Data Processing Workflow Research Articles

Detailed lipid investigation of edible seaweeds by photochemical derivatization and untargeted lipidomics

Seaweeds are macrophytic algae that have been gaining interest as alternative healthy foods, renewable drug sources, and climate change mitigation agents. In terms of their nutritional value, seaweeds are renowned for their high content of biologically active polyunsaturated fatty acids. However, little is known about the regiochemistry—the geometry and position of carbon–carbon double bonds—of free and conjugated fatty acids in seaweeds. In the present work, a detailed characterization of the seaweed lipidome was achieved based on untargeted HRMS-based analysis and lipid derivatization with a photochemical aza-Paternò–Büchi reaction. A triple-data processing strategy was carried out to achieve high structural detail on the seaweed lipidome, i.e., (i) a first data processing workflow with all samples for aligning peak and statistical analysis that led to the definition of lipid sum compositions (e.g., phosphatidylglycerol (PG) 34:1), (ii) a second data processing workflow in which the samples of each seaweed were processed separately to annotate molecular lipids with known fatty acyl isomerism (e.g., PG 16:0_18:1), and (iii) the annotation of lipid regioisomers following MS/MS annotation of the lipid derivatives obtained following the aza-Paternò–Büchi reaction (e.g., PG 16:0_18:1 ω-9). Once the platform was set up, the lipid extracts from 8 seaweed species from different seaweed families were characterized, describing over 900 different lipid species, and information on the regiochemistry of carbon–carbon double bonds uncovered unknown peculiarities of seaweeds belonging to different families. The overall analytical approach helped to fill a gap in the knowledge of the nutritional composition of seaweeds.Graphical

SKYQUANT 3D: Quantifying Vascular Anatomy With an Open-Source Workflow for Comprehensive Analysis of Volumetric Optoacoustic Angiography Data.

Efficient visualization of the vascular system is of key importance in biomedical research into tumor angiogenesis, cerebrovascular alterations, and other angiopathies. Optoacoustic (OA) angiography offers a promising solution combining molecular optical contrast with high resolution and deep penetration of ultrasound. However, its hybrid nature implies complex data collection and processing workflows, with significant variability in methodologies across developers and users. To streamline interoperability, we introduce SKYQUANT 3D, a Python-based set of instructions for the Thermo Fisher Scientific Amira/Avizo 3D Visualization & Analysis Software. Our workflow simplifies the batch processing of volumetric optoacoustic angiography images, extracting meaningful quantitative information while also providing statistical analysis and graphical representation of the results. Quantification performance of SKYQUANT 3D is demonstrated using functional preclinical and clinical in vivo 3D OA angiographic tests involving ambient temperature variations and repositioning of the imaged limb.

Cardiovascular Drugs as Water Contaminants and Analytical Challenges in the Evaluation of Their Degradation

Cardiovascular drugs have been a burning topic in the field of environmental analytical chemistry in the last few decades. Growing modern healthcare has led to the widespread use of pharmaceuticals. Among these, antihypertensives (sartans, angiotensin-converting enzyme inhibitors) and lipid-regulating drugs (fibrates and statins) are the most frequently consumed and, thus, excreted into wastewater. Their chemical fate during conventional and advanced wastewater treatment, such as ozonation, remains unclear. Analytical chemistry, providing sample pretreatment followed by instrumental analysis, has a tremendous role in water treatment evaluation, mostly from the perspective of parent contaminants’ removals and also assessment of transformation pathways. Ultrasensitive liquid chromatography–mass spectrometry (LC-MS) systems provide many opportunities. By carefully using planned workflows for chromatographic and mass-spectrometric data processing, i.e., suspect and non-target screening approaches, LC-MS allows for the identification and structural elucidation of unknown, predicted, suspected or selected transformation products. Accordingly, some examples and case studies on selected cardiovascular drugs in this review are presented to show the applicability of the used analytical approaches and workflows.

