RESUMEN

BACKGROUND: With the widespread adoption of digital health records, including electronic discharge summaries (eDS), it is important to assess their usability in order to understand whether they meet the needs of the end users. While there are established approaches for evaluating the usability of electronic health records, there is a lack of knowledge regarding suitable evaluation methods specifically for eDS. OBJECTIVE: This literature review aims to identify the usability evaluation approaches used in eDS. METHODS: We conducted a comprehensive search of PubMed, CINAHL, Web of Science, ACM Digital Library, MEDLINE, and ProQuest databases from their inception until July 2023. The study information was extracted and reported in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses). We included studies that assessed the usability of eDS, and the systems used to display eDS. RESULTS: A total of 12 records, including 11 studies and 1 thesis, met the inclusion criteria. The included studies used qualitative, quantitative, or mixed methods approaches and reported the use of various usability evaluation methods. Heuristic evaluation was the most used method to assess the usability of eDS systems (n=7), followed by the think-aloud approach (n=5) and laboratory testing (n=3). These methods were used either individually or in combination with usability questionnaires (n=3) and qualitative semistructured interviews (n=4) for evaluating eDS usability issues. The evaluation processes incorporated usability metrics such as user performance, satisfaction, efficiency, and impact rating. CONCLUSIONS: There are a limited number of studies focusing on usability evaluations of eDS. The identified studies used expert-based and user-centered approaches, which can be used either individually or in combination to identify usability issues. However, further research is needed to determine the most appropriate evaluation method which can assess the fitness for purpose of discharge summaries.

Asunto(s)

RESUMEN

BACKGROUND: Extracting principal diagnosis from patient discharge summaries is an essential task for the meaningful use of medical data. The extraction process, usually by medical staff, is laborious and time-consuming. Although automatic models have been proposed to retrieve principal diagnoses from medical records, many rare diagnoses and a small amount of training data per rare diagnosis provide significant statistical and computational challenges. OBJECTIVE: In this study, we aimed to extract principal diagnoses with limited available data. METHODS: We proposed the OLR-Net, Object Label Retrieval Network, to extract principal diagnoses for discharge summaries. Our approach included semantic extraction, label localization, label retrieval, and recommendation. The semantic information of discharge summaries was mapped into the diagnoses set. Then, one-dimensional convolutional neural networks slid into the bottom-up region for diagnosis localization to enrich rare diagnoses. Finally, OLR-Net detected the principal diagnosis in the localized region. The evaluation metrics focus on the hit ratio, mean reciprocal rank, and the area under the receiver operating characteristic curve (AUROC). RESULTS: 12,788 desensitized discharge summary records were collected from the oncology department at Hainan Hospital of Chinese People's Liberation Army General Hospital. We designed five distinct settings based on the number of training data per diagnosis: the full dataset, the top-50 dataset, the few-shot dataset, the one-shot dataset, and the zero-shot dataset. The performance of our model had the highest HR@5 of 0.8778 and macro-AUROC of 0.9851. In the limited available (few-shot and one-shot) dataset, the macro-AUROC were 0.9833 and 0.9485, respectively. CONCLUSIONS: OLR-Net has great potential for extracting principal diagnosis with limited available data through label localization and retrieval.

RESUMEN

BACKGROUND: The integration of artificial intelligence (AI; ChatGPT 4.0) into medical workflows presents a great potential to enhance efficiency and quality. The use of artificial intelligence in the creation of discharge summaries seems particularly interesting and valid. The course of each hospitalization is described in the discharge summary, which is given to each patient and then to his general practitioner at the end of hospital treatment. An exploratory analysis of discharge summaries in psychiatric clinics underscores that these documents must fulfill diverse and specific requirements. Nevertheless, AI-generated discharge summaries offer the opportunity to optimize information transfer and alleviate the workload on physicians. METHOD: The study evaluates the quality of discharge summaries produced by clinical staff and by an AI model (ChatGPT 4.0). The clinicians involved in writing of the discharge summaries were not informed about the study's purpose or methodology. The completed summaries were subsequently assessed by four attending physicians using predefined criteria. These physicians were also blinded to the study's objectives and were unaware of the individual authors of the summaries. The evaluation criteria included consistency, completeness, and comprehensibility. Additionally, the time required to prepare these summaries and its impact on overall quality were analyzed. RESULTS: The results of the study indicate that discharge summaries generated by AI are more efficient than discharge summaries prepared by clinic staff. The AI was particularly effective in terms of coherence and information structure. CONCLUSION: Further research, training and development is needed to improve the accuracy and reliability of AI-generated discharge summaries.

