A practical guide to the implementation of artificial intelligence in orthopaedic research-Part 2: A technical introduction.

Recent advances in artificial intelligence (AI) present a broad range of possibilities in medical research. However, orthopaedic researchers aiming to participate in research projects implementing AI-based techniques require a sound understanding of the technical fundamentals of this rapidly developing field. Initial sections of this technical primer provide an overview of the general and the more detailed taxonomy of AI methods. Researchers are presented with the technical basics of the most frequently performed machine learning (ML) tasks, such as classification, regression, clustering and dimensionality reduction. Additionally, the spectrum of supervision in ML including the domains of supervised, unsupervised, semisupervised and self-supervised learning will be explored. Recent advances in neural networks (NNs) and deep learning (DL) architectures have rendered them essential tools for the analysis of complex medical data, which warrants a rudimentary technical introduction to orthopaedic researchers. Furthermore, the capability of natural language processing (NLP) to interpret patterns in human language is discussed and may offer several potential applications in medical text classification, patient sentiment analysis and clinical decision support. The technical discussion concludes with the transformative potential of generative AI and large language models (LLMs) on AI research. Consequently, this second article of the series aims to equip orthopaedic researchers with the fundamental technical knowledge required to engage in interdisciplinary collaboration in AI-driven orthopaedic research. Level of Evidence: Level IV.

Tibia-first, gap-balanced patient-specific alignment restores bony phenotypes and joint line obliquity in a great majority of varus and straight knees and normalises valgus and severe varus deformities.

PURPOSE: The present study focuses on testing the capability of a restricted tibia-first, gap-balanced patient-specific alignment technique (PSA) to restore bony morphology and phenotypes. METHODS: Three-hundred and sixty-seven patients were treated with navigated total knee arthroplasty and tibia-first gap-balanced PSA technique. Boundaries for medial proximal tibial angle were 86°-92°, mechanical lateral distal femoral angle 86°-92°, and hip-knee-ankle angle 175°-183°. Knees were classified by coronal plane alignment of the knee (CPAK), with subsequent analyses comparing pre- and postoperative distributions. Phenotype classification within CPAK groups assessed pre- and postoperative distributions. RESULTS: Preoperatively, the largest CPAK group was type II (30.8%), followed by type I (20.5%) and type V (17.8%). Postoperatively, type II remained the largest group (39%), followed by type V (30%). All groups with varus/valgus deformities (I, III, IV and VI) became smaller. While in straight legs (II, IV), the CPAK was restored in more than 70%-75%, in varus groups (I, IV) in 40%-50% and in valgus (III and VI) in 5%-18%. The joint line obliquity remained the same in the majority of knees (straight >75%; varus 63%-80%; valgus VI 95%), with the exception of CPAK III (40%). The phenotype analysis showed for straight legs a phenotype restoration of 85%, for varus 94% and for valgus 37%. Joint line convergence angle was reduced significantly in all groups from 1.8°-4.3° preoperatively to 0.6°-1.2° postoperatively. CONCLUSION: PSA restores bony phenotypes and joint line obliquity in the majority of straight and varus knees, while most of the valgus and extreme varus knees are normalised. LEVEL OF EVIDENCE: Level III, retrospective cohort study.

Unexpected early loosening of rectangular straight femoral Zweymüller stems with an alumina-reduced surface after total hip arthroplasty-a prospective, double-blind, randomized controlled trial.

BACKGROUND: Alumina particles from the grit blasting of Ti-alloy stems are suspected to contribute to aseptic loosening. An alumina-reduced stem surface was hypothesized to improve osseointegration and show comparable short-term outcomes to those of a standard stem. METHODS: In this prospective, double-blind, randomized trial, 26 standard (STD) and 27 experimental new technology (NT) stems were implanted. The latter were additionally treated by acid etching and ice blasting to remove alumina particles from the grit-blasting process. Follow-up occurred at 12 and 24 months. Bone mineral density (BMD) around the stem was measured by a dual-energy x-ray absorptiometry device (DEXA). Radiographs were reviewed for alterations. Clinical scoring comprised the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) and the Harris Hip Score (HHS). Survival rates were calculated up to 50 months. RESULTS: Lower mean BMD and more severe cortical hypertrophies were found in the NT group. At 12 months, radiolucent lines were observed mostly in the metaphyseal zone for both groups, with a progression tendency in the NT group at 24 months. At 12 months, pain scores and the WOMAC total and physical activity scores were significantly lower in the NT group, without any differences thereafter. The number of NT stem revisions amounted to 6 (24%) and 11 (41%) at 24 and 50 months, respectively. CONCLUSION: In the NT group, unexpected catastrophic failure rates of 41% caused by early aseptic loosening were noted within 50 months. Compared with the STD stems, NT stems lead to poor clinical and radiographic results. LEVEL OF EVIDENCE: II. TRIAL REGISTRATION: NCT05053048.

