4.6 Editorial Material

THE ORTHOPAEDIC FORUM What's Important: The Next Academic-ChatGPT AI?

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Multidisciplinary Sciences

Abstracts written by ChatGPT fool scientists

Holly Else

NATURE (2023)

Editorial Material Orthopedics

Editorial Commentary: Machine Learning Is Just a Statistical Technique, Not a Mystical Methodology or Peer Review Panacea

Prem N. Ramkumar et al.

Summary: Orthopaedic and sports medicine research on artificial intelligence has increased significantly in the past four years. It is crucial to have meaningful application and methodological rigor in the scientific literature to ensure proper use of AI. Common errors in AI-related research include neglecting the importance and novelty of the research question, not establishing the necessity of AI in answering the question, and failing to recognize that model performance is often influenced by the data rather than the AI itself. Without appropriate safeguards, there is a risk of reusing registry data and producing low-quality research in the field of Orthopaedics.

ARTHROSCOPY-THE JOURNAL OF ARTHROSCOPIC AND RELATED SURGERY (2023)

Letter Obstetrics & Gynecology

Identifying ChatGPT-written OBGYN abstracts using a simple tool

Gabriel Levin et al.

AMERICAN JOURNAL OF OBSTETRICS & GYNECOLOGY MFM (2023)

Article Orthopedics

Feasibility of Machine Learning and Logistic Regression Algorithms to Predict Outcome in Orthopaedic Trauma Surgery

Jacobien H. F. Oosterhoff et al.

Summary: This study compared the performance of machine learning models and logistic regression models in estimating the probability of binary events in musculoskeletal trauma. The results showed that machine learning models produced probability estimates comparable to logistic regression models, but with lower variable associations.

JOURNAL OF BONE AND JOINT SURGERY-AMERICAN VOLUME (2022)

Review Orthopedics

Deep Learning and Imaging for the Orthopaedic Surgeon: How Machines Read Radiographs

Brandon G. Hill et al.

Summary: In the near future, orthopaedic surgeons will encounter machines that can automatically read medical imaging studies using deep learning technology. Deep learning has made significant progress in analyzing medical imaging across various orthopaedic modalities and has shown clinical utility in musculoskeletal radiography.

JOURNAL OF BONE AND JOINT SURGERY-AMERICAN VOLUME (2022)

Article Computer Science, Artificial Intelligence

Deep learning, reinforcement learning, and world models

Yutaka Matsuo et al.

Summary: This review summarizes the talks and discussions on deep learning and reinforcement learning at the International Symposium on Artificial Intelligence and Brain Science. The review highlights the strong connections of DL and RL with brain functions and neuroscientific findings. The focus of the discussions is on whether comprehensive understanding of human intelligence can be achieved based on the recent advances in DL and RL algorithms, with speakers presenting their recent studies that could be key technologies for achieving human-level intelligence.

NEURAL NETWORKS (2022)

Article Orthopedics

Getting More Out of Large Databases and EHRs with Natural Language Processing and Artificial Intelligence

Bardia Khosravi et al.

Summary: Electronic health records (EHRs) provide opportunities for researchers to collect information from clinical patient encounters. However, most EHR data are stored in unstructured form, and clinical natural language processing (NLP) is needed to extract structured data and meaningful relationships.

JOURNAL OF BONE AND JOINT SURGERY-AMERICAN VOLUME (2022)

Review Orthopedics

Artificial Intelligence and Orthopaedics An Introduction for Clinicians

Thomas G. Myers et al.

JOURNAL OF BONE AND JOINT SURGERY-AMERICAN VOLUME (2020)