Sage Journals: Discover world-class research

Abstract

Orthopaedic surgery is on the cusp of entering a new data-driven era, fuelled by big data and Artificial Intelligence (AI). Medical data is traditional derived from manually inputted medical records. A far richer set of data may be collected via automated means and from population registries leading to an explosion of large and complex datasets termed “big data” which are not well handled by traditional processing tools. Big data truly becomes useful when coupled with the ability to meaningfully process it with current generation AI. These two advances have reshaped possibilities in research and clinical applications. This narrative review outlines emerging opportunities and challenges brought about big data and AI while also exploring the necessary guardrails that are needed for safe application and sustainable progress.

Keywords

artificial intelligence Orthopaedic registry-based data big data

Introduction

Big data has changed the research and clinical landscape for Orthopaedic Surgeons. Medical data have traditionally been derived from manually entered medical records, collected one patient at a time, primarily for the purpose of direct clinical care. This approach constrains the scale, completeness and usability of data due to practical limitations in time, cost and legibility. A far richer set of data maybe collected via automated means with the advent of wearable technology, surgical robots and advanced imaging. Parallel advances in automated clinical summaries and image processing have further expanded the volume and accessibility of medical data.^1,2 In addition, sustained institutional and national efforts to develop and fund Orthopaedic registries capable of capturing systematically collected population-level data have contributed to an unprecedented growth in data availability, commonly referred to as big data. However, the true value of big data is realised only when paired with contemporary artificial intelligence (AI) integration techniques which encompass machine learning or deep learning models that enable meaningful processing, integration and interpretation across the perioperative continuum. Among surgical specialties, Orthopaedic Surgery is particularly well suited to leverage big data as Orthopaedic related research is underpinned by objective measures, precise imaging modalities, structured scoring systems and reproducible operations. Compared with other disciplines such as Cardiology or Oncology where molecular or physiological variability may dominate, Orthopaedic Surgery benefits from structurally defined pathology and measurable biomechanical endpoints, making it especially amenable to algorithmic modelling and prediction.^1,3

Despite rapid technological progress, the wider implementation of AI in Orthopaedics continues to face notable challenges. Current Orthopaedic big data ecosystems remain fragmented and possess limited interoperability across institutions.^4–6 Moreover, AI models are trained on single-centre or demographically narrow datasets, restricting external validity and amplifying algorithmic biases.⁴ Registry data, while extensive, continues to be plagued by inconsistencies in definition, data entry and missing information, limiting immediate applicability for real-time AI development.⁵ Furthermore, regulatory constraints, data privacy concerns and substantial manpower investments are required to maintain adaptive and well validated systems to reap the long term benefits of AI in Orthopaedics.⁶

The main aim of this review is to synthesize current evidence on big data, AI and registry-based research in Orthopaedic Surgery, critically evaluating methodological trends, applications and limitations across key Orthopaedic data domains. A comprehensive literature search was performed using PubMed, supplemented by manual screening of reference lists from key review articles. Searches were conducted for articles published between January 2000 and July 2025, reflecting the emergence and evolution of big-data analytics, AI and registry-based research in Orthopaedic Surgery. Key search terms included combinations of “Orthopaedic Surgery”, “Big Data”, “Artificial Intelligence”, “Machine Learning” and “Registry”. Studies were included if they addressed applications of big data, AI or registry-based research in Orthopaedic Surgery, including clinical, registry, imaging, intraoperative or outcomes-based studies. Included studies were organised using a domain-based scoping framework, categorising evidence into the following thematic areas: Predictive analytics, Imaging-based AI applications, Natural language processing, Robotic and intraoperative data analytics, Orthopaedic registry-based research and Governance, bias and regulatory concerns. Within each domain, studies were synthesised critically with attention to dataset characteristics, methodological robustness and validation strategies to determine generalisability.

What is big data in Orthopaedics?

If data is just data, why should big data be anything new? Traditional data typically comprises of well-structured information stored in smaller, relational and static database while big data spawns massive and diverse datasets of both structured and unstructured information. Traditional data tends to be easier to analyze though simple statistical analysis while Big data requires advanced analytical techniques such a machine learning to manage the increased volume and complexity. Big data in Orthopaedics focuses on data characteristics and analytical opportunities and can be broadly categorized and interpreted through five Vs, a framework of the innate characteristics of big data that evolved from Doug Laney’s work in 2001.⁷ The five V’s are volume, velocity, variety, veracity, and value. Understanding these dimensions helps to appreciate the opportunities and complexities involved in capitalizing on this trend to advance clinical care and research in Orthopaedics.

