Automated Data Extraction Research Articles

Creating an ERAS Audit System with Automated Data Extraction Capabilities to Reduce Overall Data Abstraction Time.

Creating an ERAS Audit System with Automated Data Extraction Capabilities to Reduce Overall Data Abstraction Time.

Artificial intelligence in visually rich document digitization for efficient asset management

This work addresses the use of digital document processing as well as its application within the financial market, with an emphasis on the automated extraction of data from balance sheet documents, data that is common in the day-to-day life of this sector and that needs to be precise due to its large number of fields and recurrence. To perform this function, optical recognition technologies such as OCR, semantic entity recognition (SER) and named entity recognition (NER) were chosen to be used. The present work is an applied research with the main objective of developing a platform with the focus of optimizing the process of extracting and digitizing data from balance sheet documents, thus reducing errors and increasing operational efficiency in the asset management process. The methodology used involves the study of financial projection layouts, the development of an updated automated data extraction model, and validation mechanisms to guarantee result consistency.

Collaborative large language models for automated data extraction in living systematic reviews.

Data extraction from the published literature is the most laborious step in conducting living systematic reviews (LSRs). We aim to build a generalizable, automated data extraction workflow leveraging large language models (LLMs) that mimics the real-world 2-reviewer process. A dataset of 10 trials (22 publications) from a published LSR was used, focusing on 23 variables related to trial, population, and outcomes data. The dataset was split into prompt development (n = 5) and held-out test sets (n = 17). GPT-4-turbo and Claude-3-Opus were used for data extraction. Responses from the 2 LLMs were considered concordant if they were the same for a given variable. The discordant responses from each LLM were provided to the other LLM for cross-critique. Accuracy, ie, the total number of correct responses divided by the total number of responses, was computed to assess performance. In the prompt development set, 110 (96%) responses were concordant, achieving an accuracy of 0.99 against the gold standard. In the test set, 342 (87%) responses were concordant. The accuracy of the concordant responses was 0.94. The accuracy of the discordant responses was 0.41 for GPT-4-turbo and 0.50 for Claude-3-Opus. Of the 49 discordant responses, 25 (51%) became concordant after cross-critique, increasing accuracy to 0.76. Concordant responses by the LLMs are likely to be accurate. In instances of discordant responses, cross-critique can further increase the accuracy. Large language models, when simulated in a collaborative, 2-reviewer workflow, can extract data with reasonable performance, enabling truly "living" systematic reviews.

Assessing the feasibility and external validity of natural language processing-extracted data for advanced lung cancer patients.

Manual extraction of real-world clinical data for research can be time-consuming and prone to error. We assessed the feasibility of using natural language processing (NLP), an AI technique, to automate data extraction for patients with advanced lung cancer (aLC). We assessed the external validity of our NLP-extracted data by comparing our findings to those reported in the literature. Patients diagnosed with stage IIIB or IV lung cancer between January 2015 to December 2017 at Princess Margaret Cancer Centre who received at least one dose of systemic therapy were included. Their electronic health records were provided to Pentavere's NLP platform, DARWENTM, in March 2019. Descriptive statistics summarized baseline patient and cancer characteristics, molecular biomarkers, and first-line systemic therapies. Cox multivariate models were used to evaluate prognostic factors for advanced non-small cell lung cancer (NSCLC) and small-cell lung cancer (SCLC) cohort. NLP extracted clinical information (n=333 patients) in a total of 8hours, with only a few missing data for smoking status (n=2), and Eastern Cooperative Oncology Group (ECOG) status (n=5). Baseline patient and cancer characteristics summarized from NLP-extracted data were comparable to those in previous studies and population reports. For NSCLC patients, being male (HR 1.44, 95% CI [1.04, 2.00]), having worse ECOG (1.48 [1.22, 1.81]), and having liver (2.24 [1.45, 3.46]), bone (2.09 [1.48, 2.96]), or lung metastases (2.54 [1.05, 2.26]) were associated with worse survival outcomes. For SCLC patients, having older age (HR 1.70 per 10years, 95% CI [1.10, 2.63]) and liver metastases (3.81 [1.61, 9.01]) were associated with worse survival outcomes. Our study demonstrated that automated data extraction using NLP is feasible and time efficient. Additionally, the NLP-extracted data can be used to identify valid and useful clinical endpoints for research. NLP holds significant potential to accelerate the extraction of real-world data for future observational studies.

