Processing Domain Research Articles

Healthcare in police custody: a conceptual framework for measuring and improving quality of care

Abstract Background Individuals in police custody are often in poor (mental) health and can be in need of medical attention. The delivery of primary healthcare in police custody differs from other custodial and non-custodial settings, due to its short-term character and the reliance on custody officers and healthcare professionals to access care. Therefore, medical care for detainees in police custody requires its own standards and indicators to measure the quality of care. We aimed to develop a conceptual framework for (actionable) indicators to measure the quality of care for people detained in short-term police custody settings in the Netherlands. Methods We conducted a scoping review and consulted with experts. The scoping review involved Embase, Medline, PsycINFO, CINAHL, Criminal Justice Abstracts, PiCarta and Cochrane, and was supplemented with grey literature searches. We consulted twenty-seven stakeholders with a wide variety of expertise in the field of healthcare in police custody to discuss and validate the conceptual framework. Results The conceptual framework consists of 14 domains of structures (e.g. staff and facilities), processes (e.g. triage and coordination of care) and outcomes (e.g. effectiveness and satisfaction) that need to be considered when developing quality indicators for the healthcare provision in police custody. The scoping review yielded 68 publications providing information on common health issues and recommendations related to quality assurance or improvement. Conclusions The conceptual framework will guide the development of (actionable) quality indicators, which will be evaluated on relevance and measurability. These are crucial for monitoring care quality and enhancing a learning health systems approach. This study fills a gap in the existing scientific literature by shedding light on the factors contributing to the quality of primary healthcare provision for people detained in short-term custody settings. Key messages • The conceptual framework guides the development of (actionable) quality indicators for healthcare in police custody. • This study contributes to the creation of a learning health system for healthcare in short-term police custody settings.

Influence of interface on nondeformable micropolar drop migration

Abstract In this article, an analytical approach is considered to study the issue of specifying Stokesian motion due to a micropolar sphere drop translating at a concentric instantaneous position within a spherical fluid-fluid interface that divides two immiscible fluids, one of which is bounded and the other is unbounded. Here, the focus is on the situation where there are two microstructure-related fluid phases (micropolar fluids) out of the three. The motion is considered to have low Reynolds numbers; thus, the drop's surface and fluid-fluid interface have insignificant deformation. For both the components of the microrotation and velocity, general solutions to the slow axisymmetric motion of the micropolar/viscous fluid in a spherical coordinate system are obtained based on a concentric position. Boundary conditions are fulfilled at the drop's surface and the fluid-fluid interface. Especially, the boundary condition for the microrotation-vorticity is utilised at the fluid-fluid interface; while the continuity of tangential couple stress and microrotation are also utilised at the drop's surface. Findings indicate that the normalised hydrodynamic force increases monotonically as the droplet-to-interface radius ratio increases, acting on a moving micropolar sphere droplet and becoming unlimited when the drop's surface touches the fluid-fluid interface. The numerical findings for the normalised force operating on the micropolar sphere droplet at different values of the suitable parameters are introduced in both graphical and tabular form. Our numerical findings are compared with the suitable data for the special cases stated in the literature. This current investigation is significant within the domains of industrial, biological, medicinal, and natural processes, for example, liquid-liquid extraction, raindrop formation, blood cells moving through a vein or artery, suspension rheology, sedimentation, and coagulation.

HIV testing services and HIV self-testing programming within emergency care in Kenya: a qualitative study of healthcare personnel to inform enhanced service delivery approaches

ABSTRACT In Kenya, persons insufficiently engaged in HIV Testing Services (HTS) are often treated in emergency departments (ED). There are limited data from healthcare workers on ED-HTS. A qualitative study was completed to understand challenges and facilitators for ED-HTS and HIV self-testing (HIVST). Data were collected via six focus groups of healthcare workers. Data were inductively analyzed and mapped to the Capability–Opportunity–Motivation Behavioral Model. Focus groups were completed with 49 healthcare workers: 18 nurses, 15 HIV counselors, 10 physicians and 6 administrators. HTS challenges included staff burdens, resources access, deficiencies in systems integration and illness severity. HTS facilitators included education of healthcare workers and patients, services coordination, and specific follow-up processes. HIVST challenges included accuracy concerns, follow-up barriers and psychosocial risks. HIVST facilitators were patient autonomy and confidentiality, resource utilization and ability to reach higher-risk persons. Mapping to the Capability–Opportunity–Motivation Behavioral Model interventions within the domains of knowledge, decision processes, environmental aspects, social influences and professional identities could support enhanced ED-HTS with integrated HIVST delivery. This study provided insights into challenges and facilitators on ED-HTS and identifies pragmatic approaches to improve healthcare workers’ behaviors and abilities to provide services to persons already in contact with healthcare.

