Automated Data Extraction Research Articles

P.62 Validating the accuracy of automated data extraction for an obstetric anaesthetic dataset: a single centre quality improvement project

P.62 Validating the accuracy of automated data extraction for an obstetric anaesthetic dataset: a single centre quality improvement project

PHENOTYPIC PARAMETER EXTRACTION FOR WHEAT EARS BASED ON AN IMPROVED MASK-RCNN ALGORITHM

The acquisition of traditional wheat ear phenotypic parameters is labour intensive and subjective, and some trait parameters are difficult to measure, which greatly limits the progress of wheat ear research. To obtain the phenotypic parameters of wheat ears in batches at a low cost, this paper proposed a convenient and accurate method for extracting phenotypic parameters of wheat ears. First, three improvement directions were proposed based on the Mask Region-Convolutional Neural Network (Mask-RCNN) model. 1) To extract the multiscale features of wheat ears, a hierarchical residual link was constructed in a single residual block of the backbone network ResNet101 to obtain information on different sizes of receptive fields. 2) The feature pyramid network (FPN) was improved to increase the recognition accuracy of wheat ear edges through multiple two-way information flow sampling. 3) The mask evaluation mechanism was improved, specific network blocks were used to learn and predict the quality of the mask, and the detection of wheat ears and grains was performed by precise segmentation; an automatic extraction algorithm was designed for wheat ear phenotypic parameters based on the segmentation results to extract 22 phenotypic parameters. The experiments showed that the improved Mask-RCNN was superior to the existing model in the segmentation accuracy of wheat ears and grains; the parameters of wheat ear length, width, and number of grains extracted by the automatic extraction algorithm were close to the manual measurement values. This research meets the demand for automatic extraction of wheat ear phenotype data for large-scale quality testing and commercial breeding and has strong practicability.

Automated assessment of hyoid movement during normal swallow using ultrasound.

BackgroundThe potential for using ultrasound by speech and language therapists (SLTs) as an adjunct clinical tool to assess swallowing function has received increased attention during the COVID‐19 pandemic, with a recent review highlighting the need for further research on normative data, objective measurement, elicitation protocol and training. The dynamic movement of the hyoid, visible in ultrasound, is crucial in facilitating bolus transition and protection of the airway during a swallow and has shown promise as a biomarker of swallowing function.AimsTo examine the kinematics of the hyoid during a swallow using ultrasound imaging and to relate the patterns to the different stages of a normal swallow. To evaluate the accuracy and robustness of two different automatic hyoid tracking methods relative to manual hyoid position estimation.Methods & ProceduresUltrasound data recorded from 15 healthy participants swallowing a 10 ml water bolus delivered by cup or spoon were analysed. The movement of the hyoid was tracked using manually marked frame‐to‐frame positions, automated hyoid shadow tracking and deep neural net (DNN) tracking. Hyoid displacement along the horizontal image axis (HxD) was charted throughout a swallow, and the maximum horizontal displacement (HxD max) and maximum hyoid velocity (HxV max) along the same axis were automatically calculated.Outcomes & ResultsThe HxD and HxV of 10 ml swallows are similar to values reported in the literature. The trajectory of the hyoid movement and its location at significant swallow event time points showed increased hyoid displacement towards the peak of the swallow. Using an interclass correlation coefficient, HxD max and HxV max values derived from the DNN tracker and shadow tracker are shown to be in high agreement and moderate agreement, respectively, when compared with values derived from manual tracking.Conclusions & ImplicationsThe similarity of the hyoid tracking results using ultrasound to previous reports based on different instrumental tools supports the possibility of using hyoid movement as a measure of swallowing function in ultrasound. The use of machine learning to automatically track the hyoid movement potentially provides a reliable and efficient way to quantify swallowing function. These findings contribute towards improving the clinical utility of ultrasound as a swallowing assessment tool. Further research on both normative and clinical populations is needed to validate hyoid movement metrics as a means of differentiating normal and abnormal swallows and to verify the reliability of automatic tracking.WHAT THIS PAPER ADDSWhat is already known on this subject There is growing interest in the use of ultrasound as an adjunct tool for assessing swallowing function. However, there is currently insufficient knowledge about the patterning and timing of lingual and hyoid movement in a typical swallow. We know that movement of the hyoid plays an essential role in bolus transition and airway protection. However, manual tracking of hyoid movement is time‐consuming and restricts the extent of large‐scale normative studies. What this study adds We show that hyoid movement can be tracked automatically, providing measurable continuous positional data. Measurements derived from this objective data are comparable with similar measures previously reported using videofluoroscopy and of the two automatic trackers assessed, the DNN approach demonstrates better robustness and higher agreement with manually derived measures. Using this kinematic data, hyoid movement can be related to different stages of swallowing. Clinical implications of this study This study contributes towards our understanding of the kinematics of a typical swallow by evaluating an automated hyoid tracking method, paving the way for future studies of typical and disordered swallow. The challenges of image acquisition highlight issues to be considered when establishing clinical protocols. The application of machine learning enhances the utility of ultrasound swallowing assessment by reducing the labour required and permitting a wider range of hyoid measurements. Further research in normative and clinical populations is facilitated by automatic data extraction allowing the validity of prospective hyoid measures in differentiating different types of swallows to be rigorously assessed.