Gender-based differences exist in the functional knee phenotypes classification of the osteoarthritic knee.

PURPOSE: To identify gender differences in (1) the coronal alignment of functional knee phenotypes and (2) the JLCA (joint line convergence angle) in relation to the phenotype classification. METHODS: This study is a retrospective data analysis, including 12,099 osteoarthritic knee computed tomography (5025 male, 7074 female) analysed by Medacta software for hip-knee-ankle angle (HKA), femoral mechanical angle (FMA), tibial mechanical angle (TMA) and JLCA. The data were grouped into genders and combined according to the Functional Knee Phenotypes Classification. RESULTS: Out of 127 phenotypes for males and 131 for females, 17 common phenotypes were reported. The commonest four were similar for both genders with VARHKA177° NEUFMA93° NEUTMA87° (9.8% males, 9.50% females), followed by VARHKA174° NEUFMA93°VARTMA84° (7.1%) and VARHKA174°VARFMA90° NEUTMA87° (7.0%) for males and VARHKA174° NEUFMA93° NEUTMA87° (6.1%), VARHKA174° NEUFMA93°VARTMA84° (5.1%) for females. The commonest FMA and TMA (91.5° to 94.5° and 85.5° to 88.5°, respectively) were the same for both genders, however, the rest of the male population observed greater femoral varus than the female population (p < 0.001). JLCA values ranged from -28.4° to 8.2° in the overall study population. Males and females had a mean JLCA of -2.96° (±2.6° SD) and -2.66° (±2.8°7 SD), respectively, p < 0.001. CONCLUSIONS: Gender differences exist within the osteoarthritic knee phenotype. The male varus phenotype is influenced by FMA, while TMA values are similar across genders. JLCA variations show similarities to both TMA and FMA, suggesting JLCA is influenced by bone morphology more than by gender. These differences inform surgical decision-making for the personalised approach to the primary TKA. LEVEL OF EVIDENCE: Level III.

Only 26% of Native Knees Show an Identical Coronal Functional Knee Phenotype in the Contralateral Knee.

BACKGROUND: A comprehensive exploration evaluating left-to-right knee symmetry across all anatomical planes utilizing three-dimensional (3D) scans stands absent from the existing body of research. Therefore, the primary objectives of this investigation involved examining potential differences and resemblances in alignment and structure between left and right non-osteoarthritic (native) knees in various planes (coronal, sagittal, and axial) using three-dimensional single-photon emission computed tomography/computed tomography (SPECT/CT) images. METHODS: A total of 282 native knees from 141 patients were retrospectively gathered from the hospital's records. Patients, aged between 16 and 45, who underwent Tc99m-methyl diphosphonate SPECT/CT scans for both knees, adhering to the Imperial Knee Protocol, were included. A statistical analysis was conducted, including 23 knee morphometric parameters, comparing left and right knees, and classifying them based on functional knee phenotypes across the coronal, sagittal, and axial planes. RESULTS: Regarding the functional coronal knee phenotype, 26% of patients (n = 37) exhibited identical phenotypes in both knees (p < 0.001). Significant correlated similarities between the left and right knees were observed in the coronal plane (Pearson's r = 0.76, 0.68, 0.76, 0.76, p < 0.001) and in several morphometric measures in the sagittal plane (Pearson's r = 0.92, 0.72, 0.64, p < 0.001). Moderately correlated similarities were noted in the axial plane (Pearson's r = 0.43, 0.44, 0.43, p < 0.001). CONCLUSIONS: Only 26% of native knees exhibit an identical coronal phenotype in their contralateral knee, whereas 67% have the adjacent coronal phenotype. Strongly correlated resemblances were established across various left and right knee morphometric parameters in the coronal, sagittal, and axial planes. These findings could enhance decisions in procedures like total knee arthroplasties or osteotomies, where alignment is key to outcomes, and reveal a potential for future artificial intelligence-driven models to improve our understanding and improve personalized treatment strategies for knee osteoarthritis.

No differences in terms of complications, readmissions, reoperations, and patient-reported outcomes in simultaneous bilateral versus staged bilateral total knee arthroplasty in selected patients.

