Conectar
With ambient listening systems increasingly adopted in healthcare, analyzing clinician-patient conversations has become essential. The Omaha System is a standardized terminology for documenting patient care, classifying health problems into four domains across 42 problems and 377 signs/symptoms. Manually identifying and mapping these problems is time-consuming and labor-intensive. This study aims to automate health problem identification from clinician-patient conversations using large language models (LLMs) with retrieval-augmented generation (RAG).
Using the Omaha System framework, we analyzed 5118 utterances from 22 clinician-patient encounters in home healthcare. RAG-enhanced LLMs detected health problems and mapped them to Omaha System terminology. We evaluated different model configurations, including embedding models, context window sizes, parameter settings (top k, top p), and prompting strategies (zero-shot, few-shot, and chain-of-thought). Three LLMs—Llama 3.1-8B-Instruct, GPT-4o-mini, and GPT-o3-mini—were compared using precision, recall, and F1-score against expert annotations.
The optimal configuration used a 1-utterance context window, top k = 15, top p = 0.6, and few-shot learning with chain-of-thought prompting. GPT-4o-mini achieved the highest F1-score (0.90) for both problem and sign/symptom identification, followed by GPT-o3-mini (0.83/0.82), while Llama 3.1-8B-Instruct performed worst (0.73/0.72).
Using the Omaha System, LLMs with RAG effectively automate health problem identification in clinical conversations. This approach can enhance documentation completeness, reduce documentation burden, and potentially improve patient outcomes through more comprehensive problem identification, translating into tangible improvements in clinical efficiency and care delivery.
Automating health problem identification from clinical conversations can improve documentation accuracy, reduce burden, and ensure alignment with standardized frameworks like the Omaha System, enhancing care quality and continuity in home healthcare.
To explore how nursing teams (co)organise their work environment by going beyond caregiving.
A descriptive qualitative study with a phenomenological approach.
Semi-structured group interviews were conducted in 2022 with nurses and managers from 18 nursing teams in a general hospital located in the Netherlands. In each group interview, 2–3 participants per team took part. The interviews were audio-recorded, transcribed verbatim, and analysed using thematic analysis.
The analysis identified four main themes contributing to a more supportive work environment: (1) embracing diversity, (2) stretching nursing roles, (3) raising voices, and (4) aligning nurses and managers. These themes show how nursing teams go beyond caregiving and actively shape and co–organise their work environment.
Teams that extend their roles create more supportive work environments, enhancing patient care and professional development. These findings contribute to the understanding of organising professionalism in nursing and provide insights for nursing teams striving to improve their work environments.
Nursing teams can use the four themes—as team features—to reflect upon their organising roles and engagement with their work environment. Our findings offer practical insights for nurses with responsibilities in areas such as team development and leadership. They can focus on team diversity, voicing, stretching roles, and organisational alignment, and facilitate their teams to become more assertive.
The Consolidated criteria for Reporting Qualitative research guideline was followed.
No patient or public involvement.
To evaluate the impact of spatial separation on patient flow in the emergency department.
This was a retrospective, time-and-motion analysis conducted from 15 to 22 August, 2022 at the emergency department of a tertiary hospital in Kuala Lumpur, Malaysia. During this duration, spatial separation was implemented in critical and semi-critical zones to separate patients with symptoms of respiratory infections into respiratory area, and patients without into non-respiratory area. This study adhered to the Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) guidelines.
Patients triaged to critical and semi-critical zones were included in this study. Timestamps of patient processes in emergency department until patient departure were documented.
The emergency department length-of-stay was longer in respiratory area compared to non-respiratory area; 527 min (381–698) versus 390 min (285–595) in critical zone and 477 min (312–739) versus 393 min (264–595) in semi-critical zone. In critical zone, time intervals of critical flow processes and compliance to hospital benchmarks were similar in both areas. More patients in respiratory area were managed within the arrival-to-contact ≤30 min benchmark and more patients in non-respiratory area had emergency department length-of-stay ≤8 h.
The implementation of spatial separation in infection control should address decision-to-departure delays to minimise emergency department length of stay.
The study evaluated the impact of spatial separation on patient flow in the emergency department. Emergency department length-of-stay was significantly prolonged in the respiratory area. Hospital administrators and policymakers can optimise infection control protocols measures in emergency departments, balancing infection control measures with efficient patient care delivery.
STROBE guidelines.
None.
The study obtained ethics approval from the institution's Medical Ethics Committee (MREC ID NO: 20221113–11727).
The author has checked and make sure our submission has conformed to the Journal's statistical guideline. There is a statistician on the author team (Noor Azhar).
Identifying health problems in audio-recorded patient–nurse communication is important to improve outcomes in home healthcare patients who have complex conditions with increased risks of hospital utilization. Training machine learning classifiers for identifying problems requires resource-intensive human annotation.
To generate synthetic patient–nurse communication and to automatically annotate for common health problems encountered in home healthcare settings using GPT-4. We also examined whether augmenting real-world patient–nurse communication with synthetic data can improve the performance of machine learning to identify health problems.
Secondary data analysis of patient–nurse verbal communication data in home healthcare settings.