Assessing author willingness to enter study information into structured data templates as part of the manuscript submission process: A pilot study

BackgroundEnvironmental health and other researchers can benefit from automated or semi-automated summaries of data within published studies as summarizing study methods and results is time and resource intensive. Automated summaries can be designed to identify and extract details of interest pertaining to the study design, population, testing agent/intervention, or outcome (etc.). Much of the data reported across existing publications lack unified structure, standardization and machine-readable formats or may be presented in complex tables which serve as barriers that impede the development of automated data extraction methodologies.As full automation of data extraction seems unlikely soon, encouraging investigators to submit structured summaries of methods and results in standardized formats with meta-data tagging of content may be of value during the publication process. This would produce machine-readable content to facilitate automated data extraction, establish sharable data repositories, help make research data FAIR, and could improve reporting quality. ObjectivesA pilot study was conducted to assess the feasibility of asking participants to summarize study methods and results using a structured, web-based data extraction model as a potential workflow that could be implemented during the manuscript submission process. MethodsEight participants entered study details and data into the Health Assessment Workplace Collaborative (HAWC). Participants were surveyed after the extraction exercise to ascertain 1) whether this extraction exercise will impact their conducting and reporting of future research, 2) the ease of data extraction, including which fields were easiest and relatively more problematic to extract and 3) the amount of time taken to perform data extractions and other related tasks. Investigators then presented participants the potential benefits of providing structured data in the format they were extracting. After this, participants were surveyed about 1) their willingness to provide structured data during the publication process and 2) whether they felt the potential application of structured data entry approaches and their implementation during the journal submission process should continue to be further explored. ConclusionsRoutine provision of structured data that summarizes key information from research studies could reduce the amount of effort required for reusing that data in the future, such as in systematic reviews or agency scientific assessments. Our pilot study suggests that directly asking authors to provide that data, via structured templates, may be a viable approach to achieving this: participants were willing to do so, and the overall process was not prohibitively arduous. We also found some support for the hypothesis that use of study templates may have halo benefits in improving the conduct and completeness of reporting of future research. While limitations in the generalizability of our findings mean that the conditions of success of templates cannot be assumed, further research into how such templates might be designed and implemented does seem to have enough chance of success that it ought to be undertaken.

Automatic extraction of tunnel centerline and cross-sections from 3D point clouds

The accurate extraction of tunnel centerline and tunnel cross-section plays a vital role in many tunnel deformation monitoring projects. To address this issue, An automatic data extraction method for a tunnel centerline and cross-section is proposed based on the three-dimensional laser scanning data. A k-dimensional tree index is first constructed based on the horizontal projection of the tunnel point clouds, and then a series of seed points is selected as the center of several neighborhood point sets with different radii; the difference set region, which will be used to calculate the tunnel horizontal centerline point based on the convex hull operation, is obtained. Then, according to the horizontal centerline, the cross-section of the tunnel point clouds is extracted and fitted to obtain the tunnel cross-section parameters and three-dimensional centerline. Based on the design values of the three-dimensional centerline and tunnel radius, the overall model of the tunnel can be constructed and applied to the visual analysis of tunnel deformation. The experimental results show that the proposed method can accurately obtain the tunnel centerline and cross-section parameters, with a minimal 0.011 cm error for the extraction of the horizontal centerline. The proposed tunnel model could simulate the undulation of the tunnel surface well and provide reference values for similar cases.

