RESUMO
Purpose: The present study reviews the available scientific literature on artificial intelligence (AI)-assisted ultrasound-guided regional anaesthesia (UGRA) and evaluates the reported intraprocedural parameters and postprocedural outcomes. Methods: A literature search was performed on 19 September 2023, using the Medline, EMBASE, CINAHL, Cochrane Library and Google Scholar databases by experts in electronic searching. All study designs were considered with no restrictions regarding patient characteristics or cohort size. Outcomes assessed included the accuracy of AI-model tracking, success at the first attempt, differences in outcomes between AI-assisted and unassisted UGRA, operator feedback and case-report data. Results: A joint adaptive median binary pattern (JAMBP) has been applied to improve the tracking procedure, while a particle filter (PF) is involved in feature extraction. JAMBP combined with PF was most accurate on all images for landmark identification, with accuracy scores of 0.83, 0.93 and 0.93 on original, preprocessed and filtered images, respectively. Evaluation of first-attempt success of spinal needle insertion revealed first-attempt success in most patients. When comparing AI application versus UGRA alone, a significant statistical difference (p < 0.05) was found for correct block view, correct structure identification and decrease in mean injection time, needle track adjustments and bone encounters in favour of having AI assistance. Assessment of operator feedback revealed that expert and nonexpert operator feedback was overall positive. Conclusion: AI appears promising to enhance UGRA as well as to positively influence operator training. AI application of UGRA may improve the identification of anatomical structures and provide guidance for needle placement, reducing the risk of complications and improving patient outcomes. Level of Evidence: Level IV.
RESUMO
OBJECTIVES: Reaching the Patient-Acceptable Symptom State (PASS) threshold for the Knee injury and Osteoarthritis Outcome Score (KOOS) has previously been reported to successfully identify individuals experiencing clinical success after anterior cruciate ligament reconstruction (ACLR). Thus, the objectives of this study were to examine and compare the percentages of patients meeting PASS thresholds for the different KOOS subscales 1 year postoperatively after primary ACLR compared with revision ACLR (rACLR) and multiply revised ACLR (mrACLR), and second, to examine the predictors for reaching PASS for KOOS Quality of Life (QoL) and Function in Sport and Recreation (Sport/Rec) after mrACLR. DESIGN: Prospective observational registry study. SETTING: The data used in this study was obtained from the Swedish National Ligament Registry and collected between 2005 and 2020. PARTICIPANTS: The study sample was divided into three different groups: (1) primary ACLR, (2) rACLR and (3) mrACLR. Data on patient demographic, injury and surgical characteristics were obtained as well as mean 1-year postoperative scores for KOOS subscales and the per cent of patients meeting PASS for each subscale. Additionally, the predictors of reaching PASS for KOOS Sport/Rec, and QoL subscales were evaluated in patients undergoing mrACLR. RESULTS: Of the 22 928 patients included in the study, 1144 underwent rACLR and 36 underwent mrACLR. Across all KOOS subscales, the percentage of patients meeting PASS thresholds was statistically lower for rACLR compared with primary ACLR (KOOS Symptoms 22.5% vs 32.9%, KOOS Pain 84.9% vs 92.9%, KOOS Activities of Daily Living 23.5% vs 31.4%, KOOS Sport/Rec 26.3% vs 45.6%, KOOS QoL 26.9% vs 51.4%). Percentages of patients reaching PASS thresholds for all KOOS subscales were comparable between patients undergoing rACLR versus mrACLR. No predictive factors were found to be associated with reaching PASS for KOOS QoL and KOOS Sport/Rec 1 year postoperatively after mrACLR. CONCLUSION: Patients undergoing ACLR in the revision setting had lower rates of reaching acceptable symptom states for functional knee outcomes than those undergoing primary ACLR. LEVEL OF EVIDENCE: Prospective observational registry study, level of evidence II.