Stable successive Neural Image Compression via coherent demodulation-based transformation

Neural Image Compression (NIC) has made significant strides in recent years. However, the existing NIC methods demonstrate instability issues during iterative re-compression cycles, which can degrade image quality with each cycle. This paper introduces a novel framework aimed at enhancing the stability of NIC methods. We first conducted a theoretical analysis and identified that the instability in current NIC methods stems from a lack of idempotency in transformations. Drawing from the domain of signal processing, we then examined the principles of idempotency in coherent demodulation techniques. This examination led to the identification of three foundational principles that inform the design of stable transformations: the cosine function, parameter sharing, and low-pass filtering. Leveraging these insights, we propose the innovative Coherent Demodulation-based Transformation (CDT), which is designed to address the stability challenges in NIC by incorporating these principles into its architecture. The experimental results suggest that CDT not only significantly improve the re-compression stability but also preserves the codec’s rate–distortion performance. Furthermore, it can be broadly applied in current NIC structures. The effectiveness of the module endorses the viability of designing transformation networks based on Coherent Demodulation principles, playing a crucial role in enhancing stability of NIC. The code will be available at https://github.com/baoyu2020/Stable_SuccessiveNIC.

Investigating translation for Indic languages with BLOOMZ-3b through prompting and LoRA fine-tuning

In the domain of natural language processing, the rise of Large Language Models and Generative AI represents a noteworthy transition, enabling machines to understand and generate text resembling that produced by humans. This research conducts a thorough examination of this transformative technology, with a focus on its influence on machine translation. The study explores the translation landscape between English and Indic languages, which include Hindi, Kannada, Malayalam, Tamil, and Telugu. To address this, the Large Language Model, BLOOMZ-3b, is utilized, which has been primarily developed for a text generation task. Multiple prompting engineering techniques for machine translation are prominently explored. The study further traverse fine-tuning the BLOOMZ-3b model using a Parameter Efficient Fine-Tuning technique called Low Rank Adaptation, aiming to reduce computational complexity. Hence, by combining innovative prompting approaches using BLOOMZ-3b model and fine-tuning the model, it contributes to continuous development of machine translation technologies beyond traditional borders of what can be done with respect to language processing. In this regard, not only does this research shed light on the intricacy of translation problems but it also sets a precedence for optimizing or adapting big language models to various languages which end up advancing Artificial Intelligence and Natural Language Processing at large.

How well can simple clinical features predict long-term language recovery after left-hemisphere glioma surgery?

Long-term language recovery after left-hemisphere glioma surgery varies substantially across patients. We investigated how well it can be predicted using clinical variables such as the postoperative decline in language processing, tumor grade, resection volume and location, extent of resection, and intraoperative language mapping. Beyond predicting the overall recovery, we examined which domains of language processing are most prone to persistent deficits. Fifty-nine patients with left-hemisphere gliomas completed the Russian Aphasia Test (RAT) before surgery, immediately after surgery, and at follow-up three to seventeen months after surgery. We modeled their average language score (Generalized Aphasia Quotient, GAQ) at follow-up using a cross-validated multiple linear regression and calculated the number of patients showing persistent deficits in each subtest of the RAT. The difference between GAQ scores at follow-up and before surgery was not significant at the group level but varied substantially across patients (mean -1.3%, range -34.2-9.2%). Our best-performing model predicted the follow-up GAQ scores with the mean absolute error of 3.5% (cross-validated R2 = 0.15). A greater decline in language processing immediately after surgery predicted worse recovery, whereas intraoperative language mapping predicted better recovery. Deficits in sentence repetition, verb production, verb and sentence comprehension, and object naming most often persisted at follow-up. The postoperative decline in language processing and intraoperative language mapping explain a substantial amount of variability in long-term language recovery. Verbal working memory and lexical retrieval, particularly that of verbs, are most prone to persistent deficits.

