A rapid review on current and potential uses of large language models in nursing

BACKGROUND

The application of large language models across commercial and consumer contexts has grown exponentially in recent years. However, a gap exists in the literature on how large language models can support nursing practice, education, and research. This study aimed to synthesize the existing literature on current and potential uses of large language models across the nursing profession.

METHODS

A rapid review of the literature, guided by Cochrane rapid review methodology and PRISMA reporting standards, was conducted. An expert health librarian assisted in developing broad inclusion criteria to account for the emerging nature of literature related to large language models. Three electronic databases (i.e., PubMed, CINAHL, and Embase) were searched to identify relevant literature in August 2023. Articles that discussed the development, use, and application of large language models within nursing were included for analysis.

RESULTS

The literature search identified a total of 2028 articles that met the inclusion criteria. After systematically reviewing abstracts, titles, and full texts, 30 articles were included in the final analysis. Nearly all (93 %; n = 28) of the included articles used ChatGPT as an example, and subsequently discussed the use and value of large language models in nursing education (47 %; n = 14), clinical practice (40 %; n = 12), and research (10 %; n = 3). While the most common assessment of large language models was conducted by human evaluation (26.7 %; n = 8), this analysis also identified common limitations of large language models in nursing, including lack of systematic evaluation, as well as other ethical and legal considerations.

DISCUSSION

This is the first review to summarize contemporary literature on current and potential uses of large language models in nursing practice, education, and research. Although there are significant opportunities to apply large language models, the use and adoption of these models within nursing have elicited a series of challenges, such as ethical issues related to bias, misuse, and plagiarism.

CONCLUSION

Given the relative novelty of large language models, ongoing efforts to develop and implement meaningful assessments, evaluations, standards, and guidelines for applying large language models in nursing are recommended to ensure appropriate, accurate, and safe use. Future research along with clinical and educational partnerships is needed to enhance understanding and application of large language models in nursing and healthcare.

Technological Challenges and Solutions in Emergency Remote Teaching for Nursing: An International Cross-Sectional Survey

OBJECTIVES

With the sudden global shift to online learning modalities, this study aimed to understand the unique challenges and experiences of emergency remote teaching (ERT) in nursing education.

METHODS

We conducted a comprehensive online international cross-sectional survey to capture the current state and firsthand experiences of ERT in the nursing discipline. Our analytical methods included a combination of traditional statistical analysis, advanced natural language processing techniques, latent Dirichlet allocation using Python, and a thorough qualitative assessment of feedback from open-ended questions.

RESULTS

We received responses from 328 nursing educators from 18 different countries. The data revealed generally positive satisfaction levels, strong technological self-efficacy, and significant support from their institutions. Notably, the characteristics of professors, such as age (p = 0.02) and position (p = 0.03), influenced satisfaction levels. The ERT experience varied significantly by country, as evidenced by satisfaction (p = 0.05), delivery (p = 0.001), teacher-student interaction (p = 0.04), and willingness to use ERT in the future (p = 0.04). However, concerns were raised about the depth of content, the transition to online delivery, teacher-student interaction, and the technology gap.

CONCLUSIONS

Our findings can help advance nursing education. Nevertheless, collaborative efforts from all stakeholders are essential to address current challenges, achieve digital equity, and develop a standardized curriculum for nursing education.

Evaluating the representation of disaster hazards in SNOMED CT: gaps and opportunities

OBJECTIVE

Climate change, an underlying risk driver of natural disasters, threatens the environmental sustainability, planetary health, and sustainable development goals. Incorporating disaster-related health impacts into electronic health records helps to comprehend their impact on populations, clinicians, and healthcare systems. This study aims to: (1) map the United Nations Office for Disaster Risk Reduction and International Science Council (UNDRR-ISC) Hazard Information Profiles to SNOMED CT International, a clinical terminology used by clinicians, to manage patients and provide healthcare services; and (2) to determine the extent of clinical terminologies available to capture disaster-related events.

MATERIALS AND METHODS

Concepts related to disasters were extracted from the UNDRR-ISC's Hazard Information Profiles and mapped to a health terminology using a procedural framework for standardized clinical terminology mapping. The mapping process involved evaluating candidate matches and creating a final list of matches to determine concept coverage.

RESULTS

A total of 226 disaster hazard concepts were identified to adversely impact human health. Chemical and biological disaster hazard concepts had better representation than meteorological, hydrological, extraterrestrial, geohazards, environmental, technical, and societal hazard concepts in SNOMED CT. Heatwave, drought, and geographically unique disaster hazards were not found in SNOMED CT.