Automated data extraction of electronic medical records: Validity of data mining to construct research databases for eligibility in gastroenterological clinical trials.

BackgroundElectronic medical records (EMRs) are adopted for storing patient-related healthcare information. Using data mining techniques, it is possible to make use of and derive benefit from this massive amount of data effectively. We aimed to evaluate validity of data extracted by the Customized eXtraction Program (CXP).MethodsThe CXP extracts and structures data in rapid standardised processes. The CXP was programmed to extract TNFα-native active ulcerative colitis (UC) patients from EMRs using defined International Classification of Disease-10 (ICD-10) codes. Extracted data were read in parallel with manual assessment of the EMR to compare with CXP-extracted data.ResultsFrom the complete EMR set, 2,802 patients with code K51 (UC) were extracted. Then, CXP extracted 332 patients according to inclusion and exclusion criteria. Of these, 97.5% were correctly identified, resulting in a final set of 320 cases eligible for the study. When comparing CXP-extracted data against manually assessed EMRs, the recovery rate was 95.6–101.1% over the years with 96.1% weighted average sensitivity.ConclusionUtilisation of the CXP software can be considered as an effective way to extract relevant EMR data without significant errors. Hence, by extracting from EMRs, CXP accurately identifies patients and has the capacity to facilitate research studies and clinical trials by finding patients with the requested code as well as funnel down itemised individuals according to specified inclusion and exclusion criteria. Beyond this, medical procedures and laboratory data can rapidly be retrieved from the EMRs to create tailored databases of extracted material for immediate use in clinical trials.

Towards automated extraction for terrestrial laser scanning data of building components based on panorama and deep learning

Terrestrial laser scanning has been widely used in the dimensional quality assessment (DQA) on building components, but the extraction of component data is mostly done by a specialized software which is not applicable to the building components assembled in a factory. The need for manual operations makes it difficult to fulfill the notion of efficient component manufacturing. Notably, due to the successful applications in image processing, deep learning has been extended to the field of quality inspection and damage diagnosis of building components, which can quickly locate targets in images. As deep learning has excellent performance for target detection and current scanner can produce a panorama with the scan resolution, it is possible to automatically extract the targets using deep learning by correlating the panorama with the scanned data. To the best of our knowledge, little research has been on the combined use of panorama and deep learning for automated data extraction of building components. Therefore, this paper proposes an approach using the panorama and deep learning to automatically extract building component data for DQA. To determine suitable scan parameters, parametric tests are first carried out on scan distance, scan resolution, scan color and scan angle. Experimental test is then conducted on a deformed concrete-filled steel tubular column to validate the proposed approach.

BatteryDataExtractor: battery-aware text-mining software embedded with BERT models.

Due to the massive growth of scientific publications, literature mining is becoming increasingly popular for researchers to thoroughly explore scientific text and extract such data to create new databases or augment existing databases. Efforts in literature-mining software design and implementation have improved text-mining productivity, but most of the toolkits that mine text are based on traditional machine-learning-algorithms which hinder the performance of downstream text-mining tasks. Natural-language processing (NLP) and text-mining technologies have seen a rapid development since the release of transformer models, such as bidirectional encoder representations from transformers (BERT). Upgrading rule-based or machine-learning-based literature-mining toolkits by embedding transformer models into the software is therefore likely to improve their text-mining performance. To this end, we release a Python-based literature-mining toolkit for the field of battery materials, BatteryDataExtractor, which involves the embedding of BatteryBERT models in its automated data-extraction pipeline. This pipeline employs BERT models for token-classification tasks, such as abbreviation detection, part-of-speech tagging, and chemical-named-entity recognition, as well as new double-turn question-answering data-extraction models for auto-generating repositories of inter-related material and property data as well as general information. We demonstrate that BatteryDataExtractor exhibits state-of-the-art performance on the evaluation data sets for both token classification and automated data extraction. To aid the use of BatteryDataExtractor, its code is provided as open-source software, with associated documentation to serve as a user guide.