Dataset for Machine Learning: Explicit All-Sky Image Features to Enhance Solar Irradiance Prediction

Prediction of solar irradiance is crucial for photovoltaic energy generation, as it helps mitigate intermittencies caused by atmospheric fluctuations such as clouds, wind, and temperature. Numerous studies have applied machine learning and deep learning techniques from artificial intelligence to address this challenge. Based on the recently proposed Hybrid Prediction Method (HPM), this paper presents an original and comprehensive dataset with nine attributes extracted from all-sky images developed using image processing techniques. This dataset and analysis of its attributes offer new avenues for research into solar irradiance forecasting. To ensure reproducibility, the data processing workflow and the standardized dataset have been meticulously detailed and made available to the scientific community to promote further research into prediction methods for photovoltaic energy generation.

Cross‐equalization for time‐lapse sparker seismic data

AbstractTime‐lapse seismic data processing is an important technique for observing subsurface changes over time. The conventional time‐lapse seismic exploration has been conducted using a large‐scale exploration system. However, for efficient monitoring of shallow subsurface, time‐lapse monitoring based on the small‐scale exploration system is required. Small‐scale exploration system using a sparker source offers high vertical resolution and cost efficiency, but it faces challenges, such as inconsistent waveforms of sparker sources, inaccurate positioning information and a low signal‐to‐noise ratio. Therefore, this study proposes a data processing workflow to preserve the signal and enhance the repeatability of small‐scale time‐lapse seismic data acquired using a sparker source. The proposed workflow has three stages: pre‐stack, post‐stack and machine learning–based data processing. Conventional seismic data processing methods were applied to enhance the quality of the sparker seismic data during the pre‐stack data processing stage. In the post‐stack processing stage, the positions and energy correction were performed, and the machine learning–based data processing stage attenuated random noise and applied a matched filter. The data processing was performed using only the seismic signals recorded near the seafloor, and the results confirmed the improvement in the repeatability of the entire seismic profile, including that of the target area. According to the repeatability quantification results, the predictability increased and the normalized root mean square decreased during data processing, indicating improved repeatability. In particular, the repeatability of the data was greatly improved through vertical correction, energy correction and matched filtering approaches. The processing results demonstrate that the data processing method proposed in this study can effectively enhance the repeatability of high‐resolution time‐lapse seismic data. Consequently, this approach could contribute to a more accurate understanding of temporal changes in subsurface structure and material properties.

Employing automated electrical resistivity tomography for detecting short- and long-term changes in permafrost and active-layer dynamics in the maritime Antarctic

Abstract. Repeated electrical resistivity tomography (ERT) surveys can substantially advance the understanding of spatial and temporal freeze–thaw dynamics in remote regions, such as Antarctica, where the evolution of permafrost has been poorly investigated. To enable time-lapse ERT surveys in Antarctica, an automated ERT (A-ERT) system is required, as regular site visits are not feasible. In this context, we developed a robust A-ERT prototype and installed it at the Crater Lake CALM-S site on Deception Island, Antarctica, to collect quasi-continuous ERT measurements. We developed an automated data processing workflow to efficiently filter and invert the A-ERT datasets and extract the key information required for a detailed investigation of permafrost and active-layer dynamics. In this paper, we report on the results of two complete year-round A-ERT datasets collected in 2010 and 2019 at the Crater Lake CALM-S site and compare them with available climate and borehole data. The A-ERT profile has a length of 9.5 m with an electrode spacing of 0.5 m, enabling a maximum investigation depth of approximately 2 m. Our detailed investigation of the A-ERT data and inverted results shows that the A-ERT system can detect the active-layer freezing and thawing events with high temporal resolution. The resistivity of the permafrost zone in 2019 is very similar to the values found in 2010, suggesting the stability of the permafrost over almost 1 decade at this site. The evolution of thaw depth exhibits a similar pattern in both years, with the active-layer thickness fluctuating between 0.20–0.35 m. However, a slight thinning of the active layer is evident in early 2019, compared to the equivalent period in 2010. These findings show that A-ERT datasets, combined with the new processing workflow that we developed, are an effective tool for studying permafrost and active-layer dynamics with very high resolution and minimal environmental disturbance. The ability of the A-ERT setup to monitor the spatiotemporal progression of thaw depth in two dimensions, and potentially in three dimensions, and to detect brief surficial refreezing and thawing of the active layer reveals the significance of the automatic ERT monitoring system to record continuous resistivity changes. An A-ERT monitoring setup with a longer profile length can investigate greater depths, offering effective monitoring at sites where boreholes are costly and invasive techniques are unsuitable. This shows that the A-ERT setup described in this paper can be a significant addition to the Global Terrestrial Network for Permafrost (GTN-P) and the Circumpolar Active Layer Monitoring (CALM) networks to further investigate the impact of fast-changing climate and extreme meteorological events on the upper soil horizons and to work towards establishing an early warning system for the consequences of climate change.

