PDF Report Research Articles

Combined location online weather data: easy-to-use targeted weather analysis for agriculture

The continuing effects of climate change require farmers and growers to have greater understanding of how these changes affect crop production. However, while climatic data is generally available to help provide much of that understanding, it can often be in a form not easy to digest. The proposed Combined Location Online Weather Data (CLOWD) framework is an easy-to-use online platform for analysing recent and historical weather data of any location within Australia at the click of a map. CLOWD requires no programming skills and operates in any HTML5 web browser on PC and mobile devices. It enables comparison between current and previous growing seasons over a range of environmental parameters, and can create a plain-English PDF report for offline use, using natural language generation (NLG). This paper details the platform, the design decisions taken and outlines how farmers and growers can use CLOWD to better understand current growing conditions. Prototypes of CLOWD are now online for PCs and smartphones.

Development and validation of an MR-driven dose-of-the-day procedure for online adaptive radiotherapy in upper gastrointestinal cancer patients

Objective. To develop and validate a dose-of-the-day (DOTD) treatment plan verification procedure for liver and pancreas cancer patients treated with an magnetic resonance (MR)-Linac system. Approach. DOTD was implemented as an automated process that uses 3D datasets collected during treatment delivery. Particularly, the DOTD pipeline’s input included the adapt-to-shape (ATS) plan—i.e. 3D-MR dataset acquired at beginning of online session, anatomical contours, dose distribution—and 3D-MR dataset acquired during beam-on (BON). The DOTD automated analysis included (a) ATS-to-BON image intensity-based deformable image registration (DIR), (b) ATS-to-BON contours mapping via DIR, (c) BON-to-ATS contours copying through rigid registration, (d) determining ATS-to-BON dosimetric differences, and (e) PDF report generation. The DIR process was validated by two expert reviewers. ATS-plans were recomputed on BON datasets to assess dose differences. DOTD analysis was performed retrospectively for 75 treatment fractions (12-liver and 5-pancreas patients). Main results. The accuracy of DOTD process relied on DIR and mapped contours quality. Most DIR-generated contours (99.6%) were clinically acceptable. DICE correlated with depreciation of DIR-based region of interest mapping process. The ATS-BON plan difference was found negligible (<1%). The duodenum and large bowel exhibited highest variations, 24% and 39% from fractional values, for 5-fraction liver and pancreas. For liver 1-fraction, a 62% variation was observed for duodenum. Significance. The DOTD methodology provides an automated approach to quantify 3D dosimetric differences between online plans and their delivery. This analysis offers promise as a valuable tool for plan quality assessment and decision-making in the verification stage of the online workflow.

A Novel Approach to Template Filling with Automatic Speech Recognition for Healthcare Professionals

In the evolving landscape of medical documentation, the necessity for efficient and accurate record-keeping systems is paramount, especially in specialised fields such as neurology where precision in terminology is crucial. This paper introduces a pioneering application of a fine-tuned Whisper model, specifically adapted for brain-related medical terms, integrated with an AI-driven system for automated template filling. The proposed system leverages advanced speech recognition technologies to capture doctors' verbal inputs and accurately transcribe these into designated report templates. The process simplifies the documentation workflow, significantly reducing the cognitive and administrative load on healthcare providers by enabling them to focus more on patient care rather than paperwork. Our research details the development and implementation of this innovative system, including the specific adaptations made to the Whisper model to enhance its accuracy with neurology-specific terminology. We also evaluate the system's performance in real-world medical settings and discuss the practical implications of integrating such AI tools in clinical practice. Furthermore, the system's capacity to generate ready-to- print PDF reports not only streamlines the documentation process but also ensures consistency and reliability in medical records. The overarching aim of this project is to demonstrate how targeted AI solutions can address the unique challenges of medical documentation, offering substantial benefits to healthcare providers and patients alike.