Virtual shoe test system

In order to solve the problem of uncomfortable wearing shoes caused by foot type or shoe type of consumers, a virtual shoe test system is developed based on computer graphics knowledge. If the online shoe test has problems, it can provide personal customization for consumers. Firstly, the shoe database is constructed to store shoe last model and key parts data for data comparison and fast data query. Secondly, the method based on OBB and AABB bounding box and plane fitting is proposed. Based on the foot bottom surface, combined with the foot shape law and foot skeleton composition of Chinese people, the automatic extraction of key data and the automatic matching of foot and shoe last are realized. Finally, the OpenGL function is realized in the MFC program, and the 3D visualization of shoes and boots is realized. The mouse control function is added to the system, which improves the human-computer interaction experience.

Evaluation of a semi-automated data extraction tool for public health literature-based reviews: Dextr

There has been limited development and uptake of machine-learning methods to automate data extraction for literature-based assessments. Although advanced extraction approaches have been applied to some clinical research reviews, existing methods are not well suited for addressing toxicology or environmental health questions due to unique data needs to support reviews in these fields. To develop and evaluate a flexible, web-based tool for semi-automated data extraction that: 1) makes data extraction predictions with user verification, 2) integrates token-level annotations, and 3) connects extracted entities to support hierarchical data extraction. Dextr was developed with Agile software methodology using a two-team approach. The development team outlined proposed features and coded the software. The advisory team guided developers and evaluated Dextr's performance on precision, recall, and extraction time by comparing a manual extraction workflow to a semi-automated extraction workflow using a dataset of 51 environmental health animal studies. The semi-automated workflow did not appear to affect precision rate (96.0% vs. 95.4% manual, p=0.38), resulted in a small reduction in recall rate (91.8% vs. 97.0% manual, p<0.01), and substantially reduced the median extraction time (436s vs. 933s per study manual, p<0.01) compared to a manual workflow. Dextr provides similar performance to manual extraction in terms of recall and precision and greatly reduces data extraction time. Unlike other tools, Dextr provides the ability to extract complex concepts (e.g., multiple experiments with various exposures and doses within a single study), properly connect the extracted elements within a study, and effectively limit the work required by researchers to generate machine-readable, annotated exports. The Dextr tool addresses data-extraction challenges associated with environmental health sciences literature with a simple user interface, incorporates the key capabilities of user verification and entity connecting, provides a platform for further automation developments, and has the potential to improve data extraction for literature reviews in this and other fields.

Automatic data extraction from 24 hour blood pressure measurement reports of a large multicenter clinical trial

Background and objectivesAmbulatory blood pressure monitoring (ABPM) is usually reported in descriptive values such as circadian averages and standard deviations. Making use of the original, individual blood pressure measurements may be advantageous, particularly for research purposes, as this increases the flexibility of the analytical process, enables alternative statistical analyses and provide novel insights. Here we describe the development of a new multistep, hierarchical data extraction algorithm to collect raw data from .pdf reports and text files as part of a large multi-center clinical study. MethodsOriginal reports were saved in a nested file system, from which they were automatically extracted, read and saved into databases with custom made programs written in Python 3. Data were further processed, cleaned and relevant descriptive statistics such as averages and standard deviations calculated according to a variety of definitions of day- and night-time. Additionally, data control mechanisms for manual review of the data and programmatic auto-detection of extraction errors was implemented as part of the project. ResultsThe developed algorithm extracted 97% of the data automatically, the missing data consisted mostly of reports that were saved incorrectly or not formatted in the specified way. Manual checks comparing samples of the extracted data to original reports indicated a high level of accuracy of the extracted data, no errors introduced due to flaws in the extraction software were detected in the extracted dataset. ConclusionsThe developed multistep, hierarchical data extraction algorithm facilitated collection from different file formats and paired with database cleaning and data processing steps led to an effective and accurate assembly of raw ABPM data for further and adjustable analyses. Manual work was minimized while data quality was ensured with standardized, reproducible procedures.

