Advertisement for orthosearch.org.uk
Bone & Joint Research Logo

Receive monthly Table of Contents alerts from Bone & Joint Research

Comprehensive article alerts can be set up and managed through your account settings

View my account settings

Visit Bone & Joint Research at:

Loading...

Loading...

Open Access

Editorial

Artificial intelligence in orthopaedics

what level of evidence does it represent and how is it validated?



Download PDF

Abstract

Cite this article: Bone Joint Res 2023;12(8):494–496.

Artificial intelligence (AI) refers to the development of computer systems that can perform tasks that typically require human intelligence. These tasks include understanding language, recognizing images, learning from experience, making decisions, and solving problems. The term ‘artificial intelligence’ was coined in 1956 during a conference at Dartmouth College, New Hampshire, USA.1 The conference brought together a group of scientists and researchers who were interested in exploring the idea of creating machines that could exhibit intelligent behaviour. John McCarthy, Marvin Minsky, Nathaniel Rochester, and Claude Shannon were among the prominent figures who organized the conference and popularized the term ‘artificial intelligence’.1 AI has various subfields that have emerged within the discipline, including machine learning, natural language processing (NLP), computer vision, robotics, and more. AI technologies are now being applied in various industries and domains, such as healthcare, finance, transportation, and entertainment, among others, which has revolutionized the way society works. AI aims to create machines that can perceive their environment, understand and learn from it, reason and make decisions, and interact with humans in a natural and intelligent manner.

AI systems are designed to mimic or simulate human cognitive functions, such as problem-solving, pattern recognition, learning, and decision-making. They achieve this through various techniques, including:

1. Machine learning, which involves training algorithms on large datasets to recognize patterns and make predictions or decisions without being explicitly programmed. This can be separated into two groups of supervised learning or unsupervised learning. It enables systems to learn from data, identify trends, and improve the performance of the algorithm over time.

2. Natural language processing (NLP), which enables machines to understand, interpret, and generate human language. It involves tasks such as speech recognition, language understanding, sentiment analysis, and machine translation, allowing AI systems to interact with humans in a more natural and intuitive way.

3. Computer vision, which involves enabling machines to understand and interpret visual information from images or videos. It includes tasks such as object detection, image classification, facial recognition, and scene understanding. Computer vision algorithms enable AI systems to analyze and make sense of visual data.

4. Robotics, which combines AI with physical systems to create intelligent machines that can interact with and manipulate their environment. AI-powered robots can perform tasks autonomously or with human guidance, enabling applications in areas such as healthcare, manufacturing, and logistics.

The goal of AI is to develop systems that can exhibit intelligent behaviour, adapt to new situations, learn from experience, and improve their performance over time. AI technologies have numerous real-world applications across various industries, including healthcare, finance, transportation, entertainment, and more. AI has the potential to greatly impact the field of orthopaedics in several ways.

Diagnostic assistance

AI can aid orthopaedic specialists in accurate and efficient diagnosis. Machine learning algorithms can analyze medical imaging to detect and classify various orthopaedic conditions, including fractures, tumours, and joint abnormalities.2,3 AI algorithms can assist in identifying subtle patterns or anomalies that might be missed by human observers, leading to earlier detection and treatment.

Surgical planning and assistance

AI can assist orthopaedic surgeons in surgical planning by providing valuable insights and recommendations.4 By analyzing patient data, such as medical images and patient records, AI algorithms could assist in preoperative planning, optimizing implant selection, and predicting surgical outcomes. During surgery, AI-powered robotic systems can provide real-time guidance, enhancing the precision and accuracy of surgical procedures.

Rehabilitation and recovery

AI can play a role in orthopaedic rehabilitation by developing personalized treatment plans.5 By analyzing patient data, AI algorithms can assess factors such as range of motion, muscle strength, and gait analysis to create tailored rehabilitation programmes. AI-powered wearable devices can monitor patient progress and provide real-time feedback, helping patients adhere to their rehabilitation plans and facilitating quicker recovery.