Skin Lesion Segmentation Using Adaptive Color Segmentation and Decision Tree

A decision tree operates as a predictive model in machine learning, utilizing a structured hierarchy of rules for the decision-making process. This model is graphically depicted through a tree-like structure, where each node symbolizes a decision point, and the ensuing branches represent the resultant outcomes of these decisions. This method proves particularly efficacious in addressing both classification and regression challenges, offering clear interpretability through its graphical illustration of the connections between input features and predicted outcomes. In the domain of image processing, color image segmentation serves as a crucial preliminary step for various applications. Specifically, the segmentation of skin lesions holds significant importance in image analysis, notably in the classification of lesions within dermoscopy images. Image segmentation involves the categorization of image pixels into uniform regions based on attributes like color, texture, and luminosity. The primary objective here is to delineate the area of interest from the healthy surrounding tissue. In methods reliant on threshold-based segmentation, the effectiveness of the segmentation hinges on the accurate selection of an appropriate threshold.

Development of Exporting Fresh Fruits Ontology for Improving the Knowledge-Based System on the Domain of Export Process in Thailand

Development of Exporting Fresh Fruits Ontology for Improving the Knowledge-Based System on the Domain of Export Process in Thailand

Clinical utility and psychometric properties of tools for early detection of developmental concerns and disability in young children: A scoping review.

To explore the clinical utility and psychometric properties of standardized tools for the early detection of developmental concerns or disability in young children. Systematic reviews and clinical practice guidelines containing psychometric data on tools appropriate for use with children from birth to 5 years 11 months were searched for in MEDLINE, CINAHL, Embase, and PsycINFO for the years 2000 to 2023, with no language restrictions. Eighty-six systematic reviews and six clinical practice guidelines guided identification of tools. A total of 246 tools were identified across domains of neurological, motor, cognition, communication/language, social-emotional, sensory processing, and/or specific diagnostic conditions of attention-deficit/hyperactivity disorder, autism spectrum disorder, cerebral palsy, developmental coordination disorder, and fetal alcohol spectrum disorder. After critical evaluation, 67 tools were included in the recommendations. Recommendations for screening and diagnostic assessment tools were based on best available evidence for predictive and discriminative validity, diagnostic accuracy, together with consideration of resource use and accessibility. This comprehensive scoping review provides recommendations on the best tools for primary care, medical, allied health professionals, nursing, and other health workers to detect and identify developmental concerns or disability in young children using evidence-based tools.

Distributed hybrid quantum-classical performance prediction for hyperparameter optimization

Hyperparameter optimization (HPO) of neural networks is a computationally expensive procedure, which requires a large number of different model configurations to be trained. To reduce such costs, this work presents a distributed, hybrid workflow, that runs the training of the neural networks on multiple graphics processing units (GPUs) on a classical supercomputer, while predicting the configurations’ performance with quantum-trained support vector regression (QT-SVR) on a quantum annealer (QA). The workflow is shown to run on up to 50 GPUs and a QA at the same time, completely automating the communication between the classical and the quantum systems. The approach is evaluated extensively on several benchmarking datasets from the computer vision (CV), high-energy physics (HEP), and natural language processing (NLP) domains. Empirical results show that resource costs for performing HPO can be reduced by up to 9% when using the hybrid workflow with performance prediction, compared to using a plain HPO algorithm without performance prediction. Additionally, the workflow obtains similar and in some cases even better accuracy of the final hyperparameter configuration, when combining multiple heuristically obtained predictions from the QA, compared to using just a single classically obtained prediction. The results highlight the potential of hybrid quantum-classical machine learning algorithms. The workflow code is made available open-source to foster adoption in the community.

Developing and Evaluating Digital Public Health Interventions Using the Digital Public Health Framework DigiPHrame: A Framework Development Study.

Digital public health (DiPH) interventions may help us tackle substantial public health challenges and reach historically underserved populations, in addition to presenting valuable opportunities to improve and complement existing services. However, DiPH interventions are often triggered through technological advancements and opportunities rather than public health needs. To develop and evaluate interventions designed to serve public health needs, a comprehensive framework is needed that systematically covers all aspects with relevance for public health. This includes considering the complexity of the technology, the context in which the technology is supposed to operate, its implementation, and its effects on public health, including ethical, legal, and social aspects. We aimed to develop such a DiPH framework with a comprehensive list of core principles to be considered throughout the development and evaluation process of any DiPH intervention. The resulting digital public health framework (DigiPHrame) was based on a scoping review of existing digital health and public health frameworks. After extracting all assessment criteria from these frameworks, we clustered the criteria. During a series of multidisciplinary meetings with experts from the Leibniz ScienceCampus Digital Public Health, we restructured each domain to represent the complexity of DiPH. In this paper, we used a COVID-19 contact-tracing app as a use case to illustrate how DigiPHrame may be applied to assess DiPH interventions. The current version of DigiPHrame consists of 182 questions nested under 12 domains. Domain 1 describes the current status of health needs and existing interventions; domains 2 and 3, the DiPH technology under assessment and aspects related to human-computer interaction, respectively; domains 4 and 5, structural and process aspects, respectively; and domains 6-12, contextual conditions and the outcomes of the DiPH intervention from broad perspectives. In the CWA use case, a number of questions relevant during its development but also important for assessors once the CWA was available were highlighted. DigiPHrame is a comprehensive framework for the development and assessment of digital technologies designed for public health purposes. It is a living framework and will, therefore, be updated regularly and as new public health needs and technological advancements emerge.