Firstly, large volumes of healthcare related data are growing exponentially year on year. It is estimated that more than two million healthcare-related data points are generated daily from a range of technologies, including electronic medical records (EMRs), radiographic imaging, intraoperative robotic systems, and wearable health monitoring devices.^8,9 This continuous accumulation of data represents a rich resource for machine learning models and is key to performing outcome-driven analytics. Secondly, the velocity at which data is generated and promulgated has accelerated significantly.¹⁰ Modern Orthopaedic workflows may include real-time data captured through wearable technologies, robotic-assisted surgical platforms and even sensor-enabled implants¹ The use of Natural Language Processing (NLP) models have similarly allowed mining of free-text operative notes and clinical charts, allowing extraction of high quality data such as implant and surgery related data.² Thirdly, the variety of analyzable data sources within the context of Orthopaedic Surgery is growing. Beyond structured datasets such as operative notes and implant registries, a rich trove of previously untapped semi-structured and unstructured data, including radiographic measurements, intraoperative alignment strategies, free-text clinical notes, and continuous physiological monitoring from wearables, presents new opportunities for multimodal analysis. Despite the potential of big data, the veracity of it remains a concern for downstream analytics. Variability in data quality and access, inconsistencies in documentation practices, and the presence of artefacts or bias can compromise the reliability of downstream analyses.^9,11 Lastly, the value of big data lies in its capacity to transform clinical information into meaningful clinical decision-making tools, from enhancing surgical precision to driving personalized patient care models. Big data can thus be utilized effectively to pinpoint risk predictors, optimize preoperative planning, and uncover patterns not otherwise evident through conventional observational methods. Evidence based medicine has always been contrasted against what has colloquially been termed “Eminence” based medicine by focusing on systematic integration of the best and broadest available research evidence to guard against personal and parochial experience at evaluating clinical information. However, evidence-based medicine is only ever as good as its underlying data. Big data is a tremendous boon for evidence-based medicine by presenting a hyper-data informed approach that considers a much greater amount of ground data to improve outcomes and health system efficiency.

Big data and Orthopaedic registries: From volume to value

While the conceptual framework of big data in Orthopaedics is broad, its most established and scalable implementation to date has been through national and international Orthopaedic registries. These registries operationalise the principles of big data through the five Vs, most importantly creating value by driving evidence based and clinician oriented medical and surgical decisions. Since the first nationwide registry was established in 1975 in Sweden, the total number of registries have been steadily increasing, with Jozefowski et al. identifying 34 trauma and fracture registries in 2025, along with 31 members in the International Society of Arthroplasty Registries (ISAR), contributed by countries such as Sweden, Australia, Canada and Japan.^12–14 Moreover, arthroplasty related registry-based publications have likewise increased. A bibliometric analysis conducted by Romanini et al. demonstrated that its annual average growth was 28% in 2020, higher than the average of 10% for general arthroplasty literature.¹⁵ Registries collect high volumes of data across populations, allowing large scale and real-world data harnessing capabilities. This supports robust analyses of events, comparative effectiveness and development of key clinical frameworks and decision making processes.¹⁶ Many modern Orthopaedic registries incorporate PROMs, including the registry affiliated with the authors’ institution. Adding patient-centred perspectives and outcome measures on top of objective data such as revision and complication rates allow the surgeon to monitor implant performance and surgical techniques. The use of computerised adaptive testing (CAT) has also allowed researchers to develop more concise orthopaedic related PROMs, improving the follow up rates.¹⁷ The aggregation of such data in the form of annual registry reports such as those of the American Joint Replacement Registry offer feedback to surgeons, institutions, governments and the general public for peer to peer comparison and quality improvement measures.^8,18,19 Evidently, registry-based data forms a solid foundation for Orthopaedic research. In order to fully unlock its utility, modern Orthopaedic registries must continue to evolve and incorporate multimodal data, embrace interoperability, standardise quality assessment and employ cross-disciplinary frameworks.