Transforming Contract Management: A Comprehensive Analysis of AI Integration in Legacy and Ongoing Contracts

Artificial intelligence (AI) and contract intelligence offer a revolutionary solution for contemporary contract administration, addressing the unique difficulties presented by both legacy and continuous contracts. This technical article investigates how automated data extraction, risk assessment, and process optimization driven by artificial intelligence transform contract management. Usually kept in conventional repositories, legacy contracts allow the system to retrieve and analyze important data in mass while including human confirmation for accuracy. By means of real-time AI processing for instantaneous analysis of third-party documentation, negotiation facilitation, and pre-signature risk evaluation, continuous contract management reduces the requirement for human review in the processing pipeline. While addressing implementation concerns, system integration issues, and future advancements in the field. This article investigates the technological underpinnings of Contract Intelligence—including Natural Language Processing and Machine Learning algorithms, including By means of thorough comparative research of heritage and contemporary contract management strategies, this article offers insightful information for companies trying to modernize their contract management systems while preserving compliance and operational effectiveness.

Data‐Driven Innovation in Metal‐Organic Frameworks Photocatalysis: Bridging Gaps for CO2 Capture and Conversion with FAIR Principles

Metal‐organic frameworks (MOFs) have emerged as key materials for carbon capture and conversion, particularly in photocatalytic CO2 reduction. However, inconsistent reporting of essential parameters in the literature hinders informed decisions about material selection and optimization. This perspective highlights the need for a user‐friendly, centralized database supported by automated data extraction using natural language processing tools to streamline comparisons of MOF materials. By consolidating crucial data from scientific literature, such a database promotes efficient decision‐making in material selection for CO2 capture and utilization. Emphasizing the significance of open‐source initiatives and the principles of FAIR data—ensuring data are Findable, Accessible, Interoperable, and Reusable—a collaborative approach to data management and sharing is advocated for. Making the database‐accessible worldwide enhances data quality and reliability, fostering innovation and progress in CO2 capture and conversion using MOF materials. Additionally, such databases are valuable in creating artificial intelligence tools to assist researchers in the discovery and synthesis of MOF materials for CO2 capture and conversion.

Data extraction from polymer literature using large language models

Automated data extraction from materials science literature at scale using artificial intelligence and natural language processing techniques is critical to advance materials discovery. However, this process for large spans of text continues to be a challenge due to the specific nature and styles of scientific manuscripts. In this study, we present a framework to automatically extract polymer-property data from full-text journal articles using commercially available (GPT-3.5) and open-source (LlaMa 2) large language models (LLM), in tandem with the named entity recognition (NER)-based MaterialsBERT model. Leveraging a corpus of ~ 2.4 million full text articles, our method successfully identified and processed around 681,000 polymer-related articles, resulting in the extraction of over one million records corresponding to 24 properties of over 106,000 unique polymers. We additionally conducted an extensive evaluation of the performance and associated costs of the LLMs used for data extraction, compared to the NER model. We suggest methodologies to optimize costs, provide insights on effective inference via in-context few-shots learning, and illuminate gaps and opportunities for future studies utilizing LLMs for natural language processing in polymer science. The extracted polymer-property data has been made publicly available for the wider scientific community via the Polymer Scholar website.

The Extractive Power of Automated Surveillance

Abstract Experts in Open-Source Intelligence (osint) and “Development Security Operations” (Dev-Sec-Ops) increasingly use automated tools to monitor databases, survey “targets” and identify cybersecurity threats. While the information they seek is usually freely available online, finding and extracting it requires special expertise. The extractive power of automated machines accelerates in this way the ubiquity of synoptic surveillance, while raising new ethical considerations that often obscure heuristic definitions between benevolent and malicious monitoring practices. Based on ethnographic research with osint and DevSecOps practitioners in the UK I identify this process analytically as an “authoritarian conundrum.” I argue that reliance on automatic data extraction thus redefines power relations online and discuss its potentially despotic effects.