Development and validation of a cloud platform for AI-enabled over-read of smart-device PDF reports

Development and validation of a cloud platform for AI-enabled over-read of smart-device PDF reports

An explainable AI-assisted web application in cancer drug value prediction

In recent years, there has been an increase in the interest in adopting Explainable Artificial Intelligence (XAI) for healthcare. The proposed system includes•An XAI model for cancer drug value prediction. The model provides data that is easy to understand and explain, which is critical for medical decision-making. It also produces accurate projections.•A model outperformed existing models due to extensive training and evaluation on a large cancer medication chemical compounds dataset.•Insights into the causation and correlation between the dependent and independent actors in the chemical composition of the cancer cell.While the model is evaluated on Lung Cancer data, the architecture offered in the proposed solution is cancer agnostic. It may be scaled out to other cancer cell data if the properties are similar. The work presents a viable route for customizing treatments and improving patient outcomes in oncology by combining XAI with a large dataset. This research attempts to create a framework where a user can upload a test case and receive forecasts with explanations, all in a portable PDF report.

The eDNA-Container App: A Simple-to-Use Cross-Platform Package for the Reproducible Analysis of eDNA Sequencing Data

The analysis of environmental DNA (eDNA) is a powerful and non-invasive method for monitoring the presence of species in ecosystems. However, ecologists and laboratory staff can find it challenging to use eDNA analysis software effectively due to the unfamiliar command-line interfaces used by many of these packages. Therefore, we developed the eDNA-container app, a free and open-source software package that provides a simple user-friendly interface for eDNA analysis. The application is based on the popular QIIME2 library and is distributed as a Docker image. The use of Docker makes it compatible with a wide range of operating systems and facilitates the reproducible analysis of data across different laboratories. The application includes a point-and-click user interface for selecting sequencing files, configuring parameters, and accessing the results. Key pipeline outputs, such as sequence quality plots, denoising, and ASV generation statistics, are automatically included in a PDF report. This open-source and freely available analysis package should be a valuable tool for scientists using eDNA in biodiversity and biosecurity applications.

BioXTAS RAW 2: new developments for a free open-source program for small-angle scattering data reduction and analysis.

BioXTAS RAW is a free open-source program for reduction, analysis and modelling of biological small-angle scattering data. Here, the new developments in RAW version 2 are described. These include improved data reduction using pyFAI; updated automated Guinier fitting and D max finding algorithms; automated series (e.g. size-exclusion chromatography coupled small-angle X-ray scattering or SEC-SAXS) buffer- and sample-region finding algorithms; linear and integral baseline correction for series; deconvolution of series data using regularized alternating least squares (REGALS); creation of electron-density reconstructions using electron density via solution scattering (DENSS); a comparison window showing residuals, ratios and statistical comparisons between profiles; and generation of PDF reports with summary plots and tables for all analysis. Furthermore, there is now a RAW API, which can be used without the graphical user interface (GUI), providing full access to all of the functionality found in the GUI. In addition to these new capabilities, RAW has undergone significant technical updates, such as adding Python 3 compatibility, and has entirely new documentation available both online and in the program.

User-Centered Development of an Online Dashboard Tool for Economic Sustainability for Small and Medium Enterprises

This study aimed to improve an existing static benchmarking tool for the economic sustainability of small and medium enterprises (SMEs) in the wine sector to develop and elevate it into a dynamic online dashboard decision support system (DSS) for economic sustainability. Development was conducted in line with a user-centered-development process in four main steps. In the first step, producers’ expectations for an optimal tool were elicited using a qualitative approach of 24 in-depth interviews with long-term users of the existing PDF reports. Among the 10 requirements, producers requested an overall summary assessment of the most important KPIs of their business (including the provision of ideal values), intuitive visual presentations, long-term time developments, flexible reference groups, and short comments. Based on the wine producers’ systemized responses, the first version of the online benchmarking tool was designed and implemented in cooperation with experienced online designers and programmers. In the third step, a usability test was conducted to elicit options for further improvements that were implemented before the fourth step, the release of the final version to the industry. The systematic development process outlined and established here and the released DSS tool that is publicly available with open access provide valuable insights for institutions planning similar future dashboards for other sectors, particularly for SMEs. This constitutes an important step toward the development of more holistic support tools for sustainability performance measurement across all pillars of sustainability moving forward. To the best of the authors’ knowledge, the DSS developed represents the first online dashboard tool for economic sustainability for SMEs globally and in the wine sector.