Transforming big data: Applications of artificial intelligence in Orthopaedics

While Orthopaedic registries and multimodal datasets have enabled data accumulation at scale, clinical utility remains constrained by traditional data analytics. AI offers a paradigm shift in the processing capabilities of analytical software, transforming the extraction and interpretation of big data. Examples of such computational capabilities and methodologies are machine learning (ML), deep learning (DL) and neural networks (NN). These tools are rapidly emerging as foundational analytical infrastructure for AI to unlock the latent potential of big data in Orthopaedics. Furthermore, advanced DL and ML techniques that employ convolutional neural networks (CNN) are increasingly able to extract and analyse radiological imaging with astounding accuracy.^20,21 Such algorithms are now capable of identifying complex, nonlinear relationships within heterogenous datasets. They represent a transitional shift away from regression based modelling that focuses on the relationships between a few well defined variables towards systems that can thrive on heterogeneity and scale whilst being adaptive and self-improving with time.^22,23

Predictive analytics in Orthopaedics

Predictive analytics leverages on rich datasets and progressive ML methods to forecast and predict downstream clinical outcomes. Illustrating how this trend may improve clinical care is developing. Domb et al. analysed the pre-operative factors of a cohort of 2415 hip arthroscopy patients via Cox proportional hazards and Fine-Gray models. Thereafter, an institution-specific, ML based prognostic model with a high C index for predicting survivorship and repeat surgeries for patients undergoing hip arthroscopy was created. This model was then adapted into a web based tool to assist surgeons with shared decision making.²⁴ Abraham et al. applied XGBoost, an open source software library for ML on the 2014 to 2019 National Surgical Quality Improvement Program database of aseptic revision total hip and knee arthroplasty. This was a large database of over 40,000 patients across a wide range of clinical settings with preoperative laboratory values. XBoost was able to handle missing data, reduce model complexity and assess nuanced and non-liner relationships between variables. This generated a model capable of predicting 30-days mortality, cardiovascular events and respiratory complications for aseptic revision total joint arthroplasty, with a C statistics ranging from 0.78 to 0.88. Similarly, this work led to a freely accessible web calculator for assessing preoperative risk.²⁵ Ghadirinejad et al. recently performed a large multi-study review, modelling postoperative clinical outcomes for hip and knee arthroplasty using supervised machine learning, reliably forecasting outcomes such as readmission, complications, length of stay and patient-reported outcome measures (PROMs).²⁶ Ghadirinejad et al. were the first to develop preoperative algorithms to predict postoperative opioid use after THA, using multimodal ML algorithms such as stochastic gradient boosting, random forest, support vector machine, neural networks and elastic-net penalized logistic regression.

Predictive analytics based on new ML techniques are able to achieve better accuracy thus aiding Orthopaedic surgeons at determining what is best for patients, optimising resource usage and minimizing surgically related complications. The capability to accurately predict resource utilization, and patient outcomes also provides immense value such as right-siting of care, healthcare policy planning and cost estimation to institutions, governments and third party payors. However, current predictive models rely on retrospective datasets with internal validation only, impeding scalability. While registry-based studies improve sample size and representativeness, external validation across healthcare systems remains inconsistent.^24,26