IMPLEMENTATION OF NATURAL LANGUAGE PROCESSING (NLP) IN EHR SYSTEMS TO IMPROVE CLINICAL DOCUMENTATION

Background: Electronic health records (EHRs) store valuable clinical data, often in unstructured narrative formats that require manual extraction. This process is time-consuming, costly, and error-prone. Natural language processing (NLP) offers a promising solution for automating data extraction, improving research efficiency, and maintaining accuracy. However, its generalizability and reliability remain areas of active investigation. This study evaluates the performance of an NLP tool for extracting clinical conditions, medications with dosage, and echocardiographic parameters compared to manual retrieval. Objective: To assess the accuracy, sensitivity, and specificity of an NLP tool for extracting clinical data from unstructured EHR narratives, validating its performance against manual data extraction methods. Methods: This prospective study was conducted in three tertiary care hospitals in Punjab, Pakistan, from December 2023 to May 2024. A total of 500 participants were included, stratified by urban (68%, 340) and rural (32%, 160) residency. The NLP tool extracted 5,700 data points across three categories: 3,000 clinical conditions, 1,500 medications with dosage, and 1,200 echocardiographic parameters. Performance metrics, including accuracy, sensitivity, and specificity, were calculated by comparing the tool's results with manual retrieval. Discrepancies were analyzed to identify root causes, including algorithmic and human errors. Results: The NLP tool achieved an accuracy of 98.5%, sensitivity of 96.7%, and specificity of 97.2%, closely aligning with manual retrieval at 99.0%, 97.5%, and 97.8%, respectively. For clinical conditions, the tool retrieved 2,955 of 3,000 data points correctly (98.5%), while manual retrieval achieved 2,970 (99.0%). For medications with dosage, the tool extracted 1,452 of 1,500 data points (96.8%) compared to 1,488 (99.2%) manually. Similarly, 1,178 of 1,200 echocardiographic parameters (98.2%) were correctly retrieved by the tool, compared to 1,185 (98.8%) through manual methods. Urban participants (242 males, 98 females) outnumbered rural participants (106 males, 54 females), with the majority aged 31–70 years (75%). Conclusion: The NLP tool demonstrated high accuracy and near-human precision in extracting structured data from unstructured EHR narratives. Its performance across clinical conditions, medications, and echocardiographic parameters highlights its potential to streamline clinical research while reducing manual workload. Further refinement is required to address context-sensitive errors and enhance generalizability across diverse datasets.

Enhancing Thyroid Pathology With Artificial Intelligence: Automated Data Extraction From Electronic Health Reports Using RUBY.

Thyroid nodules are common in the general population, and assessing their malignancy risk is the initial step in care. Surgical exploration remains the sole definitive option for indeterminate nodules. Extensive database access is crucial for improving this initial assessment. Our objective was to develop an automated process using convolutional neural networks (CNNs) to extract and structure biomedical insights from electronic health reports (EHRs) in a large thyroid pathology cohort. We randomly selected 1,500 patients with thyroid pathology from our cohort for model development and an additional 100 for testing. We then divided the cohort of 1,500 patients into training (70%) and validation (30%) sets. We used EHRs from initial surgeon visits, preanesthesia visits, ultrasound, surgery, and anatomopathology reports. We selected 42 variables of interest and had them manually annotated by a clinical expert. We developed RUBY-THYRO using six distinct CNN models from SpaCy, supplemented with keyword extraction rules and postprocessing. Evaluation against a gold standard database included calculating precision, recall, and F1 score. Performance remained consistent across the test and validation sets, with the majority of variables (30/42) achieving performance metrics exceeding 90% for all metrics in both sets. Results differed according to the variables; pathologic tumor stage score achieved 100% in precision, recall, and F1 score, versus 45%, 28%, and 32% for the number of nodules in the test set, respectively. Surgical and preanesthesia reports demonstrated particularly high performance. Our study successfully implemented a CNN-based natural language processing (NLP) approach for extracting and structuring data from various EHRs in thyroid pathology. This highlights the potential of artificial intelligence-driven NLP techniques for extensive and cost-effective data extraction, paving the way for creating comprehensive, hospital-wide data warehouses.