2024 Nebraska Crop Budgets — a Mixed Review with Some Costs Higher, Some Lower

While field operation costs are projected higher for the 2024 Nebraska crop enterprises, some material input costs are lower than were projected for 2023. One driving force on lower cost projections for 2024 is 20% to 40% less on fertilizer prices is factored in on many budgets, and five pounds less nitrogen fertilizer was entered for a majority of the corn budgets due to continued improvement of application practices. Cost scenarios for individual producers can vary based on their timing of input purchases and price variabilities. The 84 1Nebraska crop budgets are now available online in three formats with a complete 96-page pdf report, an Excel file, along with links to all of the budget reports created using the Agricultural Budget Calculator (ABC) program where enterprise budget data can be downloaded into user accounts and then modified for individual farm operations.

DAHNA-An integrated innovative mobile application for the screening and personalised management of the atherosclerotic cardiovascular disease risk

Abstract Background DAHNA (Diet According to the Healthy Heart Nutritional Approach) is an integrated and innovative mobile app that allows for: 1. Screening of atherosclerotic cardiovascular disease (ASCVD) risk; 2. A personalized healthy diet (macro- and micronutrients) based on cardiometabolic screening; 3. Long-term management of major risk factors; 4. Highly incentivizing rewards within the app. Objective To present the functionalities, mode of operation, and initial results of DAHNA through public implementation. Methods DAHNA can be downloaded on mobile phones (iOS and Android). Firstly, the app assesses the user's ASCVD risk score based on their country of residence using a "one-size-fits-all" risk calculator that combines the 2021 European Society of Cardiology (ESC) SCORE2/SCORE2-OP scores and the American Heart Association (AHA) Framingham score. For Europe, the calculation is based on the four SCORE2/SCORE2-OP tables for the four risk regions. DAHNA is not limited to healthy individuals and allows the user to indicate if they have diabetes, chronic kidney disease, or ASCVD. Secondly, based on the individual ASCVD risk score, DAHNA offers the following features: 1. Personalized healthy menus (Mediterranean diet) based on the only macro- and micronutrients proven to reduce individual ASCVD risk and in the recommended daily dose, with an automatically generated ingredient list and quantities; the user can choose to purchase the ingredients personally or order the list from suppliers; 2. Periodic follow-up of ASCVD risk outcomes; 3. Display of healthy life minutes gained by the user; 4. Notifications, reminders, rewards within the app, personalized weight loss plans, PDF reports to share with healthcare teams, and nutritional education; 5. A recommendation for a medical examination for those with high or very high risk; 6. Short movies to introduce physical activity and up-to-date medical information; 7. All data is collected in a central database. Results Between August 10th, 2022 and February 12th, 2023, 19,780 users downloaded DAHNA (mean age 48 +/- 10 years, 58% females, 11.13% with diabetes, 15.16% smokers, 16.4% with hypertension; 14% had low-to-moderate risk, 40% had high risk, and 46% had very high risk). A 100% correspondence was confirmed between the results of the DAHNA calculator and the ESC tables. Conclusion 1. DAHNA self-screening showed that 86% of users belong to the high or very high ASCVD risk group, which is consistent with statistical data showing Romania among the countries with a very high ASCVD risk. 2. This app is the first to assign a personalized healthy diet based on specific micronutrients to control ASCVD risk, provide medical recommendations for a healthy lifestyle, and allow for real-time management of major risk factors and ASCVD risk in large populations. These data should be important for adjusting health policies.