RESUMEN

BACKGROUND: Discharge letters are a critical component in the continuity of care between specialists and primary care providers. However, these letters are time-consuming to write, underprioritized in comparison to direct clinical care, and are often tasked to junior doctors. Prior studies assessing the quality of discharge summaries written for inpatient hospital admissions show inadequacies in many domains. Large language models such as GPT have the ability to summarize large volumes of unstructured free text such as electronic medical records and have the potential to automate such tasks, providing time savings and consistency in quality. OBJECTIVE: The aim of this study was to assess the performance of GPT-4 in generating discharge letters written from urology specialist outpatient clinics to primary care providers and to compare their quality against letters written by junior clinicians. METHODS: Fictional electronic records were written by physicians simulating 5 common urology outpatient cases with long-term follow-up. Records comprised simulated consultation notes, referral letters and replies, and relevant discharge summaries from inpatient admissions. GPT-4 was tasked to write discharge letters for these cases with a specified target audience of primary care providers who would be continuing the patient's care. Prompts were written for safety, content, and style. Concurrently, junior clinicians were provided with the same case records and instructional prompts. GPT-4 output was assessed for instances of hallucination. A blinded panel of primary care physicians then evaluated the letters using a standardized questionnaire tool. RESULTS: GPT-4 outperformed human counterparts in information provision (mean 4.32, SD 0.95 vs 3.70, SD 1.27; P=.03) and had no instances of hallucination. There were no statistically significant differences in the mean clarity (4.16, SD 0.95 vs 3.68, SD 1.24; P=.12), collegiality (4.36, SD 1.00 vs 3.84, SD 1.22; P=.05), conciseness (3.60, SD 1.12 vs 3.64, SD 1.27; P=.71), follow-up recommendations (4.16, SD 1.03 vs 3.72, SD 1.13; P=.08), and overall satisfaction (3.96, SD 1.14 vs 3.62, SD 1.34; P=.36) between the letters generated by GPT-4 and humans, respectively. CONCLUSIONS: Discharge letters written by GPT-4 had equivalent quality to those written by junior clinicians, without any hallucinations. This study provides a proof of concept that large language models can be useful and safe tools in clinical documentation.

Asunto(s)

RESUMEN

BACKGROUND: Patients who have benefited from specialist intervention during periods of acute/complex palliative care needs often transition from specialist-to-primary care once such needs have been controlled. Effective communication between services is central to co-ordination of care to avoid the potential consequences of unmet needs, fragmented care, and poor patient and family experience. Discharge communications are a key component of care transitions. However, little is known about the experiences of those primarily receiving these communications, to include patients', carers' and primary care healthcare professionals. This study aims to have a better understanding of how the discharge communications from specialist palliative care services to primary care are experienced by patients, carers, and healthcare professionals, and how these communications might be improved to support effective patient-centred care. METHODS: This is a 15-month qualitative study. We will interview 30 adult patients and carers and 15 healthcare professionals (n = 45). We will seek a range of experiences of discharge communication by using a maximum variation approach to sampling, including purposively recruiting people from a range of demographic backgrounds from 4-6 specialist palliative care services (hospitals and hospices) as well as 5-7 general practices. Interview data will be analysed using a reflexive thematic approach and will involve input from the research and advisory team. Working with clinicians, commissioners, and PPI representatives we will co-produce a list of recommendations for discharge communication from specialist palliative care. DISCUSSION: Data collection may be limited by the need to be sensitive to participants' wellbeing needs. Study findings will be shared through academic publications and presentations. We will draft principles for how specialist palliative care clinicians can best communicate discharge with patients, carers, and primary care clinicians. These will be shared with clinicians, policy makers, commissioners, and PPI representatives and key stakeholders and organisations (e.g. Hospice UK) and on social media. Key outputs will be recommendations for a specialist palliative care discharge proforma. TRIAL REGISTRATION: Registered in ISRCTN Registry on 29.12.2023 ref: ISRCTN18098027.

Asunto(s)

RESUMEN

INTRODUCTION: Discharge from hospital is a risk to drug continuity and medication safety. In Germany, new legal requirements concerning the management of patient discharge from the hospital came into force in 2017. They set minimum requirements for the documentation of medications in patient discharge summaries, which are the primary means of communication at transitions of care. Six years later, data on their practical implementation in routine care are lacking. METHODS: Within the scope of an explorative retrospective observational study, the minimum requirements were operationalized and a second set of assessment criteria was derived from the recommendation "Good Prescribing Practice in Drug Therapy" published by the Aktionsbündnis Patientensicherheit e.V. as a comparative quality standard. A sample of discharge summaries was drawn from routine care at the University Hospital Heidelberg and assessed according to their fulfilment of the criteria sets. In addition, the potential influence of certain context factors (e. g., involvement of clinical pharmacists or software usage) was evaluated. RESULTS: In total, 11 quality criteria were derived from the minimum requirements. According to the eligibility criteria (i. e., three or more discharge medications) 352 discharge summaries (42 wards; issued in May-July 2021), containing in total 3,051 medications, were included. The practical implementation of the minimum requirements for documenting medications in patient discharge summaries differed considerably depending on the criterion and defined context factors. Core elements (i. e., drug name, strength, and dosage at discharge) were fulfilled in 82.8 %, while further minimum requirements were rarely met or completely lacking (e. g., explanations for special pharmaceutical forms). Involvement of clinical pharmacists and usage of software were shown to be a facilitator of documentation quality, while on-demand medication (compared to long-term medication) as well as newly prescribed medication (compared to home medication or medication changed during hospitalisation) showed poorer documentation quality. In addition, the documentation quality seemed to depend on the department and the day of discharge. CONCLUSION: To date, the wording of the German legal requirements allows for different interpretations without considering the respective clinical setting and the medication actually prescribed. For future clarification of the requirements, implications of the wording for the clinical setting should be considered.

