Search for: All records

Abstract The Spatial Data Lab (SDL) project is a collaborative initiative by the Center for Geographic Analysis at Harvard University, KNIME, Future Data Lab, China Data Institute, and George Mason University. Co-sponsored by the NSF IUCRC Spatiotemporal Innovation Center, SDL aims to advance applied research in spatiotemporal studies across various domains such as business, environment, health, mobility, and more. The project focuses on developing an open-source infrastructure for data linkage, analysis, and collaboration. Key objectives include building spatiotemporal data services, a reproducible, replicable, and expandable (RRE) platform, and workflow-driven data analysis tools to support research case studies. Additionally, SDL promotes spatiotemporal data science training, cross-party collaboration, and the creation of geospatial tools that foster inclusivity, transparency, and ethical practices. Guided by an academic advisory committee of world-renowned scholars, the project is laying the foundation for a more open, effective, and robust scientific enterprise. 

Abstract BackgroundLung cancer is the deadliest and second most common cancer in the United States due to the lack of symptoms for early diagnosis. Pulmonary nodules are small abnormal regions that can be potentially correlated to the occurrence of lung cancer. Early detection of these nodules is critical because it can significantly improve the patient's survival rates. Thoracic thin‐sliced computed tomography (CT) scanning has emerged as a widely used method for diagnosing and prognosis lung abnormalities. PurposeThe standard clinical workflow of detecting pulmonary nodules relies on radiologists to analyze CT images to assess the risk factors of cancerous nodules. However, this approach can be error‐prone due to the various nodule formation causes, such as pollutants and infections. Deep learning (DL) algorithms have recently demonstrated remarkable success in medical image classification and segmentation. As an ever more important assistant to radiologists in nodule detection, it is imperative ensure the DL algorithm and radiologist to better understand the decisions from each other. This study aims to develop a framework integrating explainable AI methods to achieve accurate pulmonary nodule detection. MethodsA robust and explainable detection (RXD) framework is proposed, focusing on reducing false positives in pulmonary nodule detection. Its implementation is based on an explanation supervision method, which uses nodule contours of radiologists as supervision signals to force the model to learn nodule morphologies, enabling improved learning ability on small dataset, and enable small dataset learning ability. In addition, two imputation methods are applied to the nodule region annotations to reduce the noise within human annotations and allow the model to have robust attributions that meet human expectations. The 480, 265, and 265 CT image sets from the public Lung Image Database Consortium and Image Database Resource Initiative (LIDC‐IDRI) dataset are used for training, validation, and testing. ResultsUsing only 10, 30, 50, and 100 training samples sequentially, our method constantly improves the classification performance and explanation quality of baseline in terms of Area Under the Curve (AUC) and Intersection over Union (IoU). In particular, our framework with a learnable imputation kernel improves IoU from baseline by 24.0% to 80.0%. A pre‐defined Gaussian imputation kernel achieves an even greater improvement, from 38.4% to 118.8% from baseline. Compared to the baseline trained on 100 samples, our method shows less drop in AUC when trained on fewer samples. A comprehensive comparison of interpretability shows that our method aligns better with expert opinions. ConclusionsA pulmonary nodule detection framework was demonstrated using public thoracic CT image datasets. The framework integrates the robust explanation supervision (RES) technique to ensure the performance of nodule classification and morphology. The method can reduce the workload of radiologists and enable them to focus on the diagnosis and prognosis of the potential cancerous pulmonary nodules at the early stage to improve the outcomes for lung cancer patients. 

Abstract MotivationExpanding our knowledge of small molecules beyond what is known in nature or designed in wet laboratories promises to significantly advance cheminformatics, drug discovery, biotechnology and material science. In silico molecular design remains challenging, primarily due to the complexity of the chemical space and the non-trivial relationship between chemical structures and biological properties. Deep generative models that learn directly from data are intriguing, but they have yet to demonstrate interpretability in the learned representation, so we can learn more about the relationship between the chemical and biological space. In this article, we advance research on disentangled representation learning for small molecule generation. We build on recent work by us and others on deep graph generative frameworks, which capture atomic interactions via a graph-based representation of a small molecule. The methodological novelty is how we leverage the concept of disentanglement in the graph variational autoencoder framework both to generate biologically relevant small molecules and to enhance model interpretability. ResultsExtensive qualitative and quantitative experimental evaluation in comparison with state-of-the-art models demonstrate the superiority of our disentanglement framework. We believe this work is an important step to address key challenges in small molecule generation with deep generative frameworks. Availability and implementationTraining and generated data are made available at https://ieee-dataport.org/documents/dataset-disentangled-representation-learning-interpretable-molecule-generation. All code is made available at https://anonymous.4open.science/r/D-MolVAE-2799/. Supplementary informationSupplementary data are available at Bioinformatics online. 

Abstract Previous research has noted that many factors greatly influence the spread of COVID‐19. Contrary to explicit factors that are measurable, such as population density, number of medical staff, and the daily test rate, many factors are not directly observable, for instance, culture differences and attitudes toward the disease, which may introduce unobserved heterogeneity. Most contemporary COVID‐19 related research has focused on modeling the relationship between explicitly measurable factors and the response variable of interest (such as the infection rate or the death rate). The infection rate is a commonly used metric for evaluating disease progression and a state's mitigation efforts. Because unobservable sources of heterogeneity cannot be measured directly, it is hard to incorporate them into the quantitative assessment and decision‐making process. In this study, we propose new metrics to study a state's performance by adjusting the measurable county‐level covariates and unobservable state‐level heterogeneity through random effects. A hierarchical linear model (HLM) is postulated, and we calculate two model‐based metrics—the standardized infection ratio (SDIR) and the adjusted infection rate (AIR). This analysis highlights certain time periods when the infection rate for a state was high while their SDIR was low and vice versa. We show that trends in these metrics can give insight into certain aspects of a state's performance. As each state continues to develop their individualized COVID‐19 mitigation strategy and ultimately works to improve their performance, the SDIR and AIR may help supplement the crude infection rate metric to provide a more thorough understanding of a state's performance. 