Web Scraping or Web Crawling: State of Art, Techniques, Approaches and Application

Web scraping or web crawling refers to the procedure of automatic extraction of data from websites using software. It is a process that is particularly important in fields such as Business Intelligence in the modern age. Web scrapping is a technology that allow us to extract structured data from text such as HTML. Web scrapping is extremely useful in situations where data isn’t provided in machine readable format such as JSON or XML. The use of web scrapping to gather data allows us to gather prices in near real time from retail store sites and provide further details, web scrapping can also be used to gather intelligence of illicit businesses such as drug marketplaces in the darknet to provide law enforcement and researchers valuable data such as drug prices and varieties that would be unavailable with conventional methods. It has been found that using a web scraping program would yield data that is far more thorough, accurate, and consistent than manual entry. Based on the result it has been concluded that Web scraping is a highly useful tool in the information age, and an essential one in the modern fields. Multiple technologies are required to implement web scrapping properly such as spidering and pattern matching which are discussed. This paper is looking into what web scraping is, how it works, web scraping stages, technologies, how it relates to Business Intelligence, artificial intelligence, data science, big data, cyber securityو how it can be done with the Python language, some of the main benefits of web scraping, and what the future of web scraping may look like, and a special degree of emphasis is placed on highlighting the ethical and legal issues. Keywords: Web Scraping, Web Crawling, Python Language, Business Intelligence, Data Science, Artificial Intelligence, Big Data, Cloud Computing, Cybersecurity, legal, ethical.

Toward Automated Data Extraction According to Tabular Data Structure: Cross-sectional Pilot Survey of the Comparative Clinical Literature.

BackgroundSystematic reviews depend on time-consuming extraction of data from the PDFs of underlying studies. To date, automation efforts have focused on extracting data from the text, and no approach has yet succeeded in fully automating ingestion of quantitative evidence. However, the majority of relevant data is generally presented in tables, and the tabular structure is more amenable to automated extraction than free text.ObjectiveThe purpose of this study was to classify the structure and format of descriptive statistics reported in tables in the comparative medical literature.MethodsWe sampled 100 published randomized controlled trials from 2019 based on a search in PubMed; these results were imported to the AutoLit platform. Studies were excluded if they were nonclinical, noncomparative, not in English, protocols, or not available in full text. In AutoLit, tables reporting baseline or outcome data in all studies were characterized based on reporting practices. Measurement context, meaning the structure in which the interventions of interest, patient arm breakdown, measurement time points, and data element descriptions were presented, was classified based on the number of contextual pieces and metadata reported. The statistic formats for reported metrics (specific instances of reporting of data elements) were then classified by location and broken down into reporting strategies for continuous, dichotomous, and categorical metrics.ResultsWe included 78 of 100 sampled studies, one of which (1.3%) did not report data elements in tables. The remaining 77 studies reported baseline and outcome data in 174 tables, and 96% (69/72) of these tables broke down reporting by patient arms. Fifteen structures were found for the reporting of measurement context, which were broadly grouped into: 1×1 contexts, where two pieces of context are reported in total (eg, arms in columns, data elements in rows); 2×1 contexts, where two pieces of context are given on row headers (eg, time points in columns, arms nested in data elements on rows); and 1×2 contexts, where two pieces of context are given on column headers. The 1×1 contexts were present in 57% of tables (99/174), compared to 20% (34/174) for 2×1 contexts and 15% (26/174) for 1×2 contexts; the remaining 8% (15/174) used unique/other stratification methods. Statistic formats were reported in the headers or descriptions of 84% (65/74) of studies.ConclusionsIn this cross-sectional pilot review, we found a high density of information in tables, but with major heterogeneity in presentation of measurement context. The highest-density studies reported both baseline and outcome measures in tables, with arm-level breakout, intervention labels, and arm sizes present, and reported both the statistic formats and units. The measurement context formats presented here, broadly classified into three classes that cover 92% (71/78) of studies, form a basis for understanding the frequency of different reporting styles, supporting automated detection of the data format for extraction of metrics.

