Echocardiography and pulmonary hypertension in patients with chronic obstructive pulmonary disease undergoing lung transplantation evaluation.

BACKGROUND: The use of echocardiography in pulmonary hypertension (PH) in advanced chronic obstructive pulmonary disease (COPD) is understudied. We aimed to compare the performance of echocardiography with right heart catheterization (RHC) in the diagnosis of PH in COPD patients undergoing lung transplant evaluation. METHODS: We included 111 patients with severe COPD who underwent RHC in a single center as part of lung transplantation evaluation. COPD-PH and severe COPD-PH were defined based on RHC per the 6th world symposium on pulmonary hypertension. Echocardiographic probability of PH was described according to the European Society of Cardiology guidelines. Summary and univariate analyses were performed. RESULTS: The mean age (±SD) was 62 (8) and 47% (n=52) were men. A total of 82 patients (74 %) had COPD-PH. The sensitivity, specificity, positive predictive, and negative predictive values of echocardiography in diagnosing COPD-PH were 43 %, 83 %, 88 %, and 34 % respectively and for severe COPD-PH were 67 %, 75 %, 50 %, and 86 % respectively. Echocardiography was consistent with RHC in ruling in/out PH in 53% (n=59) of patients. After controlling for age, sex. BMI, pack year, echocardiography-RHC time difference, GOLD class, FVC, and CT finding of emphysema, higher TLC decreased consistency (parameter estimate=-0.031; odds ratio: 0.97, 95%CI 0.94-0.99; p=0.037) and higher DLCO increased consistency (parameter estimate=0.070; odds ratio: 1.07, 95%CI 0.94-0.99; p=0.026). CONCLUSIONS: Echocardiography has high specificity but low sensitivity for the diagnosis of PH in advanced COPD. Its performance improves when ruling out severe COPD-PH. This performance correlates inversely with lung hyperinflation.

AI-Powered Renal Diet Support: Performance of ChatGPT, Bard AI, and Bing Chat.

Patients with chronic kidney disease (CKD) necessitate specialized renal diets to prevent complications such as hyperkalemia and hyperphosphatemia. A comprehensive assessment of food components is pivotal, yet burdensome for healthcare providers. With evolving artificial intelligence (AI) technology, models such as ChatGPT, Bard AI, and Bing Chat can be instrumental in educating patients and assisting professionals. To gauge the efficacy of different AI models in discerning potassium and phosphorus content in foods, four AI models-ChatGPT 3.5, ChatGPT 4, Bard AI, and Bing Chat-were evaluated. A total of 240 food items, curated from the Mayo Clinic Renal Diet Handbook for CKD patients, were input into each model. These items were characterized by their potassium (149 items) and phosphorus (91 items) content. Each model was tasked to categorize the items into high or low potassium and high phosphorus content. The results were juxtaposed with the Mayo Clinic Renal Diet Handbook's recommendations. The concordance between repeated sessions was also evaluated to assess model consistency. Among the models tested, ChatGPT 4 displayed superior performance in identifying potassium content, correctly classifying 81% of the foods. It accurately discerned 60% of low potassium and 99% of high potassium foods. In comparison, ChatGPT 3.5 exhibited a 66% accuracy rate. Bard AI and Bing Chat models had an accuracy rate of 79% and 81%, respectively. Regarding phosphorus content, Bard AI stood out with a flawless 100% accuracy rate. ChatGPT 3.5 and Bing Chat recognized 85% and 89% of the high phosphorus foods correctly, while ChatGPT 4 registered a 77% accuracy rate. Emerging AI models manifest a diverse range of accuracy in discerning potassium and phosphorus content in foods suitable for CKD patients. ChatGPT 4, in particular, showed a marked improvement over its predecessor, especially in detecting potassium content. The Bard AI model exhibited exceptional precision for phosphorus identification. This study underscores the potential of AI models as efficient tools in renal dietary planning, though refinements are warranted for optimal utility.

Impact of COVID-19 Self-Isolation on Medical Students' Education and Adherence to Protective Measures.

This study aims to evaluate the impact of self-isolation on the level of adherence to health protective measures among medical students in Jordan and on their clinical education. Because of being suspected of having or testing positive for COVID-19, 336 students were self-isolated . A questionnaire was sent to study the clinical adherence of students to COVID-19 protective measures after their self-isolation period, the student's satisfaction about the policy followed during the pandemic, the impact of these measures on their clinical training, and the level of vaccine acceptance among them. The study included 283 participants, with a mean age of 22.5 (±1.50) years; 49.5% males and 50.5% females. We found that students' adherence to protective measures generally increased after their self-isolation. Gender, age, and having an infection from the hospital were the most important predictors for better adherence to health safety measures. Most students (83%) have registered to take the vaccine. 97.5% of self-isolated students reported that they are aware and satisfied of the School of Medicine instructions and policies. The findings suggest the need to ensure that medical students' clinical training should not be negatively affected by COVID-19 and COVID-19 self-isolation, as medical students are adherent to COVID-19 precautionary measures and willing to take the vaccine.