Clinical Care Processes Research Articles

Predicting non-responders to lifestyle intervention in prediabetes: a machine learning approach.

The clinical care process for people with prediabetes starts with lifestyle intervention, often escalating to more intense treatment due to the low success rate of the first-line intervention. Clinicians lack clear guidelines on which patients would benefit from early treatment with more intensive therapeutic options, so we aimed to develop an algorithm to early identify non-responders to lifestyle intervention for prediabetes. Several statistical and machine learning algorithms were screened with internal cross-validation on the basis of accuracy and discrimination ability to correctly classify patients that would fail to normalize fasting glycemia within one year of being prescribed a lifestyle intervention, solely based on the first examination measurements. Of the many screened algorithm, only a random forest model performed with sufficient accuracy to exceed the historical failure rate of patients within our center, with an accuracy of 0.689 (CI 0.669, 0.710) and an AUROC of 0.687 (CI 0.673, 0.701). This study showcases the ability of machine learning models to provide useful insight in clinical practice leveraging knowledge contained in routinely collected data.

Hospital 4Ms: Documentation and association with patient characteristics.

For the thousands of health systems recognized as Age-Friendly, considerable progress has been made to integrate 4Ms into clinical care. This study evaluated associations between 4Ms documentation and patient characteristics in an inpatient setting. In this prospective cohort, hospitalizations included were from patients in an Acute Care for Elders (ACE) unit where the 4Ms were adopted and implemented. Each M (What Matters, Medication, Mentation, and Mobility) was stratified into three categories (not documented, partly documented, and fully documented) reflecting "assessment" and "action" clinical care processes. Electronic health records were reviewed for patient and hospitalization characteristics. Descriptive statistics evaluated these characteristics across categories of each M. There were 620 hospital encounters (573 patients) included in the cohort. Patients had a median age of 80 years [IQR 76, 86] and 85% were White. Of all 4Ms, What Matters had the lowest documentation with 413 (67%) of encounters falling into the not documented group. Medication had the highest documentation with 453 (73%) of encounters in the fully documented group. Significant differences in documentation were associated with age and partlyversus fully documented Mobility (80 [76, 86] and 82 [77, 88] (p = 0.019)). Hospital length of stay was differentially associated with documentation of all 4M categories. Initial mobility scores were associated with not versus partly documented Medication (6 [2, 7] and 2 [2, 6] (p = 0.041)). We developed a structured way to categorize "assessment" and "action" 4Ms care processes reflective of three documentation categories in the hospital (not, partly, and fully) and identified important patient and hospital characteristics associated with each. These results offer opportunities for future improvement efforts and insight to which characteristics may be important to measure with wider 4Ms adoption and uptake.

A-188 Modal Failure and Effects Analysis, FMEA methodology, as a strategy to increase patient safety

Abstract Background Patient safety during the clinical care process is considered a priority in healthcare. Failure Mode and Effects Analysis (FMEA) is a proactive and systematic method of process evaluation and is used to identifying where and how each phase of the analytical process could fail allowing the detection of the causes and the effects they produce on the quality of the results that are issued. A regular use of this tool makes possible to identify the most critical steps, propose improvement strategies and evaluate their impact. The aim of the study is to evaluate applicability of the FMEA tool to identify errors in the pre analytical, analytical, and post analytical phase of a clinical laboratory as well as the main causes and effects, to reduce them by proposing improvement strategies Methods For each phase into which the laboratory activity is divided, the frequency and type of errors that are made and their final consequences on the patient are evaluated. A risk index (NPR=OxDxS) is calculated for each error considering the frequency with which it occurs (O), the ease with which it is detected (D) and the severity of the consequences on the patient (S). Values goes from 1 (rarely) to 10 (often). Improvement actions are proposed for all errors with a risk index greater than 100 and this index is re-evaluated after the implementation of that improvement measures. This same analysis is performed for three times over the last 10 years (in 2014, 2019 and 2023). Results In FMEA analysis carried out in 2014, a total of 40 errors were identified in the pre-analytical phase (63.5% of the total), 12 in the analytical phase and 11 in the post-analytical phase. 50% of the total errors detected required improvement strategies because they had an NPR≥100 value. In the 2023 evaluation, a total of 27 errors were identified in the pre-analytical phase, 10 in the analytical phase, and 5 in the post-analytical phase but only 6 required improvement strategies, which represents an 80% reduction in the most critical errors for patient safety. However, the pre-analytical phase continues to be the most critical, as it continues to account for 64% of the total errors identified, including the lack of identification of the patient or sample and the inadequate prior preparation of the patient. In analytical and post-analytical phases, the NPR values obtained in 2023 decrease significantly over analysis carried out in 2014 and its not needed to apply improvement strategies. Automation and the IT tools significantly reduce the number of errors with high NPR values, but it is undoubtedly the involvement of service professionals that makes the difference over the years. Conclusions The use of the FMEA methodological tool allows the design of appropriate indicators to detect and reduce errors in the clinical laboratory. Its application as part of a good quality control allows a continuous improvement in the laboratory process and consequently a guarantee of quality for the patient