Asunto(s)

RESUMEN

BACKGROUND: Although discharge summaries in patient-friendly language can enhance patient comprehension and satisfaction, they can also increase medical staff workload. Using a large language model, we developed and validated software that generates a patient-friendly discharge summary. METHODS: We developed and tested the software using 100 discharge summary documents, 50 for patients with myocardial infarction and 50 for patients treated in the Department of General Surgery. For each document, three new summaries were generated using three different prompting methods (Zero-shot, One-shot, and Few-shot) and graded using a 5-point Likert Scale regarding factuality, comprehensiveness, usability, ease, and fluency. We compared the effects of different prompting methods and assessed the relationship between input length and output quality. RESULTS: The mean overall scores differed across prompting methods (4.19 ± 0.36 in Few-shot, 4.11 ± 0.36 in One-shot, and 3.73 ± 0.44 in Zero-shot; P < 0.001). Post-hoc analysis indicated that the scores were higher with Few-shot and One-shot prompts than in zero-shot prompts, whereas there was no significant difference between Few-shot and One-shot prompts. The overall proportion of outputs that scored ≥ 4 was 77.0% (95% confidence interval: 68.8-85.3%), 70.0% (95% confidence interval [CI], 61.0-79.0%), and 32.0% (95% CI, 22.9-41.1%) with Few-shot, One-shot, and Zero-shot prompts, respectively. The mean factuality score was 4.19 ± 0.60 with Few-shot, 4.20 ± 0.55 with One-shot, and 3.82 ± 0.57 with Zero-shot prompts. Input length and the overall score showed negative correlations in the Zero-shot (r = -0.437, P < 0.001) and One-shot (r = -0.327, P < 0.001) tests but not in the Few-shot (r = -0.050, P = 0.625) tests. CONCLUSION: Large-language models utilizing Few-shot prompts generally produce acceptable discharge summaries without significant misinformation. Our research highlights the potential of such models in creating patient-friendly discharge summaries for Korean patients to support patient-centered care.

Asunto(s)

RESUMEN

AIMS: To investigate the ways that nurses engage with referral letters and discharge summaries, and the qualities of these documents they find valuable for safe and effective practice. DESIGN: This study comprised a qualitative, case-study design within a constructivist paradigm using convenience sampling. METHODS: Interviews were conducted with nurses to investigate their practices relating to referral letters and discharge summaries. Data collection also involved nurses' examination and evaluation of a diverse range of 10 referral letters and discharge summaries from medical records at two Australian hospitals through focus-group sessions. The data were transcribed and analysed inductively. RESULTS: In all, 67 nurses participated in interviews or focus groups. Nurses indicated they used referral letters and discharge summaries to inform their work when caring for patients at different times throughout their hospitalisation. These documents assisted them with verbal handovers, to enable them to educate patients about their condition and treatment and to provide a high standard of care. The qualities of referral letters and discharge summaries that they most valued were language and communication, an awareness of audience and clinical knowledge, as well as balancing conciseness with comprehensiveness of information. CONCLUSION: Nurses relied on referral letters and discharge summaries to ensure safe and effective patient care. They used these documents to enhance their verbal handovers, contribute to patient care and to educate the patient about their condition and treatment. They identified several qualities of these documents that assisted them in maintaining patient safety including clarity and conciseness of information. IMPLICATIONS FOR THE PROFESSION AND PATIENT CARE: It is important that referral letters and discharge summaries are written clearly, concisely and comprehensively because nurses use them as key sources of evidence in planning and delivering care, and in communicating with other health professionals in relaying goals of care and implementing treatment plans. IMPACT: Nurses reported that they regularly used referral letters and discharge summaries as valuable sources of evidence throughout their patients' hospitalisation. The qualities of these documents which they most valued were language and communication styles, awareness of audience and clinical knowledge, as well as balancing conciseness with comprehensiveness of information. This research has important impact on the patient experience in relation to encouraging effective referral letter and discharge summary writing. REPORTING METHOD: We have adhered to the relevant EQUATOR guidelines through the SRQR reporting method. PATIENT OR PUBLIC CONTRIBUTION: No patient or public contribution.

