Karlsson, Jón

AbstractDeep learning is a subset of artificial intelligence (AI) with enormous potential to transform orthopaedic surgery. As has already become evident with the deployment of Large Language Models (LLMs) like ChatGPT (OpenAI Inc.), deep learning can rapidly enter clinical and surgical practices. As such, it is imperative that orthopaedic surgeons acquire a deeper understanding of the technical terminology, capabilities and limitations associated with deep learning models. The focus of this series thus far has been providing surgeons with an overview of the steps needed to implement a deep learning‐based pipeline, emphasizing some of the important technical details for surgeons to understand as they encounter, evaluate or lead deep learning projects. However, this series would be remiss without providing practical examples of how deep learning models have begun to be deployed and highlighting the areas where the authors feel deep learning may have the most profound potential. While computer vision applications of deep learning were the focus of Parts I and II, due to the enormous impact that natural language processing (NLP) has had in recent months, NLP‐based deep learning models are also discussed in this final part of the series. In this review, three applications that the authors believe can be impacted the most by deep learning but with which many surgeons may not be familiar are discussed: (1) registry construction, (2) diagnostic AI and (3) data privacy. Deep learning‐based registry construction will be essential for the development of more impactful clinical applications, with diagnostic AI being one of those applications likely to augment clinical decision‐making in the near future. As the applications of deep learning continue to grow, the protection of patient information will become increasingly essential; as such, applications of deep learning to enhance data privacy are likely to become more important than ever before.Level of Evidence: Level IV.

AbstractPurposeAnterior cruciate ligament tears and anterior cruciate ligament reconstruction (ACLR) are common in young athletes. The modifiable and non‐modifiable factors contributing to ACLR failure and reoperation are incompletely understood. The purpose of this study was to determine ACLR failure rates in a physically high‐demand population and identify the patient‐specific risk factors, including prolonged time between diagnosis and surgical correction, that portend failure.MethodsA consecutive series of military service members with ACLR with and without concomitant procedures (meniscus [M] and/or cartilage [C]) done at military facilities between 2008 and 2011 was completed via the Military Health System Data Repository. This was a consecutive series of patients without a history of knee surgery for two years prior to the primary ACLR. Kaplan–Meier survival curves were estimated and evaluated with Wilcoxon test. Cox proportional hazard models calculated hazard ratios (HR) with 95% confidence intervals (95% CI) to identify demographic and surgical factors that influenced ACLR failure.ResultsOf the 2735 primary ACLRs included in the study, 484/2,735 (18%) experienced ACLR failure within four years, including (261/2,735) (10%) undergoing revision ACLR and (224/2,735) (8%) due to medical separation. The factors that increased failure include Army Service (HR 2.19, 95% CI 1.67, 2.87), > 180 days from injury to ACLR (HR 1.550, 95% CI 1.157, 2.076), tobacco use (HR 1.429 95% CI 1.174, 1.738), and younger patient age (HR 1.024, 95% CI 1.004, 1.044).ConclusionThe overall clinical failure rate of service members with ACLR is 17.7% with minimum four‐year follow‐up, where more patients are likely to fail due to revision surgery than medical separation. The cumulative probability of survival at 4 years was 78.5%. Smoking cessation and treating ACLR patients promptly are modifiable risk factors impacting either graft failure or medical separation.Level of evidenceLevel III.

AbstractDeep learning has the potential to be one of the most transformative technologies to impact orthopedic surgery. Substantial innovation in this area has occurred over the past 5 years, but clinically meaningful advancements remain limited by a disconnect between clinical and technical experts. That is, it is likely that few orthopedic surgeons possess both the clinical knowledge necessary to identify orthopedic problems, and the technical knowledge needed to implement deep learning‐based solutions. To maximize the utilization of rapidly advancing technologies derived from deep learning models, orthopedic surgeons should understand the steps needed to design, organize, implement, and evaluate a deep learning project and its workflow. Equipping surgeons with this knowledge is the objective of this three‐part editorial review. Part I described the processes involved in defining the problem, team building, data acquisition, curation, labeling, and establishing the ground truth. Building on that, this review (Part II) provides guidance on pre‐processing and augmenting the data, making use of open‐source libraries/toolkits, and selecting the required hardware to implement the pipeline. Special considerations regarding model training and evaluation unique to deep learning models relative to “shallow” machine learning models are also reviewed. Finally, guidance pertaining to the clinical deployment of deep learning models in the real world is provided. As in Part I, the focus is on applications of deep learning for computer vision and imaging.