Abstract 16707: Clinical Validation of a Chest-Worn Personal ECG Device for the Detection of Atrial Fibrillation

Introduction: Novel consumer-focused personal ECG devices have the potential to revolutionise the way that cardiac arrhythmias are diagnosed and managed. These devices can be used remotely to monitor patients for arrhythmias, which could lead to earlier detection and treatment. In this study, we aimed to compare the cardiologist's interpretation of clinical 12-lead ECG recordings to a consumer-focused dry-electrode ECG chest strap device (Fourth Frontier FX+). Methods: We included patients seen in an outpatient cardiology clinic at the Sri Jayadeva Institute of Cardiovascular Science and Research, Bangalore, India. A total of 163 paired ECG recordings were captured from 85 adult patients (50% female, median age 54 years, AF present at the time of recording in 38%). Patients with critical cardiac problems or life support systems were excluded. ECG data from the Fourth Frontier FX+ (Fourth Frontier, Bangalore, India) and a standard 12-lead ECG were obtained simultaneously in the supine position. PDF reports for both devices were then generated, and the cardiologist's interpretation of the Fourth Frontier FX+ ECG was compared to the cardiologist's interpreted 12L ECG. Results: The cardiologist's interpretation of the Fourth Frontier FX+ data matched the cardiologist-interpreted 12L data for all patients. One FX+ ECG was excluded from the analysis due to not enough data being captured by the device. A total of 33 patients were correctly identified as having atrial fibrillation. Conclusion: The results of this study demonstrate that the Fourth Frontier FX+ ECG monitor is comparable to a 12-lead ECG for cardiac rhythm monitoring and that it can be used remotely to monitor patients for cardiac arrhythmias. This has the potential to change the way that arrhythmias are diagnosed and managed and lead to earlier detection and treatment at scale.

Using Pathology Synoptic Reporting Data to Create Individual Dashboards for Pathologists and Surgeons.

Electronic synoptic pathology reporting using xPert from mTuitive is available to all pathologists in British Columbia, Canada. Comparative feedback reports for pathologists and surgeons were created by using the synoptic reporting software. To use data stored in a single central data repository to provide nonpunitive confidential comparative feedback reports (dashboards) to individual pathologists and surgeons for reflection on their practice and to use aggregate data for quality improvement initiatives. Integration of mTuitive middleware in 5 different laboratory information systems to have 1 software solution (xPert) sending discrete data elements to the central data repository was performed. Microsoft Office products were used to build comparative feedback reports and made the infrastructure sustainable. Two different types of reports were developed: individual confidential feedback reports (dashboards) and aggregated data reports. Pathologists have access to an individual confidential live feedback report for the 5 major cancer sites. Surgeons get an annual confidential emailed PDF report. Several quality improvement initiatives were identified from the aggregate data. We present 2 novel dashboards: a live pathologist dashboard and a static surgeon dashboard. Individual confidential dashboards incentivize use of nonmandated electronic synoptic pathology reporting tools and have increased adoption rates. Use of dashboards has also led to discussions about how patient care may be improved.

Clinical Trial Risk Tool: software application using natural language processing to identify the risk of trial uninformativeness

Background: A large proportion of clinical trials end without delivering results that are useful for clinical, policy, or research decisions. This problem is called “uninformativeness”. Some high-risk indicators of uninformativeness can be identified at the stage of drafting the protocol, however the necessary information can be hard to find in unstructured text documents. Methods: We have developed a browser-based tool which uses natural language processing to identify and quantify the risk of uninformativeness. The tool reads and parses the text of trial protocols and identifies key features of the trial design, which are fed into a risk model. The application runs in a browser and features a graphical user interface that allows a user to drag and drop the PDF of the trial protocol and visualize the risk indicators and their locations in the text. The user can correct inaccuracies in the tool’s parsing of the text. The tool outputs a PDF report listing the key features extracted. The tool is focused HIV and tuberculosis trials but could be extended to more pathologies in future. Results: On a manually tagged dataset of 300 protocols, the tool was able to identify the condition of a trial with 100% area under curve (AUC), presence or absence of statistical analysis plan with 87% AUC, presence or absence of effect estimate with 95% AUC, number of subjects with 69% accuracy, and simulation with 98% AUC. On a dataset of 11,925 protocols downloaded from ClinicalTrials.gov, the tool was able to identify trial phase with 75% accuracy, number of arms with 58% accuracy, and the countries of investigation with 87% AUC. Conclusion: We have developed and validated a natural language processing tool for identifying and quantifying risks of uninformativeness in clinical trial protocols. The software is open-source and can be accessed at the following link: https://app.clinicaltrialrisk.org

