000 to 2020. We then analyzed the meteorological elements, on a seasonal scale, that affect the vegetation coverage change in terms of temperature, precipitation, and solar radiation. We revealed that the critical meteorological elements facilitating vegetation coverage area change differ in both time and space and gave a detailed analysis in line with such findings. Moreover, an apparent seasonal delay effect of meteorological elements on the vegetation coverage change is uncovered.

Data-driven methods for dengue prediction and surveillance using real-world and Big Data: A systematic review.

BackgroundTraditionally, dengue surveillance is based on case reporting to a central health agency. However, the delay between a case and its notification can limit the system responsiveness. Machine learning methods have been developed to reduce the reporting delays and to predict outbreaks, based on non-traditional and non-clinical data sources. The aim of this systematic review was to identify studies that used real-world data, Big Data and/or machine learning methods to monitor and predict dengue-related outcomes.Methodology/Principal findingsWe performed a search in PubMed, Scopus, Web of Science and grey literature between January 1, 2000 and August 31, 2020. The review (ID: CRD42020172472) focused on data-driven studies. Reviews, randomized control trials and descriptive studies were not included. Among the 119 studies included, 67% were published between 2016 and 2020, and 39% used at least one novel data stream. The aim of the included studies was to predict a dengue-related outcome (55%), assess the validity of data sources for dengue surveillance (23%), or both (22%). Most studies (60%) used a machine learning approach. Studies on dengue prediction compared different prediction models, or identified significant predictors among several covariates in a model. The most significant predictors were rainfall (43%), temperature (41%), and humidity (25%). The two models with the highest performances were Neural Networks and Decision Trees (52%), followed by Support Vector Machine (17%). We cannot rule out a selection bias in our study because of our two main limitations: we did not include preprints and could not obtain the opinion of other international experts.Conclusions/SignificanceCombining real-world data and Big Data with machine learning methods is a promising approach to improve dengue prediction and monitoring. Future studies should focus on how to better integrate all available data sources and methods to improve the response and dengue management by stakeholders.

Psoriatic Spondylitis: A Disease Manifestation in Debate: Evidences to Know for the Clinical Rheumatologist.

With the advent of classification criteria for psoriatic arthritis (PsA) and axial spondyloarthritis (axSpA), patients with axial manifestations associated with psoriasis, initially described in the l950s as a specific entity termed psoriatic spondylitis (PS), are now categorized within PsA, ankylosing spondylitis (AS), and axSpA. Thus, different terms are used to describe axial disease in patients with PsA including PS, axial psoriatic arthritis (axPsA), and psoriatic spondyloarthritis. Patients with PS may present with inflammatory and/or mechanical back pain, but also may display axial disease on imaging despite not complaining of back pain. Cervical spondylitis has been reported in 35% to 75% of patients with PsA. Axial disease is silent in 20% and 25% of patients with axial PsA and PsA, respectively. The majority of axPsA patients have peripheral arthritis alongside the axial involvement, whereas only 2% to 5% of PsA patients have solely axial arthritis with no peripheral arthritis.A debate is currently underway as to whether inflammatory axial disease and psoriasis represent axSpA with psoriasis or a subset of PsA named axPsA. Studies have recognized that axial disease in PsA patients seems to be different demographically, genetically, clinically, and radiographically when compared with AS with or without psoriasis. This narrative review summarizes current knowledge regarding axial involvement of PsA in terms of history, terminology, classification, epidemiology, clinical presentation, imaging, diagnosis, and treatment, with the aim of providing advice for management of PS in clinical evidence-based practice. Data-driven studies are needed to develop clear, nonoverlapping classification criteria for spinal involvement in PsA.

Discovering the effects of learning analytics dashboard on students’ behavioral patterns using differential sequence mining

Interventions based on learning analytics have a very important place in closing the learning analytics loop. However, data-driven studies that test the effects of learning analytics-based interventions on students' online learning behaviors are very limited. In this study, the effect of the student-facing learning analytics dashboard (LAD) on the learning behavior of students in the online learning environment was investigated by using the differential pattern mining method. In a completely remote course, the learning behaviors of the participants before the introduction of the dashboard were compared with the learning behaviors they exhibited after the dashboard was introduced. In this way, it has become possible to analyze the behavior changes after the dashboard intervention. Wilcoxon signed-rank test was used to test whether these behavioral changes were statistically significant or not. According to the Wilcoxon signed-rank test results, while there is no significant difference in terms of students’ assignment and quiz interactions, it is seen that there is a statistically significant increase in terms of students’ forum-related activities such as reading other students’ posts, starting a new discussion, and replying others’ posts. Students’ SCORM interactions (e.g, launch, complete) were also increased after engaging with the LAD. In addition, it was found that the overall interaction of students in the online learning environment increased by 57% when the LAD was used.

