Introduction: As artificial intelligence systems like large language models (LLM) and natural language processing advance, the need to evaluate their utility within medicine and medical education grows. As medical research publications continue to grow exponentially, AI systems offer valuable opportunities to condense and synthesize information, especially in underrepresented areas such as Sleep Medicine. The present study aims to compare summarization capacity between LLM generated summaries of sleep medicine research article abstracts, to summaries generated by Medical Student (humans) and to evaluate if the research content, and literary readability summarized is retained comparably.Methods: A collection of three AI-generated and human-generated summaries of sleep medicine research article abstracts were shared with 19 study participants (medical students) attending a sleep medicine conference. Participants were blind as to which summary was human or LLM generated. After reading both human and AI-generated research summaries participants completed a 1–5 Likert scale survey on the readability of the extracted writings. Participants also answered article-specific multiple-choice questions evaluating their comprehension of the summaries, as a representation of the quality of content retained by the AI-generated summaries.Results: An independent sample t-test between the AI-generated and human-generated summaries comprehension by study participants revealed no significant difference between the Likert readability ratings (p = 0.702). A chi-squared test of proportions revealed no significant association (χ² = 1.485, p = 0.223), and a McNemar test revealed no significant association between summary type and the proportion of correct responses to the comprehension multiple choice questions (p = 0.289).Discussion: Some limitations in this study were a small number of participants and user bias. Participants attended at a sleep conference and study summaries were all from sleep medicine journals. Lastly the summaries did not include graphs, numbers, and pictures, and thus were limited in material extraction. While the present analysis did not demonstrate a significant difference among the readability and content quality between the AI and human-generated summaries, limitations in the present study indicate that more research is needed to objectively measure, and further define strengths and weaknesses of AI models in condensing medical literature into efficient and accurate summaries.

Simulation labs provide trainees the opportunity to practice procedures in a safe, controlled, nonjudgmental environment. It is unclear which teaching method leads to the highest levels of trainee skill competency when learning complex simulated procedures, such as lumbar puncture. First-year medical students participated in a randomized controlled trial of an early-exposure simulated lumbar puncture (sLP) workshop. All were randomized to 1 of 2 teaching methods: 1) traditional "see one, do one" method or 2) Peyton's 4-step method. Students were taught how to perform an sLP based on the specific teaching method. Competence during sLP attempts was assessed using binary checklists, and student confidence was assessed using pre- and post-workshop surveys. Independent t tests and bivariate correlations were performed. Thirty-five first-year medical students participated in the sLP workshops. There were no statistically significant differences between the "see one, do one" method and Peyton's 4-step teaching method in checklist scores (P = .121, Cohen's d = 0.540) or change in confidence (P = .631, Cohen's d = 0.164). The difference in the speed of task completion favored Peyton's teaching method (P = .044, Cohen's d = -0.711). None of these outcomes demonstrated a significant correlation with each other within the cohort, the Peyton's subgroup, or the "see one, do one" subgroup. In this study, the traditional "see one, do one" model and Peyton's 4-step approach produced similar skill acquisition and confidence levels among medical students during an sLP workshop. Peyton's 4-step approach led to faster procedural completion times. The current study adds to the body of literature that has failed to find a notable impact in skill competence outcomes when teaching complex procedures.

Background/ Objectives Patients with poor sleep are at high risk for developing diabetes (T2DM). Since T2DM is linked to increased risk of obstructive sleep apnea (OSA), and Metformin is commonly used to treat T2DM, we examined how Metformin affects sleep stages in patients with concurrent T2DM and OSA-related symptoms of snoring and fatigue. T2DM patients on Metformin, progressively develop increased insulin resistance associated with sleep disturbances, and poor glycemic control. We explored changes in sleep patterns in T2DM patients on Metformin. We explored if Metformin affects sleep Architecture in T2DM patients. Methods Evaluate PSG (polysomnogram data from T2DM patients on Metformin along with data on age, BMI and sex. Data to be analyzed as mean +SE and linear regression, t test p< 0.5 taken as significant. Results Non-obese patients taking Metformin experienced a significant decrease in REM duration compared to patients on alternative therapies (p = 0.036). There was no such change in REM for obese patients taking Metformin. While there was no change in N3 duration with Metformin use, linear regression identified a moderate negative correlation between N3 and age in patients taking non-Metformin therapies (R2 = 0.4555). No significant correlations between sleep stage duration and patient sex, smoking status, or body-mass index (BMI) were identified. Conclusion T2DM patients on Metformin had OSA with reduced deep sleep (N3) and REM (Rapid Eye Movement) sleep. These diabetic patients with OSA being treated with Metformin had decreased REM sleep, regardless of sex, smoking history, and BMI. N3 and REM sleep are needed for timely secretion of growth hormone and memory consolidation. Metformin affects sleep architecture and impacts N3 and REM sleep. This may contribute to the development of insulin resistance. Future studies are needed to explore potential causes for this decrease and how it may affect treatment of T2DM.