BACKGROUND: The safety and the clinical success of simultaneous bilateral total knee arthroplasty (BTKA) is controversial. The aim of this study was to compare complications and patient-reported outcomes following simultaneous BTKA (simBTKA) versus staged BKTA (staBTKA) in patients affected by bilateral symptomatic end-stage knee osteoarthritis (OA). METHODS: Data from patients who underwent simBTKA or staBTKA at a single institution from January 2017 to December 2020, with a minimum 1-year follow up period were retrospectively collected. Differences in terms of complications and clinical success were compared among the simBTKA and staBTKA patient groups. Alpha was set at 0.05. RESULTS: A total of 173 patients were included in this study. The results revealed no statistically significant differences between the two groups in terms of mortality, revision rate, readmission rate, local and systemic complications and patient-reported outcomes. SimBTKA group had a shorter operating room time (96 (73-119) vs. 195 (159-227); P < 0.0001), and length of hospital stay (4 (3-5) vs. 7 (6-9); P < 0.0001) compared with the staBTKA group. CONCLUSIONS: SimBTKA performed in a selected patient population at a high-volume center can be considered comparable to staBTKA in terms of safety, postoperative complications, 30-day readmissions and patient satisfaction. Consequently, reduced operating room time and hospital stay renders simBTKA a cost-effective and advantageous option, not only for patients, but also for healthcare institutes. Furthermore, the current study also highlights the importance of correct patient selection based on clinical preoperative characteristics.

Definition of normal, neutral, deviant and aberrant coronal knee alignment for total knee arthroplasty.

PURPOSE: One of the most pertinent questions in total knee arthroplasty (TKA) is: what could be considered normal coronal alignment? This study aims to define normal, neutral, deviant and aberrant coronal alignment using large data from a computed tomography (CT)-scan database and previously published phenotypes. METHODS: Coronal alignment parameters from 11,191 knee osteoarthritis (OA) patients were measured based on three dimensional reconstructed CT data using a validated planning software. Based on these measurements, patients' coronal alignment was phenotyped according to the functional knee phenotype concept. These phenotypes represent an alignment variation of the overall hip knee ankle angle (HKA), femoral mechanical angle (FMA) and tibial mechanical angle (TMA). Each phenotype is defined by a specific mean and covers a range of ±1.5° from this mean. Coronal alignment is classified as normal, neutral, deviant and aberrant based on distribution frequency. Mean values and distribution among the phenotypes are presented and compared between two populations (OA patients in this study and non-OA patients from a previously published study). RESULTS: The arithmetic HKA (aHKA), combined normalised data of FMA and TMA, showed that 36.0% of knees were neutral within ±1 SD from the mean in both angles, 44.3% had either a TMA or a FMA within ±1-2 SD (normally aligned), 15.3% of the patients were deviant within ±2-3 SD and only 4.4% of them had an aberrant alignment (±3-4 SD in 3.4% and >4 SD in 1.0% of the patients respectively). However, combining the normalised data of HKA, FMA and TMA, 15.4% of patients were neutral in all three angles, 39.7% were at least normal, 27.7% had at least one deviant angle and 17.2% had at least one aberrant angle. For HKA, the males exhibited 1° varus and females were neutral. For FMA, the females exhibited 0.7° more valgus in mean than males and grew 1.8° per category (males grew 2.1° per category). For TMA, the males exhibited 1.3° more varus than females and both grew 2.3° and 2.4° (females) per category. Normal coronal alignment was 179.2° ± 2.8-5.6° (males) and 180.5 > ± 2.8-5.6° (females) for HKA, 93.1 > ± 2.1-4.2° (males) and 93.8 > ± 1.8-3.6° (females) for FMA and 86.7 > ± 2.3-4.6° (males) and 88 > ± 2.4-4.8° (females) for TMA. This means HKA 6.4 varus or 4.8° valgus (males) or 5.1° varus to 6.1° valgus was considered normal. For FMA HKA 1.1 varus or 7.3° valgus (males) or 0.2° valgus to 7.4° valgus was considered normal. For TMA HKA 7.9 varus or 1.3° valgus (males) or 6.8° varus to 2.8° valgus was considered normal. Aberrant coronal alignment started from 179.2° ± 8.4° (males) and 180.5 > ± 8.4° (females) for HKA, 93.1 > ± 6.3° (males) 93.8 > ± 5.4° (females) for FMA and 86.7 > ± 6.9° (males) and 88 > ± 7.2° (females) for TMA. This means HKA > 9.2° varus or 7.6° valgus (males) or 7.9° varus to 8.9° valgus was considered aberrant. CONCLUSION: Definitions of neutrality, normality, deviance as well as aberrance for coronal alignment in TKA were proposed in this study according to their distribution frequencies. This can be seen as an important first step towards a safe transition from the conventional one-size-fits-all to a more personalised coronal alignment target. There should be further definitions combining bony alignment, joint surfaces' morphology, soft tissue laxities and joint kinematics. LEVEL OF EVIDENCE: III.