De-risking clinical trial failure through mechanistic simulation.

Drug development typically comprises a combination of pre-clinical experimentation, clinical trials, and statistical data-driven analyses. Therapeutic failure in late-stage clinical development costs the pharmaceutical industry billions of USD per year. Clinical trial simulation represents a key derisking strategy and combining them with mechanistic models allows one to test hypotheses for mechanisms of failure and to improve trial designs. This is illustrated with a T-cell activation model, used to simulate the clinical trials of IMA901, a short-peptide cancer vaccine. Simulation results were consistent with observed outcomes and predicted that responses are limited by peptide off-rates, peptide competition for dendritic cell (DC) binding, and DC migration times. These insights were used to hypothesise alternate trial designs predicted to improve efficacy outcomes. This framework illustrates how mechanistic models can complement clinical, experimental, and data-driven studies to understand, test, and improve trial designs, and how results may differ between humans and mice.

Prediction of solar cell materials via unsupervised literature learning

Despite the significant advancement of the data-driven studies for physical science, the textual data that are numerous in the literature are not fully embraced by the physics and materials community. In this manuscript, we successfully employ the natural language processing (NLP) technique to unsupervisedly predict the existence of solar cell types including the dye-sensitized solar cells and the perovskite solar cells based on literatures published prior to their first discovery without human annotation. Enlightened by this, we further identify possible solar cell material candidates via NLP starting with a comprehensive training database of 3.2 million paper abstracts published before 2021. The NLP model effectively predicts the existing solar cell materials, while an uncommon solar cell material namely PtSe2 is suggested as an appropriate candidate for the future solar cells. Its optoelectronic properties are comprehensive investigated via first-principles calculations to reveal the decent stability and optoelectronic performance of the NLP-predicted candidate. This study demonstrates the viability of the textual data for the data-driven materials prediction and highlights the NLP method as a powerful tool to reliably predict the solar cell materials.

Spatiotemporal monsoon characteristics and maize yields in West Africa

To assess the vulnerability of rainfed agriculture in West Africa (WA) to climate change, a detailed understanding of the relationship between food crop yields and seasonal rainfall characteristics is required. The highly seasonal rainfall in the region is expected to change characteristics such as seasonal timing, duration, intensity, and intermittency. The food crop yield response to changes in these characteristics needs greater understanding. We follow a data-driven approach based on historical yield and climate data. Such an approach complements model-based approaches. Previous data-driven studies use spatially and temporally averaged precipitation measures, which do not describe the high degree of spatial and temporal variability of the West African Monsoon (WAM), the primary source of water for agriculture in the region. This has led previous studies to find small or insignificant dependence of crop yields on precipitation amount. Here, we develop metrics that characterize important temporal features and variability in growing season precipitation, including total precipitation, onset and duration of the WAM, and number of non-precipitating days. For each temporal precipitation metric, we apply several unique spatial aggregation functions that allow us to assess how different patterns of high-resolution spatial variability are related to country-level maize yields. We develop correlation analyses between spatiotemporal precipitation metrics and detrended country-level maize yields based on findings that non-climatic factors, such as agricultural policy reform and increased investment, have driven the region’s long-term increase in maize yields. Results show that that the variability in the number of days without rain during the monsoon season and the lower bounds to the spatial rain pattern and end to the monsoon season are most strongly associated with maize yields. Our findings highlight the importance of considering spatial and temporal variability in precipitation when evaluating impacts on crop yields, providing a possible explanation for weak connections found in previous studies.

Research data infrastructure for high-throughput experimental materials science

SummaryThe High-Throughput Experimental Materials Database (HTEM-DB, htem.nrel.gov) is a repository of inorganic thin-film materials data collected during combinatorial experiments at the National Renewable Energy Laboratory (NREL). This data asset is enabled by NREL's Research Data Infrastructure (RDI), a set of custom data tools that collect, process, and store experimental data and metadata. Here, we describe the experimental data flow from the RDI to the HTEM-DB to illustrate the strategies and best practices currently used for materials data at NREL. Integration of the data tools with experimental instruments establishes a data communication pipeline between experimental researchers and data scientists. This work motivates the creation of similar workflows at other institutions to aggregate valuable data and increase their usefulness for future machine learning studies. In turn, such data-driven studies can greatly accelerate the pace of discovery and design in the materials science domain.