Identifying Barriers and Implementation Strategies to Inform TBI Screening Adoption in Behavioral Healthcare Settings.

Identify barriers to the adoption of the Ohio State University Traumatic Brain Injury Identification Method (OSU TBI-ID) in behavioral healthcare organizations and match these barriers to implementation strategies to inform future implementation efforts. Twenty behavioral health providers. Qualitative study involving individual, semi-structured interviews regarding barriers to adopting the OSU TBI-ID. Data were thematically analyzed around constructs from the Consolidated Framework for Implementation Research (CFIR). Results were matched to strategies using the Expert Recommendations for Implementing Change (CFIR/ERIC) matching tool. Ten barriers were identified across 4 CFIR domains. Inner-Setting barriers were inadequate leadership engagement, priorities, resources, and organizational incentives. Individual-Characteristics barriers were insufficient knowledge about the connection between TBI and behavioral health and how to conduct the OSU TBI-ID with fidelity, low self-efficacy to conduct screening, and inadequate motivation and buy-in to conduct screening. Outer-Setting barriers were lack of state-level mandates and inadequate incentives to conduct screenings. The Process domain barrier was an insufficient engagement of key personnel. Strategy recommendations include: identify and prepare champions; alter incentive and allowance structures; inform local opinion leaders; build a coalition; access new funding; conduct local consensus discussions; involve executive boards; capture/share local knowledge; conduct educational meetings; assess for readiness and identify determinants; identify early adopters; fund and contract for the clinical innovation; create a learning collaborative; and conduct a local needs assessment. This is the first study to examine barriers to adopting the OSU TBI-ID in real-world practice settings. Our results suggest that multilevel implementation strategies addressing mechanisms of change are necessary at the provider, organizational, and systems levels to overcome the complex barriers affecting TBI screening adoption and implementation. Future research is needed to test these strategies and their mechanisms of action on the adoption, implementation, and sustainment of TBI screening, as well as their effect on client-level outcomes.

Image Caption Generator Using CNN and LSTM

In this have a look at, we discover the integration of Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks for the motive of image caption generation, a mission that involves a fusion of herbal language processing and computer imaginative and prescient techniques to describe images in English. Delving into the realm of photograph captioning, we meticulously investigate several fundamental concepts and methodologies associated with this area. Our technique includes leveraging prominent equipment inclusive of the Keras library, numpy, and Jupyter notebooks to facilitate the development of our studies. Furthermore, we delve into the utilization of the flickr_dataset and CNNs for image category, elucidating their significance in our examination. Through this research endeavor, we aim to make a contribution to the development of image captioning structures with the aid of combining modern-day strategies from both laptop imaginative and prescient and herbal language processing domain names.

Computational and intelligence modeling analysis of pharmaceutical freeze drying for prediction of temperature in the process

Accurate temperature prediction is crucial for various scientific and engineering applications, yet it remains challenging due to the complex relationships between spatial coordinates and temperature variations. This study addresses this challenge by exploring advanced machine learning models to improve prediction accuracy, filling the research gap in optimizing predictive models for temperature estimation in freeze drying of pharmaceuticals. We employed Support Vector Regression (SVR), Poisson Regression (POR), and Adaptive Neuro-Fuzzy Inference System (ANFIS) models, each enhanced using the Cheetah Optimizer (CO), to estimate temperature based on spatial coordinates (X, Y, Z) in the domain of process. The methodology involved training and testing these models on a dataset comprising spatial and temperature data, with a focus on improving accuracy through optimization techniques. Validation of the models showed that the CO-SVR model outperformed the others, achieving an R2 score of 0.953, Mean Squared Error (MSE) of 9.893, and Mean Absolute Error (MAE) of 2.549. This represents a significant improvement over the CO-ANFIS model, which obtained an R2 of 0.863, MSE of 23.583, and MAE of 3.912. The CO-POR model showed the lowest predictive capability, with an R2 score of 0.753, MSE of 57.608, and MAE of 6.756. These findings underscore the effectiveness of the Cheetah Optimizer in enhancing the accuracy of SVR models for temperature prediction, suggesting its potential for broader applications in predictive modeling where accuracy is paramount.