CONCLUSION

To enhance clinical reporting of disaster hazards and climate-sensitive health outcomes, the poorly represented and missing concepts in SNOMED CT must be included. Documenting the impacts of climate change on public health using standardized clinical terminology provides the necessary real time data to capture climate-sensitive outcomes. These data are crucial for building climate-resilient healthcare systems, enhanced public health disaster responses and workflows, tracking individual health outcomes, supporting disaster risk reduction modeling, and aiding in disaster preparedness, response, and recovery efforts.

Representation of Environmental Concepts Associated with Health Impacts in Computer Standardized Clinical Terminologies

OBJECTIVE

To evaluate the representation of environmental concepts associated with health impacts in standardized clinical terminologies.

METHODS

This study used a descriptive approach with methods informed by a procedural framework for standardized clinical terminology mapping. The United Nations Global Indicator Framework for the Sustainable Development Goals and Targets was used as the source document for concept extraction. The target terminologies were the Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT) and the International Classification for Nursing Practice (ICNP). Manual and automated mapping methods were utilized. The lists of candidate matches were reviewed and iterated until a final mapping match list was achieved.

RESULTS

A total of 119 concepts with 133 mapping matches were added to the final SNOMED CT list. Fifty-three (39.8%) were direct matches, 37 (27.8%) were narrower than matches, 35 (26.3%) were broader than matches, and 8 (6%) had no matches. A total of 26 concepts with 27 matches were added to the final ICNP list. Eight (29.6%) were direct matches, 4 (14.8%) were narrower than, 7 (25.9%) were broader than, and 8 (29.6%) were no matches.

CONCLUSION

Following this evaluation, both strengths and gaps were identified. Gaps in terminology representation included concepts related to cost expenditures, affordability, community engagement, water, air and sanitation. The inclusion of these concepts is necessary to advance the clinical reporting of these environmental and sustainability indicators. As environmental concepts encoded in standardized terminologies expand, additional insights into data and health conditions, research, education, and policy-level decision-making will be identified.

Assessing the carbon footprint of digital health interventions: a scoping review

OBJECTIVE

Integration of environmentally sustainable digital health interventions requires robust evaluation of their carbon emission life-cycle before implementation in healthcare. This scoping review surveys the evidence on available environmental assessment frameworks, methods, and tools to evaluate the carbon footprint of digital health interventions for environmentally sustainable healthcare.

MATERIALS AND METHODS

Medline (Ovid), Embase (Ovid). PsycINFO (Ovid), CINAHL, Web of Science, Scopus (which indexes IEEE Xplore, Springer Lecture Notes in Computer Science and ACM databases), Compendex, and Inspec databases were searched with no time or language constraints. The Systematic Reviews and Meta-analyses Extension for Scoping Reviews (PRISMA_SCR), Joanna Briggs Scoping Review Framework, and template for intervention description and replication (TiDiER) checklist were used to structure and report the findings.

RESULTS

From 3299 studies screened, data was extracted from 13 full-text studies. No standardised methods or validated tools were identified to systematically determine the environmental sustainability of a digital health intervention over its full life-cycle from conception to realisation. Most studies (n = 8) adapted publicly available carbon calculators to estimate telehealth travel-related emissions. Others adapted these tools to examine the environmental impact of electronic health records (n = 2), e-prescriptions and e-referrals (n = 1), and robotic surgery (n = 1). One study explored optimising the information system electricity consumption of telemedicine. No validated systems-based approach to evaluation and validation of digital health interventions could be identified.

CONCLUSION

There is a need to develop standardised, validated methods and tools for healthcare environments to assist stakeholders to make informed decisions about reduction of carbon emissions from digital health interventions.

The Untapped Potential of Nursing and Allied Health Data for Improved Representation of Social Determinants of Health and Intersectionality in Artificial Intelligence Applications: A Rapid Review

OBJECTIVES

The objective of this paper is to draw attention to the currently underused potential of clinical documentation by nursing and allied health professions to improve the representation of social determinants of health (SDoH) and intersectionality data in electronic health records (EHRs), towards the development of equitable artificial intelligence (AI) technologies.

METHODS

A rapid review of the literature on the inclusion of nursing and allied health data and the nature of health equity information representation in the development and/or use of artificial intelligence approaches alongside expert perspectives from the International Medical Informatics Association (IMIA) Student and Emerging Professionals Working Group.

RESULTS

Consideration of social determinants of health and intersectionality data are limited in both the medical AI and nursing and allied health AI literature. As a concept being newly discussed in the context of AI, the lack of discussion of intersectionality in the literature was unsurprising. However, the limited consideration of social determinants of health was surprising, given its relatively longstanding recognition and the importance of representation of the features of diverse populations as a key requirement for equitable AI.