Quantitative Distribution of Verbal Structures with Reference to the Authorship Factor in Legal Stylistics

Abstract The paper aims at describing the findings and conclusions formulated in the analysis of the authorship factor in legal discourse. It is hypothesised that verbal structures show systemically varied distribution across legal discourse and the relevant distinctions run through the authorship categories. When it comes to the aim of the research it draws on the tradition of sociolinguistic methodology targeting issues related to language variation which follows the basic assumptions of functional grammar. From the point of view of the material covered by the analysis it contributes to the research on legal discourse and specifically on its specialised domain referred to as corporate, company or business discourse. It provides additional empirical data pointing to the non-homogeneity of the legal style and formal distinctions originating from rich contextual background. The study is conducted on the material of a custom-designed corpus of English legal texts, classified as secondary genres. Methodologically, the study makes use of the tenets of supervised search of digitalised corpora and automatic data extraction based on discrete units, subsequent identification of recurring longer contiguous and/or non-contiguous sequences, if any, built around the axis of specific verbal structures and finally qualitative comparative analysis (characterisation) of the material. The discussion presents sample data and focuses on the most salient categories, both quantitatively and qualitatively. The inductive approach confirms the formal divergencies in the communicative situation covered by the analysis. The findings encapsulate patterns and tendencies in the quantitative distribution of verbal structures depending on the authorship category. It may be concluded that authorship is a factor delineating distinctions as regards (i) the repertoire of grammatical instruments exploited (verbal structures), which contributes to the specific stylistic profile of given authors. This shows that the thesis posed is verified positively and the study shows further, more detailed distinctions running through groups of subcategories distinguished within the authorship categories specified upon the start of the research.

Financial Hardship Amongst Patients with Hematologic Malignancies: Using the EMR to Streamline and Prioritize Patient-Centered Care