MSR187 Automated Data Extraction in Systematic Literature Reviews (SLRs): Assessing the Accuracy and Reliability of a Large Language Model (LLM)

MSR187 Automated Data Extraction in Systematic Literature Reviews (SLRs): Assessing the Accuracy and Reliability of a Large Language Model (LLM)

Curating protected area-level species lists in an era of diverse and dynamic data sources

Dynamic yet accurate species lists for protected areas are essential for conservation and biodiversity research. Even when such lists exist, changing taxonomy, ongoing species migrations and invasions, and new discoveries of historically overlooked species mean static lists can become rapidly outdated. Biodiversity databases such as the Global Biodiversity Information Facility, and citizen science platforms such as iNaturalist, offer rapidly accessible, georeferenced data, but their accuracy is rarely tested. Here we compare species lists generated for two of the world's oldest, more famous protected areas – Yosemite National Park in California, United States and Royal National Park in New South Wales, Australia – using both automated data extraction techniques and extensive manual curation steps. We show that automated list creation without manual curation offers inflated measures of species diversity. Lists generated from herbarium vouchers required more curation than lists generated from iNaturalist, with both incorrect coordinates attached to vouchers and long-outdated names inflating voucher-based species lists. In comparison, iNaturalist data had relatively few errors, in part due to continual curation by a large community, including many botanical experts, and the frequent and automatic implementation of taxonomic updates. As such, iNaturalist will become an increasingly accurate supplementary source for automated biodiversity lists over time, but currently offers poor coverage of graminoid species and introduced species relative to showier, native taxa, and relies on continued expert contributions to identifications. At this point, researchers must manually curate lists extracted from herbarium vouchers or static park lists, and integrate these data with records from iNaturalist, to produce the most robust and taxonomically up-to-date species lists for protected areas.

STEED: A data mining tool for automated extraction of experimental parameters and risk of bias items from in vivo publications.

Systematic reviews, i.e., research summaries that address focused questions in a structured and reproducible manner, are a cornerstone of evidence-based medicine and research. However, certain steps in systematic reviews, such as data extraction, are labour-intensive, which hampers their feasibility, especially with the rapidly expanding body of biomedical literature. To bridge this gap, we aimed to develop a data mining tool in the R programming environment to automate data extraction from neuroscience in vivo publications. The function was trained on a literature corpus (n = 45 publications) of animal motor neuron disease studies and tested in two validation corpora (motor neuron diseases, n = 31 publications; multiple sclerosis, n = 244 publications). Our data mining tool, STEED (STructured Extraction of Experimental Data), successfully extracted key experimental parameters such as animal models and species, as well as risk of bias items like randomization or blinding, from in vivo studies. Sensitivity and specificity were over 85% and 80%, respectively, for most items in both validation corpora. Accuracy and F1-score were above 90% and 0.9 for most items in the validation corpora, respectively. Time savings were above 99%. Our text mining tool, STEED, can extract key experimental parameters and risk of bias items from the neuroscience in vivo literature. This enables the tool's deployment for probing a field in a research improvement context or replacing one human reader during data extraction, resulting in substantial time savings and contributing towards the automation of systematic reviews.

ChemPrice, a Python Package for Automated Chemical Price Search

AbstractThe open‐access movement in chemistry has led to a surge in publicly accessible data repositories such as PubChem and ChemSpider, housing more than 100 million chemical compounds. These repositories are invaluable for large‐scale virtual screening but lack crucial pricing information, a vital economic aspect influencing commercial decisions. Currently, these databases merely provide hyperlinks to vendor websites for pricing details, necessitating manual exploration due to the diverse structures of vendor websites, making automated data extraction impractical. To tackle this challenge, we introduce ChemPrice, a Python package that streamlines the collection of pricing data through the integration of ChemSpace, Mcule, and Molport platforms that provide up‐to‐date price information from over 100 suppliers. ChemPrice standardizes pricing units, offering consolidated and best‐pricing information for specified compounds. Its modular design facilitates integration into automated virtual screening workflows, and a user‐friendly web interface caters to those with limited coding skills, enabling easy compound list uploading and pricing data retrieval. This innovation addresses the complexity of collecting compound prices and enables integration into the virtual screening code workflows, providing a valuable resource for a wide community of users seeking comprehensive and up‐to‐date pricing information to enhance their decision‐making processes.