A RDF model-based predictive model on Dengue patients’ diagnostic PDF reports

A RDF model-based predictive model on Dengue patients’ diagnostic PDF reports

Automated HL7v2 LRI informatics framework for streamlining genomics-EHR data integration

While VCF formatted files are the lingua franca of next-generation sequencing, most EHRs do not provide native VCF support. As a result, labs often must send non-structured PDF reports to the EHR. On the other hand, while FHIR adoption is growing, most EHRs support HL7 interoperability standards, particularly those based on the HL7 Version 2 (HL7v2) standard. The HL7 Version 2 genomics component of the HL7 Laboratory Results Interface (HL7v2 LRI) standard specifies a formalism for the structured communication of genomic data from lab to EHR. We previously described an open-source tool (vcf2fhir) that converts VCF files into HL7 FHIR format. In this report, we describe how the utility has been extended to output HL7v2 LRI data that contains both variants and variant annotations (e.g., predicted phenotypes and therapeutic implications). Using this HL7v2 converter, we implemented an automated pipeline for moving structured genomic data from the clinical laboratory to EHR. We developed an open source hl7v2GenomicsExtractor that converts genomic interpretation report files into a series of HL7v2 observations conformant to HL7v2 LRI. We further enhanced the converter to produce output conformant to Epic's genomic import specification and to support alternative input formats. An automated pipeline for pushing standards-based structured genomic data directly into the EHR was successfully implemented, where genetic variant data and the clinical annotations are now both available to be viewed in the EHR through Epic's genomics module. Issues encountered in the development and deployment of the HL7v2 converter primarily revolved around data variability issues, primarily lack of a standardized representation of data elements within various genomic interpretation report files. The technical implementation of a HL7v2 message transformation to feed genomic variant and clinical annotation data into an EHR has been successful. In addition to genetic variant data, the implementation described here releases the valuable asset of clinically relevant genomic annotations provided by labs from static PDFs to calculable, structured data in EHR systems.

MS-DAP Platform for Downstream Data Analysis of Label-Free Proteomics Uncovers Optimal Workflows in Benchmark Data Sets and Increased Sensitivity in Analysis of Alzheimer's Biomarker Data.

In the rapidly moving proteomics field, a diverse patchwork of data analysis pipelines and algorithms for data normalization and differential expression analysis is used by the community. We generated a mass spectrometry downstream analysis pipeline (MS-DAP) that integrates both popular and recently developed algorithms for normalization and statistical analyses. Additional algorithms can be easily added in the future as plugins. MS-DAP is open-source and facilitates transparent and reproducible proteome science by generating extensive data visualizations and quality reporting, provided as standardized PDF reports. Second, we performed a systematic evaluation of methods for normalization and statistical analysis on a large variety of data sets, including additional data generated in this study, which revealed key differences. Commonly used approaches for differential testing based on moderated t-statistics were consistently outperformed by more recent statistical models, all integrated in MS-DAP. Third, we introduced a novel normalization algorithm that rescues deficiencies observed in commonly used normalization methods. Finally, we used the MS-DAP platform to reanalyze a recently published large-scale proteomics data set of CSF from AD patients. This revealed increased sensitivity, resulting in additional significant target proteins which improved overlap with results reported in related studies and includes a large set of new potential AD biomarkers in addition to previously reported.

35. The development, testing, and validation of an automatic LIMS import method for NGS myeloid panel results

For oncology genetic testing, there is a critical need for patient results to be readily available and accessible for the ordering pathologist's review. After an initial genetic testing workup, emergency treatment or follow-up testing may be required, thus accessibility of results is a key feature in providing patient-focused laboratory testing. Ideally, genetic testing results would be incorporated into a LIMS data management system in order to have a permanent record of testing and to allow for the results to be easily accessible, searchable, and transferable by the clinical or pathology team working on behalf of the patient. For maximum impact, Next Generation Sequencing (NGS) reports should be electronically integrated into the patient's electronic health record. NGS reports uploaded as PDF attachments constrain health record searches. Additionally, data in PDF reports often are not able to be transferred to a comprehensive pathology report and may require cumbersome manual entry. Our team has recently completed a project to create an automatic import method for our Myeloid Complete NGS Panel report into our electronic patient data management system. Our data management system is interfaced with our client's LIMS platform enabling the direct and automatic transfer of orders coming in as well as delivery of the resultant NGS report into the patients' health records. We will present the steps taken to create, test, troubleshoot, and validate the automatic upload system. We will also detail critical components of the NGS LIMS report and challenges that were addressed during this project.