Asunto(s)

RESUMEN

BACKGROUND: Medication discrepancies can occur in transitions of care because of a lack of communication between hospitals and community pharmacies. These discrepancies can lead to preventable adverse drug events (ADEs). AIM: To investigate the effect of electronic transmission of the basic discharge medication report on unintentional medication discrepancies observed between this report and the 28-day post-discharge status in the community pharmacy. METHOD: The study took place in a Dutch teaching hospital and 8 community pharmacies. A quality improvement study with a nonrandomized, historically controlled intervention design was performed. The intervention consisted of the electronic transmission of a basic discharge medication report to the community pharmacies. Unintentional medication discrepancies were identified by comparing the basic discharge medication report to the 28-day post-discharge medication record in community pharmacies. The main outcome measure was the proportion of drugs with one or more unintentional discrepancies compared between the historical control group and intervention group, using the chi-square test. Secondary outcome measure was the proportion of patients with one or more unintentional discrepancies. RESULTS: The participants used a total of 1078 drugs in the control group and 862 in the intervention group. The intervention significantly reduced the proportion of drugs with an unintentional discrepancy from 230 out of 1078 in the control group (21.3%) to 149 out of 862 drugs in the intervention group (17.3%; p = 0.025). At patient level, a non-significant increase was seen (62.4-78.8%; p = 0.41). CONCLUSION: The electronic transmission of the basic discharge medication report reduced the proportion of drugs with an unintentional discrepancy after discharge, but not the proportion of patients.

Asunto(s)

RESUMEN

BACKGROUND: Successful transitions of care require communication between inpatient and outpatient physicians. The discharge summary is the main communication tool used by physicians during these transitions. OBJECTIVE: With the goal of improving care transitions, we explored primary care physicians (PCPs) perspectives on characteristics of high-quality discharge summaries. DESIGN: We conducted semi-structured individual interviews in this qualitative study and surveyed participants for sociodemographic characteristics. PARTICIPANTS: PCPs were recruited from multiple health systems in California. APPROACH: An interview guide was created by the study authors to solicit PCPs' experiences with discharge summaries and perspectives on four discharge summary templates previously used by large health systems. Interviews were transcribed verbatim and qualitative data were analyzed interactively through thematic analysis. KEY RESULTS: Twenty PCPs participated in interviews lasting an average of 35 min (range 26-47 min). Sixty percent were female. Most (70%) had trained in internal medicine (IM); 5% had trained in both IM and pediatrics and 25% in family medicine. Some (45%) participants practiced both inpatient and outpatient medicine; 55% had exclusively outpatient practices. Half worked in university-affiliated clinics, 15% community clinics, 15% public health clinics, 5% private practice, and 15% multiple clinic types. Many PCPs (65%) had been in practice for ≥ 10 years. Participants reported multiple concerns with typical discharge summaries, including frustration with lengthy documents containing information irrelevant to outpatient care. Suggested recommendations included beginning the discharge summary with action items, clear identification of incidental findings requiring follow-up, specifying reasons for any medication changes, and including dates for treatment regimens rather than expected duration of treatment. Participants highlighted the importance of feedback to trainees to assist in crafting succinct discharge summaries containing relevant information. CONCLUSION: Clinical training programs and healthcare systems must optimize discharge summaries for PCPs to achieve goals of providing high-quality care that improves population health.

RESUMEN

Encouraged by the success of pretrained Transformer models in many natural language processing tasks, their use for International Classification of Diseases (ICD) coding tasks is now actively being explored. In this study, we investigated two existing Transformer-based models (PLM-ICD and XR-Transformer) and proposed a novel Transformer-based model (XR-LAT), aiming to address the extreme label set and long text classification challenges that are posed by automated ICD coding tasks. The Transformer-based model PLM-ICD, which currently holds the state-of-the-art (SOTA) performance on the ICD coding benchmark datasets MIMIC-III and MIMIC-II, was selected as our baseline model for further optimisation on both datasets. In addition, we extended the capabilities of the leading model in the general extreme multi-label text classification domain, XR-Transformer, to support longer sequences and trained it on both datasets. Moreover, we proposed a novel model, XR-LAT, which was also trained on both datasets. XR-LAT is a recursively trained model chain on a predefined hierarchical code tree with label-wise attention, knowledge transferring and dynamic negative sampling mechanisms. Our optimised PLM-ICD models, which were trained with longer total and chunk sequence lengths, significantly outperformed the current SOTA PLM-ICD models, and achieved the highest micro-F1 scores of 60.8 % and 50.9 % on MIMIC-III and MIMIC-II, respectively. The XR-Transformer model, although SOTA in the general domain, did not perform well across all metrics. The best XR-LAT based models obtained results that were competitive with the current SOTA PLM-ICD models, including improving the macro-AUC by 2.1 % and 5.1 % on MIMIC-III and MIMIC-II, respectively. Our optimised PLM-ICD models are the new SOTA models for automated ICD coding on both datasets, while our novel XR-LAT models perform competitively with the previous SOTA PLM-ICD models.