Scientific knowledge management in Brazil: an analysis of the Lattes Platform

The Lattes Platform (PL) is an essential resource for Brazil's scientific and technological landscape, centralizing researchers' curricular information and facilitating the management of scientific data. However, the lack of rigorous standardization in the data entered compromises the efficiency of retrieving and analyzing this information, limiting academic knowledge management. This study investigated the limitations of the PL and proposed a solution that integrates new technologies to optimize scientific data management. The research was conducted in two main stages: a systematic literature review on knowledge management and technologies applied to the PL, and a case study at the Federal Institute of Acre (IFAC). The review included the analysis of 79 articles and a survey of software records at the National Institute of Industrial Property (INPI). In the case study, semi-structured questionnaires were administered to IFAC staff to understand their needs and perceptions regarding the PL. The results reveal a significant demand for tools that automate data extraction and integrate the PL with other academic management systems. The analysis of software records at INPI highlighted solutions that can enhance the PL’s efficiency. The integration of Artificial Intelligence (AI), exemplified by the proposed LattesAI, emerges as a promising solution to overcome the platform's current limitations, automating processes and personalizing knowledge management. This innovation not only optimizes academic management but also strengthens Brazil's position in the global scientific landscape, promoting greater efficiency and collaboration in educational and research institutions. Future studies should focus on developing AI algorithms specifically for the PL, ensuring its continuous evolution in response to the demands of the academic environment.

Adaptive questionnaires for facilitating patient data entry in clinical decision support systems: methods and application to STOPP/START v2

Clinical decision support systems are software tools that help clinicians to make medical decisions. However, their acceptance by clinicians is usually rather low. A known problem is that they often require clinicians to manually enter a lot of patient data, which is long and tedious. Existing solutions, such as the automatic data extraction from electronic health record, are not fully satisfying, because of low data quality and availability. In practice, many systems still include long questionnaire for data entry. In this paper, we propose an original solution to simplify patient data entry, using an adaptive questionnaire, i.e. a questionnaire that evolves during user interaction, showing or hiding questions dynamically. Considering a rule-based decision support systems, we designed methods for determining the relationships between rules and translating the system’s clinical rules into display rules that determine the items to show in the questionnaire, and methods for determining the optimal order of priority among the items in the questionnaire. We applied this approach to a decision support system implementing STOPP/START v2, a guideline for managing polypharmacy. We show that it permits reducing by about two thirds the number of clinical conditions displayed in the questionnaire, both on clinical cases and real patient data. Presented to clinicians during focus group sessions, the adaptive questionnaire was found “pretty easy to use”. In the future, this approach could be applied to other guidelines, and adapted for data entry by patients.

Preparing for future pandemics: Automated intensive care electronic health record data extraction to accelerate clinical insights

BackgroundManual data abstraction from electronic health records (EHRs) for research on intensive care patients is time-intensive and challenging, especially during high-pressure periods such as pandemics. Automated data extraction is a potential alternative but may raise quality concerns. This study assessed the feasibility and credibility of automated data extraction during the coronavirus disease 2019 (COVID-19) pandemic. MethodsWe retrieved routinely collected data from the COVID-Predict Dutch Data Warehouse, a multicenter database containing the following data on intensive care patients with COVID-19: demographic, medication, laboratory results, and data from monitoring and life support devices. These data were sourced from EHRs using automated data extraction. We used these data to determine indices of wasted ventilation and their prognostic value and compared our findings to a previously published original study that relied on manual data abstraction largely from the same hospitals. ResultsUsing automatically extracted data, we replicated the original study. Among 1515 patients intubated for over 2 days, Harris–Benedict (HB) estimates of dead space fraction increased over time and were higher in non-survivors at each time point: at the start of ventilation (0.70±0.13 vs. 0.67±0.15, P <0.001), day 1 (0.74±0.10 vs. 0.71±0.11, P<0.001), day 2 (0.77±0.09 vs. 0.73±0.11, P<0.001), and day 3 (0.78±0.09 vs. 0.74±0.10, P<0.001). Patients with HB dead space fraction above the median had an increased mortality rate of 13.5%, compared to 10.1% in those with values below the median (P<0.005). Ventilatory ratio showed similar trends, with mortality increasing from 10.8% to 12.9% (P=0.040). Conversely, the end-tidal-to-arterial partial pressure of carbon dioxide (PaCO₂) ratio was inversely related to mortality, with a lower 28-day mortality in the higher than median group (8.5% vs. 15.1%, P<0.001). After adjusting for base risk, impaired ventilation markers showed no significant association with 28-day mortality. ConclusionManual data abstraction from EHRs may be unnecessary for reliable research on intensive care patients, highlighting the feasibility and credibility of automated data extraction as a trustworthy and scalable solution to accelerate clinical insights, especially during future pandemics.