Effect of Data Quality and Data Quantity on the Estimation of Intrinsic Solubility: Analysis Based on a Single-Source Data Set.

Aqueous solubility is one of the most important physicochemical properties of drug molecules and a major driving force for oral drug absorption. To date, the performance of in silico models for the estimation of solubility for novel chemical space is limited. To investigate possible reasons and remedies for this, the Johnson and Johnson in-house aqueous solubility data with over 40,000 compounds was leveraged. All data were generated through the same high-throughput assay, providing a unique opportunity to explore the relationship between data quality, quantity, and model estimations. Six intrinsic solubility data sets with different sizes and noise levels were generated by making use of three different approaches: (i) inclusion or exclusion of amorphous solid residue, (ii) measured or experimental log D to identify the intrinsic solubility, and (iii) adopting or omitting a quality check process in the data processing workflow. A random forest regressor was trained on the data sets with three different sets of descriptors calculated from RDKit, ADMET predictor, or Mordred, and the performances were evaluated with nested cross-validation as well as ten refined test sets. The models confirm, as expected, that with the same data set size, high-quality data leads to better model performance; however, also, models trained with larger data sets containing analytical variability can give equally accurate estimations compared to models trained with small, clean, and diverse data sets. However, noise introduced by including the presence of amorphous solid postsolubility measurement in the training data set cannot be overcome by increasing data size, as they are introducing a biased systematic positive error in the data set, confirming the importance of critical data review. Finally, two top-performing models were tested on the first test set from the second solubility challenge, achieving RMSE values of 0.74 and 0.72 and log S ± 0.5 of 46 and 48%, respectively. These results demonstrated improved performance compared to those reported in the findings of the competition, highlighting that a single-source curated data set can enhance the prediction of intrinsic solubility.

Research on simulation and validation methods of aerosol radiative forcing on the Tibetan Plateau based on satellite and ground-based remote sensing observations over the past 20 years