Identification of core indicators for the integration of a palliative care approach in hospitals: An international Delphi study.

Healthcare providers working in hospitals have significant exposure to patients with palliative care needs. For many patients, these needs often reflect non-specialist rather than specialist palliative care needs. Embedding a palliative care approach in acute hospital-based care however is challenging. To identify core indicators for the integration of a palliative care approach in hospitals. A Delphi technique used three sequential online survey rounds. Preliminary indicators were identified in a concept analysis of a palliative care approach, and a systematic review of hospital-based healthcare providers' views of a palliative care approach. An international expert panel of three key stakeholder groups (clinicians, researchers, patients/family members) participated in each Delphi round. The Delphi participants were recruited from 12 countries; 97 individuals responded to round 1, 78 to round 2 and 72 to round 3 (74% overall response rate). Consensus was achieved (defined a priori as >70%) on 32 core indicators of a hospital-based palliative care approach, with five structural indicators (relating to infrastructure and governance), 21 organisational indicators (relating to clinical care processes) and six staff indicators (relating to training and support for healthcare providers). This study offers multi-level guidance for clinical practice, policy and research related to integration of a palliative care approach in hospitals, based on evidence and international consensus from major stakeholder groups. These core indicators provide a means to assess, review and communicate the core elements of a palliative care approach in hospitals.

Novel artificial intelligence for diabetic retinopathy and diabetic macular edema: what is new in 2024?

Given the increasing global burden of diabetic retinopathy and the rapid advancements in artificial intelligence, this review aims to summarize the current state of artificial intelligence technology in diabetic retinopathy detection and management, assessing its potential to improve care and visual outcomes in real-world settings. Most recent studies focused on the integration of artificial intelligence in the field of diabetic retinopathy screening, focusing on real-world efficacy and clinical implementation of such artificial intelligence models. Additionally, artificial intelligence holds the potential to predict diabetic retinopathy progression, enhance personalized treatment strategies, and identify systemic disease biomarkers from ocular images through 'oculomics', moving towards a more precise, efficient, and accessible care. The emergence of foundation model architectures and generative artificial intelligence, which more clearly reflect the clinical care process, may enable rapid advances in diabetic retinopathy care, research and medical education. This review explores the emerging technology of artificial intelligence to assess the potential to improve patient outcomes and optimize personalized management in healthcare delivery and medical research. While artificial intelligence is expected to play an increasingly important role in diabetic retinopathy care, ongoing research and clinical trials are essential to address implementation issues and focus on long-term patient outcomes for successful real-world adoption of artificial intelligence in diabetic retinopathy.

Development and validation of the attitude scale for the clinical nutrition care process of hospitalized patients for physicians

Objective: Evaluating physicians’ attitudes towards malnutrition and clinical nutrition in hospitalized patients are crucial for the implementation of optimal nutritional care process and the prevent of hospital malnutrition. The aim of this study is to develop a scale that evaluates physicians’ attitudes towards malnutrition in hospitalized patients. Methods: Based on the existing literature on clinical nutrition and the clinical experience of experts in this field, a 5-point Likert-type attitude scale consisting of 12 items was developed. Analysis was carried out using Parallel Analysis to determine the number of factors in the Exploratory factor analysis based on the Polychoric correlation matrix and Unweighted Least Squares as the factor extraction method. Results: There are 8 items in the 1st factor (Physician duties) and 4 items in the 2nd factor (Non-Physician duties). The Cronbach Alpha and McDonald’s Omega coefficients of the scale were found to be 0.72 and 0.81 respectively, from the sub-dimensions 0.78 and 0.85 for the 1st Factor, and 0.66 and 0.75 for the 2nd Factor. Conclusion: Attitude scale for the clinical nutrition care process of hospitalized patients for physicians is an instrument with good psychometric properties that measures examination of physicians’ attitudes related to clinical nutrition care process.