Q-omics: Smart Software for Assisting Oncology and Cancer Research.

The rapid increase in collateral omics and phenotypic data has enabled data-driven studies for the fast discovery of cancer targets and biomarkers. Thus, it is necessary to develop convenient tools for general oncologists and cancer scientists to carry out customized data mining without computational expertise. For this purpose, we developed innovative software that enables user-driven analyses assisted by knowledge-based smart systems. Publicly available data on mutations, gene expression, patient survival, immune score, drug screening and RNAi screening were integrated from the TCGA, GDSC, CCLE, NCI, and DepMap databases. The optimal selection of samples and other filtering options were guided by the smart function of the software for data mining and visualization on Kaplan-Meier plots, box plots and scatter plots of publication quality. We implemented unique algorithms for both data mining and visualization, thus simplifying and accelerating user-driven discovery activities on large multiomics datasets. The present Q-omics software program (v0.95) is available at http://qomics.sookmyung.ac.kr.

Data-Driven Design-By-Analogy: State-of-the-Art and Future Directions

AbstractDesign-by-analogy (DbA) is a design methodology wherein new solutions, opportunities, or designs are generated in a target domain based on inspiration drawn from a source domain; it can benefit designers in mitigating design fixation and improving design ideation outcomes. Recently, the increasingly available design databases and rapidly advancing data science and artificial intelligence (AI) technologies have presented new opportunities for developing data-driven methods and tools for DbA support. In this study, we survey existing data-driven DbA studies and categorize individual studies according to the data, methods, and applications into four categories, namely, analogy encoding, retrieval, mapping, and evaluation. Based on both nuanced organic review and structured analysis, this paper elucidates the state-of-the-art of data-driven DbA research to date and benchmarks it with the frontier of data science and AI research to identify promising research opportunities and directions for the field. Finally, we propose a future conceptual data-driven DbA system that integrates all propositions.

Decision-Making Ethics with Regard to Life-Sustaining Interventions: Summoning what other Patients Chose

"Health decisions occur in a rich context in which social influences are omnipresent. The tendency to compare oneself with others has been described as one of the critical social factors influencing decision making. Based on a collection of 43 audio-recordings of hospital admission encounters which were analyzed though a conversation analytic methodology, we present findings and reflections in regard to how patients and physicians discuss cardio-pulmonary resuscitation. The phenomena of interest concerns how and when patients and physicians refer to what other people decide (for example: “Often the patients tell us: No futile care”). This practice is encountered in 6 of the conversations recorded. Reference to other people’s decisions is a way to talk about options, but it does much more than just enumerating them. As a resource in interaction, this reference is employed when the patient can’t or doesn’t express a preference (thereby clarifying options) or when the preference the patient expressed is problematic (because contrary to expectations). By using this reference, decision making is projected as a matter of membership to a group of individuals, and not as a matter of individual prognostic.The ethical implications of referring to other people’s choices are significant, since it can influence the patient and pose a serious threat to autonomous decisions. We argue that findings such as ours, stemming from data-driven studies of healthcare communication, are pivotal for informing ethics education in its effort to address the biases that physicians impose upon patients during decision making. "

Benign Cardiac Neoplasms in the United States: A Thirteen-Year Review

Cardiac neoplasms are uncommon tumors. For epidemiological purposes, they can be divided into benign and malignant subtypes, with the former occurring at a significantly higher rate than the latter. Due to their uncommon nature, there are few data-driven studies examining the characteristics and trends of benign cardiac neoplasms. Our retrospective HCUP-NIS data review purports to illuminate some of the trends surrounding benign cardiac neoplasms and their associated co-occurrences. The data consisted of 482,872,274 weighted discharges. There were 45,568 weighted discharges that included a benign cardiac neoplasm. Benign cardiac neoplasms were more often observed in women (64.33%), and the average age was 63.8 years. The most common cardiovascular co-occurrences in patients with benign cardiac neoplasm were atrial tachyarrhythmias (28.93%), heart failure (19.61%), and embolic events such as stroke, myocardial infarct, or pulmonary embolism (19.82%). Other co-occurrences included pulmonary hypertension (7.55%), ventricular arrhythmias (3.23%), and other EKG abnormalities (3.70%). Procedures were numerous in patients with benign cardiac neoplasms. 43% of patients with this diagnosis had some form of cardiac surgery during their hospitalization. Overall, this study found low incidence of benign cardiac neoplasms in the USA during this 13-year study period. However, in the presence of benign cardiac neoplasms, our study showed that cardiovascular co-occurrences are not uncommon and may help to illuminate this otherwise rare diagnosis.