Imaging-based analytics

Imaging-based AI applications represent one of the most mature domains of big-data analytics in Orthopaedic Surgery, largely due to the availability of standardised imaging modalities. CNNs and DL models may be applied to radiographs, magnetic resonance imaging (MRI) and computerised tomography (CT) scans for diagnostic tasks. Longo et al. performed a recent systematic review summarising over 11 million imaging studies, concluding that AI algorithms which incorporate CNNs consistently achieved high performance on segmentation, detection and classification across multiple imaging modalities.²⁷ These models have demonstrated performance comparable to or exceeding radiologists in specific, well-defined imaging tasks under controlled conditions, although large scale generalisability across institutions and clinical settings remain limited. For plain radiographs of the wrist, CNN models such as VGG-16, ResNet-50 and GoogLeNet achieved high accuracy in identifying fractures, achieving rates of up to 93% accuracy. In a 2023 systematic review, Dankelman et al. first noted that CNNs applied to fracture recognition and classification on CT scans could aid surgeons by improving diagnostic accuracy, reducing both time to diagnosis and the number of missed diagnoses consistently.²⁸ This effect is further amplified in cases where there is high inter-observer variability such as when CT scans are interpreted by more than one professional. Despite the improving diagnostic accuracy of these models, Groot et al. demonstrated that many of the current studies are predominantly retrospective, single-centre datasets with limited external validation.²⁹ Oeding et al. further described that the reliance on retrospectively curated datasets with homogenous imaging protocols, consistent hardware and expert-level annotations result in failure of the models to capture the variability encountered in routine clinical practice.³⁰ This includes differences in radiographic positioning, exposure parameters, implant designs and reporting standards. Consequently, models demonstrating excellent internal accuracy still exhibit degraded performances when applied to external datasets.^30,31 Collectively, despite promising results, the translational readiness of Orthopaedic imaging based AI remains constrained. Addressing the external validation gap will require purposeful integration of multicentre datasets, registry-based imaging repositories and prospective evaluation frameworks that ensure algorithmic performance is reproducible, generalisable and clinically meaningful.

Robotics and intraoperative data

Robotic-assisted surgeries in Orthopaedics have become more prevalent, especially in joint arthroplasty. Robotic-assisted TKA (RATKA) has demonstrated improved component alignment, reduced hip-knee-ankle (HKA) outliers and reduced coronal plane outliers compared to conventional TKA.³² Robotic and navigational systems in arthroplasty necessarily require the acquisition of various anatomical landmark data which are usually stored data. This provides a huge anatomical database that can be further researched beyond aiding the performance of the surgery. The current capabilities for ML and DL provides the catalyst for research using this huge minefield of data. As the ideal targets for TKA and THA are constantly changing, AI applications to existing navigational and robotic acquired data can be directed at integrating alignment accuracy and outcome metrics to derive patient specific personalised targets. MacDessi et al. first described the Coronal Plane Alignment of the Knee (CPAK) as a means to examine soft tissue parameters and balancing associated with TKA, comparing kinematic and conventional TKA alignment strategies.³³ Since then, the use of RATKA has allowed surgeons to accurately plan surgical alignment strategies in order to find the right alignment strategy for the right patient, even in the South-East Asian population.^34–37 Moreover, RATKA has provided surgeons with more real time high-frequency data such as joint angles, alignment parameters, and resection margins, enabling correlation with clinical outcome measures and final implant positioning.

Challenges and limitations

While AI holds transformative promise to improve patient outcomes and expand research opportunities, its integration into Orthopaedic research and clinical care remains constrained by several structural and methodological limitations. While early studies frequently report high internal performance metrics, implantation and deployment have continued to reveal challenges related to generalisability, validation, governance and cost.

Methodological and translational limitations

A primary limitation in the current developments of Orthopaedic AI is the prevalence of retrospective, single-institution datasets used for model development.^29,31 While these cohorts demonstrate high internal validity by capitalizing on consistent imaging protocols and standardized surgical workflows, they lack the demographic and technical diversity necessary for robust clinical application. Consequently, models developed in these environments often encounter performance degradation when used across a multitude of different clinical settings, driven by domain shift and inter-observer annotation variability. Literature reviews indicate a systemic deficiency in rigorous testing, with only a small fraction of medical imaging AI models undergoing independent external validation.^9,31 Within the Orthopaedic Surgery domain, this representation is sparse. The emerging trend of “negative findings” in external validation studies highlights a critical disconnect between successful proof-of-concept research and the realization of clinically deployable, generalizable diagnostic tools. Addressing this gap requires a transition toward multi-center prospective validation to ensure AI systems remain resilient to the nuances of global clinical practice.