Assuntos
Lesões do Ligamento Cruzado Anterior , Reconstrução do Ligamento Cruzado Anterior , Qualidade de Vida , Sistema de Registros , Reoperação , Humanos , Feminino , Masculino , Adulto , Estudos Prospectivos , Lesões do Ligamento Cruzado Anterior/cirurgia , Lesões do Ligamento Cruzado Anterior/fisiopatologia , Reoperação/estatística & dados numéricos , Adulto Jovem , Suécia , Medidas de Resultados Relatados pelo Paciente , Pessoa de Meia-Idade , Resultado do Tratamento , Recuperação de Função FisiológicaRESUMO
The application of Artificial intelligence (AI) and machine learning (ML) tools in total (TKA) and unicompartmental knee arthroplasty (UKA) emerges with the potential to improve patient-centered decision-making and outcome prediction in orthopedics, as ML algorithms can generate patient-specific risk models. This review aims to evaluate the potential of the application of AI/ML models in the prediction of TKA outcomes and the identification of populations at risk.An extensive search in the following databases: MEDLINE, Scopus, Cinahl, Google Scholar, and EMBASE was conducted using the PIOS approach to formulate the research question. The PRISMA guideline was used for reporting the evidence of the data extracted. A modified eight-item MINORS checklist was employed for the quality assessment. The databases were screened from the inception to June 2022.Forty-four out of the 542 initially selected articles were eligible for the data analysis; 5 further articles were identified and added to the review from the PUBMED database, for a total of 49 articles included. A total of 2,595,780 patients were identified, with an overall average age of the patients of 70.2 years ± 7.9 years old. The five most common AI/ML models identified in the selected articles were: RF, in 38.77% of studies; GBM, in 36.73% of studies; ANN in 34.7% of articles; LR, in 32.65%; SVM in 26.53% of articles.This systematic review evaluated the possible uses of AI/ML models in TKA, highlighting their potential to lead to more accurate predictions, less time-consuming data processing, and improved decision-making, all while minimizing user input bias to provide risk-based patient-specific care.
Assuntos
Artroplastia do Joelho , Inteligência Artificial , Aprendizado de Máquina , Humanos , Artroplastia do Joelho/métodos , Tomada de Decisão Clínica/métodos , Articulação do Joelho/cirurgia , Aprendizado de Máquina/tendências , Osteoartrite do Joelho/cirurgia , Medição de Risco/métodos , Resultado do TratamentoRESUMO
The 3 primary factors involved with preservation of the hip joint are femoroacetabular impingement (FAI), hip dysplasia, and femoral torsion abnormalities. Each of these factors affects the health of the acetabular labrum and femoroacetabular cartilage. The appropriate surgical treatments for each of these factors include arthroscopic or open femoroplasty or acetabuloplasty for FAI, periacetabular osteotomy (PAO) for acetabular dysplasia, and de-rotational femoral osteotomy for femoral torsion abnormalities. When evaluating patients with prearthritic hip conditions, orthopaedic surgeons should be aware of the various factors involved in hip joint preservation and, if surgery is indicated, surgeons should be sure to address all factors that need surgical treatment rather than focusing on the most obvious issue or injury (e.g., a labral tear). The purpose of this infographic is to illustrate the importance of the factors involved in hip joint preservation and the appropriate treatments for pathology in any of these factors.
Assuntos
Impacto Femoroacetabular , Articulação do Quadril , Humanos , Acetábulo/cirurgia , Artroscopia/métodos , Impacto Femoroacetabular/cirurgia , Fêmur/cirurgia , Luxação do Quadril/cirurgia , Articulação do Quadril/cirurgia , Osteotomia/métodosRESUMO
The three primary factors involved in preservation of the hip joint include femoroacetabular impingement (FAI), hip dysplasia/instability, and femoral torsion abnormalities. Each of these factors affects the health of the acetabular labrum and femoroacetabular cartilage. The appropriate surgical treatments for each of these factors include arthroscopic or open femoroplasty/acetabuloplasty for FAI, periacetabular osteotomy for hip dysplasia/instability, and derotational femoral osteotomy for femoral torsion abnormalities. When evaluating patients with prearthritic hip conditions, orthopaedic surgeons should be aware of the various factors involved in hip joint preservation and, if surgery is indicated, the surgeon should be sure to address all factors that need surgical treatment rather than focusing on the commonly diagnosed issue or visible injury, for example, a labral tear. If any of these factors is ignored, the hip joint may not thrive. The purpose of this review was to explain the importance of the most common factors involved in hip joint preservation and the appropriate surgical treatments for pathology in these factors.
RESUMO
PURPOSE: Patient dissatisfaction rates following total knee arthroplasty (TKA) reported in the literature reach 20%. The optimal coronal alignment is still under debate. The aim of this retrospective study was to compare clinical outcomes in different coronal plane alignment of the knee (CPAK) phenotypes undergoing mechanically aligned (MA) TKA. The hypothesis was that knees with preoperative varus arithmetic hip-knee-ankle angle (aHKA) would achieve inferior clinical outcomes after surgery compared to other aHKA categories. Additionally, another objective was to assess CPAK phenotypes distribution in the study population. METHODS: A retrospective selection was made of 180 patients who underwent MA TKA from April 2021 to December 2022, with a 1-year follow-up. Coronal knee alignment was classified according to the CPAK classification. Clinical outcome evaluations were measured using the Knee Society Score (KSS), Oxford Knee Score (OKS), Short Form Survey 12 and Forgotten Joint Score (FJS). Differences in clinical outcomes were considered statistically significant with a p value <0 .05. RESULTS: Patients with varus aHKA achieved significantly inferior outcomes at final follow-up compared to other aHKA categories in KSS pt. 1 (79.7 ± 17.2 vs. 85.6 ± 14.7; p = 0.028), OKS (39.2 ± 9.2 vs. 42.2 ± 7.2; p = 0.019) and FJS (75.4 ± 31.0 vs. 87.4 ± 22.9; p =0 .003). The most common aHKA category was the varus category (39%). The most common CPAK phenotypes were apex distal Types I (23.9%), II (22.8%) and III (13.3%). CONCLUSION: MA TKA does not yield uniform outcomes across all CPAK phenotypes. Varus aHKA category shows significantly inferior results at final follow-up. The most prevalent CPAK categories are varus aHKA and apex distal JLO, with phenotypes I, II and III being the most common. However, their gender distribution varies significantly. LEVEL OF EVIDENCE: Level IV.