Data-driven remaining useful life prediction based on domain adaptation.

As an important part of prognostics and health management, remaining useful life (RUL) prediction can provide users and managers with system life information and improve the reliability of maintenance systems. Data-driven methods are powerful tools for RUL prediction because of their great modeling abilities. However, most current data-driven studies require large amounts of labeled training data and assume that the training data and test data follow similar distributions. In fact, the collected data are often variable due to different equipment operating conditions, fault modes, and noise distributions. As a result, the assumption that the training data and the test data obey the same distribution may not be valid. In response to the above problems, this paper proposes a data-driven framework with domain adaptability using a bidirectional gated recurrent unit (BGRU). The framework uses a domain-adversarial neural network (DANN) to implement transfer learning (TL) from the source domain to the target domain, which contains only sensor information. To verify the effectiveness of the proposed method, we analyze the IEEE PHM 2012 Challenge datasets and use them for verification. The experimental results show that the generalization ability of the model is effectively improved through the domain adaptation approach.

Utilizing a Biology-Driven Approach to Map the Exposome in Health and Disease: An Essential Investment to Drive the Next Generation of Environmental Discovery.

Background:Recent developments in technologies have offered opportunities to measure the exposome with unprecedented accuracy and scale. However, because most investigations have targeted only a few exposures at a time, it is hypothesized that the majority of the environmental determinants of chronic diseases remain unknown.Objectives:We describe a functional exposome concept and explain how it can leverage existing bioassays and high-resolution mass spectrometry for exploratory study. We discuss how such an approach can address well-known barriers to interpret exposures and present a vision of next-generation exposomics.Discussion:The exposome is vast. Instead of trying to capture all exposures, we can reduce the complexity by measuring the functional exposome—the totality of the biologically active exposures relevant to disease development—through coupling biochemical receptor-binding assays with affinity purification–mass spectrometry. We claim the idea of capturing exposures with functional biomolecules opens new opportunities to solve critical problems in exposomics, including low-dose detection, unknown annotations, and complex mixtures of exposures. Although novel, biology-based measurement can make use of the existing data processing and bioinformatics pipelines. The functional exposome concept also complements conventional targeted and untargeted approaches for understanding exposure-disease relationships.Conclusions:Although measurement technology has advanced, critical technological, analytical, and inferential barriers impede the detection of many environmental exposures relevant to chronic-disease etiology. Through biology-driven exposomics, it is possible to simultaneously scale up discovery of these causal environmental factors. https://doi.org/10.1289/EHP8327

In silico model for miRNA-mediated regulatory network in cancer.

Deregulation of gene expression is associated with the pathogenesis of numerous human diseases including cancer. Current data analyses on gene expression are mostly focused on differential gene/transcript expression in big data-driven studies. However, a poor connection to the proteome changes is a widespread problem in current data analyses. This is partly due to the complexity of gene regulatory pathways at the post-transcriptional level. In this study, we overcome these limitations and introduce a graph-based learning model, PTNet, which simulates the microRNAs (miRNAs) that regulate gene expression post-transcriptionally in silico. Our model does not require large-scale proteomics studies to measure the protein expression and can successfully predict the protein levels by considering the miRNA-mRNA interaction network, the mRNA expression, and the miRNA expression. Large-scale experiments on simulations and real cancer high-throughput datasets using PTNet validated that (i) the miRNA-mediated interaction network affects the abundance of corresponding proteins and (ii) the predicted protein expression has a higher correlation with the proteomics data (ground-truth) than the mRNA expression data. The classification performance also shows that the predicted protein expression has an improved prediction power on cancer outcomes compared to the prediction done by the mRNA expression data only or considering both mRNA and miRNA. Availability: PTNet toolbox is available at http://github.com/CompbioLabUCF/PTNet.