Emerging Artificial Intelligence In Therapeutic Agreements With A Medicolegal Approach

Introduction: Medical services use artificial intelligence for operating to help and even transform the healthcare system. AI innovators have developed tools to improve clinical care processes, advance medical research, and increase efficiency in medical services.Purposes of the Research: The purpose of this article is to analyse the legal validity of therapeutic agreements using AI in medical field.Methods of the Research: The research method used is a normative juridical research type with an analytical approach.Results of the Research: The results show that medical services are complex and closely related systems, and always contain risks, so they must be carried out with great care. Legal provisions governing the use of AI in therapeutic agreements with a medicolegal approach must be able to evaluate and ensure the safety and accuracy of medical decisions made by AI "thinking algorithms".

How personnel diversity and affective bonds affect performance-based financing: a moderator analysis of a difference-in-difference estimator.

To spur improvement in health-care service quality and quantity, performance-based financing (PBF) is an increasingly common policy tool, especially in low- and middle-income countries. This study examines how personnel diversity and affective bonds in primary care clinics affect their ability to improve care quality in PBF arrangements. Leveraging data from a large-scale matched PBF intervention in Tajikistan including 208 primary care clinics, we examined how measures of personnel diversity (position and tenure variety) and affective bonds (mutual support and group pride) were associated with changes in the level and variability of clinical knowledge (diagnostic accuracy of 878 clinical vignettes) and care processes (completion of checklist items in 2485 instances of direct observations). We interacted the explanatory variables with exposure to PBF in cluster-robust, linear regressions to assess how these explanatory variables moderated the PBF treatment's association with clinical knowledge and care process improvements. Providers and facilities with higher group pride exhibited higher care process improvement (greater checklist item completion and lower variability of items completed). Personnel diversity and mutual support showed little significant associations with the outcomes. Organizational features of clinics exposed to PBF may help explain variation in outcomes and warrant further research and intervention in practice to identify and test opportunities to leverage them. Group pride may strengthen clinics' ability to improve care quality in PBF arrangements. Improving health-care facilities' pride may be an affordable and effective way to enhance health-care organization adaptation.

The Brain Injury Guidelines (BIG) and emergency department observation and admission rates: A retrospective cohort study

BackgroundEmergency Department (ED) Observation Units (OU) can provide safe, effective care for low risk patients with intracranial hemorrhages. We compared current ED OU use for patients with subdural hematomas (SDH) to the validated Brain Injury Guidelines (BIG) to evaluate the potential impact of implementing this risk stratification tool. MethodsRetrospective cohort of patients ≥18 years old with SDH of any cause from 2014 to 2020 to evaluate for potential missed OU cases. Missed OU cases were defined as patients with an initial Glasgow Coma Score (GCS) of 15 with hospital length of stays (LOS) <2 days, who did not meet the composite outcome and were not cared for in the OU or discharged from the ED. Composite outcome included in-hospital death or transition to hospice care, neurosurgical intervention, GCS decline, and worsening SDH size. Secondary outcomes were whether application of BIG would increase ED OU use or reduce CT use. Results264 patients met inclusion criteria over 5.3 year study timeframe. Mean age was 61 years (range 19–93) and 61.4% were male. SDH were traumatic in 76.9% and 60.2% of the cohort had additional injuries. The admission rate was 81.4% (n = 215). Fourteen (6.5%) missed OU cases were identified (2.6/year). Retrospective application of BIG resulted in 82.6% (n = 217) at BIG 3, 10.2% (n = 27) at BIG 2 and 7.6% (n = 20) at BIG 1. Application of BIG would not have decreased admission rates (82.6% BIG 3) and BIG 1 and 2 admissions were often for medical co-morbidities. The composite outcome was met in 50% of BIG 3, 22% of BIG 2, and no BIG 1 patients. ConclusionIn a level 1 trauma center with an established observation unit, current clinical care processes missed very few patients who could be discharged or placed in ED OU for SDH. Hospital admissions in BIG 1/2 were driven by co-morbidities and/or injuries, limiting applicability of BIG to this population.

Physicians’ emotion awareness and emotion regulation training during medical education: a systematic scoping review protocol

IntroductionThe objective of this systematic scoping review is to identify what approaches have been implemented in medical education programmes to teach medical students the skills to identify and manage emotions...