RESUMO
Explorative data analysis (EDA) is a critical step in scientific projects, aiming to uncover valuable insights and patterns within data. Traditionally, EDA involves manual inspection, visualization, and various statistical methods. The advent of artificial intelligence (AI) and machine learning (ML) has the potential to improve EDA, offering more sophisticated approaches that enhance its efficacy. This review explores how AI and ML algorithms can improve feature engineering and selection during EDA, leading to more robust predictive models and data-driven decisions. Tree-based models, regularized regression, and clustering algorithms were identified as key techniques. These methods automate feature importance ranking, handle complex interactions, perform feature selection, reveal hidden groupings, and detect anomalies. Real-world applications include risk prediction in total hip arthroplasty and subgroup identification in scoliosis patients. Recent advances in explainable AI and EDA automation show potential for further improvement. The integration of AI and ML into EDA accelerates tasks and uncovers sophisticated insights. However, effective utilization requires a deep understanding of the algorithms, their assumptions, and limitations, along with domain knowledge for proper interpretation. As data continues to grow, AI will play an increasingly pivotal role in EDA when combined with human expertise, driving more informed, data-driven decision-making across various scientific domains. Level of Evidence: Level V - Expert opinion.
RESUMO
Purpose: To assess the possibility of using Generative Pretrained Transformer (ChatGPT) specifically in the context of orthopaedic trauma surgery by questions posed to ChatGPT and to evaluate responses (correctness, completeness and adaptiveness) by orthopaedic trauma surgeons. Methods: ChatGPT (GPT-4 of 12 May 2023) was asked to address 34 common orthopaedic trauma surgery-related questions and generate responses suited to three target groups: patient, nonorthopaedic medical doctor and expert orthopaedic surgeon. Three orthopaedic trauma surgeons independently assessed ChatGPT's responses by using a three-point response scale with a response range between 0 and 2, where a higher number indicates better performance (correctness, completeness and adaptiveness). Results: A total of 18 (52.9%) of all responses were assessed to be correct (2.0) for the patient target group, while 22 (64.7%) and 24 (70.5%) of the responses were determined to be correct for nonorthopaedic medical doctors and expert orthopaedic surgeons, respectively. Moreover, a total of 18 (52.9%), 25 (73.5%) and 28 (82.4%) of the responses were assessed to be complete (2.0) for patients, nonorthopaedic medical doctors and expert orthopaedic surgeons, respectively. The average adaptiveness was 1.93, 1.95 and 1.97 for patients, nonorthopaedic medical doctors and expert orthopaedic surgeons, respectively. Conclusion: The study results indicate that ChatGPT can yield valuable and overall correct responses in the context of orthopaedic trauma surgery across different target groups, which encompassed patients, nonorthopaedic medical surgeons and expert orthopaedic surgeons. The average correctness scores, completeness levels and adaptiveness values indicated the ability of ChatGPT to generate overall correct and complete responses adapted to the target group. Level of Evidence: Not applicable.