Algorithmic bias

The key driver for progress in AI is data-driven algorithmic computation. Many successful AI models use adaptive AI, which is designed to continuously learn and improve over time by incorporating new data and information, as compared to previous static AI models which are trained on a fixed dataset.³⁸ These adaptive AI models are able to modify their outputs based on feedback and evolving environments, allowing the models to constantly adapt and stay accurate. However, if these systems are trained on non-representative cohorts and datasets, outcomes and findings can become biased. A 2024 study done by Siddiqui et al. demonstrated that AI models trained using knee and hip X-ray data from Caucasian males performed sub-optimally on females and non-Caucasian populations, leading to misdiagnosis and unideal treatment recommendations.³⁹ Unfortunately, AI models trained on registry data may reflect biases such as demographic, socioeconomic and institutional biases if key structural frameworks are not put in place before the promulgation of AI models across registries. Kurmis and Ianuzio first noted in 2022 on the integration of electronic health records, imaging, registry data and intraoperative data that due to varying operating and software platforms used and the overly heterogenous datasets generated, data analysis was difficult.⁴⁰ While AI models trained on registry data offers larger and more robust datasets, the lack of global consistency, the perennial problem of compliance and subsequent generalizability of results will continue to pose a significant hurdle for AI and Orthopaedics.

Regulatory constraints and data privacy

One of the greatest challenges in the foreseeable future for AI and its’ incorporation into Orthopaedics is the regulatory constraints with respect to the safety and equitable integration of data into models. There are divergent regulatory philosophies employed by the United States, European Union and China, as described by Tang et al.⁴¹ The United States adopts a more flexible and market-oriented approach, while the European Union enforces rigorous data protection measures as per the General Data Protection Regulation, and finally China employs a more comprehensive and process-driven framework heavily backed by real world data validation and algorithm traceability. Even locally, Singapore enforces a slightly different privacy policy following the Personal Data Protection Act (PDPA), which is more business-friendly and pragmatic, emphasising on consent and sectoral flexibility. For Orthopaedic surgeons operating across these different landscapes, differing priorities will be placed with regard to the use of AI in patient care. In the United States, there is priority in clinical performance over interpretability, whereas the European Union demands explainability and defensibility. Ultimately, clinical decisions such as those involving implant selection and fracture classification must both be defensible and transparent yet be made in a highly accurate, precise and reproducible way.

Future directions

The increasing availability of large-scale datasets and technological advancements in AI have garnered considerable optimism regarding the transformation of Orthopaedic research and clinical care. However, the current body of evidence reveal gaps between methodological promise and clinical implementation. Despite improved diagnostic accuracy and predictive performance, there has yet to be concrete evidence that supports generalisability, validation and real world impact in Orthopaedics.

Data deployment

At the core of AI is data, the foundational building block of all algorithms and models. As more emerging technologies in Orthopaedics present new avenues for data collection, Orthopaedic surgeons need to work with data scientists, regulatory authorities and researchers to develop standardised frameworks and workflows to optimise data analysis. In order to reduce algorithmic biases, registries need to be aggregated appropriately using methods such as standardized coding systems, common data dictionaries and harmonized outcome measures, allowing more care to be taken in order to address biases that might arise from registry based data. Chen et al. proposed techniques to mitigate algorithmic bias in a three pronged approach with pre-processing steps that improve subgroup balance through data blinding, augmentation or reweighting, in-processing steps that impose fairness-oriented optimisation constraints and post-processing strategies that recalibrate predictions to improve equity across subgroups.⁴² This also highlights that AI programmes and technologies, and the subsequent downstream use cases need to be clinician-informed. These AI based programs need to be explainable and surgeon-validated, allowing for seamless integration into clinical workflows and offer clinical utility to the Orthopaedic surgeon. Once algorithms are matured, there needs to be large scale, multi-institutional and international clinical trials to rigorously validate these AI algorithms across different patient populations and clinical settings. These efforts will be instrumental in enhancing generalisability and allow Orthopaedic surgeons to understand the clinical relevance of these tools. With the generation of multiple matured AI systems, Orthopaedic surgeons should then work to establish standardised data protocols and algorithmic transparency to facilitate integration into existing workflows, however diverse the target patient population is. Once these workflows are promulgated, processes will need to have a quality control system. Lee et al. proposed an auditing framework for registry data in a public hospital, improving data quality and ensuring the presence of integrated feedback loops, further providing internal consistency and validation to the collected data.⁴³