Background/Objectives: Patients with poor sleep are at high risk of developing type II diabetes mellitus (T2DM). Since T2DM is linked to increased risk of obstructive sleep apnea (OSA), and Metformin is commonly used to treat T2DM, we examined how Metformin affects sleep stages in patients with concurrent T2DM and OSA-related symptoms of snoring and fatigue. Patients with T2DM on Metformin progressively develop increased insulin resistance associated with sleep disturbances and poor glycemic control. We therefore explored sleep pattern changes in patients with OSA symptoms and T2DM on Metformin, with a special focus on whether Metformin affects sleep architecture. Methods: Polysomnogram (PSG) data from patients with T2DM on Metformin was evaluated along with data on age, body-mass index (BMI), and biological sex. Data analysis included mean ± standard deviation, t-test with p < 0.05 taken as significant, and linear regression. Results: Patients with a BMI of less than 30 (non-obese) and taking Metformin exhibited a significantly shorter rapid eye movement sleep stage (REM) duration than patients on alternative therapies (p = 0.036). No such difference in REM was found for patients with a BMI of 30 or greater (obese) taking Metformin. While there was also no significant difference in slow-wave sleep stage (N3) duration with Metformin use, linear regression identified a moderate negative correlation between N3 and age in patients taking non-Metformin therapies (R² = 0.4555). No significant correlations between sleep stage duration and patient sex, smoking status, or BMI greater than 30 were identified. Conclusions: Overall, patients with OSA and T2DM on Metformin had lower mean quantities of N3, and REM sleep compared to those not on Metformin. Non-obese patients with T2DM and OSA being treated with Metformin were observed to have less REM sleep, regardless of sex or smoking history. N3 and REM sleep are needed for the timely secretion of growth hormone and memory consolidation. Since Metformin is correlated with differences in N3 and REM sleep, it may contribute to the development of insulin resistance. Future studies are needed to explore potential causes for this relationship and how it may affect the treatment of T2DM.

Obstructive sleep apnea (OSA) is a highly prevalent yet frequently underdiagnosed condition that is associated with significant cardiopulmonary, metabolic, and neurocognitive outcomes. Risk factors for OSA overlap with illnesses commonly observed in intensive care unit (ICU) patients, resulting in a disproportionately elevated burden in healthcare. This study evaluates the prevalence, diagnostic challenges, and management limitations of OSA in the ICU to identify strategies to improve awareness and outcomes in critically ill populations. An analysis of published literature was conducted using PubMed, EMBASE, and Scopus. Key search terms included “obstructive sleep apnea,” “ICU,” and “critical illness.” Results showed that OSA is present in up to 60–70% of ICU patients, yet only ~5% are formally diagnosed during hospitalization. Underdiagnosis is linked to prolonged mechanical ventilation, extubation failure as high as 30%, 2-fold higher perioperative complication rates, cardiovascular instability, 1.8-fold greater 30-day ICU readmission, and 2.2-fold mortality. Standard screening tools have limited applicability in ICU patients. Emerging alternatives, such as overnight oximetry, polygraphy, and machine learning models lack validation. Our analyses reveal that current diagnostic and treatment strategies are poorly adapted to critically ill patients. Integration of OSA as a part of ICU management, diagnosis, and intervention may reduce readmissions and mortality.

Obstructive sleep apnea (OSA) is a highly prevalent yet frequently underdiagnosed condition that is associated with significant cardiopulmonary, metabolic, and neurocognitive outcomes. Risk factors for OSA overlap with illnesses commonly observed in intensive care unit (ICU) patients, resulting in a disproportionately elevated burden on healthcare. This structured narrative review synthesizes current evidence regarding the prevalence, diagnostic challenges, and clinical implications of obstructive sleep apnea (OSA) in critically ill adults admitted to intensive care units (ICUs) using PubMed, EMBASE, and Scopus. Key search terms included “obstructive sleep apnea,” “ICU,” and “critical illness.” Results showed that OSA is present in up to 60–70% of ICU patients, yet only ~5% are formally diagnosed during hospitalization. Underdiagnosis is linked to prolonged mechanical ventilation, extubation failure rates as high as 30%, 2-fold higher perioperative complication rates, cardiovascular instability, 1.8-fold greater 30-day ICU readmission rates, and 2.2-fold mortality. Standard screening tools have limited applicability in ICU patients. Emerging alternatives, such as overnight oximetry, polygraphy, and machine learning models lack validation. Our analyses reveal that current diagnostic and treatment strategies are poorly adapted to critically ill patients. Integration of OSA as a part of ICU management, diagnosis, and intervention may reduce readmissions and mortality.