Computerized clinical decision support to improve stroke prevention therapy in primary care management of atrial fibrillation: a cluster randomized trial

Despite guidelines supporting antithrombotic therapy use in atrial fibrillation (AF), under-prescribing persists. We assessed whether computerized clinical decision support (CDS) would enable guideline-based antithrombotic therapy for AF patients in primary care. This cluster randomized trial of CDS versus usual care (UC) recruited participants from primary care practices across Nova Scotia, following them for 12 months. The CDS tool calculated bleeding and stroke risk scores and provided recommendations for using oral anticoagulants (OAC) per Canadian guidelines. From June 14, 2014 to December 15, 2016, 203 primary care providers (99 UC, 104 CDS) with access to high-speed Internet were recruited, enrolling 1,145 eligible patients (543 UC, 590 CDS) assigned to the same treatment arm as their provider. Patient mean age was 72.3 years; most were male (350, 64.5% UC, 351, 59.5% CDS) and from a rural area (298, 54.9% UC, 315, 53.4% CDS). At baseline, a higher than anticipated proportion of patients were receiving guideline-based OAC therapy (373, 68.7% UC, 442, 74.9% CDS; relative risk [RR] 0.97 (95% confidence interval [CI], 0.87-1.07; P = .511)). At 12 months, prescription data were available for 538 usual care and 570 CDS patients, and significantly more CDS patients were managed according to guidelines (415, 77.1% UC, 479, 84.0% CDS; RR 1.08 (95% CI, 1.01-1.15; P = .024)). Notwithstanding high baseline rates, primary care provider access to the CDS over 12 months further optimized the prescribing of OAC therapy per national guidelines to AF patients potentially eligible to receive it. This suggests that CDS can be effective in improving clinical process of care. Clinical Trials NCT01927367. https://clinicaltrials.gov/ct2/show/NCT01927367?term=NCT01927367&draw=2&rank=1.

How Hospitals Differentiate Health Information Technology Portfolios for Clinical Care Efficiency: Insights from the HITECH Act

Our research reveals the significant impact of evolving policy uncertainty on hospital strategies to mitigate cost-based performance deficits in clinical care processes through differentiation in search for health information technology (HIT). Key for hospital administrators and managers, our findings reveal the benefit of leveraging external benchmarks for performance feedback, enabling strategic, innovative approaches to HIT investments tailored to enhance clinical care efficiency and cost-effectiveness. Moreover, our findings have important implications for healthcare policymakers, highlighting the necessity to consider the varied responses of hospitals to policy fluctuations. Recognizing that hospitals proactively adapt their HIT portfolios in anticipation of new laws, and that these adaptations are most diverse under moderate policy uncertainty, is crucial. This nuanced understanding can guide policymakers in fostering an environment that encourages both the exploration of novel technologies and the widespread adoption of effective solutions across the healthcare spectrum. By bridging the gap between policy development and hospital administration, our work offers a road map for aligning strategic technological differentiation with policy objectives, ultimately enhancing healthcare delivery and outcomes.

Supporting patient decision-making in non-invasive prenatal testing: a comparative study of professional values and practices in England and France

BackgroundNon-invasive prenatal testing (NIPT), which can screen for aneuploidies such as trisomy 21, is being implemented in several public healthcare systems across Europe. Comprehensive communication and information have been highlighted in the literature as important elements in supporting women’s reproductive decision-making and addressing relevant ethical concerns such as routinisation. Countries such as England and France are adopting broadly similar implementation models, offering NIPT for pregnancies with high aneuploidy probability. However, we do not have a deeper understanding of how professionals’ counselling values and practices may differ between these contexts.MethodsIn this paper, we explore how professionals in England and France support patient decision-making in the provision of NIPT and critically compare professional practices and values. We draw on data from semi-structured interviews with healthcare professionals.ResultsBoth English and French professionals emphasised values relating to patient choice and consent. However, understandings and application of these values into the practice of NIPT provision differed. English interviewees placed a stronger emphasis on interpreting and describing the process of counselling patients and clinical care through a “principle” lens. Their focus was on non-directiveness, standardisation, and the healthcare professional as “decision-facilitator” for patients. French interviewees described their approach through a “procedural” lens. Their focus was on formal consent, information, and the healthcare professional as “information-giver”. Both English and French professionals indicated that insufficient resources were a key barrier in effectively translating their values into practice.ConclusionOur findings illustrate that supporting patient choice in the provision of NIPT may be held as an important value in common on a surface level, but can be understood and translated into practice in different ways. Our findings can guide further research and beneficially inform practice and policy around NIPT provision.

The Impact of Hospice Care Structures on Care Processes: A Retrospective Cohort Study.