CONCLUSIONS

Leveraging the rich contextual data collected by nursing and allied health professions has the potential to improve the capture and representation of social determinants of health and intersectionality. This will require addressing issues related to valuing AI goals (e.g., diagnostics versus supporting care delivery) and improved EHR infrastructure to facilitate documentation of data beyond medicine. Leveraging nursing and allied health data to support equitable AI development represents a current open question for further exploration and research.

Mapping of Wound Infection Concepts

Wound infection is a serious health care complication. Standardized clinical terminologies could be leveraged to support the early identification of wound infection. The purpose of this study was to evaluate the representation of wound infection assessment and diagnosis concepts (N=26) in SNOMED CT and ICNP, using a synthesized procedural framework. A total of 13/26 (50%) assessment and diagnosis concepts had exact matches in SNOMED CT and 2/7 (29%) diagnosis concepts had exact matches in ICNP. This study demonstrated that the source concepts were moderately well represented in SNOMED CT and ICNP; however, further work is necessary to increase the representation of diagnostic infection types. The use of the framework facilitated a systematic, transparent, and repeatable mapping process, with opportunity to extend.

Comparison of terminology mapping methods for nursing wound care knowledge representation

BACKGROUND

Standardized clinical terminologies are increasingly used to design and support advanced information systems. In order to examine the representativeness of these terminologies for different professional groups or clinical areas, researchers may perform different methods of terminology mapping.

OBJECTIVE

The purpose of this study was to evaluate the ability of four mapping methods to identify concepts related to wound care in SNOMED CT.

METHODS

A class diagram of 107 concepts was developed to represent the nursing context of wound assessment, wound diagnosis, and goal of care for wound management. All concepts were mapped to SNOMED CT and identified as a direct match, a one-to-many match, or no match using four mapping methods (manual, automated, comparison, and concordance). The manual, automated and comparison methods produced candidate lists of SNOMED CT concepts, which were then used by two nursing wound care experts. The experts completed concordance mapping, which produced the final list. The SNOMED CT concepts from the manual, automated and comparison mappings were compared to the concordance mapping to generate a proportion of representation by each mapping method.

RESULTS

The manual, automated and comparison mappings produced partial lists of unique candidate concept matches not found in the other mapping methods. The concordance mapping produced a final list which included: 43 terms (40%) that had direct matches, 2 terms (2%) that had one-to-many matches, and 62 terms (58%) that had no matches to SNOMED CT. All mapping methods were necessary to achieve the representativeness captured in the final list.

CONCLUSION

To increase the representativeness of candidate mapping lists, multiple mapping methods and considerations may be necessary.

Exploring prevalence of wound infections and related patient characteristics in homecare using natural language processing

We aimed to create and validate a natural language processing algorithm to extract wound infection-related information from nursing notes. We also estimated wound infection prevalence in homecare settings and described related patient characteristics. In this retrospective cohort study, a natural language processing algorithm was developed and validated against a gold standard testing set. Cases with wound infection were identified using the algorithm and linked to Outcome and Assessment Information Set data to identify related patient characteristics. The final version of the natural language processing vocabulary contained 3914 terms and expressions related to the presence of wound infection. The natural language processing algorithm achieved overall good performance (F-measure = 0.88). The presence of wound infection was documented for 1.03% (n = 602) of patients without wounds, for 5.95% (n = 3232) of patients with wounds, and 19.19% (n = 152) of patients with wound-related hospitalisation or emergency department visits. Diabetes, peripheral vascular disease, and skin ulcer were significantly associated with wound infection among homecare patients. Our findings suggest that nurses frequently document wound infection-related information. The use of natural language processing demonstrated that valuable information can be extracted from nursing notes which can be used to improve our understanding of the care needs of people receiving homecare. By linking findings from clinical nursing notes with additional structured data, we can analyse related patients' characteristics and use them to develop a tailored intervention that may potentially lead to reduced wound infection-related hospitalizations.

Visibility of Community Nursing Within an Administrative Health Classification System: Evaluation of Content Coverage

Background

The World Health Organization is in the process of developing an international administrative classification for health called the International Classification of Health Interventions (ICHI). The purpose of ICHI is to provide a tool for supporting intervention reporting and analysis at a global level for policy development and beyond. Nurses represent the largest resource carrying out clinical interventions in any health system. With the shift in nursing care from hospital to community settings in many countries, it is important to ensure that community nursing interventions are present in any international health information system. Thus, an investigation into the extent to which community nursing interventions were covered in ICHI was needed.

Objective

The objectives of this study were to examine the extent to which International Classification for Nursing Practice (ICNP) community nursing interventions were represented in the ICHI administrative classification system, to identify themes related to gaps in coverage, and to support continued advancements in understanding the complexities of knowledge representation in standardized clinical terminologies and classifications.