Data analysis and research

AI can assist in analyzing large volumes of orthopaedic data, including patient records, clinical trials, and research articles. By applying NLP and data mining techniques, AI can identify patterns and correlations within the data, leading to improved understanding of orthopaedic conditions, better treatment strategies, and the development of innovative therapies. These may have advantages over traditional risk models using regression analysis when analyzing large datasets.6,7

Predictive analytics

AI can leverage predictive analytics to forecast patient outcomes and identify potential complications.8 By analyzing patient data and historical records, AI algorithms can identify risk factors and predict the likelihood of postoperative complications, such as infections or implant failures. This can enable proactive intervention and personalized patient care.

Patient communication

Freely available AI dialogue platforms can be used to facilitate optimization of patient education materials and convert them to the appropriate reading age with retention of the accuracy of content.9 Interestingly, there is also the potential to expand the AI application to optimize the reading level to documents used for patient consent and postoperative instructions.

AI holds great promise in orthopaedics, but it may be no substitute to human expertise. There are limitations and these should be acknowledged when interpreting the AI data.10 There are also publishing implications with language models having the ability to create research manuscripts that are challenging to identify. This has led to the editors of several of the leading orthopaedic journals stating that AI applications cannot be listed as an author, but a description of how AI was used should be stated in the methods section of the manuscript in addition to an acknowledgement of its use.11 An area that seems to be deficient in the literature is where AI research is placed in the traditional evidence-based medicine model; what level of evidence is it and how is the validity of the outputs assessed? There are, however, limitations with traditional evidence-based medicine and some of these may be addressed with AI using large data sets.12 The surgeon may also feel a little uneasy in trusting the results from an AI platform when the workings may not be clear. Furthermore, how does AI cope with missing data, outliers, and other variables that typically influence and skew the outputs from traditionally accepted regression models? It does, however, serve as a powerful tool to augment the capabilities of orthopaedic specialists, leading to improved diagnostics, treatment planning, and patient care.

When asking ChatGPT13 to “to make a rhyme that highlights the benefits of AI in orthopaedics”, the response was:

In the world of orthopaedics, AI takes flight, bringing benefits that shine so bright. With precision and insight, it aids the way, enhancing patient care day by day.

AI’s diagnostic prowess, a remarkable feat, analyzing images with speed, accuracy so sweet. Fractures and ailments it swiftly detects, empowering doctors, their skills it perfects.

Surgical planning, a realm it excels, AI’s guidance, the surgeon compels. From implant selection to strategies refined, precise procedures, outcomes redefined.

Rehabilitation, a journey it aids, personalized plans, AI creates. Monitoring progress, providing feedback, accelerating recovery, getting patients on track.

Data analysis, a treasure trove revealed, unveiling insights that were once concealed. Research advances with AI’s keen eye, expanding knowledge, reaching new highs.

Predictive analytics, a visionary guide, identifying risks, potential troubles it cannot hide. Pre-emptive measures, proactive care, AI’s foresight, ensuring patients fare.

In orthopaedics, AI takes its stance, improving lives with its intelligent dance. A partner to experts, a valuable ally, embracing the future, where innovation will fly.

It is clear from this that AI rather smugly considers itself to be a great asset to orthopaedics. However, in 2016 Professor Stephen Hawking declared AI to be “either the best, or the worst thing, ever to happen to humanity”14 and similar anxieties have been raised by Geoffrey Hinton (dubbed the “godfather of AI” due to his work in the field) and Sam Altman, CEO of OpenAI (the developer of ChatGPT). It is therefore an innovation for us to embrace, but with caution.


Correspondence should be sent to Nick D. Clement. E-mail:

References

1. Hamet P , Tremblay J . Artificial intelligence in medicine . Metabolism . 2017 ; 69S : S36 S40 . Crossref PubMed Google Scholar

2. Archer H , Reine S , Alshaikhsalama A , et al. Artificial intelligence-generated hip radiological measurements are fast and adequate for reliable assessment of hip dysplasia: an external validation study . Bone Jt Open . 2022 ; 3 ( 11 ): 877 884 . Crossref PubMed Google Scholar

3. Gurung B , Liu P , Harris PDR , et al. Artificial intelligence for image analysis in total hip and total knee arthroplasty: a scoping review . Bone Joint J . 2022 ; 104-B ( 8 ): 929 937 . Crossref PubMed Google Scholar