The data were collected from one of the largest home healthcare organizations in the United States. We used 23 audio recordings of patient–nurse communications from 15 patients. The audio recordings were transcribed verbatim and manually annotated for health problems (e.g., circulation, skin, pain) indicated in the Omaha System Classification scheme. Synthetic data of patient–nurse communication were generated using the in-context learning prompting method, enhanced by chain-of-thought prompting to improve the automatic annotation performance. Machine learning classifiers were applied to three training datasets: real-world communication, synthetic communication, and real-world communication augmented by synthetic communication.
Average F1 scores improved from 0.62 to 0.63 after training data were augmented with synthetic communication. The largest increase was observed using the XGBoost classifier where F1 scores improved from 0.61 to 0.64 (about 5% improvement). When trained solely on either real-world communication or synthetic communication, the classifiers showed comparable F1 scores of 0.62–0.61, respectively.
Integrating synthetic data improves machine learning classifiers' ability to identify health problems in home healthcare, with performance comparable to training on real-world data alone, highlighting the potential of synthetic data in healthcare analytics.
This study demonstrates the clinical relevance of leveraging synthetic patient–nurse communication data to enhance machine learning classifier performances to identify health problems in home healthcare settings, which will contribute to more accurate and efficient problem identification and detection of home healthcare patients with complex health conditions.
To explore relatives' needs in terms of bereavement care during euthanasia processes, how healthcare providers respond to these needs, and the degree of commonality between relatives' and healthcare providers' reports.
A phenomenological design was employed, utilising reflexive thematic analysis to examine interviews conducted with relatives (N = 19) and healthcare providers (N = 47).
Relatives' needs throughout euthanasia processes are presented in five main themes and several subthemes, with similar findings between both sets of participants. Although relatives infrequently communicated their needs explicitly to healthcare providers, they appreciated it when staff proactively met their needs. Healthcare providers aimed to assist with the relatives' grief process by tending to their specific needs. However, aftercare was not consistently offered, but relatives did not have high expectations for professional follow-up care.
Our research offers important directions for healthcare professionals, empowering them to provide needs-based bereavement care during euthanasia processes. Moreover, it emphasises the importance of recognising the unique needs of relatives and proactively addressing them in the period before the loss to positively contribute to relatives' grief process.
Insights into relatives' needs in the context of euthanasia. Good practices on how healthcare providers can attend to relatives' needs before, during and after the loss
Current literature and guidelines on needs-based bereavement care in the context of euthanasia and, more generally, assisted dying, are limited. These findings provide concrete directions for practice in supporting (nearly) bereaved relatives in the context of euthanasia, potentially mitigating adverse health outcomes.
Standards for Reporting Qualitative Research (SRQR checklist).
Relatives of deceased cancer patients were involved in the conduct of the study.
The aim of this research study is to collaboratively generate insights in the current institutional long-term care environment for activity and mobility of older adults, and of solutions that could be used to increase the activity and improve the mobility of the older adults.
This research constitutes a qualitative study with a critical approach.
Data were collected using photo-elicitation in four long-term care units in Finland during the spring of 2022. Older adults participated in individual data collection sessions which combined photographing and discussion. Staff members individually took photographs and later participated in a group discussion based on the photographs. Reflexive thematic analysis was used to analyse all data together.
Ten older adults and 12 staff members participated in the research study. Four themes were identified: (1) facilities should be designed and equipped for their users, (2) moving in the institutional environment, (3) passivity as a norm, and (4) nurses should act differently and have the resources to do so.
To increase the activity and improve the mobility of older adults, improvements are needed in terms of the design of facilities, opportunities for freedom of movement, outdoor activity, daily life activities, exercise, nurses' role in activating older adults and resources.
Increased attention to the support of activity and mobility could benefit older adults in institutional long-term care. Physical activity promotion should be incorporated as an integral part of nursing practice.
Directors of units were consulted when planning the study. Older adults and nurses contributed to the data collection and interpretation of data.
What problem did the study address? ○Older adults have recurrently been reported as living inactive lives in institutional long-term care. ○There is evidence of the relationship between the environment and the activity and mobility of older adults, but there seems to be a research-practice gap in terms of implementing activity- and mobility-promoting environments. ○Older adults and staff members are important in developing practice and change-oriented knowledge that can be used to increase the activity and improve the mobility of older adults in institutional long-term care.
What were the main findings? ○Various environmental improvements are recommended to increase the activity and improve the mobility of older adults in institutional long-term care settings. ○Improvements for the design of facilities, opportunities for freedom of movement, outdoor activity, daily life activities, exercise, nurses' role in activating older adults and resources for activity support would benefit older adults' activity and mobility.
Where and on whom will the research have an impact? ○Increasing the activity of older adults requires better activity promotion and mobility support by nurses in institutional care. Sufficient education and resources should be organized for activity promotion, in addition to a care and organizational culture that values activity. ○Environmental aspects to promote activity and mobility need to be considered already at the planning, building and renovating phases of facilities. ○Policymakers and care organizers should consider evidence of the harms and benefits of different institutional living environments when making decisions on organizing care.
The study is reported using the Consolidated Criteria for Reporting Qualitative Research (COREQ).
FreshRSS 