Asunto(s)

RESUMEN

Introduction Discharge summaries (DS), which are sent from inpatient to outpatient settings, transmit critical clinical information. DS play a crucial role in the discharge process since they provide critical information about the patients that is simple to remember and help with patient follow-up in the community. This audit sought to determine if a quality improvement (QI) program may have an influence on the severity of mistakes at the moment of discharge and to assess the existing degree of inconsistencies on handwritten DS for orthopaedic patients. Methodology From the orthopaedics department at a tertiary care facility in south India, 100 handwritten DS and 100 electronic DS over six months were randomly chosen, and they were retrospectively audited against a predetermined set of criteria. The errors were compiled and compared by three reviewers. Results Some of the criteria, such as the doctor's signature, the speciality of admission, procedural therapy at the hospital, and the date of admission, were contained in all handwritten and electronic DS. Some of the metrics showed that electronic DS performed better than handwritten DS in areas such as hospital complications, which increased from 50% to 100%, contact information, which increased from 34% to 95%, and condition at discharge, which increased from 66% to 96%. Also, understandability increased from 58% to 100%, prognostic details increased from 70% to 96%, allergies increased from 66% to 100%, physical examination findings increased from 88% to 100%, admission diagnosis increased from 80% to 100%, patient/physician details increased from 92% to 100%, the information given to patient increased from 88% to 100%, problem list/issue pending increased from 35% to 92%, investigation increased from 80% to 100%, discharge medications increased from 88% to 100%, follow-up plan increased from 80% to 100%, discharge diagnosis increased from 94% to 100%, International Classification of Diseases, Tenth Revision (ICD-10) code increased from 93% to 100%, and days of admission increased from 92% to 100%. Conclusion Following the deployment of electronic DS, we were able to better care for patients and lessen their discomfort. We advise converting to electronic DS to enhance patient care and better record-keeping since this will become a significant problem if all notes are not accurately filled and are not readable.

RESUMEN

ABSTRACT Objective: To map the evidence on self-care guidelines for patients in the post-hematopoietic stem cell transplantation (HSCT) period. Method: Scoping review supported by Joanna Briggs Institute recommendations, with searches conducted between March and April 2022 in national and international databases and repositories of theses and dissertations. Results: Of the 11 studies that composed the final sample, the guidelines had a social and personal aspect, as post-transplant patients need to follow numerous essential recommendations for the prevention of infections and complications for successful treatment and improved quality of life. Conclusion: Knowing the self-care guidelines that must be performed by post-HSCT patients is fundamental for the nursing team to provide the necessary information for care outside the controlled environment of the hospital, in addition to minimizing episodes of infection, death, and increasing the survival and quality of life of transplant recipients.

RESUMEN Objetivo: mapear las evidencias sobre las orientaciones realizadas para el autocuidado de pacientes en el post-trasplante de células madre hematopoyéticas (TCTH). Método: Scoping Review apoyada en las recomendaciones del Instituto Joanna Briggs, con búsquedas entre marzo y abril de 2022 en bases de datos y repositorios de tesis y disertaciones nacionales e internacionales. Resultados: de los 11 estudios que compusieron la muestra final, las orientaciones tenían un carácter social y personal, ya que el paciente en el post-trasplante necesita seguir numerosas recomendaciones imprescindibles para la prevención de infecciones y complicaciones para el éxito del tratamiento y la mejora de la calidad de vida. Conclusión: Conocer las orientaciones para el autocuidado que deben ser realizadas por pacientes en el post-TCTH es fundamental para que el equipo de enfermería proporcione la información necesaria para los cuidados fuera del contexto controlado del ambiente hospitalario, además de minimizar los episodios de infección, muerte y aumentar la sobrevida y calidad de vida de los transplantados.

RESUMO Objetivo: mapear as evidências sobre as orientações realizadas para o autocuidado de pacientes no pós-transplante de células-tronco hematopoéticas (TCTH). Método: Scoping Review apoiada nas recomendações do Joanna Briggs Institute, com buscas entre março e abril de 2022 em bases de dados e repositórios de teses e dissertações nacionais e internacionais. Resultados: dos 11 estudos que compuseram a amostra final, as orientações tinham cunho social e pessoal, visto que o paciente do pós-transplante precisa seguir inúmeras recomendações imprescindíveis para a prevenção de infecções e complicações para o êxito do tratamento e melhoria da qualidade de vida. Conclusão: Conhecer as orientações para o autocuidado que devem ser realizadas por pacientes no pós-TCTH é fundamental para que a equipe de Enfermagem forneça as informações necessárias para os cuidados fora do contexto controlado do ambiente hospitalar, além de minimizar os episódios de infecção, morte e aumentar a sobrevida e qualidade de vida dos transplantados.

