ChatGPT Outperforms Biomedical AI in Designing Cardiac Surgery Anesthesia Plans
In a comparative study of one hundred cardiac surgery records, ChatGPT substantially outperformed the domain-specific OpenBioLLM model in generating personalized ...
Tag: ChatGPT
Mandarin Instructors Find Word Frequency Shapes ChatGPT Quality More Than Prompt Design
A study of 59 language instructors found that ChatGPT's teaching accuracy depended far more on vocabulary difficulty than whether educators ...
ChatGPT Accurately Identifies STEMI on ECGs and Guides Reperfusion Decisions
In a retrospective study of 210 patients, ChatGPT localized STEMI on electrocardiograms with 91.4 percent accuracy and achieved 90 percent ...
Generative AI Grammar Support Improves Ethiopian University Students’ Writing Performance
A ten-week quasi-experimental study of eighty-eight Ethiopian university students found that structured ChatGPT-supported grammar instruction produced large, statistically significant gains ...
ChatGPT Assists Systematic Review Screening in Environmental Science
A new framework integrating fine-tuned ChatGPT with domain knowledge shows potential for improving the consistency and efficiency of evidence screening ...
An empirical framework for assessing AI in early childhood education: a global versus local perspective
A new study finds that local Chinese AI models significantly outperform global platforms in early childhood education tasks requiring cultural ...
AI Pilates Matches Traditional Training in Posture Gains
A randomised trial found that an eight-week Reformer Pilates programme improved posture and functional movement in both AI-assisted and traditional ...
ChatGPT Evaluates Cancer Immunotherapy Videos More Accurately Than Competing AI Models
A cross-sectional study found ChatGPT-5.5 closely matched oncologist evaluations of cancer immunotherapy videos, whereas other artificial intelligence models frequently misclassified ...
Health science students report higher GPA with frequent AI use, but most get no formal training
A cross-sectional survey of 310 health science students found frequent AI use linked to higher self-reported GPA, while 82.6% received ...
From structured analysis to normative decision-making: a comparative evaluation of large language models in clinical ethics consultation
While the models produced well-organized documents that identified key clinical and social dimensions, the study found that high analytical scores ...
-
Mothers who receive childcare support from maternal grandparents show more parental warmth, finds NTU Singapore study
-
University of Seville Breaks 120-Year-Old Mystery, Revises a Key Einstein Concept
-
Bee body mass, pathogens and local climate influence heat tolerance
-
Researchers record first-ever images and data of a shark experiencing a boat strike
-
Groundbreaking Clinical Trial Reveals Lubiprostone Enhances Kidney Function
Embark on a thrilling journey of discovery with Scienmag.com—your ultimate source for cutting-edge breakthroughs. Immerse yourself in a world where curiosity knows no limits and tomorrow’s possibilities become today’s reality!