Atmospheric radiative changes induced by aerosol radiative forcing are the most uncertain factors in climate change, affecting a comprehensive understanding of aerosol's role in the climate system and ecosystem, with current research mainly focused on densely populated and heavily polluted regions. This study utilizes satellite and ground-based remote sensing data to establish a multi-source data processing and analysis workflow suitable for the Qinghai-Tibet Plateau region, and based on atmospheric radiative transfer models, constructs methods for simulating and validating regional aerosol radiative forcing, optimizing the long-term observational, simulation, and variation studies of aerosol radiative forcing at regional scales. The results indicate: (1) Key input parameters for simulating aerosol radiative forcing regions were determined through sensitivity tests of radiative transfer model parameters to be AOD, surface albedo, atmospheric column water vapor content, and total atmospheric ozone. A method for simulating aerosol direct radiative forcing regions was constructed. Comparison and validation against aerosol radiative forcing site simulations based on ground-based remote sensing observations at the Yangbajing station in Tibet showed R2 values above 0.8 and NRMSE values between 0.25 and 0.39, indicating high accuracy of the method, suitable for the Qinghai-Tibet Plateau. (2) Utilizing satellite remote sensing data, aerosol direct radiative forcing simulations for the Qinghai-Tibet Plateau region over the past 20 years were conducted based on the constructed method. Results showed: ① The annual mean aerosol radiative forcing at the top of the atmosphere was −3.03 W/m2, gradually increasing from west to east; monthly means were negative, decreasing by an average of 0.0025 W/m2 per year, with decreases mainly in February to May. ② The annual mean surface aerosol radiative forcing was −13.56 W/m2, gradually increasing from west to east; monthly means were negative, decreasing by an average of 0.015 W/m2 per year, with decreases mainly in February, June to July, and October to December. ③ The annual mean atmospheric aerosol radiative forcing was 10.6 W/m2, gradually increasing from southwest to northeast; monthly means were positive, increasing by 0.007 W/m2 per year, with increases mainly in October to December. Overall, the annual and monthly mean aerosol direct radiative forcing values at the top of the atmosphere and surface were negative, indicating a cooling effect, while those in the atmosphere were positive, indicating a heating effect; the strongest aerosol radiative forcing occurred in summer at the top of the atmosphere, and in spring for both surface and atmosphere; April showed the fastest variation.

PharmaBench: Enhancing ADMET benchmarks with large language models

Accurately predicting ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) properties early in drug development is essential for selecting compounds with optimal pharmacokinetics and minimal toxicity. Existing ADMET-related benchmark sets are limited in utility due to their small dataset sizes and the lack of representation of compounds used in drug discovery projects. These shortcomings hinder their application in model building for drug discovery. To address this issue, we propose a multi-agent data mining system based on Large Language Models that effectively identifies experimental conditions within 14,401 bioassays. This approach facilitates merging entries from different sources, culminating in the creation of PharmaBench. Additionally, we have developed a data processing workflow to integrate data from various sources, resulting in 156,618 raw entries. Through this workflow, we constructed PharmaBench, a comprehensive benchmark set for ADMET properties, which comprises eleven ADMET datasets and 52,482 entries. This benchmark set is designed to serve as an open-source dataset for the development of AI models relevant to drug discovery projects.

Portable Acceleration of CMS Computing Workflows with Coprocessors as a Service

Computing demands for large scientific experiments, such as the CMS experiment at the CERN LHC, will increase dramatically in the next decades. To complement the future performance increases of software running on central processing units (CPUs), explorations of coprocessor usage in data processing hold great potential and interest. Coprocessors are a class of computer processors that supplement CPUs, often improving the execution of certain functions due to architectural design choices. We explore the approach of Services for Optimized Network Inference on Coprocessors (SONIC) and study the deployment of this as-a-service approach in large-scale data processing. In the studies, we take a data processing workflow of the CMS experiment and run the main workflow on CPUs, while offloading several machine learning (ML) inference tasks onto either remote or local coprocessors, specifically graphics processing units (GPUs). With experiments performed at Google Cloud, the Purdue Tier-2 computing center, and combinations of the two, we demonstrate the acceleration of these ML algorithms individually on coprocessors and the corresponding throughput improvement for the entire workflow. This approach can be easily generalized to different types of coprocessors and deployed on local CPUs without decreasing the throughput performance. We emphasize that the SONIC approach enables high coprocessor usage and enables the portability to run workflows on different types of coprocessors.

Super-resolved highly multiplexed immunofluorescence imaging for precise protein localization and podocyte ultrastructure.