Breathing in fine particulate matter of diameter less than 2.5 µm (PM2.5) greatly increases an individual’s risk of cardiovascular and respiratory diseases. As climate change progresses, extreme weather events, including wildfires, are expected to increase, exacerbating air pollution. However, models often struggle to capture extreme pollution events due to the rarity of high PM2.5 levels in training datasets. To address this, we implemented cluster-based undersampling and trained Transformer models to improve extreme event prediction using various cutoff thresholds (12.1 µg/m3 and 35.5 µg/m3) and partial sampling ratios (10/90, 20/80, 30/70, 40/60, 50/50). Our results demonstrate that the 35.5 µg/m3 threshold, paired with a 20/80 partial sampling ratio, achieved the best performance, with an RMSE of 2.080, MAE of 1.386, and R2 of 0.914, particularly excelling in forecasting high PM2.5 events. Overall, models trained on augmented data significantly outperformed those trained on original data, highlighting the importance of resampling techniques in improving air quality forecasting accuracy, especially for high-pollution scenarios. These findings provide critical insights into optimizing air quality forecasting models, enabling more reliable predictions of extreme pollution events. By advancing the ability to forecast high PM2.5 levels, this study contributes to the development of more informed public health and environmental policies to mitigate the impacts of air pollution, and advanced the technology for building better air quality digital twins. 

Accurate air pollution monitoring is critical to understand and mitigate the impacts of air pollution on human health and ecosystems. Due to the limited number and geographical coverage of advanced, highly accurate sensors monitoring air pollutants, many low-cost and low-accuracy sensors have been deployed. Calibrating low-cost sensors is essential to fill the geographical gap in sensor coverage. We systematically examined how different machine learning (ML) models and open-source packages could help improve the accuracy of particulate matter (PM) 2.5 data collected by Purple Air sensors. Eleven ML models and five packages were examined. This systematic study found that both models and packages impacted accuracy, while the random training/testing split ratio (e.g., 80/20 vs. 70/30) had minimal impact (0.745% difference for R2). Long Short-Term Memory (LSTM) models trained in RStudio and TensorFlow excelled, with high R2 scores of 0.856 and 0.857 and low Root Mean Squared Errors (RMSEs) of 4.25 µg/m3 and 4.26 µg/m3, respectively. However, LSTM models may be too slow (1.5 h) or computation-intensive for applications with fast response requirements. Tree-boosted models including XGBoost (0.7612, 5.377 µg/m3) in RStudio and Random Forest (RF) (0.7632, 5.366 µg/m3) in TensorFlow offered good performance with shorter training times (<1 min) and may be suitable for such applications. These findings suggest that AI/ML models, particularly LSTM models, can effectively calibrate low-cost sensors to produce precise, localized air quality data. This research is among the most comprehensive studies on AI/ML for air pollutant calibration. We also discussed limitations, applicability to other sensors, and the explanations for good model performances. This research can be adapted to enhance air quality monitoring for public health risk assessments, support broader environmental health initiatives, and inform policy decisions. 

Data dashboards provide a means for sharing multiple data products at a glance and were ubiquitous during the COVID-19 pandemic. Data dashboards tracked global and country-specific statistics and provided cartographic visualizations of cases, deaths, vaccination rates and other metrics. We examined the role of geospatial data on COVID-19 dashboards in the form of maps, charts, and graphs. We organize our review of 193 COVID-19 dashboards by region and compare the accessibility and operationality of dashboards over time and the use of web maps and geospatial visualizations. We found that of the dashboards reviewed, only 17% included geospatial visualizations. We observe that many of the COVID-19 dashboards from our analysis are no longer accessible (66%) and consider the ephemeral nature of data and dashboards. We conclude that coordinated efforts and a call to action to ensure the standardization, storage, and maintenance of geospatial data for use on data dashboards and web maps are needed for long-term use, analyses, and monitoring to address current and future public health and other challenging issues. 

Deep learning’s performance has been extensively recognized recently. Graph neural networks (GNNs) are designed to deal with graph-structural data that classical deep learning does not easily manage. Since most GNNs were created using distinct theories, direct comparisons are impossible. Prior research has primarily concentrated on categorizing existing models, with little attention paid to their intrinsic connections. The purpose of this study is to establish a unified framework that integrates GNNs based on spectral graph and approximation theory. The framework incorporates a strong integration between spatial- and spectral-based GNNs while tightly associating approaches that exist within each respective domain. 

With recent advancements, large language models (LLMs) such as ChatGPT and Bard have shown the potential to disrupt many industries, from customer service to healthcare. Traditionally, humans interact with geospatial data through software (e.g., ArcGIS 10.3) and programming languages (e.g., Python). As a pioneer study, we explore the possibility of using an LLM as an interface to interact with geospatial datasets through natural language. To achieve this, we also propose a framework to (1) train an LLM to understand the datasets, (2) generate geospatial SQL queries based on a natural language question, (3) send the SQL query to the backend database, (4) parse the database response back to human language. As a proof of concept, a case study was conducted on real-world data to evaluate its performance on various queries. The results show that LLMs can be accurate in generating SQL code for most cases, including spatial joins, although there is still room for improvement. As all geospatial data can be stored in a spatial database, we hope that this framework can serve as a proxy to improve the efficiency of spatial data analyses and unlock the possibility of automated geospatial analytics.