Can Workplace Tracking Ever Empower? Collective Sensemaking for the Responsible Use of Sensor Data at Work

People are increasingly subject to the tracking of data about them at their workplaces. Sensor tracking is used by organizations to generate data on the movement and interaction of their employees to monitor and manage workers, and yet this data also poses significant risks to individual employees who may face harms from such data, and from data errors, to their job security or pay as a result of such analyses. Working with a large hospital, we developed a set of intervention strategies to enable what we call "collective sensemaking" describing worker contestation of sensor tracking data. We did this by participating in the sensor data science team, analyzing data on badges that employees wore over a two-week period, and then bringing the results back to the employees through a series of participatory workshops. We found three key aspects of collective sensemaking important for understanding data from the perspectives of stakeholders: 1) data shadows for tempering possibilities for design with the realities of data tracking; 2) data transducers for converting our assumptions about sensor tracking, and 3) data power for eliciting worker inclusivity and participation. We argue that researchers face what Dourish (2019) called the "legitimacy trap" when designing with large datasets and that research about work should commit to complementing data-driven studies with in-depth insights to make them useful for all stakeholders as a corrective to the underlying power imbalance that tracked workers face.

PCN137 Measuring Driving Access to Genetic Counselors and Examining Equity of Coverage

Genetic counseling is a prerequisite for precision clinical care in certain cancers. This study measured drive-time (accessibility) to genetic counselors (GCs) at the county level and investigated differences in accessibility (equity) by region and by cancer type. Physical location data of GCs in the US and cancer incidence rates were downloaded from public websites at the Centers for Medicare and Medicaid Services, two GC professional societies, and the Centers for Disease Control and Prevention. Geospatial information systems (GIS) technologies were used to geocode GC locations and to calculate drive-times to GCs at the county level. Median access measures weighted by cancer incidence rates were calculated at the state-level, and differences were investigated across dimensions of geographical and disease type using non-parametric hypothesis tests. At the county-level there were significant differences (p<0.001) in drive-time to the nearest GC. The metro county median was 33.0 minutes (interquartile range (IQR) 34.0) vs. nonmetro county median 78.8 minutes (IQR 55.7). At the state-level, median patient drive-time to a GC for any cancer type was 55.6 minutes (IQR 36.6). There were significant differences (p=0.001) in drive-time across regions, e.g., between Northeastern (median 31.3 minutes, IQR 22.8) and Western regions (median 80.6 minutes, IQR 37.2; pairwise p=0.006). Lastly, there were significant differences in access depending on specific cancer type (p<0.001), e.g., between patients with ovarian cancer (median 35.5 minutes, IQR 21.2) and prostate cancer (median 53.5 minutes, IQR 33.3; pairwise p<0.001). This study reveals systemic differences in access to precision cancer care across the United States both geographically and by cancer type. The methodology and results presented here could be used to identify pockets of unmet need and to inform data-driven health network adequacy studies and policy interventions. Further work could explore relationships with health outcomes or care utilization data.

Using Machine Learning to Predict the Diagnosis, Management and Severity of Pediatric Appendicitis.

Background: Given the absence of consolidated and standardized international guidelines for managing pediatric appendicitis and the few strictly data-driven studies in this specific, we investigated the use of machine learning (ML) classifiers for predicting the diagnosis, management and severity of appendicitis in children.Materials and Methods: Predictive models were developed and validated on a dataset acquired from 430 children and adolescents aged 0-18 years, based on a range of information encompassing history, clinical examination, laboratory parameters, and abdominal ultrasonography. Logistic regression, random forests, and gradient boosting machines were used for predicting the three target variables.Results: A random forest classifier achieved areas under the precision-recall curve of 0.94, 0.92, and 0.70, respectively, for the diagnosis, management, and severity of appendicitis. We identified smaller subsets of 6, 17, and 18 predictors for each of targets that sufficed to achieve the same performance as the model based on the full set of 38 variables. We used these findings to develop the user-friendly online Appendicitis Prediction Tool for children with suspected appendicitis.Discussion: This pilot study considered the most extensive set of predictor and target variables to date and is the first to simultaneously predict all three targets in children: diagnosis, management, and severity. Moreover, this study presents the first ML model for appendicitis that was deployed as an open access easy-to-use online tool.Conclusion: ML algorithms help to overcome the diagnostic and management challenges posed by appendicitis in children and pave the way toward a more personalized approach to medical decision-making. Further validation studies are needed to develop a finished clinical decision support system.