Case studies in automation of forensic toxicology practices with R

The last decade has seen a considerable growth in data generated by scientific instrumentation. Accountability requirements have grown similarly, requiring forensic toxicology laboratories to generate summary of findings to funders, stakeholders and the general public. This work aims to show how the programming language R and its integrated development environment (IDE) RStudio can be harnessed to speed up data analysis and produce summary reports in three different forensic toxicology applications. R version 3.6.1 or above and RStudio® version 1.2.5001 or above were used in developing and implementing all applications. A wide array of packages were employed, including readr, readtext and docxtractr to import data; tidyr and dplyr for data preparation (“wrangling”); stringr for text manipulation; ggplot2 and plotly for data visualization; rmarkdown to generate HTML and PDF reports; and shiny for the creation of interactive web applications. Automation can begin with the instrumental output analysis. The authors have already published two such examples (Desharnais et al. Journal of Analytical Toxicology 2017;41:261–268 and Desharnais et al. Journal of Analytical Toxicology 2019;43:512–519). A new example presented here is the implementation of trend monitoring, as required for the ISO 17025 accreditation. An interactive application allows for importation of raw instrument output into the database and periodic creation of PDF reports assessing a number of fixed criteria for the wide-scope LC-MS/MS method under analysis. Furthermore, a diagnostic tool allows interactive creation of scatterplots where a variable of interest (area, area ratio, concentration) is plotted for selected time frame, instrument(s), sample type(s) (e.g., standards, QC) and analytes. This allows to not only identify concerns via the presence of warning and action lines, but to explore potential causes of instrument issues with a single tool, which decreases troubleshooting time. This type of interactive data exploration is also possible for casework. Indeed, an application allowing inquiry into basically all variables related to driving under the influence of drugs or alcohol cases was built. The user can obtain summary statistics (e.g., total number of cases) and graphs (e.g., bar plots) by selecting and/or modulating one or more of the following: biological matrix analyzed, drug(s) detected, concentration, administrative region, date and time of the event, etc. As an example, with a few clicks, the user can find out how many DUI cases included a combination of THC and flubromazolam between June 2020 and September 2021 in a given city. This allows for seamless production of yearly reports (within 30 minutes instead of 3 days) as well as quick answers to punctual inquiries by other stakeholders such as police officers, prosecutors and deputy ministers. Annual summary reports can also be extracted from atypical datasets, such as toxicology reports in .docx or PDF format. Using this tool, a periodic update of xenobiotics concentrations found in postmortem casework can be quickly performed. Toxicologists can therefore inform their interpretation with recent data from within the lab–without a time-consuming manual search. It also allows for the production of an annual prospectus designed for the general public, summarizing the caseload and findings. When a suitable Laboratory Information Management System (LIMS) is not available, or mis-adapted to accomplish the desired task, R and its IDE RStudio offer unparalleled power and flexibility to achieve data importation, analysis and presentation. Since they are both available at no cost, the online documentation and community to support the user is vast, which is an advantage for laboratories with scant resources. In order to add another pillar to this network, the creation of an R User Group in Forensic Toxicology is first announced here.