RESUMEN

ABSTRACT Objective: to map the scientific evidence on the educational technologies used to teach self-management in hematopoietic stem cell post-transplantation. Method: a scoping review, based on JBI recommendations. The searches took place between January and February 2022, in databases and repositories of dissertations and theses. The PCC strategy was used, namely: P (Population) - patients (patient participation); C (Concept) - educational technologies and self-management (instructional technology, self-management); and C (Context) - post hematopoietic stem cell transplantation (bone marrow transplantation). Studies that discussed the educational technologies used to teach self-management after hematopoietic stem cell transplantation, available in full electronically, were included. Editorials, letters to the editor and opinion articles were excluded. Duplicate studies were considered only once. The data are presented in figures and chart format. Results: sixteen studies were selected to compose the final sample, most of which showed that the most used educational technologies in the context of hospital discharge after hematopoietic stem cell transplantation are websites, software, movies, online videos or not, care plans, posters, books and booklets aimed at teaching. Conclusion: the use of educational technologies in teaching and patient health education is a reality present in services at any level of health care. The highlight of the approach to this topic is anchored in how these technologies are used and whether they are properly defined for each patient, according to the results of this study.

RESUMEN Objetivo: mapear la evidencia científica sobre las tecnologías educativas utilizadas para enseñar el automanejo en el postrasplante de células madre hematopoyéticas. Método: revisión de alcance, basado en las recomendaciones del JBI. Las búsquedas se realizaron entre enero y febrero de 2022, en bases de datos y repositorios de disertaciones y tesis. Se utilizó la estrategia PCC, a saber: P (Población) - pacientes (participación de los pacientes); C (Concepto) - tecnologías educativas y autogestión (tecnología instruccional, autogestión); y C (Contexto): postrasplante de células madre hematopoyéticas (trasplante de médula ósea). Se incluyeron estudios que discutieron las tecnologías educativas utilizadas para enseñar el autocuidado después del trasplante de células madre hematopoyéticas, disponibles en su totalidad electrónicamente. Se excluyeron editoriales, cartas al editor y artículos de opinión. Los estudios duplicados se consideraron una sola vez. Los datos se presentan en formato de tablas y figuras. Resultados: se seleccionaron 16 estudios para componer la muestra final, la mayoría de los cuales mostró que las tecnologías educativas más utilizadas en el contexto del alta hospitalaria después del trasplante de células madre hematopoyéticas son sitios web, software, películas, videos en línea o no, planes de atención, carteles, libros y folletos destinados a la enseñanza. Conclusión: el uso de tecnologías educativas en la enseñanza y educación en salud del paciente es una realidad presente en los servicios de cualquier nivel de atención a la salud. Lo más destacado del abordaje de este tema está anclado en cómo se utilizan estas tecnologías y si están bien definidas para cada paciente, según los resultados de este estudio.

RESUMO Objetivo: mapear as evidências científicas sobre as tecnologias educacionais utilizadas para o ensino da autogestão no pós-transplante de células-tronco hematopoéticas. Método: scoping review, apoiada nas recomendações do JBI. As buscas ocorreram entre janeiro e fevereiro de 2022, em bases de dados e repositórios de dissertações e teses. Utilizou-se a estratégia PCC, a saber: P (População) - pacientes (participação do paciente); C (Conceito) - tecnologias educacionais e autogestão (tecnologia instrucional, autogerenciamento); e C (Contexto) - pós-transplante de células-tronco (transplante de medula óssea). Foram incluídos estudos que discutissem sobre as tecnologias educacionais utilizadas para o ensino da autogestão no pós-transplante de células-tronco hematopoéticas, disponíveis na íntegra em meio eletrônico. Foram excluídos editoriais, cartas ao editor e artigos de opinião. Os estudos duplicados foram considerados apenas uma vez. Os dados estão apresentados em formato de figuras e quadro. Resultados: foram selecionados 16 estudos para compor a amostra final, dentre os quais, em sua maioria, evidenciaram que as tecnologias educacionais mais utilizadas no contexto de alta hospitalar no pós-transplante de células tronco-hematopoéticas são websites, softwares, filmes, vídeos online ou não, planos de cuidado, cartazes, livros e cartilhas voltados para o ensino. Conclusão: o uso das tecnologias educacionais no ensino e na educação em saúde dos pacientes é uma realidade presente nos serviços em qualquer um dos níveis de atenção à saúde. O ponto de destaque da abordagem a este tema se ancora em como essas tecnologias são utilizadas e se são definidas de forma adequada para cada paciente, conforme resultados deste estudo.

RESUMEN

Objective: To implement a quality improvement initiative to achieve an institutional targeted discharge summary distribution metric of 50% within 48 hours of patient discharge from hospital within an academic tertiary care otolaryngology-head and neck surgery department. Methods: A pre- and postintervention study was conducted. Process mapping was performed. Interventions included education and engagement, implementation of auto-authentication (distribution immediately following transcription without review by the most responsible physician), and audit and feedback. The percentage of discharge summaries dictated with the auto-authentication code was evaluated. Process measures were collected for 12 months pre- and postimplementation. Balancing measures included workload and revisions to auto-authenticated notes. Analysis included summary statistics, statistical process control charting, and unpaired t tests. Results: The mean ± SD percentage of discharge summaries distributed within 48 hours increased from 19% ± 6.4% preintervention to 54% ± 20% postintervention (P < .0001). Seventy-four percent of discharge summaries were dictated via the auto-authentication code. The target metric was met in 71% of discharges with the auto-authentication codes as compared with 26% with non-auto-authentication. The interventions did not result in any change to perceived workload, and the incidence of auto-authentication revisions was <1%. The results were sustained with an increase of 72% the following quarter. For fiscal year 2021-2022, performance remained sustained with an 85% completion rate. Discussion: Our surgical department exceeded and sustained the targeted metric for timely discharge summary distribution using a quality improvement approach. Implications for Practice: Timely distribution of discharge summaries optimizes patients' transitions of care and can be achieved through stakeholder education and engagement, auto-authentication, and audit with feedback.