4. Fernandes LR , Arce C , Martinho G , Campos JP , Meneghini RM . Accuracy, reliability, and repeatability of a novel artificial intelligence algorithm converting two-dimensional radiographs to three-dimensional bone models for total knee arthroplasty . J Arthroplasty . 2022 ; S0883-5403(22)01062-2 . Crossref PubMed Google Scholar

5. Santilli V , Mangone M , Diko A , et al. The Use of Machine Learning for Inferencing the Effectiveness of a Rehabilitation Program for Orthopedic and Neurological Patients . Int J Environ Res Public Health . 2023 ; 20 ( 8 ): 5575 . Crossref PubMed Google Scholar

6. Lenguerrand E , Whitehouse MR , Beswick AD , et al. Mortality and re-revision following single-stage and two-stage revision surgery for the management of infected primary hip arthroplasty in England and Wales . Bone Joint Res . 2023 ; 12 ( 5 ): 321 330 . Crossref PubMed Google Scholar

7. Lenguerrand E , Whitehouse MR , Kunutsor SK , et al. Mortality and re-revision following single-stage and two-stage revision surgery for the management of infected primary knee arthroplasty in England and Wales: evidence from the National Joint Registry . Bone Joint Res . 2022 ; 11 ( 10 ): 690 699 . Crossref PubMed Google Scholar

8. Klemt C , Uzosike AC , Esposito JG , et al. The utility of machine learning algorithms for the prediction of patient-reported outcome measures following primary hip and knee total joint arthroplasty . Arch Orthop Trauma Surg . 2023 ; 143 ( 4 ): 2235 2245 . Crossref PubMed Google Scholar

9. Kirchner GJ , Kim RY , Weddle JB , Bible JE . Can artificial intelligence improve the readability of patient education materials? Clin Orthop Relat Res . 2023 ; Epub ahead of print . Crossref PubMed Google Scholar

10. Lisacek-Kiosoglous AB , Powling AS , Fontalis A , Gabr A , Mazomenos E , Haddad FS . Artificial intelligence in orthopaedic surgery . Bone Joint Res . 2023 ; 12 ( 7 ): 447 454 . Crossref PubMed Google Scholar

11. Leopold SS , Haddad FS , Sandell LJ , Swiontkowski M . Artificial intelligence applications and scholarly publication in orthopaedic surgery . Bone Joint J . 2023 ; 105-B ( 6 ): 585 586 . Crossref PubMed Google Scholar

12. Greenhalgh T , Howick J , Maskrey N , Evidence Based Medicine Renaissance Group . Evidence based medicine: a movement in crisis? BMJ . 2014 ; 348 : g3725 . Crossref PubMed Google Scholar

13. No authors listed . Introducing ChatGPT . OpenAI . 2022 . https://openai.com/blog/chatgpt ( date last accessed 2 June 2023 ). Google Scholar

14. Hern A . Stephen Hawking: AI will be “either best or worst thing” for humanity . The Guardian . 2016 . https://www.theguardian.com/science/2016/oct/19/stephen-hawking-ai-best-or-worst-thing-for-humanity-cambridge#:~:text=Professor%20Stephen%20Hawking%20has%20warned,future%20of%20our%20civilisation%20and ( date last accessed 31 July 2023 ). Google Scholar

Author contributions

N. D. Clement: Conceptualization, Writing – original draft.

A. H. R. W. Simpson: Conceptualization, Writing – review & editing.

Funding statement

The authors received no financial or material support for the research, authorship, and/or publication of this article.

ICMJE COI statement

N. D. Clement is a member of the editorial board for Bone & Joint Research. A. H. R. W. Simpson is the Editor-in-Chief of Bone & Joint Research.

Acknowledgements

ChatGPT was used to compose part of this editorial.

© 2023 Author(s) et al. This is an open-access article distributed under the terms of the Creative Commons Attribution Non-Commercial No Derivatives (CC BY-NC-ND 4.0) licence, which permits the copying and redistribution of the work only, and provided the original author and source are credited. See https://creativecommons.org/licenses/by-nc-nd/4.0/