Background: Self-reported financial hardship (FH) amongst cancer patients is increasingly becoming a challenge for patients, caregivers, and healthcare providers. FH not only leads to financial struggles, significant lifestyle changes, and emotional distress, but also contributes to treatment noncompliance, affecting clinical outcomes. As treatment costs rise, it is crucial to develop efficient methods to proactively identify and alleviate FH in hematology practice. One potential approach is utilizing automated processes to identify those at highest risk of FH. At Mayo Clinic, screening for FH involves using a single financial strain question ‘How hard is it for you to pay for the very basics like food, housing, medical care, and heating?‘ which all cancer patients answer annually as part of the institution's Social Determinants of Health (SDOH) assessment. Answers are on a five-point scale including not hard at all, not very hard, somewhat hard, hard, and very hard. In this study, we assess the prevalence and predictors for FH (denoted by a response of “Very hard” “Hard” or “Somewhat hard”) amongst the Mayo Clinic hematologic malignancy patient population. Our study objective was to determine if this automated process could identify those at risk for FH.Methods: Patients who received care for hematologic malignancies (lymphoma, leukemia, plasma disorders, myelodysplastic/myeloproliferative disorders, and other heme malignancies) at any of the Mayo Clinic cancer centers (Minnesota, Arizona, and Florida) and who had completed the SDOH screen at least once were included in this study. The electronic medical record (EMR) and Mayo Clinic Cancer Registry were utilized to extract demographic and disease variables. Patient's home zip code was used to determine rural/urban residence, distance from cancer center, and the Area Deprivation Index (ADI), a measure of socioeconomic disadvantage based on home zip code (ranging from 1-100, with 100 representing the most disadvantaged). Multivariable logistic regression modeling was used to examine predictor variables for FH in this patient population.Results: The final cohort included 10,024 patients from 2018 to 2020. Median age was 64.6 years (IQR 58.1,73.7), 58% were male, and 79% married. Race/ethnicity composition was 94% White (n=9,268), 2.5% Black (n=246), 0.4% American Indian/Alaskan Native (44), and 4% Hispanic (n=360). Fifty-six percent of patients had Medicare and 41% had commercial insurance. Fifty percent were retired, 40% were working/students, and 72% were urban residents. Mean ADI was 41.2. Fifty-six percent of patients had lymphomas, 23.5% had plasma cell disorders, 8.5% had leukemias, 6.8% had other hematological malignancies, and 5.5% had myelodysplastic/myeloproliferative neoplasms. FH was reported by 12.8% (n=1286) of the patients. Table 1 shows the results of the multivariable model. A significantly higher likelihood of endorsing FH was noted in Hispanic vs non-Hispanics, Black and American Indian/Alaskan Native groups vs whites, Disabled/Unemployed vs working, Medicaid, Medicare, and Self-Pay groups vs commercial insurance, higher ADI (5 th quintile vs 1 st), and myelodysplastic/myeloproliferative disorder and other hematologic malignancy vs lymphoma patients. Older age, being retired, and living farther from the cancer center were associated with significantly less likelihood of endorsing FH.Conclusion: Our study used automated data extraction from the EMR to efficiently identify predictors of FH in hematologic cancer patients. Employing a dichotomized and automated “flag” for FH, particularly if incorporated in the EMR, could ease the identification of SDOH issues, facilitate timely connection to appropriate resources, and help provide better patient-centered care. [Display omitted] DisclosuresAilawadhi: Sanofi: Consultancy; Cellectar: Research Funding; Karyopharm: Consultancy; Ascentage: Research Funding; Genentech: Consultancy; Janssen: Consultancy, Research Funding; BMS: Consultancy, Research Funding; Beigene: Consultancy; GSK: Consultancy, Research Funding; AbbVie: Consultancy; Medimmune: Research Funding; Pharmacyclics: Consultancy, Research Funding; Takeda: Consultancy; Amgen: Consultancy, Research Funding; Xencor: Research Funding. Fonseca: OncoTracker: Consultancy, Membership on an entity's Board of Directors or advisory committees; Takeda: Consultancy; BMS: Consultancy; Mayo Clinic in Arizona: Current Employment; Aduro: Consultancy; AbbVie: Consultancy; GSK: Consultancy; Merck: Consultancy; Juno: Consultancy; Scientific Advisory Board: Adaptive Biotechnologies: Membership on an entity's Board of Directors or advisory committees; Patent: Prognosticaton of myeloma via FISH: Patents & Royalties; Novartis: Consultancy; Bayer: Consultancy; Celgene: Consultancy; Caris Life Sciences: Membership on an entity's Board of Directors or advisory committees; Kite: Consultancy; Janssen: Consultancy; Amgen: Consultancy; Pharmacyclics: Consultancy; Sanofi: Consultancy. Griffin: Exact Sciences: Research Funding.

Disease risk analysis for schizophrenia patients by an automatic AHP framework

BackgroundBased on more than 15 million follow-up records of 404,426 patients from Guangdong Mental Health Center over the past 10 years, this study aims to propose a disease risk analysis and prediction model to support chronic disease management and clinical research for schizophrenia patients.MethodsBased on a mental health information and intelligent data processing platform, we design an automatic AHP framework called AutoAHP to analyze and predict the disease risks of schizophrenia patients. Through automatic extraction, transformation and integration of follow-up data in the real world such as demography, treatment, and the disease course, a chronic database of patient status is established. In combination with age-period-cohort, logistic regression and Cox models, we apply the AutoAHP to assess disease risk and implement risk prediction in practice.ResultsA list of essential factors for risk prediction are identified, including annual changes in mental health policy, public support, regional difference, patient gender, compliance, and social function. After the verification of 1,222,038 complete disease course and treatment records of 256,050 patients, the AutoAHP framework achieves a precision of 0.923, a recall of 0.924, and a F1 of 0.923. The model is demonstrated to be superior to general models and has better performance in risk prediction.ConclusionsAiming at the risk assessment of patients with schizophrenia which is influenced by factors, such as time, region and complication, the AutoAHP framework is able to be applied as a model in combination with logistic regression and Cox models to support clinical analysis of disease risk related factors and assist decision-making in chronic disease management.

