RESUMEN
BACKGROUND: The underrepresentation of women in leadership remains a pervasive issue, prompting a critical examination of support mechanisms within professional settings. Previous studies have identified challenges women face, ranging from limited visibility to barriers to career advancement. This survey aims to investigate perceptions regarding the effectiveness of women's leadership programs, mentoring initiatives, and a specialized communication course. Particularly it specifically targets addressing the challenges encountered by professional women. METHODS: This multi-center, observational, international online survey was developed in partnership between ESICM NEXT and the ESICM Diversity and Inclusiveness Monitoring Group for Healthcare. Invitations to participate were distributed to both females and men through emails and social networks. Data were collected from April 1, 2023, through October 1, 2023. RESULTS: Out of 354 respondents, 90 were men (25.42%) and 264 were women (74.58%). Among them, 251 completed the survey, shedding light on the persistent challenges faced by women in leadership roles, with 10%-50% of respondents holding such positions. Women's assertiveness is viewed differently, with 65% recognizing barriers such as harassment. Nearly half of the respondent's experience interruptions in meetings. Only 47.4% receiving conference invitations, with just over half accepting them. A mere 12% spoke at ESICM conferences in the last three years, receiving limited support from directors and colleagues, indicating varied obstacles for female professionals. Encouraging family participation, reducing fees, providing childcare, and offering economic support can enhance conference involvement. Despite 55% applying for ESICM positions, barriers like mobbing, harassment, lack of financial support, childcare, and language barriers were reported. Only 14% had access to paid family leave, while 32% benefited from subsidized childcare. Participation in the Effective Communication Course on Career Advancement Goals and engagement in women's leadership and mentoring programs could offer valuable insights and growth opportunities. Collaborating with Human Resources and leadership allies is crucial for overcoming barriers and promoting women's career growth. CONCLUSIONS: The urgency of addressing identified barriers to female leadership in intensive care medicine is underscored by the survey's comprehensive insights. A multifaceted and intersectional approach, considering sexism, structural barriers, and targeted strategies, is essential.
RESUMEN
BACKGROUND: Artificial intelligence, through improved data management and automated summarisation, has the potential to enhance intensive care unit (ICU) care. Large language models (LLMs) can interrogate and summarise large volumes of medical notes to create succinct discharge summaries. In this study, we aim to investigate the potential of LLMs to accurately and concisely synthesise ICU discharge summaries. METHODS: Anonymised clinical notes from ICU admissions were used to train and validate a prompting structure in three separate LLMs (ChatGPT, GPT-4 API and Llama 2) to generate concise clinical summaries. Summaries were adjudicated by staff intensivists on ability to identify and appropriately order a pre-defined list of important clinical events as well as readability, organisation, succinctness, and overall rank. RESULTS: In the development phase, text from five ICU episodes was used to develop a series of prompts to best capture clinical summaries. In the testing phase, a summary produced by each LLM from an additional six ICU episodes was utilised for evaluation. Overall ability to identify a pre-defined list of important clinical events in the summary was 41.5 ± 15.2% for GPT-4 API, 19.2 ± 20.9% for ChatGPT and 16.5 ± 14.1% for Llama2 (p = 0.002). GPT-4 API followed by ChatGPT had the highest score to appropriately order a pre-defined list of important clinical events in the summary as well as readability, organisation, succinctness, and overall rank, whilst Llama2 scored lowest for all. GPT-4 API produced minor hallucinations, which were not present in the other models. CONCLUSION: Differences exist in large language model performance in readability, organisation, succinctness, and sequencing of clinical events compared to others. All encountered issues with narrative coherence and omitted key clinical data and only moderately captured all clinically meaningful data in the correct order. However, these technologies suggest future potential for creating succinct discharge summaries.