RESUMEN

Electronic Medical Records (EMRs) contain clinical narrative text that is of great potential value to medical researchers. However, this information is mixed with Personally Identifiable Information (PII) that presents risks to patient and clinician confidentiality. This paper presents an end-to-end de-identification framework to automatically remove PII from Australian hospital discharge summaries. Our corpus included 600 hospital discharge summaries which were extracted from the EMRs of two principal referral hospitals in Sydney, Australia. Our end-to-end de-identification framework consists of three components: (1) Annotation: labelling of PII in the 600 hospital discharge summaries using five pre-defined categories: person, address, date of birth, individual identification number, phone/fax number; (2) Modelling: training six named entity recognition (NER) deep learning base-models on balanced and imbalanced datasets; and evaluating ensembles that combine all six base-models, the three base-models with the best F1 scores and the three base-models with the best recall scores respectively, using token-level majority voting and stacking methods; and (3) De-identification: removing PII from the hospital discharge summaries. Our results showed that the ensemble model combined using the stacking Support Vector Machine (SVM) method on the three base-models with the best F1 scores achieved excellent results with a F1 score of 99.16% on the test set of our corpus. We also evaluated the robustness of our modelling component on the 2014 i2b2 de-identification dataset. Our ensemble model, which uses the token-level majority voting method on all six base-models, achieved the highest F1 score of 96.24% at strict entity matching and the highest F1 score of 98.64% at binary token-level matching compared to two state-of-the-art methods. The end-to-end framework provides a robust solution to de-identifying clinical narrative corpuses safely. It can easily be applied to any kind of clinical narrative documents.

Asunto(s)

RESUMEN

BACKGROUND: The provision of palliative care is increasing, with many people dying in community-based settings. It is essential that communication is effective if and when patients transition from hospice to community palliative care. Past research has indicated that communication issues are prevalent during hospital discharges, but little is known about hospice discharges. METHODS: An explanatory sequential mixed methods study consisting of a retrospective review of hospice discharge letters, followed by hospice focus groups, to explore patterns in communication of palliative care needs of discharged patients and describe why these patients were being discharged. Discharge letters were extracted for key content information using a standardised form. Letters were then examined for language patterns using a linguistic methodology termed corpus linguistics. Thematic analysis was used to analyse the focus group transcripts. Findings were triangulated to develop an explanatory understanding of discharge communication from hospice care. RESULTS: We sampled 250 discharge letters from five UK hospices whereby patients had been discharged to primary care. Twenty-five staff took part in focus groups. The main reasons for discharge extracted from the letters were symptoms "managed/resolved" (75.2%), and/or the "patient wishes to die/for care at home" (37.2%). Most patients had some form of physical needs documented on the letters (98.4%) but spiritual needs were rarely documented (2.4%). Psychological/emotional needs and social needs were documented in 46.4 and 35.6% of letters respectively. There was sometimes ambiguity in "who" will be following up "what" in the discharge letters, and whether described patients' needs were resolved or ongoing for managing in the community setting. The extent to which patients received a copy of their discharge letter varied. Focus groups conveyed a lack of consensus on what constitutes "complexity" and "complex pain". CONCLUSIONS: The content and structure of discharge letters varied between hospices, although generally focused on physical needs. Our study provides insights into patterns associated with those discharged from hospice, and how policy and guidance in this area may be improved, such as greater consistency of sharing letters with patients. A patient-centred set of hospice-specific discharge letter principles could help improve future practice.

Asunto(s)

RESUMEN

Primary care providers (PCPs) receive limited information about their patients' ICU stays; we sought to understand what additional information PCPs desire to support patients' recovery following critical illness. DESIGN: Semistructured interviews with PCPs conducted between September 2020 and April 2021. SETTING: Academic health system with central quaternary-care hospital and associated Veterans Affairs medical center. SUBJECTS: Fourteen attending internal medicine or family medicine physicians working in seven clinics across Southeast Michigan (median, 10.5 yr in practice). MAIN OUTCOMES AND MEASURES: We analyzed using a modified Rigorous and Accelerated Data Reduction (RADaR) technique to identify gaps in current discharge summaries for patients with ICU stays, impacts of these gaps, and desired ICU-specific information. We employed RADaR to efficiently consolidate data in Excel Microsoft (Redmond, WA) tables across multiple formats (lists, themes, etc.). RESULTS: PCPs reported receiving limited ICU-specific information in hospital discharge summaries. PCPs often spent significant time reading inpatient records for additional information. Information desired included life-support interventions provided and duration (mechanical ventilation, dialysis, etc.), reasons for treatment decisions (code status changes, medication changes, etc.), and potential complications (delirium, dysphagia, postintensive care syndrome, etc.). Pervasive discharge gaps (ongoing needs, incidental findings, etc.) were described as worse among patients with ICU stays due to more complex illness and required interventions. Insufficient information was felt to lead to incomplete follow-up on critical issues, PCP frustration, and patient harm. PCPs stated that the COVID-19 pandemic exacerbated gaps due to decreased staffing, limited visitation policies, and reliance on telehealth follow-up visits. CONCLUSIONS AND RELEVANCE: Our results identified key data elements sought by PCPs about patients' ICU stays and suggest opportunities to improve care through developing tools/templates to provide PCPs with ICU-specific information for outpatient follow-up.