Clinician driven cost-benefit modelling

Research must quantify AI’s return on investments for it to be adopted. AI requires an increasingly sophisticated technological infrastructure along with hiring of experts with subject matter expertise. An AI based project will require multidisciplinary teams involving clinical scientists, data scientists, process and innovation managers. These infrastructure and manpower demands will lead to a significant increase in resource expenditure which must compete with a myriad of other demands. Returns in clinical efficiency, cost efficiency, cost savings and improved patient outcomes must then be used to justify this added expense. Crucially, these returns may not be immediately apparent and a balance will have to sought between increasing expenses and real returns. Hassan et al. described a process of technical evaluation, followed by clinical validation and finally economic validation by institutions and governing bodies as a means of providing adopters with the confidence in the effectiveness and accuracy of AI models. This confidence will then translate into AI use cases that are scalable and equitable.⁸

Governance

Governance is a key enabler in the successful integration of AI, facilitating progress from conceptualisation to clinical implementation. Hassan et al. recently introduced a new AI governance framework with the goal of equipping healthcare organisations with a means to implement and adopt AI systems.⁴⁴ The authors proposed an AI framework based on trust, with the three pillars of Ethics, Bias/Fairness and Transparency and Explainability, allowing for an adoption-centred governance framework with clearly defined responsibilities for organisations to consider. Ultimately, a good governance system within a healthcare institution should aim to ensure that AI is deployed safely, ethically and accurately. It should also aim to protect patient safety and foster trust, while still allowing innovation alongside rapid technological advancement. A good governance system should also uphold key ethical principles, maintaining equity, justice, accountability and informed consent. A robust governance structure should therefore comprise of a multidisciplinary team with sufficiently varied expertise and viewpoints with members holding clearly defined responsibilities. Clearly defined responsibilities ensure subsequent transparency, accountability and improves trust related concerns.^5,6,45,46 A governance body also has to responsible for maintaining high standards of equitable data collection, data quality and analysis whilst being adaptive and capable and adaptive at responding to rapid technological advancements and quick changes in regulatory landscapes.⁴⁷ As this is a nascent field, insight and direction from professional associations, thought leaders and even international collaborative think tanks will continue to shape the trajectory and regulatory frameworks. Overall, governing bodies will take the lead in being the regulatory watchdog that are responsible for AI oversight and approvals, establishing clear and robust regulatory and legal frameworks that clarify development requirements, clinical and technical responsibilities and the bounds of acceptable AI uses in Orthopaedics.^1,4,48 Government and institutional entities will also play critical roles beyond just oversight, ensuring that funding is secured, fostering integration between the healthcare and data science communities, aligning institutional and national goals as well as maintaining long term performance and public health related targets.^6,47

Conclusion

Big data, AI and registry-based data offer substantial opportunities to advance Orthopaedic research and clinical care but their translation into routine clinical practice is limited. Although early applications of AI in imaging and predictive analytics have demonstrated commendable proof-of-concept performance, concerns regarding single-centre datasets, external validation and subsequent integration into clinical workflows continue to hinder widespread adoption. Future progress will include depend on the standardisation of data definitions, scalable multicentre registry-linked datasets and rigorous external validation. Similarly, multidisciplinary teams will need to develop robust and adaptive frameworks to steward these systems and technologies in an effective and ethical manner.

Footnotes

ORCID iDs

Jia Yi Loh

Xian Khing Kenny Tay

Joyce Suang Bee Koh

Youheng Ou Yang

Funding

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

Declaration of conflicting interests

The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

References

Budhiparama

Kort

, et al. The future outlook for data in orthopedic surgery: a new era of real-time innovation. J Orthop Surg 2025; 33: 10225536251331664.

AlShehri

Sidhu

Lakshmanan

LVS

, et al. Applications of natural language processing for automated clinical data analysis in Orthopaedics. J Am Acad Orthop Surg 2024; 32: 439–446.

Vela

Sonay

Limani

, et al. Toward artificial intelligence in oncology and cardiology: a narrative review of systems, challenges, and opportunities. J Clin Med 2025; 14: 7555.

Bartsch

Behn

Benlian

, et al. Governance of high-risk AI systems in healthcare and credit scoring. Bus Inf Syst Eng 2025; 67: 563–581.

Baxter

Bass

Sitapati

. Barriers to implementing an artificial intelligence model for unplanned readmissions. ACI Open 2020; 4: e108–e113.

Hassan

Kushniruk

Borycki

. Barriers to and facilitators of artificial intelligence adoption in health care: scoping review. JMIR Hum Factors 2024; 11: e48633.