Gluteal Complex is important in External Snapping Hip: intraoperative identification of syndrome origin and endoscopic stepwise release-a case series.

PURPOSE: External snapping hip syndrome (ESHS) was historically attributed to isolated iliotibial band (ITB) contracture. However, the gluteus maximus complex (GMC) may also be involved. This study aimed to intraoperatively identify the ESHS origin and assess the outcomes of endoscopic treatment based on the identified aetiological type. METHODS: From 2008-2014, 30 consecutive patients (34 hips) with symptomatic ESHS cases refractory to conservative treatment underwent endoscopic stepwise "fan-like" release, gradually addressing all known reasons of ESHS: from the isolated ITB, through the fascial part of the GMC until a partial release of gluteus maximus femoral attachment occurred. Snapping was assessed intra-operatively after each surgical step and prospectively recorded. Functional outcomes were assessed via the MAHORN Hip Outcome Tool (MHOT-14). RESULTS: Twenty seven patients (31 hips) were available to follow-up at 24-56 months. In all cases, complete snapping resolution was achieved intra-operatively: in seven cases (22.6%) after isolated ITB release, in 22 cases (70.9%), after release of ITB + fascial part of the GMC, and in two cases (6.5%) after ITB + fascial GMC release + partial release of GM femoral insertion. At follow-up, there were no snapping recurrences and MHOT-14 score significantly increased from a pre-operative average of 46 to 93(p<0.001). CONCLUSION: Intraoperative identification and gradual addressing of all known causes of ESHS allows for maximum preservation of surrounding tissue during surgery while precisely targeting the directly involved structures. Endoscopic stepwise "fan-like" release of the ITB and GMC is an effective, tailor-made treatment option for ESHS regardless of the snapping origin in the patients with possibility to manually reproduce the snapping.

Ten Flaws of Systematic Mechanical Alignment Total Knee Arthroplasty.

Mechanical alignment (MA) and its tenets have been considered essential for total knee arthroplasty (TKA) success since they were introduced in 1973. However, over time, there have been colossal advances in our knowledge and understanding of the anatomy and kinematics of the knee, as well as in surgical precision and implants. However, the MA systematic principles of prosthetic arthroplasty and implant position related to the lower-extremity mechanical axis, have only recently been called into question. The high rates of dissatisfaction and residual pain reported after MA TKA prompted this questioning, and that leaves plenty of room for improvement. Despite the general consensus that there is great variability between patients' anatomy, it is still the norm to carry out a systematic operation that does not consider individual variations. Evolving to a more personalized arthroplasty surgery was proposed as a rational and reasonable option to improve patient outcomes. Transitioning to a personalized TKA approach requires questioning and even disregarding certain MA TKA principles. Based on current knowledge, we can state that certain principles are erroneous or unfounded. The aim of this narrative review was to discuss and challenge 10 previously accepted, yet we believe, flawed, principles of MA, and to present an alternative concept, which is rooted in personalized TKA techniques.

Why personalized surgery is the future of hip and knee arthroplasty: a statement from the Personalized Arthroplasty Society.

Although hip and knee joint replacements provide excellent clinical results, many patients still do not report the sensation and function of a natural joint. The perception that the joint is artificial may result from the anatomical modifications imposed by the surgical technique and the implant design. Moreover, the joint replacement material may not function similarly to human tissues. To restore native joint kinematics, function, and perception, three key elements play a role: (i) joint morphology (articular surface geometry, bony anatomy, etc.), (ii) lower limb anatomy (alignment, joint orientation), and (iii) soft tissue laxity/tension. To provide a 'forgotten joint' to most patients, it is becoming clear that personalizing joint replacement is the key solution. Performing a personalized joint replacement starts with patient selection and preoperative optimization, followed by using a surgical technique and implant design aimed at restoring the patient's native anatomy, creating optimal implant-to-bone stress transfer, restoring the joint's native articular range of motion without imposed limitations, macro- and micro-stability of the soft tissues, and a bearing whose wear resistance provides lifetime survivorship with unrestricted activities. In addition, the whole perioperative experience should follow enhanced recovery after surgery principles, favoring a rapid and complication-free recovery. As a new concept, some confusion may arise when applying these personalized surgery principles. Therefore, the Personalized Arthroplasty Society was created to help structure and accelerate the adoption of this paradigm change. This statement from the Society on personalized arthroplasty will serve as a reference that will evolve with time.