Deep insights into the complex cellular and molecular changes occurring during (patho-)physiological conditions are essential for understanding the interactions and regulation of proteins. This understanding is crucial for research and diagnostics. However, the effectiveness of conventional immunofluorescence and light microscope, tools for visualizing the spatial distribution of cells or proteins, are limited both in resolution and multiplexity in complex tissues. This is mainly due to challenges such as the spectral overlap of fluorophore wavelengths, a limited range of antibody types, the inherent variability of samples and the optical resolution limit. The herein demonstrated combination of multiplex immunofluorescence imaging and super resolution microscopy offers a solution to these limitations by enabling the identification of different cell types and precise subcellular localization of proteins in tissue sections. In this study, we demonstrate the cyclic staining and de-staining of paraffin kidney sections, making it suitable for routine use and compatible with super-resolution microscopy for podocyte ultrastructural studies. We have further developed a computerized workflow for data processing which is accessible through available reagents and open-access code. As a proof of principle, we identified CDH2 as a marker for cellular lesions of sclerotic glomeruli in the nephrotoxic serum nephritis mouse model and cross-validated this finding with a human Nephroseq dataset indicating its translatability. In summary, our work represents an advance in multiplex imaging, which is crucial for understanding the localization of numerous proteins in a single FFPE kidney section and the compatibility with super-resolution microscopy to study ultrastructural changes of podocytes.

Chlomito: a novel tool for precise elimination of organelle genome contamination from nuclear genome assembly.

Accurate reference genomes are fundamental to understanding biological evolution, biodiversity, hereditary phenomena and diseases. However, many assembled nuclear chromosomes are often contaminated by organelle genomes, which will mislead bioinformatic analysis, and genomic and transcriptomic data interpretation. To address this issue, we developed a tool named Chlomito, aiming at precise identification and elimination of organelle genome contamination from nuclear genome assembly. Compared to conventional approaches, Chlomito utilized new metrics, alignment length coverage ratio (ALCR) and sequencing depth ratio (SDR), thereby effectively distinguishing true organelle genome sequences from those transferred into nuclear genomes via horizontal gene transfer (HGT). The accuracy of Chlomito was tested using sequencing data from Plum, Mango and Arabidopsis. The results confirmed that Chlomito can accurately detect contigs originating from the organelle genomes, and the identified contigs covered most regions of the organelle reference genomes, demonstrating efficiency and precision of Chlomito. Considering user convenience, we further packaged this method into a Docker image, simplified the data processing workflow. Overall, Chlomito provides an efficient, accurate and convenient method for identifying and removing contigs derived from organelle genomes in genomic assembly data, contributing to the improvement of genome assembly quality.

Role-Based Access Control (RBAC) Enabled Secure and Efficient Data Processing Framework for IoT Networks

Internet of Things (IoT) has the potential to significantly impact various domains e.g. health, transportation, automation, and emergency response to both man-made and natural disasters, particularly in scenarios where human decision is challenging. In this research a Role-Based Access Control (RBAC) Enabled Secure and Efficient Data Processing Framework for IoT Networks has been proposed. This framework ensures robust security and optimized data handling through granular access control mechanisms based on predefined roles. By leveraging RBAC, it mitigates unauthorized access risks, thereby safeguarding sensitive IoT data during transmission and storage. Our approach emphasizes efficiency by streamlining data processing workflows, reducing latency, and optimizing resource utilization. The framework is designed to scale with IoT network expansions and adapt to evolving security needs, promising enhanced reliability and trustworthiness in data operations for contemporary IoT environments. According to this research work current security effectiveness is 99 percent.Home area network (HAN) can be used for smart connectivity of different home appliances using IoT and automatic start and stop feature may be possible.Access control server (ACS) is used to control access and provide permission for different operations.

BIM and individual physical needs-trained model-enabled approach to spatial redesign and visualization

ABSTRACT This paper presents a new spatial visualization technique to redesign indoor spaces that reflect individual physical requirements. Designing safe and convenient environments necessitates differentiated facility installations based on factors such as age, gender, and disability status, emphasizing the need for customized spatial configurations. The study specifically focuses on elderly users, visualizing appropriate safety equipment placement to address physical aging challenges and proposing tailored space redesigns. High-Level of detail (LoD) Building Information Modeling (BIM) components were developed for the training model and utilized in the data processing workflow. The training data consists of images paired with explanatory text, and additional training was completed by optimizing the training hyperparameters. The resulting trained model generates high-quality images that accurately reflect the provided contextual prompts. Furthermore, this study showcases a practical application through the development of a user-friendly mobile web/application interface. This tool allows non-professional users to capture images using their smartphones and visualize potential redesign alternatives tailored to their specific physical requirements. By bridging the gap between spatial visualization techniques and users, this study contributes to making more inclusive and adaptable indoor environments for diverse users, particularly the elderly.