Abstract 4090: Creating research quality cancer genomic data from electronic health records

Abstract Background: Understanding the impact of precision medicine on medical practice, patient care, and clinical outcomes is a priority for advancing cancer care. With the recent dramatic increase in the use of tumor genomic testing (TGT), records within EHRs are a rich data source for evaluating the impact of TGT results in real-world clinical practice of care and on patient outcomes. However, extracting TGT results from electronic health records (EHR) is challenging due to a lack of standards to communicate genomic information and an inability to store such information in commonly available EHR systems. Moreover, TGT results are delivered to clinicians in unstructured formats and image-based files (PDFs). We initiated a pilot study to assess the ability of natural language processing (NLP) algorithms to convert EHR unstructured clinical text and PDF-formatted TGT results into research-quality data. Methods: One author (RY) drew a sample of approximately 800 clinical text records from 21 breast cancer patients treated at University of Washington. Sources used for data extraction included medical record notes and PDF reports for two breast cancer gene expression tests: 21-gene Recurrence Score (RS, OncotypeDx) and/or the 70-gene signature (MMP, Mammaprint). A team redacted all PHI and provided records to a commercial collaborator (Pangaeadata.AI, UK), along with definitions of variables to be extracted, but without annotated target answers. Existing NLP algorithms that leverage pre-training, fine-tuning and rules were adapted to extract 26 variables specified by the research team (e.g., age at diagnosis, histology, and RS or MMP dates and scores). The output placed variables into relevant, standardized formats and produced a research quality data set. The extraction strategy depended on the feature and variable characteristics. For example, cancer stage, an ordinal numerical variable, was determined with a rule-based extraction method from outpatient clinic notes and pathology reports, whereas the RS score, a continuous variable, came from OncotypeDx PDF and OCR semi-structured retrieval produced the output. Results/Conclusions: The Pangaea tool obtained an average accuracy of 97.3% with a standard deviation of 3.5% across all 26 variables. The approach is developed based on rules designed and validated by clinical experts, using a model that does not require training, making overfitting likely minimal. Qualitative analysis showed that: 1] algorithms used to electronically extract TGT results provided the same data as manual abstraction by physicians, and 2] context matters, namely, the capability of preliminary semantic understanding in the Pangaea model using contextual words and phrases contributed to high accuracy and can be generalized further with larger datasets. Expansion to other health care data systems is needed to assess scalability of these technologies to create research-quality data fit for use. Citation Format: Rachel Yung, Kari A. Stephens, Meliha Yetisgen, Andrea Burnett-Hartman, Ashwani Tanwar, Guilherme Freire, Atri Sharma, Jingqing Zhang, Vibhor Gupta, Yike Guo, VK Gadi, Larry Kessler. Creating research quality cancer genomic data from electronic health records [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 4090.

HOME BLOOD PRESSURE MEASUREMENT AND E-HEALTH DURING PREGNANCY: PRACTICE AND EXPERIENCE WITH THE HY-RESULT SYSTEM

Objective: To evaluate the practice and the experience of pregnant women using the Hy-Result app. Design and method: Descriptive, multicentric study conducted in France Overall, 10 centers were included (5 maternity units, 2 ESH excellence hypertension centers, 1 primary care center, 2 patients’ associations network). Women were asked to measure the BP, use the app, share their report to the investigator and reply to on-line questionnaires (Q1, Q2, Q 3). Results: Among the 107 women included in the study, 82 (77%) responded after using successfully the Hy-Result system. Among them, 72 participants shared to the investigator their PDF report by email. Of these, 95% declared the software was easy or very easy to use; 93% believe the software helps them better monitor their BP; 94% that the color code classification was clear; 93 % affirmed that the app helped them when consulting their physician for their BP evaluation. Majority (87%) perceived the software to be reliable. Furthermore, 87 % said they trust the system and 62 % declared that performing HBPM and self-interpret their readings was reassuring whereas 7% felt that is was a concern. Out of the 72 e-mailed Hy-Result PDF report, 83% measured their BP 3 times in the morning, 3 times in the evening, for at least 3 days as recommended by ESH guidelines. Sixty-four women answered to Q3 after giving birth. Among them, 75% shared their BP reports with their doctor or midwife (even when their measurements were in the Green; 8% only when their measurements were in the Orange or Red). After delivery, 48% women continue to self-monitor their BP, half of them upon their physician’s request and the others by their own initiative). When analyzing the responses to Q 2, we found that 68% women declared that the software helps me talk to my doctor or midwife about my BP readings. Conclusions: HBPM with self-interpretation of the BP readings using the Hy-Result software is feasible during pregnancy. The use of this coaching app by pregnant women may be recommended in common practice by healthcare professionals and patient associations.