AbstractDeep learning has a profound impact on daily life. As Orthopedics makes use of this rapid escalation in technology, Orthopedic surgeons will need to take leadership roles on deep learning projects. Moreover, surgeons must possess an understanding of what is necessary to design and implement deep learning‐based project pipelines. This review provides a practical guide for the Orthopedic surgeon to understand the steps needed to design, develop, and deploy a deep learning pipeline for clinical applications. A detailed description of the processes involved in defining the problem, building the team, acquiring and curating the data, labeling the data, establishing the ground truth, pre‐processing and augmenting the data, and selecting the required hardware is provided. In addition, an overview of unique considerations involved in the training and evaluation of deep learning models is provided. This review strives to provide surgeons with the groundwork needed to identify gaps in the clinical landscape that deep learning models may be able to fill and equips them with the knowledge needed to lead an interdisciplinary team through the process of creating novel deep‐learning‐based solutions to fill those gaps.

AbstractMean, median, and mode are among the most basic and consistently used measures of central tendency in statistical analysis and are crucial for simplifying data sets to a single value. However, there is a lack of understanding of when to use each metric and how various factors can impact these values. The aim of this article is to clarify some of the confusion related to each measure and explain how to select the appropriate metric for a given data set. The authors present this work as an educational resource, ensuring that these common statistical concepts are better understood throughout the Orthopedic research community.

AbstractSupervised learning is the most common form of machine learning utilized in medical research. It is used to predict outcomes of interest or classify positive and/or negative cases with a known ground truth. Supervised learning describes a spectrum of techniques, ranging from traditional regression modeling to more complex tree boosting, which are becoming increasingly prevalent as the focus on “big data” develops. While these tools are becoming increasingly popular and powerful, there is a paucity of literature available that describe the strengths and limitations of these different modeling techniques. Typically, there is no formal training for health care professionals in the use of machine learning models. As machine learning applications throughout medicine increase, it is important that physicians and other health care professionals better understand the processes underlying application of these techniques. The purpose of this study is to provide an overview of commonly used supervised learning techniques with recent case examples within the orthopedic literature. An additional goal is to address disparities in the understanding of these methods to improve communication within and between research teams.

Background: Factors relating to the patient and anterior cruciate ligament (ACL) reconstruction may help to identify prognostic factors of long-term outcome after reconstruction. Purpose: To determine 10-year risk factors for inferior knee function after ACL reconstruction. Study Design: Cohort study; Level of evidence, 2. Methods: Prospectively collected data from the Swedish National Knee Ligament Register were extracted for patients who underwent ACL reconstruction between January 2005 and December 2006. Patients who had no data at the 10-year follow-up for the Knee injury and Osteoarthritis Outcome Score (KOOS) were excluded. Multivariable proportional odds regression modeling was used to assess 10-year patient- and surgery-related risk factors across all the KOOS subscales and the KOOS 4 (mean score of 4 subscales: pain, knee-related symptoms, function in sport and recreation, and knee-related quality of life). Results: A total of 874 (41%) patients were included (male, 51.5%; median age at the time of ACL reconstruction, 27.5 years [range, 11.2-61.5 years]). An increase in the severity of concomitant articular cartilage injuries resulted in a reduced KOOS on 4 subscales (odds ratio, 0.64-0.80; P < .05). A higher preoperative KOOS pain score increased the odds of a higher score on the pain, symptoms, and sport subscales and the KOOS 4 . In addition, a higher preoperative body mass index was a significant risk factor for lower scores on 3 KOOS subscales and the KOOS 4 . No patient- or surgery-related predictor was significant across all KOOS subscales. Conclusion: This 10-year risk factor analysis identified several factors that can affect long-term knee function after ACL reconstruction. Most risk factors were related to preoperative patient-reported outcome and potentially modifiable. On the other hand, most of the surgery-related risk factors were nonmodifiable. Nevertheless, this information may be helpful to physicians and physical therapists counseling patients on their expectations of outcome after ACL reconstruction.