NanoSIP: NanoSIMS Applications for Microbial Biology.

High-resolution imaging with secondary ion mass spectrometry (nanoSIMS) has become a standard method in systems biology and environmental biogeochemistry and is broadly used to decipher ecophysiological traits of environmental microorganisms, metabolic processes in plant and animal tissues, and cross-kingdom symbioses. When combined with stable isotope-labeling-an approach we refer to as nanoSIP-nanoSIMS imaging offers a distinctive means to quantify net assimilation rates and stoichiometry of individual cell-sized particles in both low- and high-complexity environments. While the majority of nanoSIP studies in environmental and microbial biology have focused on nitrogen and carbon metabolism (using 15N and 13C tracers), multiple advances have pushed the capabilities of this approach in the past decade. The development of a high-brightness oxygen ion source has enabled high-resolution metal analyses that are easier to perform, allowing quantification of metal distribution in cells and environmental particles. New preparation methods, tools for automated data extraction from large data sets, and analytical approaches that push the limits of sensitivity and spatial resolution have allowed for more robust characterization of populations ranging from marine archaea to fungi and viruses. NanoSIMS studies continue to be enhanced by correlation with orthogonal imaging and 'omics approaches; when linked to molecular visualization methods, such as in situ hybridization and antibody labeling, these techniques enable in situ function to be linked to microbial identity and gene expression. Here we present an updated description of the primary materials, methods, and calculations used for nanoSIP, with an emphasis on recent advances in nanoSIMS applications, key methodological steps, and potential pitfalls.

Automatic Extraction of Interior Orientation Data in Aerial Photography Using Image Matching Method

The Interior Orientation is a set of parameters that have been determined to transform the coordinates of the camera photo. The pixel coordinates of Fiducial Mark in the base image (Search window) are obtained automatically. The template of the fiducial mark is designed on single-frame aerial photographs. The concept of photogrammetry with Image Matching techniques is applied in the programming works. The Normalized Cross-Correlation (NCC) method coupling with the Area Based Matching technique is precisely used in the automatic computation for measuring the coordinate of fiducial marks. Herein, three templates are provided for this calculation. The coordinates from the manual rectification are employed. The results reveal that the third template is more accurate than the others with the RMSE value of 0.0066. The accuracy regarding the results of manual rectification depends on the operator when they are identifying for pixel values.

OA08.04 Validation of Scalable, Automated Data Extraction in an Advanced Lung Cancer Patient Population

Manual extraction from electronic health records (EHRs) is currently the standard approach for accessing real-world healthcare data but can be time consuming and challenging to maintain over time. Automated data extraction using natural language processing (NLP) is emerging as a viable method of data extraction from structured and unstructured fields of EHRs. While speed of NLP-based data extraction is established, some question the validity of the extracted data. This study compares the accuracy of, and concordance between, manual and NLP-extracted data from EHRs of patients with advanced lung cancer (aLC).

Evaluation of Automatic Microstructural Analysis of Energy Dispersive Spectroscopy (EDS) Maps via a Python-Based Data Processing Framework

Computer-aided data acquisition, analysis and interpretation have been employed in various research areas generating useful information. Among these, image processing is most often implemented for post-processing of material characterization data. However, to tackle ambiguity of multi-component materials analysis, spectral data analysis can be used instead. The current study introduces a unique Python-based data processing method for in-depth analysis of energy dispersive spectroscopy (EDS) elemental maps to analyze agglomerate size distribution, average area of each component and their overlap. The framework developed in this study is applied to examine interaction of Cerium (Ce) and Palladium (Pd) particles in membrane electrode assembly (MEA) of Anion-Exchange Membrane Fuel Cell (AEMFC) and investigate if this approach can be utilized to predict the fuel cell’s electrochemical behavior. The study concludes that the developed framework is a promising method for automatic data extraction and can be beneficial for use in a variety of clean energy applications.