Capabilities of cellebrite universal forensics extraction device in mobile device forensics

The powerful digital forensics tool cellebrite universal forensics extraction device (UFED) extracts and analyzes mobile device data, helping investigators solve criminal and cybersecurity cases. Advanced methods and algorithms allow Cellebrite UFED to recover data from erased or obscured devices. Cellebrite UFED can pull data from call logs, texts, emails, and social media, providing valuable evidence for investigations. The use of smartphones and tablets in personal and professional settings has spurred the development of mobile device forensics. The intuitive user interface speeds up data extraction and analysis, revealing crucial information. It can decrypt encrypted data, recover deleted files, and extract data from multiple devices. The sector's best data extraction functionality, Cellebrite UFED, helps forensic analysts gather crucial evidence for investigations. Legal and ethical considerations are crucial in mobile device forensics. Legal considerations include allowing access to data, protecting privacy, and adhering to chain of custody protocols. Ethics include transparency, defamation, and information exploitation protection. Using Cellebrite UFED, researchers can navigate complex data on mobile devices more efficiently and precisely. Artificial intelligence (AI) and machine learning (ML) algorithms may automate data extraction in future tools. Examiners must train, maintain, and establish clear protocols for using Cellebrite UFED in forensic investigations.

Automated Electronic Health Record Data Extraction and Curation Using ExtractEHR.

Although the potential transformative effect of electronic health record (EHR) data on clinical research in adult patient populations has been very extensively discussed, the effect on pediatric oncology research has been limited. Multiple factors contribute to this more limited effect, including the paucity of pediatric cancer cases in commercial EHR-derived cancer data sets and phenotypic case identification challenges in pediatric federated EHR data. The ExtractEHR software package was initially developed as a tool to improve clinical trial adverse event reporting but has expanded its use cases to include the development of multisite EHR data sets and the support of cancer cohorts. ExtractEHR enables customized, automated data extraction from the EHR that, when implemented across multiple hospitals, can create pediatric cancer EHR data sets to address a very wide range of research questions in pediatric oncology. After ExtractEHR data acquisition, EHR data can be cleaned and graded using CleanEHR and GradeEHR, companion software packages. ExtractEHR has been installed at four leading pediatric institutions: Children's Healthcare of Atlanta, Children's Hospital of Philadelphia, Texas Children's Hospital, and Seattle Children's Hospital. ExtractEHR has supported multiple use cases, including five clinical epidemiology studies, multicenter clinical trials, and cancer cohort assembly. Work is ongoing to develop Fast Health care Interoperability Resources ExtractEHR and implement other sustainability and scalability enhancements.

GPT models classify free text from emergency department accesses in children with medical complexity

Abstract Background Emergency Department (ED) management software often collects clinical information as free text, but its unstructured nature limits routine use. While Machine Learning (ML) techniques have been employed to classify such information, they demand substantial data and computational resources. GPT-based models, using direct text prompts, offer a solution without requiring retraining, potentially simplifying clinical practice. Aims To assess OpenAI GPT’s performance in automating data extraction from ED medical records of complex pediatric patients. Methods Electronic admission records of children and young adults referring to the pediatric ED of Padova University Hospital (2007-2023) were analyzed. Principal variables of interest were discharge diagnosis, reason for ED access, required medical procedures, color code at triage, color code at discharge/hospitalization, outcome of the access. GPT-4 classification, via OpenAI API, was compared with manual classification by an expert pediatrician on sample of 791 records. Results Preliminary results of this study analyzed 107 records, showing a correct classification of discharge diagnosis in 95% of records. The reason for access to the ED was correctly identified in 97% of cases, while outcome of admission and color code, both at triage and discharge/hospitalization, were correctly classified in all given cases. Misclassification occurred mainly in cases where classification made by the model was incomplete (e.g., in the case of a trauma, abbreviated site of lesion was not identified by the model). Conclusions GPT-based models demonstrate feasibility, accuracy, and efficiency in transforming unstructured data into structured formats. Ultimately, GPT-based models could provide aid to the medical personnel in decision-making processes. Key messages • Emergency departments often collect clinical data in unstructured free text format, resulting in usability limitations. • GPT-powered models efficiently convert unstructured data to structured formats, offering potential support for medical decision-making.