Standardizing Protein Corona Characterization in Nanomedicine: A Multicenter Study to Enhance Reproducibility and Data Homogeneity.

We recently revealed significant variability in protein corona characterization across various proteomics facilities, indicating that data sets are not comparable between independent studies. This heterogeneity mainly arises from differences in sample preparation protocols, mass spectrometry workflows, and raw data processing. To address this issue, we developed standardized protocols and unified sample preparation workflows, distributing uniform protein corona digests to several top-performing proteomics centers from our previous study. We also examined the influence of using similar mass spectrometry instruments on data homogeneity and standardized database search parameters and data processing workflows. Our findings reveal a remarkable stepwise improvement in protein corona data uniformity, increasing overlaps in protein identification from 11% to 40% across facilities using similar instruments and through a uniform database search. We identify the key parameters behind data heterogeneity and provide recommendations for designing experiments. Our findings should significantly advance the robustness of protein corona analysis for diagnostic and therapeutics applications.

An automated and high-throughput data processing workflow for PFAS identification in biota by direct infusion ultra-high resolution mass spectrometry

The increasing recognition of the health impacts from human exposure to per- and polyfluorinated alkyl substances (PFAS) has surged the need for sophisticated analytical techniques and advanced data analyses, especially for assessing exposure by food of animal origin. Despite the existence of nearly 15,000 PFAS listed in the CompTox chemicals dashboard by the US Environmental Protection Agency, conventional monitoring and suspect screening methods often fall short, covering only a fraction of these substances. This study introduces an innovative automated data processing workflow, named PFlow, for identifying PFAS in environmental samples using direct infusion Fourier transform ion cyclotron resonance mass spectrometry (DI-FT-ICR MS). PFlow’s validation on a bream liver sample, representative of low-concentration biota, involves data pre-processing, annotation of PFAS based on their precursor masses, and verification through isotopologues. Notably, PFlow annotated 17 PFAS absent in the comprehensive targeted approach and tentatively identified an additional 53 compounds, thereby demonstrating its efficiency in enhancing PFAS detection coverage. From an initial dataset of 30,332 distinct m/z values, PFlow thoroughly narrowed down the candidates to 84 potential PFAS compounds, utilizing precise mass measurements and chemical logic criteria, underscoring its potential in advancing our understanding of PFAS prevalence and of human exposure.Graphical abstract

Packaging code and data for reproducible research: A case study of journey time statistics

The effective and ethical use of data to inform decision-making offers huge value to the public sector, especially when delivered by transparent, reproducible, and robust data processing workflows. One way that governments are unlocking this value is through making their data publicly available, allowing more people and organisations to derive insights. However, open data is not enough in many cases: publicly available datasets need to be accessible in an analysis-ready form from popular data science tools, such as R and Python, for them to realise their full potential. This paper explores ways to maximise the impact of open data with reference to a case study of packaging code to facilitate reproducible analysis. We present the jtstats project, which consists of a main Python package, and a smaller R version, for importing, processing, and visualising large and complex datasets representing journey times, for many transport modes and trip purposes at multiple geographic levels, released by the UK Department for Transport (DfT). jtstats shows how domain specific packages can enable reproducible research within the public sector and beyond, saving duplicated effort and reducing the risks of errors from repeated analyses. We hope that the jtstats project inspires others, particularly those in the public sector, to add value to their data sets by making them more accessible.