Methods

This descriptive study used a content mapping approach in 2 phases in 2018. A total of 187 nursing intervention codes were extracted from the ICNP Community Nursing Catalogue and mapped to ICHI. In phase 1, 2 coders completed independent mapping activities. In phase 2, the 2 coders compared each list and discussed concept matches until consensus on ICNP-ICHI match and on mapping relationship was reached.

Results

The initial percentage agreement between the 2 coders was 47% (n=88), but reached 100% with consensus processes. After consensus was reached, 151 (81%) of the community nursing interventions resulted in an ICHI match. A total of 36 (19%) of community nursing interventions had no match to ICHI content. A total of 100 (53%) community nursing interventions resulted in a broader ICHI code, 9 (5%) resulted in a narrower ICHI code, and 42 (23%) were considered equivalent. ICNP concepts that were not represented in ICHI were thematically grouped into the categories family and caregivers, death and dying, and case management.

Conclusions

Overall, the content mapping yielded similar results to other content mapping studies in nursing. However, it also found areas of missing concept coverage, difficulties with interterminology mapping, and further need to develop mapping methods.

Regulation of androgen receptor mRNA and protein in the rat testis by testosterone

Adult rats were treated with ethane dimethane sulphonate (EDS), an agent that destroys Leydig cells. Within 5 days after EDS treatment, the levels of testosterone (T) in the circulation and in the testis were decreased to very low values, which makes it possible to manipulate the testicular T concentration through administration of exogenous T. Spermatogenesis was not markedly affected within 5 days after EDS treatment, also not in the absence of T administration. In testes of EDS-treated rats, the androgen receptor mRNA (ARmRNA) level remained unaltered for 5 days. In ventral prostate, however, this treatment caused a pronounced upregulation of the level of ARmRNA, which could be counteracted by implantation of silastic T implants immediately after EDS treatment. In EDS-treated rats carrying a T implant and in untreated rats, the same number of specific [3H]R1881 binding sites was observed using a total testis nuclear fraction (Scatchard analysis). In testes from EDS-treated rats without T implants, androgen receptors (AR) did not fractionate into the nuclear fraction; however, the total testicular AR content in these animals (measured by nuclear [3H]R1881 binding after receptor transformation through injection of a high dose of T, 2 h before killing the rats) remained unaltered. Immunoprecipitation and Western blotting using anti N-terminal antibodies seemed to indicate that the total testicular amount of AR protein in the EDS-treated rats was very low as compared to that in EDS-treated rats carrying T implants and in untreated rats. Even after receptor retransformation (by injection of a high dose of T) the receptors were not quantitatively detected by immunoprecipitation and Western blotting. This may point to a structural modification of the AR that occurs in the prolonged absence of androgens.

Laryngeal complications in a patient with inactive systemic lupus erythematosus

Laryngeal complications in systemic lupus erythematosus (SLE) are rarely described. They range from hoarseness to life-threatening respiratory distress. To our knowledge, previous reports describe laryngeal involvement with SLE occurring only during periods of active disease. We saw a patient with inactive SLE in whom hoarseness and exertional dyspnea developed as a result of arytenoiditis and vocal cord paresis during steroid tapering. The condition responded dramatically to readjustment of her steroid dosage. Involvement of the larynx with SLE is a potentially life-threatening complication and may occur in patients with either active or inactive disease. It is an indication for close observation and steroid therapy in patients with SLE.

Pemphigus of the air and food passages

Pemphigus vulgaris is one among many bullous diseases which involve the mucous membranes of the oropharynx and the larynx. The pernicious nature and previous high mortality of this disease have been greatly reduced with early diagnosis and the appropriate use of corticosteroids and immunosuppressive agents. Thirteen patients with pemphigus vulgaris were seen at Rush-Presbyterian-St. Luke's Medical Center from 1970 through 1976. All patients had moderate-to-severe generalized eruptions and were biopsy-positive for pemphigus vulgaris. A moderate prednisone dosage of 80 to 120 mg/day in moderate-to-severe cases was utilized in 11 out of 13 patients. All patients were treated initially with prednisone only, and after control of the acute generalized eruptions was achieved, Cytoxan® was added to the regimen to allow reduction of the prednisone dosage. One patient in our series died as a result of disseminated herpes simplex, probably secondary to high-dose corticosteroid treatment. Mortality in our series was 7.6% This investigation suggests that lower prednisone doses of 80 to 120 mg/day, except in recalcitrant cases, may be efficacious in the treatment of pemphigus vulgaris, especially in conjunction with adjuvant immunosuppressive therapy.