Medical Bulletin 04/ November/ 2024
Here are the top medical news for the day:
Can GPT-4 Improve Diagnosis? JAMA Network Open Study
A new study in JAMA Network Open found that the availability of GPT-4 to physicians as a diagnostic aid did not significantly improve clinical reasoning compared to conventional resources. A collaborative team of researchers from the University of Minnesota Medical School, Stanford University, Beth Israel Deaconess Medical Center and the University of Virginia studied how well doctors used GPT-4 — an artificial intelligence (AI) large language model system — for diagnosing patients.
The study was conducted with 50 U.S.-licensed physicians in family medicine, internal medicine and emergency medicine. Key findings include:
GPT-4 alone demonstrated significantly better scores in diagnostic performance, surpassing the performance of clinicians using conventional diagnostic online resources and clinicians assisted by GPT-4.
There was no significant enhancement in diagnostic performance with the addition of GPT-4 when assessing clinicians using GPT-4 against clinicians using conventional diagnostic resources.
These results underline the complexity of integrating AI into clinical practice. While GPT-4 alone showed promising results, the integration of GPT-4 as a diagnostic aid alongside clinicians did not significantly outperform the use of conventional diagnostic resources. This suggests a nuanced potential for AI in healthcare, emphasizing the importance of further exploration into how AI can best support clinical practice.
Reference: Goh E, Gallo R, Hom J, et al. Large Language Model Influence on Diagnostic Reasoning: A Randomized Clinical Trial. JAMA Netw Open. 2024;7(10):e2440969. doi:10.1001/jamanetworkopen.2024.40969
Long Covid Common After Other Respiratory Tract Infections: Study Finds
Continued illness post Covid-19 is common after other respiratory infections, according to a study. A team of researchers from the University of Oxford in the UK analysed data from 190,000 participants. They classified them into: people hospitalised with Covid and those hospitalised with other lower respiratory tract infections (LRTIs). These were then compared with a reference group with no lower respiratory tract infections hospitalisations.
Participants completed surveys reporting on 45 different physical and psychological symptoms observed across the ear, nose, and throat; respiratory; neurological; gastrointestinal; and musculoskeletal systems.
The findings, published in JAMA Network Open, showed that people hospitalised with Covid had higher risks of 23 out of 45 symptoms. Similarly, those hospitalised for non-Covid lower respiratory tract infections had 18 out of 45.
While those with Long Covid are more likely to suffer from continued fatigue, breathlessness, and even brain fog. Some previous studies have shown that Covid patients are also likely to have a persistent loss of taste. However, neurological and cognitive symptoms were also observed in the latest study. They found that problems with thinking and communicating were higher than in the reference group. But it was also higher than those hospitalised for other lower respiratory tract infections.
Reference: Gao Y, Wang Y, Chen L, Xie J, Prieto-Alhambra D. Hospitalization for COVID-19, Other Respiratory Infections, and Postacute Patient-Reported Symptoms. JAMA Netw Open. 2024;7(10):e2441615. doi:10.1001/jamanetworkopen.2024.41615
Can a Child’s Current BMI Affect Their Future Lung Function?
An abnormal BMI in children -- be it high or low -- can now be associated with impaired lung function, but if their BMI is normalised before they reach adulthood, the impairment can be offset, researchers from Karolinska Institutet report. Their results, which are based on data collected under the BAMSE project in Sweden, are presented in The European Respiratory Journal.
One risk factor associated with impaired lung function development is abnormal weight and height. The most common body measurement, BMI (body mass index), takes account of weight, but not muscle and fat composition.
The participants could be divided up into different BMI groups, which had already begun to differentiate themselves by the age of two. Unlike children with a normal BMI, those with a persistently high BMI or an accelerated increasing BMI had impaired lung function as adults, primarily the result of restricted airflow in the lungs, a condition known as obstruction. A stable low BMI could also be linked to reduced lung function caused by inadequate lung growth. In these cases, BMI was not normalised over the course of the study.
The study was based on the BAMSE project, in which over 4,000 children have been followed from birth to the age of 24. BMI has been repeatedly measured over this time, at most 14 times. The present study includes 3,200 participants with at least four BMI measurements.
Lung function was measured using spirometry at the ages of 8, 16 and, finally, 24, at which point the function of the smaller airways was also measured via the volume of exhaled nitrogen. Urine samples were also taken so that an analysis of the substances being metabolised could be performed in collaboration with docent Craig Wheelock at Karolinska Institute's Institute of Environmental Medicine.
The urine samples from the high BMI group showed elevated levels of metabolites of the amino acid histidine, corroborating the observations of other researchers who found a similar increase in patients with asthma and chronic obstructive pulmonary disease.
Reference: https://news.ki.se/childrens-bmi-can-affect-their-future-lung-function
Our comments section is governed by our Comments Policy . By posting comments at Medical Dialogues you automatically agree with our Comments Policy , Terms And Conditions and Privacy Policy .
Disclaimer: This website is primarily for healthcare professionals. The content here does not replace medical advice and should not be used as medical, diagnostic, endorsement, treatment, or prescription advice. Medical science evolves rapidly, and we strive to keep our information current. If you find any discrepancies, please contact us at corrections@medicaldialogues.in. Read our Correction Policy here. Nothing here should be used as a substitute for medical advice, diagnosis, or treatment. We do not endorse any healthcare advice that contradicts a physician's guidance. Use of this site is subject to our Terms of Use, Privacy Policy, and Advertisement Policy. For more details, read our Full Disclaimer here.
NOTE: Join us in combating medical misinformation. If you encounter a questionable health, medical, or medical education claim, email us at factcheck@medicaldialogues.in for evaluation.