Editorial Commentary: Machine Learning and Artificial Intelligence Are Tools Requiring Physician and Patient Input When Screening Patients at Risk for Extended, Postoperative Opioid Use

Article Orthopedics

How to Develop and Validate Prediction Models for Orthopedic Outcomes1

Isabella Zaniletti et al.

Summary: Prediction models are commonly used in medicine to predict outcomes in treatment. However, their adoption in clinical practice, specifically in arthroplasty, is limited. This paper provides an overview of statistical concepts, practical steps, and the importance of robustly built and validated prediction models in arthroplasty research.

JOURNAL OF ARTHROPLASTY (2023)

添加到收藏夹

Article Orthopedics

Machine Learning Model Identifies Preoperative Opioid Use, Male Sex, and Elevated Body Mass Indexas Predictive Factors for Prolonged Opioid Consumption Following Arthroscopic Meniscal Surgery

Joshua P. Castle et al.

Summary: The purpose of this study was to develop a predictive machine learning model to identify prognostic factors for continued opioid prescriptions after arthroscopic meniscus surgery. The study found that preoperative opioid consumption and male sex were the most significant predictors for sustained opioid use beyond 1 month postoperatively.

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

添加到收藏夹

Review Orthopedics

Machine Learning Algorithms Predict Achievement of Clinically Significant Outcomes After Orthopaedic Surgery: A Systematic Review

Kyle N. Kunze et al.

Summary: This study aimed to determine the application of machine learning in predicting clinically significant outcomes in orthopaedic surgery. The results showed that machine learning algorithms can be used to predict outcomes after spine, joint arthroplasty, and sports medicine surgery, but the ability to predict patient acceptable symptomatic state and substantial clinical benefit is unclear.

ARTHROSCOPY-THE JOURNAL OF ARTHROSCOPIC AND RELATED SURGERY (2022)

添加到收藏夹

Article Orthopedics

Meaningless Applications and Misguided Methodologies in Artificial Intelligence-Related Orthopaedic Research Propagates Hype Over Hope

Prem N. Ramkumar et al.

Summary: There is great hope and hype surrounding artificial intelligence (AI) applications in orthopaedic surgery. However, the existing AI-related research in orthopaedics often fails to provide meaningful use cases and leaves the uninitiated unable to evaluate the importance of AI. The hype perpetuates a cycle that rewards those with limited understanding and basic technical knowhow, resulting in several errors. Relevant AI-specific guidelines are forthcoming, but applying existing guidelines designed for regression analyses is irrelevant and misleading for AI research in orthopaedics.

ARTHROSCOPY-THE JOURNAL OF ARTHROSCOPIC AND RELATED SURGERY (2022)

添加到收藏夹

Editorial Material Orthopedics

Editorial Commentary: Machine Learning in Medicine Requires Clinician Input, Faces Barriers, and High-Quality Evidence Is Required to Demonstrate Improved Patient Outcomes

Ayoosh Pareek et al.

Summary: Machine learning and artificial intelligence are advanced statistical techniques that use algorithms to learn and predict relationships between input and results with high accuracy. While there is increasing use and optimism for AI in orthopaedic surgery, there is a lack of high-quality evidence to prove its ability to improve patient outcome. It is the responsibility of clinicians to provide context for ML models and guide their use to optimize patient outcome.

ARTHROSCOPY-THE JOURNAL OF ARTHROSCOPIC AND RELATED SURGERY (2022)

添加到收藏夹

Editorial Material Orthopedics

Artificial intelligence and machine learning: an introduction for orthopaedic surgeons

R. Kyle Martin et al.

Summary: The application of artificial intelligence and machine learning in orthopaedic surgery is increasing rapidly, but the statistical jargon and techniques associated with AI may be unfamiliar to many clinicians. In order to bridge this knowledge gap and make these novel techniques more accessible to orthopaedic surgeons, we introduce the concepts of AI and machine learning and provide examples of their impact on clinical practice and patient care.

KNEE SURGERY SPORTS TRAUMATOLOGY ARTHROSCOPY (2022)

添加到收藏夹

Review Orthopedics

Concerns surrounding application of artificial intelligence in hip and knee arthroplasty a review of literature and recommendations for meaningful adoption

T. S. Polisetty et al.

Summary: Literature on the application of artificial intelligence (AI) in hip and knee arthroplasty has grown rapidly. However, despite the wide range of applications, there have been limited meaningful advances in the practice and delivery of joint arthroplasty using AI. A review of AI literature from 2018 to 2021 focused on image-based analyses, value-based care, remote patient monitoring, and augmented reality in hip and knee arthroplasty. Concerns regarding the appropriate use and methodological approaches of AI in joint arthroplasty research are summarized. Among the 233 AI-related orthopedics articles published during the period, 76% constituted original research, with the majority focusing on hip and knee arthroplasty. Several pitfalls in current research methods are identified, including confusion in terminology, premature release of internally validated prediction models, and evaluation of model architecture instead of inputted data. However, the future prospects for AI in hip and knee arthroplasty remain promising if meaningful questions are addressed, rigorous and transparent methodologies are used, rich data is available, and external validation is conducted.

BONE & JOINT JOURNAL (2022)

添加到收藏夹

Article Clinical Neurology

Long-term postoperative opioid prescription after cholecystectomy or gastric by-pass surgery: a retrospective observational study

Viktoria Larsson et al.

Summary: The proportion of patients using opioids 6-12 months after cholecystectomy or GBP surgery was low, with preoperative opioid use being a significant risk factor for long-term opioid use. Affective disorders and prior use of benzodiazepines and amitriptyline were associated with long-term opioid use among patients.

SCANDINAVIAN JOURNAL OF PAIN (2021)

添加到收藏夹

Article Orthopedics