ChatGPT shows promise in addressing heart failure queries with accuracy and precision UCIrvine CedarsSinai CharGPT heartfailure health AI artificialintelligence
By Susha Cheriyedath, M.Sc.Jul 14 2023Reviewed by Benedette Cuffari, M.Sc. In a recent study posted to the medRxiv* preprint server, researchers evaluate the accuracy and reproducibility of responses from ChatGPT versions 3.5 and 4 in answering heart failure-related questions.
Background By 2030, researchers estimate that healthcare costs associated with heart failure will reach around $70 billion USD every year in the United States. About 70% of these costs are due to hospitalizations, which constitute 1-2% of all hospital admissions in the United States. Studies have shown that patients who possess more knowledge about managing their heart condition tend to have fewer and shorter hospital stays.
About the study In the current study, researchers collected a list of 125 commonly asked questions about heart failure from reputable medical organizations and Facebook support groups. After careful evaluation, 18 questions with duplicate content, vague phrasing, or did not address the patient’s perspective were eliminated.
Any discrepancies in grading between the reviewers were resolved by a third reviewer who is a board-certified specialist in advanced heart failure with over 20 years of clinical experience. About 2% of responses from ChatGPT-3.5 was graded as ‘some correct and some incorrect,’ while no responses from ChatGPT-4 fell into this category or the ‘completely incorrect’ category. When examining reproducibility, both models provided consistent responses for most questions, with the ChatGPT-3.5 version scoring more than 94% in all categories and GPT-4 achieving 100% reproducibility for all answers.
While ChatGPT performed well in this study, there are important limitations to consider. Occasionally, the model may provide inaccurate but believable responses and, at times, nonsensical answers.
Danmark Seneste Nyt, Danmark Overskrifter
Similar News:Du kan også læse nyheder, der ligner denne, som vi har indsamlet fra andre nyhedskilder.
Google's ChatGPT rival Bard launches in Europe and BrazilGoogle’s Bard artificial intelligence chatbot can now also talk and respond to visual prompts.
Læs mere »
ChatGPT Probed by FTC Over Consumer HarmsThe US Federal Trade Commission has sent a request for information to startup OpenAI Inc. as part of a probe into its ChatGPT conversational AI bot
Læs mere »
FTC probes OpenAI's ChatGPT for consumer law violationsBTW: The FTC is looking into whether OpenAI's ChatGPT is breaking US consumer protection laws by causing reputational or privacy damage
Læs mere »
ChatGPT owner in probe over risks around false answersUS regulators are asking the maker of ChatGPT about protections for privacy and reputational risk.
Læs mere »
Trends in antibiotic usage among inpatients in South America during COVID-19 pandemicTrends in antibiotic usage among inpatients in South America during COVID-19 pandemic CIDJournal CDCgov usponline antibiotics COVID19 coronavirus covid pandemic
Læs mere »
What effect does honey have on human health?What effect does honey have on human health? Nutrients_MDPI CanalUGR honey health humanhealth diet nutrients
Læs mere »