“Healthy” Machine Learning Models Could Reduce Bias
Spoon Feed
This medical news article interview highlights the risk of biased data leading to inherently biased medical AI models. The ethics of machine learning in general and approaches to minimize bias are also touched on.
Source
AI Developers Should Understand the Risks of Deploying Their Clinical Tools, MIT Expert Says. JAMA. 2024 Feb 27;331(8):629-631. doi: 10.1001/jama.2023.22981. PMID: 38324320.
Could Teleconsultation Reduce Pediatric Transfers?
Spoon Feed
This retrospective study found that of the 4,446 patients transferred over a 4.5-year period, 1,509 (34%) transfers could have possibly been avoided by utilizing telehealth/teleconsultation, with the most common transfer complaints being abdominal pain, asthma, and cough.
Source
Pediatric Patients Discharged After Transfer to a Pediatric Emergency Department: Opportunities for Telehealth?. Ann Emerg Med. 2024;83(3):208-213. doi:10.1016/j.annemergmed.2023.08.489
Pulse Oximetry’s Color Bias
Spoon Feed
In a controlled hypoxemia study, pulse oximetry was falsely elevated in subjects with darker skin pigmentation and low perfusion.
Source
Low Perfusion and Missed Diagnosis of Hypoxemia by Pulse Oximetry in Darkly Pigmented Skin: A Prospective Study. Anesth Analg. 2024 Mar 1;138(3):552-561. doi: 10.1213/ANE.0000000000006755. Epub 2023 Dec 18. PMID: 38109495.
Pay to Play – Telehealth and Inappropriate Antibiotics
Spoon Feed
Using online telemedicine platforms, the authors found that it was appallingly easy to rapidly obtain inappropriate antibiotic prescriptions for symptoms of viral URIs by paying a nominal fee. This highlights the need for increased education and regulations around inappropriate prescribing of antibiotics to safeguard the public and uphold good medical practices.
Source
Antibiotics on Demand: Advances in Asynchronous Telemedicine Call for Increased Antibiotic Surveillance. Clin Infect Dis. 2024 Feb 17;78(2):308-311. doi: 10.1093/cid/ciad472.
Emergency Medicine Should Embrace Our Technological Overlords
Spoon Feed
This article is a call to action for emergency medicine clinicians to encourage us to embrace the opportunity to leverage digital technologies and shape their implementation within our healthcare system.
Pop Quiz for Dr. Chatbot – How Did AI Do?
Spoon Feed
A popular artificial intelligence (AI) chatbot, ChatGPT, was fed hundreds of medical questions of varying difficulty. Responses generally demonstrated high accuracy and completeness, but inaccuracies were still noted. AI chatbot use in routine clinical practice simply isn’t ready for primetime.
Source
Accuracy and Reliability of Chatbot Responses to Physician Questions. JAMA Netw Open. 2023 Oct 2;6(10):e2336483. doi: 10.1001/jamanetworkopen.2023.36483.
Identifying Objective Performance Errors During Intubation
Spoon Feed
Using intubation videos, this group identified 13 key performance errors that occur during laryngoscopy. Read more to see what the proceduralists did wrong.
New App for Pediatric Cardiac Arrest
Spoon Feed
This RCT found residents using a pediatric cardiac arrest app better adhered to the pediatric cardiac arrest algorithm when compared to those using a PALS visual aid or no aid at all.
Source
Effectiveness of a Novel Tablet Application in Reducing Guideline Deviations During Pediatric Cardiac Arrest: A Randomized Clinical Trial. JAMA Netw Open. 2023 Aug 1;6(8):e2327272. doi: 10.1001/jamanetworkopen.2023.27272.
Can ChatGPT Solve the Tough Cases?
Spoon Feed
The newest generation GPT chatbot performed similarly, if not better than, current differential diagnosis generators explicitly designed for this purpose.
Source
Accuracy of a Generative Artificial Intelligence Model in a Complex Diagnostic Challenge. JAMA. 2023 Jul 3;330(1):78-80. doi: 10.1001/jama.2023.8288.
ChatGPT vs Physician Message Responses – Who Won?
Spoon Feed
Verified physician answers to patient questions on a public social media forum were compared to Chatbot answers to the same questions by rating the quality and empathy of responses. Guess who won?