Wearable Near-Eye Tracking Technologies for Health: A Review.

With the rapid advancement of computer vision, machine learning, and consumer electronics, eye tracking has emerged as a topic of increasing interest in recent years. It plays a key role across diverse domains including human-computer interaction, virtual reality, and clinical and healthcare applications. Near-eye tracking (NET) has recently been developed to possess encouraging features such as wearability, affordability, and interactivity. These features have drawn considerable attention in the health domain, as NET provides accessible solutions for long-term and continuous health monitoring and a comfortable and interactive user interface. Herein, this work offers an inaugural concise review of NET for health, encompassing approximately 70 related articles published over the past two decades and supplemented by an in-depth examination of 30 literatures from the preceding five years. This paper provides a concise analysis of health-related NET technologies from aspects of technical specifications, data processing workflows, and the practical advantages and limitations. In addition, the specific applications of NET are introduced and compared, revealing that NET is fairly influencing our lives and providing significant convenience in daily routines. Lastly, we summarize the current outcomes of NET and highlight the limitations.

Progress, applications, and challenges in high-throughput effect-directed analysis for toxicity driver identification - is it time for HT-EDA?

The rapid increase in the production and global use of chemicals and their mixtures has raised concerns about their potential impact on human and environmental health. With advances in analytical techniques, in particular, high-resolution mass spectrometry (HRMS), thousands of compounds and transformation products with potential adverse effects can now be detected in environmental samples. However, identifying and prioritizing the toxicity drivers among these compounds remain a significant challenge. Effect-directed analysis (EDA) emerged as an important tool to address this challenge, combining biotesting, sample fractionation, and chemical analysis to unravel toxicity drivers in complex mixtures. Traditional EDA workflows are labor-intensive and time-consuming, hindering large-scale applications. The concept of high-throughput (HT) EDA has recently gained traction as a means of accelerating these workflows. Key features of HT-EDA include the combination of microfractionation and downscaled bioassays, automation of sample preparation and biotesting, and efficient data processing workflows supported by novel computational tools. In addition to microplate-based fractionation, high-performance thin-layer chromatography (HPTLC) offers an interesting alternative to HPLC in HT-EDA. This review provides an updated perspective on the state-of-the-art in HT-EDA, and novel methods/tools that can be incorporated into HT-EDA workflows. It also discusses recent studies on HT-EDA, HT bioassays, and computational prioritization tools, along with considerations regarding HPTLC. By identifying current gaps in HT-EDA and proposing new approaches to overcome them, this review aims to bring HT-EDA a step closer to monitoring applications.

Surveillance of Health Care-Associated Violence Using Natural Language Processing.

Patient and family violent outbursts toward staff, caregivers, or through self-harm, have increased during the ongoing behavioral health crisis. These health care-associated violence (HAV) episodes are likely under-reported. We sought to assess the feasibility of using nursing notes to identify under-reported HAV episodes. We extracted nursing notes across inpatient units at 2 hospitals for 2019: a pediatric tertiary care center and a community-based hospital. We used a workflow for narrative data processing using a natural language processing (NLP) assisted manual review process performed by domain experts (a nurse and a physician). We trained the NLP models on the tertiary care center data and validated it on the community hospital data. Finally, we applied these surveillance methods to real-time data for 2022 to assess reporting completeness of new cases. We used 70 981 notes from the tertiary care center for model building and internal validation and 19 332 notes from the community hospital for external validation. The final community hospital model sensitivity was 96.8% (95% CI 90.6% to 100%) and a specificity of 47.1% (39.6% to 54.6%) compared with manual review. We identified 31 HAV episodes in July to December 2022, of which 26 were reportable in accordance with the hospital internal criteria. Only 7 of 26 cases were reported by employees using the self-reporting system, all of which were identified by our surveillance process. NLP-assisted review is a feasible method for surveillance of under-reported HAV episodes, with implementation and usability that can be achieved even at a low information technology-resourced hospital setting.