Background: Palliative care is subject to substantial variations in care, which may be shaped through adapting the organisational structures through which care is provided. Whilst the goal of these structures is to improve patient care, there is a lack of evidence regarding their effect on care processes and patient outcomes. Aims: This study aims to describe the relationship between care structures and the quantity and domains of care processes in hospice care. Design: Retrospective cohort study. Settings/Participants: Data were collected from Dutch hospice patient's clinical records and hospice surveys, detailing hospice structures, patient clinical characteristics and care processes. Results: 662 patients were included from 42 hospices, mean age 76.1years. Hospices were categorised according to their care structures - structured clinical documentation and multidisciplinary meetings. Patients receiving care in hospices with structured multidisciplinary meetings had an increased quantity of documented care processes per patient on admission through identification (median 4 vs 3, P < .001), medication (2 vs 1, P = .004) and non-medication (1 vs 0, P < .001) interventions, monitoring (2 vs 1, P < .001) and evaluation (0 vs 0, P = .014), and prior to death. Similar increases were identified for patients who received care in hospices with structured documentation upon admission, but these changes were not consistent prior to death. Conclusions: This study details that the care structures of documentation and multidisciplinary meetings are associated with increased quantity and breadth of documentation of care processes in hospice care. Employing these existing structures may result in improvements in the documentation of patient care processes, and thus better communication around patient care.

Ten years of the Citizen's Electronic Health Record e-SUS Primary Healthcare: in search of an electronic Unified Health System.

Contextualize the adherence to the Prontuário Eletrônico do Cidadão (PEC - Citizen's Electronic Health Record) by Brazilian municipalities and the evolution of the electronic strategy of the Unified Health System (e-SUS) for Primary Healthcare (PHC) during its 10 years. This descriptive study added information on adherence to the use of medical records extracted from the database of the Secretaria de Atenção Primária à Saúde (SAPS- Primary Healthcare Secretary) of the Federal Government between 2017 and 2022. We analized the number of computerized basic healthcare units that used some electronic medical records, the number of those that used simplified data collection (SDC), and those that implemented the citizen's electronic health record (PEC) in the same period. A descriptive synthesis of the functionalities and modules implemented in the system during its 10 years of development was also carried out. The adherence of Brazilian municipalities to the PEC has grown exponentially in the last five years, going from 8,930 healthcare units in 2017 to 26,091 in 2022. As expected, while the main functionalities and improvements developed in this decade sought to implement new flows and modules of administrative, clinical care, and care management processes and health service administration, improving aspects of usability and technological infrastructure of the application architecture was also crucial for the success of the system. In 2023, the milestone of a decade will be celebrated since the beginning of health records implementation by Brazilian municipalities, marked by technological and infrastructure challenges and improvements and new functionalities that highlight the technological evolution of the e-SUS PHC system and strategy. Despite many other tools, the PEC is arguably Brazil's leading electronic medical record today, as it has always invested in evolution, updating itself in technological and usability opportunities.

O que dizem familiares de autistas sobre o trabalho desenvolvido pelos CAPSi?

Abstract The child and adolescent mental health policy, implemented in Brazil from the beginning of the 21st century, established the Centros de Atenção Psicossocial Infantojuvenis (CAPSi - Psychosocial Care Centers for Children and Adolescent) as strategic services to prioritize more complex cases, with emphasis on autism. This study aims to compare two sources of information on the perception family members of autistic people regarding the work carried out by CAPSi: the first was collected in a 2011 survey, which used focus groups; and the second, from the literature produced on the subject in the following 10 years. The family member’s narratives were organized into four thematic axes: perception of the effects of psychosocial care; information sharing; perception about care processes; and demands and claims. Despite the heterogeneity between the studies, the results indicated that the work of the CAPSi produces positive effects, especially regarding socialization. However, this perception is not accompanied by a better understanding of the clinical picture and care processes. The value of treatment is often attributed to the personal attitude of professionals, indicating the lack of sharing and participation by family members. These aspects should encourage the CAPSi to involve family members as partners in care, particularly valuing the transmission of the psychosocial reasoning, its strategies and direction of care.