RESUMEN

Purpose: This qualitative study aimed to investigate experiences and perceptions of hospital physicians regarding the discharging process, focusing on information transfer regarding medications. Methods: By purposive sampling three focus groups were formed. To facilitate discussions and maintain consistency, a semi-structured interview guide was used. Discussions were audio recorded and transcribed verbatim. Qualitative content analysis was used to analyze the anonymized data. A confirmatory analysis concluded that the main findings were supported by data. Results: Identified obstacles were divided into three categories with two sub-categories each: Infrastructure; IT-systems currently used are suboptimal and complex. Hospital and primary care use different electronic medical records, complicating matters. The work organization is not helping with time scarcity and lack of continuity. Distinct routines could help create continuity but are not always in place, known, and/or followed. Physician: knowledge and education in the systems is not always provided nor prioritized. Understanding the consequences of not following routines and taking responsibility regarding the medications list is important. Not everyone has the self-reliance or willingness to do so. Patient/next of kin: For patients to provide information on medications used is not always easy when hospitalized. Understanding information provided can be hard, especially when medical jargon is used and there is no one available to provide support. A central theme, "We're only human", encompasses how physicians do their best despite difficult conditions. Conclusion: There are several obstacles in transferring information regarding medications at discharge. Issues regarding infrastructure are seldom possible for the individual physician to influence. However, several issues raised by the participating physicians are possible to act upon. In doing so medication errors in care transitions might decrease and information transfer at discharge might improve.

RESUMEN

BACKGROUND: Electronic discharge communication tools (EDCTs) are increasingly common in pediatric emergency departments (EDs). These tools have been shown to improve patient-centered communication, support postdischarge care at home, and reduce unnecessary return visits to the ED. OBJECTIVE: This study aimed to map and assess the evidence base for EDCTs used in pediatric EDs according to their functionalities, intended purpose, implementation context features, and outcomes. METHODS: A systematic review was conducted following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) procedures for identification, screening, and eligibility. A total of 7 databases (EBSCO, MEDLINE, CINAHL, PsycINFO, EMBASE Scopus, and Web of Science) were searched for studies published between 1989 and 2021. Studies evaluating discharge communication-related outcomes using electronic tools (eg, text messages, videos, and kiosks) in pediatric EDs were included. In all, 2 researchers independently assessed the eligibility. Extracted data related to study identification, methodology, settings and demographics, intervention features, outcome implementation features, and practice, policy, and research implications. The Mixed Method Appraisal Tool was used to assess methodological quality. The synthesis of results involved structured tabulation, vote counting, recoding into common metrics, inductive thematic analysis, descriptive statistics, and heat mapping. RESULTS: In total, 231 full-text articles and abstracts were screened for review inclusion with 49 reports (representing 55 unique tools) included. In all, 70% (26/37) of the studies met at least three of five Mixed Method Appraisal Tool criteria. The most common EDCTs were videos, text messages, kiosks, and phone calls. The time required to use the tools ranged from 120 seconds to 80 minutes. The EDCTs were evaluated for numerous presenting conditions (eg, asthma, fracture, head injury, fever, and otitis media) that required a range of at-home care needs after the ED visit. The most frequently measured outcomes were knowledge acquisition, caregiver and patient beliefs and attitudes, and health service use. Unvalidated self-report measures were typically used for measurement. Health care provider satisfaction or system-level impacts were infrequently measured in studies. The directionality of primary outcomes pointed to positive effects for the primary measure (44/55, 80%) or no significant difference (10/55, 18%). Only one study reported negative findings, with an increase in return visits to the ED after receiving the intervention compared with the control group. CONCLUSIONS: This review is the first to map the broad literature of EDCTs used in pediatric EDs. The findings suggest a promising evidence base, demonstrating that EDCTs have been successfully integrated across clinical contexts and deployed via diverse technological modalities. Although caregiver and patient satisfaction with EDCTs is high, future research should use robust trials using consistent measures of communication quality, clinician experience, cost-effectiveness, and health service use to accumulate evidence regarding these outcomes. TRIAL REGISTRATION: PROSPERO CRD42020157500; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=157500.