How Iran’s Hospital Accreditation Program Meets the International Society for Quality in Health Care (ISQua)

Background: Hospital health service quality is a fundamental component of the health system. Hospital accreditation is a key approach to enhancing this quality, necessitating the correct implementation of processes. Objectives: This study aims to investigate the compliance of the executive processes of Iran’s hospital accreditation program with the requirements of the International Society for Quality in Health Care and to provide corrective solutions. Methods: This qualitative study uses an inductive content analysis technique. A checklist with seven axes was established by extracting and interpreting the requirements of the executive processes from the International Society for Quality in Health Care. By examining existing documents at the Ministry of Health’s Accreditation Office and conducting interviews with managers and experts in the field, challenges in the domain of the executive processes of Iran’s hospital accreditation program were identified using the relevant checklist. Corrective solutions were then gathered through semi-structured interviews with 19 experts, managers, and accreditation field specialists, categorized inductively, and presented using MAXQDA software. Results: Challenges in seven areas were identified, including governance; strategic, operational and financial management; risk management; human resources management; information management; survey and client management; and the granting of accreditation approval. Subsequently, solutions were categorized into five groups encompassing 26 concepts, focusing on reforming macro policies, addressing implementation challenges, fostering appropriate interactions, improving human resource management, and promoting evidence-based decision-making. Conclusions: The Iran hospital accreditation program’s adherence to International Society for Quality in Health Care standards is inadequate. Establishing a semi-autonomous, non-profit accreditation body that operates under government control and ensuring the independence of the accreditation office is essential for achieving higher compliance and receiving certification from International Society for Quality in Health Care.

Benchmarking in pancreatic surgery: a systematic review of metric development and validation.

Benchmarking in healthcare, particularly in the context of complex surgical procedures like pancreatic surgery, plays a pivotal role in comparing and evaluating the quality of care provided to patients. There is a growing body of evidence validating existent metrics and introducing new ones in the pursuit of safety and excellence in pancreatic surgery. A systematic review adhering to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines was conducted on metric development and validation across multiple databases, including PUBMED Medline, Scopus, and Web of Science, until February 2024. The extracted data were categorized into three domains according to the Donabedian model: structure, process, and outcomes. Thirty-four studies were deemed eligible for inclusion in this review. Among these articles, 20 contributed to metric development, while 14 studies validated them. A total of 234 metrics were identified across the 34 studies, of which 185 were included in the analysis. Thirty-three of these metrics were relative to structure, 79 to processes, and 73 to outcomes. The distribution of metric domains across the included studies revealed that structure, process, and outcome domains were reported in 12, 26, and 26 studies, respectively. In conclusion, this systematic review underscores the heterogeneity in metric development methodologies and the varying degrees of consensus among different quality indicators, despite the growing interest in benchmarking in pancreatic surgery. This review aims to inform future research efforts and contribute to the ongoing pursuit of excellence in pancreatic surgical care.

Perspectives of older adults with chronic illness on person-centered practice at an inpatient hospital department: a descriptive study

BackgroundThe growing aging trend associated with a higher prevalence of chronic illnesses is increasing the demand for the development of person-centered practice in specific care settings. Knowing the person’s perception of the care and the care experience is essential to improving inpatient care toward person-centeredness. This study aims to characterize the perceptions of person-centered practice of hospitalized older adults with chronic illness at a Portuguese inpatient hospital department.MethodsA quantitative, descriptive, cross-sectional approach was followed. Data were collected using a sociodemographic and health history questionnaire and the Person-Centered Practice Inventory - Care (PCPI-C). The effect of the different variables on each PCPI-C construct was determined using analysis of variance (ANOVA).ResultsThe results show that person-centered practice was positively perceived in the five constructs of the person-centered processes domain (M = 3.92; SD = 0.47). The highest-scored construct was working with the person’s beliefs and values (M = 4.12; SD = 0.51), and the lowest was working holistically (M = 3.68; SD = 0.70). No significant effect of the independent variables was found to influence the perceptions of any of the constructs in the person-centered processes domain.ConclusionsThese results might indicate that person-centered processes are perceived uniquely by each person through individualized therapeutic relationships rather than a pattern of care shared by hospitalized older adults.