Doing Social Space as a Chacterestic of Clinical Leadership Based on Advanced Nursing Practice - A Qualitative Ethnographic Study

Aim: The study aims to present and analyze the daily practices of Advanced Practice Nurses in hospitals and to reconstruct the constitutive spaces of action, especially in the context of clinical leadership. In doing so, a detailed picture of the prevailing social practices will be described. Research Question: How can Clinical Leadership be interpreted in dynamic work processes and their interaction in the hospital? Methods: An ethnographic research design including participant observation of nine Advanced Practice Nurses in two hospitals was conducted during the period 5/2020 to 8/2020. Data analysis included sequence analysis of participant observations. The study was classified as ethically unobjectionable. Results: This study shows how Advanced Practice Nurses connect people in the hospital through spacing processes and how they influence clinical care processes. The findings paint a detailed picture of the recurring everyday social practices of advanced practice nurses that are interwoven in a bundle and help to constitute and occupy social space. The results are presented in the Doing social space model. Conclusion: This process of reflection helps nurses and other health professionals to critically examine the conventions and rules that underlie their actions in clinical care and to explain the reasons for their actions. The findings should be of great interest as the actions of nurses can be explained and understood from both practice-based theoretical approaches and a spatial sociological perspective.

REVISITING THE TEACHING NURSING HOME: PRAGMATIC EVALUATION IN A REAL-WORLD SETTING

Abstract Revisiting the Teaching Nursing Home (RTNH) is a renewal of the Teaching Nursing Home model pioneered in the 1980s, which found that creating partnerships between schools of nursing (SONs) and nursing homes (NHs) improved clinical outcomes. In its first two years, the RTNH initiative has fostered partnerships between three SONs and four NHs in Pennsylvania, and is planning to expand. The program is implementing the Institute for HealthCare Improvement Age-Friendly Health System “4Ms” quality improvement framework through an online learning network. The 4M quality improvement framework focuses on four evidence-based elements: Mobility, Mentation, Medication, and What Matters. In addition, the participating SONs are incorporating the 4Ms into curricula and clinical rotations. The evaluation will examine both implementation and outcomes for SONs and NHs. Measures include student competency, staff satisfaction and burnout, clinical process of care and resident outcomes. While some resident level measures can be extracted from the Minimum Data Set (MDS), others (deprescribing, rehabilitation goals, preference sensitive care) require access to the electronic medical record (EMR). The goal of this presentation is to describe the methodology for measuring the wide range of outcomes and to examine the performance of a synthetic comparison group to study overall quality using CASPAR data. We selected 1,764 similarly sized, non-profit NHs and conducted bivariate, and propensity score analysis to determine if the participating NHs were different on any observable characteristics. The findings suggest that the participating NHs were not statistically significantly different in terms of overall quality rating, staffing, or inspections.

Applying Natural Language Processing to Textual Data From Clinical Data Warehouses: Systematic Review.

In recent years, health data collected during the clinical care process have been often repurposed for secondary use through clinical data warehouses (CDWs), which interconnect disparate data from different sources. A large amount of information of high clinical value is stored in unstructured text format. Natural language processing (NLP), which implements algorithms that can operate on massive unstructured textual data, has the potential to structure the data and make clinical information more accessible. The aim of this review was to provide an overview of studies applying NLP to textual data from CDWs. It focuses on identifying the (1) NLP tasks applied to data from CDWs and (2) NLP methods used to tackle these tasks. This review was performed according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. We searched for relevant articles in 3 bibliographic databases: PubMed, Google Scholar, and ACL Anthology. We reviewed the titles and abstracts and included articles according to the following inclusion criteria: (1) focus on NLP applied to textual data from CDWs, (2) articles published between 1995 and 2021, and (3) written in English. We identified 1353 articles, of which 194 (14.34%) met the inclusion criteria. Among all identified NLP tasks in the included papers, information extraction from clinical text (112/194, 57.7%) and the identification of patients (51/194, 26.3%) were the most frequent tasks. To address the various tasks, symbolic methods were the most common NLP methods (124/232, 53.4%), showing that some tasks can be partially achieved with classical NLP techniques, such as regular expressions or pattern matching that exploit specialized lexica, such as drug lists and terminologies. Machine learning (70/232, 30.2%) and deep learning (38/232, 16.4%) have been increasingly used in recent years, including the most recent approaches based on transformers. NLP methods were mostly applied to English language data (153/194, 78.9%). CDWs are central to the secondary use of clinical texts for research purposes. Although the use of NLP on data from CDWs is growing, there remain challenges in this field, especially with regard to languages other than English. Clinical NLP is an effective strategy for accessing, extracting, and transforming data from CDWs. Information retrieved with NLP can assist in clinical research and have an impact on clinical practice.

Long COVID in long-term care: a rapid realist review

ObjectivesThe goals of this rapid realist review were to ask: (a) what are the key mechanisms that drive successful interventions for long COVID in long-term care (LTC) and (b) what...