Definitions and consequences of current alignment techniques and phenotypes in total knee arthroplasty (TKA) - there is no winner yet.

Dissatisfaction following total knee arthroplasty (TKA) has been extensively documented and it was attributed to numerous factors. In recent years, significant focus has been directed towards implant alignment and stability as potential causes and solutions to this issue. Surgeons are now exploring a more personalized approach to TKA, recognizing the importance of thoroughly understanding each individual patient's anatomy and functional morphology. A more comprehensive preoperative analysis of alignment and knee morphology is essential to address the unresolved questions in knee arthroplasty effectively. The crucial task of determining the most appropriate alignment strategy for each patient arises, given the substantial variability in bone resection resulting from the interplay of phenotype and the alignment strategy chosen. This review aims to comprehensively present the definitions of different alignment techniques in all planes and discuss the consequences dependent on knee phenotypes.Level of evidence V.

A practical guide to the implementation of AI in orthopaedic research - part 1: opportunities in clinical application and overcoming existing challenges.

Artificial intelligence (AI) has the potential to transform medical research by improving disease diagnosis, clinical decision-making, and outcome prediction. Despite the rapid adoption of AI and machine learning (ML) in other domains and industry, deployment in medical research and clinical practice poses several challenges due to the inherent characteristics and barriers of the healthcare sector. Therefore, researchers aiming to perform AI-intensive studies require a fundamental understanding of the key concepts, biases, and clinical safety concerns associated with the use of AI. Through the analysis of large, multimodal datasets, AI has the potential to revolutionize orthopaedic research, with new insights regarding the optimal diagnosis and management of patients affected musculoskeletal injury and disease. The article is the first in a series introducing fundamental concepts and best practices to guide healthcare professionals and researcher interested in performing AI-intensive orthopaedic research studies. The vast potential of AI in orthopaedics is illustrated through examples involving disease- or injury-specific outcome prediction, medical image analysis, clinical decision support systems and digital twin technology. Furthermore, it is essential to address the role of human involvement in training unbiased, generalizable AI models, their explainability in high-risk clinical settings and the implementation of expert oversight and clinical safety measures for failure. In conclusion, the opportunities and challenges of AI in medicine are presented to ensure the safe and ethical deployment of AI models for orthopaedic research and clinical application. Level of evidence IV.

Tips and tricks for how to become a good reviewer.

Peer review is an essential process to ensure that scientific articles meet high standards of methodology, ethics and quality. The peer-review process is a part of the academic mission for physicians in the university setting. The work of reviewers is of great value for authors, as it gives constructive criticism and improves manuscript quality before publication. Often, however, reviews are of suboptimal quality. Usually, reviewers do not receive formal training either on how to perform a review or on the peer-review process. In addition, it is generally believed that experienced authors are great reviewers, but this may not always be true. The overarching goal of a review is to make the manuscript better; to help the authors. The purpose of this article is to offer relevant suggestions and provide a checklist on how to perform a useful review.

Significant correlations between postoperative outcomes and various limb and component alignment strategies in medial unicompartmental knee arthroplasty: a systematic review.

PURPOSE: To investigate the correlation between postoperative limb/component alignments and clinical/functional outcomes following medial unicondylar knee arthroplasty (mUKA). METHODS: Inclusion criteria included peer-reviewed English- or German-language publications assessing postoperative limb or implant alignment and clinical outcomes of mUKA. Methodological Index for Non-Randomized Studies (MINORS) was used to assess article quality. RESULTS: A total of 2767 knees from 2604 patients were evaluated. Significant correlations were observed between postoperative limb/component alignments and clinical/functional outcomes after mUKA. Inferior outcomes were associated with lower placement and excessive valgus alignment of the tibia component (> 3°). A recommended external rotation of 4°-5° was identified for the tibia component, with specific cut-off values for the femoral and tibia components. CONCLUSIONS: Optimal outcomes in mUKA were associated with a varus coronal limb alignment. The tibia implant component performed well within a specific alignment range. An exact external rotation value was recommended for the tibia component, while internal rotation correlated negatively with the femoral component. LEVEL OF EVIDENCE: IV (level IV retrospective case series were included).