Hate speech detection in low-resourced Indian languages: An analysis of transformer-based monolingual and multilingual models with cross-lingual experiments

Abstract Warning: This paper is based on hate speech detection and may contain examples of abusive/ offensive phrases. Cyberbullying, online harassment, etc., via offensive comments are pervasive across different social media platforms like ™Twitter, ™Facebook, ™YouTube, etc. Hateful comments must be detected and eradicated to prevent harassment and violence on social media. In the Natural Language Processing (NLP) domain, the most prevalent task is comment classification, which is challenging, and language models based on transformers are at the forefront of this advancement. This paper intends to analyze the performance of language models based on transformers like BERT, ALBERT, RoBERTa, and DistilBERT on the Indian hate speech datasets over binary classification. Here, we utilize the existing datasets, i.e., HASOC (Hindi and Marathi) and HS-Bangla. So, we evaluate several multilingual language models like MuRIL-BERT, XLM-RoBERTa, etc., few monolingual language models like RoBERTa-Hindi, Maha-BERT (Marathi), Bangla-BERT (Bangla), Assamese-BERT (Assamese), etc., and perform cross-lingual experiment also. For further analyses, we perform multilingual, monolingual, and cross-lingual experiments on our Hate Speech Assamese (HS-Assamese) (Indo-Aryan language family) and Hate Speech Bodo (HS-Bodo) (Sino-Tibetan language family) dataset (HS dataset version 2) also and achieved a promising result. The motivation of the cross-lingual experiment is to encourage researchers to learn about the power of the transformer. Note that no pre-trained language models are currently available for Bodo or any other Sino-Tibetan languages.

Hot compression recrystallization and processing characteristics of 18 %Cr lean duplex stainless steel with Mn addition

The deformation differences of hot compression tests for 18 % Cr lean duplex stainless steels, alloyed with 3.1 and 5.8 wt% Mn concentrations were comparatively investigated. The deformed microstructure revealed that more Mn promoted the formation of austenitic dislocation cells, inhibited the occurrence of dynamic recrystallization (DRX), and resulted in a decrease in the number of refined austenite grains at lower temperatures and strain rates. Meanwhile, more Mn addition promoted ferrite DRX, and delayed austenite DRX initiation deformed at higher strain rates and lower deformation temperatures. The nearly complete refinement of austenite grains formed due to DRX deformation at 950℃/0.01 s−1 with 3.1 % Mn addition, while fine grains caused by ferrite DRX mainly occurred at 850℃/1 s−1 with 5.8 wt% Mn addition. The relationships between the Zener–Hollomon parameter (Z) and critical strain (stress) were established using the power law relation. The stability processing domains with high power efficiency greater than 0.34 narrowed with increasing Mn content, are located in the temperature range of 1000–1150℃ and strain rate range of 0.01–0.03 s−1, and austenite DRX plays a significant role in compression deformation improvement. At a low deformation temperature of 850 ℃, the work hardening rate in the initial strain increased with increasing Mn addition, and a lower strain rate and deformation temperature contributed to the dynamic deformation softening caused by austenite DRX, but ferrite DRX slightly contributed to the improvement of compression deformation. The DRX kinetics models show that the trend of the volume fraction of DRX as a function of processing variables is in good agreement with experimental data.

Towards a Reporting Guideline for Studies on Information Extraction from Clinical Texts.

The rapid technical progress in the domain of clinical Natural Language Processing and information extraction (IE) has resulted in challenges concerning the comparability and replicability of studies. This paper proposes a reporting guideline to standardize the description of methodologies and outcomes for studies involving IE from clinical texts. The guideline is developed based on the experiences gained from data extraction for a previously conducted scoping review on IE from free-text radiology reports including 34 studies. The guideline comprises the five top-level categories information model, architecture, data, annotation, and outcomes. In total, we define 28 aspects to be reported on in IE studies related to these categories. The proposed guideline is expected to set a standard for reporting in studies describing IE from clinical text and promote uniformity across the research field. Expected future technological advancements may make regular updates of the guideline necessary. In future research, we plan to develop a taxonomy that clearly defines corresponding value sets as well as integrating both this guideline and the taxonomy by following a consensus-based methodology.