Doug

. 3D data management: controlling data volume, velocity, and variety. Gart File No 949 2001. https://blogs.gartner.com/douglaney/files/2012/01/ad949-3D-Data-Management-ControllingData-Volume-Velocity-and-Variety.pdf

Carender

Hegde

Levine

, et al. Highlights of the 2024 American joint replacement registry annual report. Arthroplasty Today 2025; 33: 101727.

Tan

Wakefield

Conaghan

, et al. Imaging of the musculoskeletal system: magnetic resonance imaging, ultrasonography and computed tomography. Best Pract Res Clin Rheumatol 2003; 17: 513–528.

10.

Kambhampati

SBS

Vishwanathan

Patralekh

, et al. Data for orthopaedic surgeons – a review. J Clin Orthop Trauma 2021; 21: 101505.

11.

Kumar

Sporn

Ong

, et al. Integrating artificial intelligence in orthopedic care: advancements in bone care and future directions. Bioengineering 2025; 12: 513.

12.

Delaunay

. Registries in Orthopaedics. Orthop Traumatol Surg Res 2015; 101: S69–S75.

13.

Magaway

Malanga

. Patient registries in orthopedics and orthobiologic procedures: a narrative review. BMC Musculoskelet Disord 2022; 23: 543.

14.

Jozefowski

Eikani

Lingampalli

, et al. The impact of national Orthopaedic fracture registries: a systematic review. OTA Int 2025; 8: e361.

15.

Romanini

Schettini

Torre

, et al. The rise of registry-based research: a bibliometric analysis. Acta Orthop 2021; 92: 628–632.

16.

Inacio

MCS

Paxton

Dillon

. Understanding orthopaedic registry studies: a comparison with clinical studies. J Bone Jt Surg 2016; 98: e3.

17.

Kane

Namdari

Plummer

, et al. Use of computerized adaptive testing to develop more concise patient-reported outcome measures. JBJS Open Access 2020; 5: e0052.

18.

Hegde

Stambough

Levine

, et al. Highlights of the 2022 American joint replacement registry annual report. Arthroplasty Today 2023; 21: 101137.

19.

Ryan

Stambough

Huddleston

, et al. Highlights of the 2023 American joint replacement registry annual report. Arthroplasty Today 2024; 26: 101325.

20.

Lemore

Vogt

Oster

, et al. Enhanced CT and MRI focal bone tumor classification with machine learning–based stratification: a multicenter retrospective study. Radiology 2025; 315: e232834.

21.

Rouzrokh

Wyles

Philbrick

, et al. A deep learning tool for automated radiographic measurement of acetabular component inclination and version after total hip arthroplasty. J Arthroplast 2021; 36: 2510–2517.e6.

22.

Youssef

De Wet

Back

, et al. Digitalization in Orthopaedics: a narrative review. Front Surg 2024; 10: 1325423.

23.

Tafat

Budka

McDonald

, et al. Artificial intelligence in orthopaedic surgery: a comprehensive review of current innovations and future directions. Comput Struct Biotechnol Rep 2024; 1: 100006.

24.

Domb

Ouyang

, et al. Personalized medicine using predictive analytics: a machine learning-based prognostic model for patients undergoing hip arthroscopy. Am J Sports Med 2022; 50: 1900–1908.

25.

Abraham

Booth

Geiger

, et al. Machine-learning models predict 30-Day mortality, cardiovascular complications, and respiratory complications after aseptic revision total joint arthroplasty. Clin Orthop 2022; 480: 2137–2145.

26.

Ghadirinejad

Milimonfared

Taylor

, et al. Supervised machine learning for the prediction of post‐operative clinical outcomes of hip and knee replacements: a review. ANZ J Surg 2024; 94: 1228–1233.

27.

Longo

Lalli

Nicodemi

, et al. Artificial intelligence demonstrates potential to enhance orthopaedic imaging across multiple modalities: a systematic review. J Exp Orthop 2025; 12: e70259.

28.

Dankelman

LHM

Schilstra

IJpma

FFA

, et al. Artificial intelligence fracture recognition on computed tomography: review of literature and recommendations. Eur J Trauma Emerg Surg 2023; 49: 681–691.

29.

Groot

Bongers

MER

Ogink

, et al. Does artificial intelligence outperform natural intelligence in interpreting musculoskeletal radiological studies? A systematic review. Clin Orthop 2020; 478: 2751–2764.

30.

Oeding

Krych

Pearle

, et al. Medical imaging applications developed using artificial intelligence demonstrate high internal validity yet are limited in scope and lack external validation. Arthrosc J Arthrosc Relat Surg 2025; 41: 455–472.

31.

Brejnebøl

Hansen

Nybing

, et al. External validation of an artificial intelligence tool for radiographic knee osteoarthritis severity classification. Eur J Radiol 2022; 150: 110249.

32.

García-Sanz

Sosa-Reina

Jaén-Crespo

, et al. Redefining knee arthroplasty: does robotic assistance improve outcomes beyond alignment? An evidence-based umbrella review. J Clin Med 2025; 14: 2588.

33.

MacDessi

Griffiths-Jones

Harris

, et al. Coronal plane alignment of the knee (CPAK) classification: a new system for describing knee phenotypes. Bone Jt J 2021; 103-B: 329–337.

34.

Schelker

Moret

Von Eisenhart-Rothe

, et al. The impact of different alignment strategies on bone cuts for neutral knee phenotypes in total knee arthroplasty. Knee Surg Sports Traumatol Arthrosc 2023; 31: 1267–1275.

35.

Vendittoli

Beckers

Massé

, et al. Why we should use boundaries for personalised knee arthroplasty and the lack of evidence for unrestricted kinematic alignment. Knee Surg Sports Traumatol Arthrosc 2024; 32: 1917–1922.

36.

Liu

Feng

. Kinematic alignment versus mechanical alignment in primary total knee arthroplasty: an updated meta-analysis of randomized controlled trials. J Orthop Surg 2022; 17: 201.

37.

Loh

Liow

MHL

Purnomo

, et al. Restricted kinematic total knee arthroplasty provided better functional outcomes and higher satisfaction rates for Asians of genu varum with apex distal joint line over unrestricted kinematic total knee arthroplasty. Arthroplasty 2025; 7: 33.

38.

Topol

. High-performance medicine: the convergence of human and artificial intelligence. Nat Med 2019; 25: 44–56.

39.

Siddiqui

Littlefield

Carlson

, et al. Fair AI-powered orthopedic image segmentation: addressing bias and promoting equitable healthcare. Sci Rep 2024; 14: 16105.

40.

Kurmis

Ianunzio

. Artificial intelligence in orthopedic surgery: evolution, current state and future directions. Arthroplasty 2022; 4: 9.

41.

Tang

, et al. Regulatory approaches towards AI medical devices: a comparative study of the United States, the European Union and China. Health Policy 2025; 153: 105260.

42.

Chen

Wang

Williamson

DFK

, et al. Algorithmic fairness in artificial intelligence for medicine and healthcare. Nat Biomed Eng 2023; 7: 719–742.

43.

Lee

Ebrahimi

Ektas

, et al. Implementation and quality assessment of a clinical Orthopaedic registry in a public hospital department. BMC Health Serv Res 2020; 20: 393.

44.

Hassan

Borycki

Kushniruk

. Artificial intelligence governance framework for healthcare. Healthc Manage Forum 2025; 38: 125–130.

45.

Isbanner

O’Shaughnessy

Steel

, et al. The adoption of artificial intelligence in health care and social services in Australia: findings from a methodologically innovative national survey of values and attitudes (the AVA-AI study). J Med Internet Res 2022; 24: e37611.

46.

Sunarti

Fadzlul Rahman

Naufal

, et al. Artificial intelligence in healthcare: opportunities and risk for future. Gac Sanit 2021; 35: S67–S70.

47.

Hussein

Zink

Ramadan

, et al. Advancing healthcare AI governance: a comprehensive maturity model based on systematic review 2024. medRvix 2024.12.39.24319785 DOI: 10.1101/2024.12.30.24319785.

48.

Kader

Coppola

Vijay

, et al. The future of precision Orthopaedics: personalized data-driven practice. Bone Jt Open. 2025 Jul 17; 6(7): 836–840. DOI:10.1302/2633-1462.