RESUMO
BACKGROUND: The relationship between hamstring strength and hop performance after anterior cruciate ligament (ACL) reconstruction with hamstring tendon (HT) autografts has not been well elucidated. The aim was to investigate the relationship between eccentric hamstring strength, assessed with the NordBord, and concentric hamstring strength, assessed with the Biodex, with hop performance at 8 and 12 months after ACL reconstruction. METHODS: Registry study. Patients ≥ 16 years who had undergone primary ACL reconstruction with HT autograft, followed by muscle strength and hop tests at 8 and 12 months were included. Correlations of the relative hamstring strength (Nm/kg or N/kg) and limb symmetry index (LSI) with hop performance were analyzed. Pearson's correlation coefficient, and coefficient of determination (r2) were used for statistical analysis. RESULTS: A total of 90 patients were included, of which 48 (53%) were women. The mean age at ACL reconstruction was 27.0 ± 8.0 years. Relative hamstring strength had significant positive correlations with hop performance, ranging from r = 0.25-0.66, whereas hamstring strength LSI had significant positive correlations which ranged from r = 0.22-0.37 at 8 and 12 months after ACL reconstruction. At 12 months, the relative hamstring strength in the Biodex explained 32.5-43.6% of the hop performance in vertical hop height, hop for distance relative to height, and the total number of side hops, whereas the relative hamstring strength in the NordBord explained 15.2-23.0% of the hop performance. CONCLUSION: The relative hamstring strength in the Biodex test explained 32.5-43.6% of the hop performance, whereas the relative hamstring strength in the NordBord explained 15.2-23.0%. Thus, our findings suggest that relative hamstring strength, especially in the hip-flexed position may be a better indicator of hop performance at 8 and 12 months after ACL reconstruction in patients treated with HT autograft.
RESUMO
Artificial intelligence's (AI) accelerating progress demands rigorous evaluation standards to ensure safe, effective integration into healthcare's high-stakes decisions. As AI increasingly enables prediction, analysis and judgement capabilities relevant to medicine, proper evaluation and interpretation are indispensable. Erroneous AI could endanger patients; thus, developing, validating and deploying medical AI demands adhering to strict, transparent standards centred on safety, ethics and responsible oversight. Core considerations include assessing performance on diverse real-world data, collaborating with domain experts, confirming model reliability and limitations, and advancing interpretability. Thoughtful selection of evaluation metrics suited to the clinical context along with testing on diverse data sets representing different populations improves generalisability. Partnering software engineers, data scientists and medical practitioners ground assessment in real needs. Journals must uphold reporting standards matching AI's societal impacts. With rigorous, holistic evaluation frameworks, AI can progress towards expanding healthcare access and quality. Level of Evidence: Level V.
RESUMO
Objective: The purpose of this study was to review the current literature regarding the non-operative treatment of isolated medial collateral ligament (MCL) injuries. Design: Systematic review, registered in the Open Science Framework (https://doi.org/10.17605/OSF.IO/E9CP4). Data sources: The Embase, MEDLINE and PEDro databases were searched; last search was performed on December 2023. Eligibility criteria: Peer-reviewed original reports from studies that included information about individuals who sustained an isolated MCL injury with non-surgical treatment as an intervention, or reports comparing surgical with non-surgical treatment were eligible for inclusion. Included reports were synthesised qualitatively. Risk of bias was assessed with the Risk of Bias Assessment tool for Non-randomized Studies. Certainty of evidence was determined using the Grading of Recommendations Assessment Development and Evaluation. Results: A total of 26 reports (1912 patients) were included, of which 18 were published before the year 2000 and 8 after. No differences in non-operative treatment were reported between grade I and II injuries, where immediate weight bearing and ambulation were tolerated, and rehabilitation comprised different types of strengthening exercises with poorly reported details. Some reports used immobilisation with a brace as a treatment method, while others did not use any equipment. The use of a brace and duration of use was inconsistently reported. Conclusion: There is substantial heterogeneity and lack of detail regarding the non-operative treatment of isolated MCL injuries. This should prompt researchers and clinicians to produce high-quality evidence studies on the promising non-operative treatment of isolated MCL injuries to aid in decision-making and guide rehabilitation after MCL injury. Level of evidence: Level I, systematic review.
RESUMO
Background: The timing of return to work (RTW) after anterior cruciate ligament (ACL) reconstruction (ACLR) is a less studied milestone compared with return to sports. Purpose: To systematically review the rate and postoperative timing of RTW after ACLR. Study Design: Systematic review; Level of evidence, 4. Methods: This study was conducted in accordance with the 2020 PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) statement. A literature search was performed in PubMed, Embase, Cochrane, and Ovid databases for clinical studies reporting RTW after ACLR, and 806 studies were identified in August 2022. A quality assessment was performed using the Methodological Index of Nonrandomized Studies (MINORS) grading system. The following data were extracted from studies: study characteristics, cohort demographics, ACLR technique, concomitant meniscal and/or cartilage procedures, preoperative patient-reported outcomes, rates of RTW, and days required for RTW after ACLR. Results: A total of 13 studies met inclusion criteria, totaling 1791 patients (86.4% male). Wide variability was observed in the methodological quality of the assessed studies (MINORS score range, 8-17). Hamstring tendon (HT) autograft was used in 76.8% (n = 1377; mean age, 30.5 years old), allograft in 17.1% (n = 308; mean age, 33.1 years old), the ligament advanced reinforcement system in 2.5% (n = 46; mean age, 33.2 years old), bone-patellar tendon-bone autograft in 2% (n = 36; mean age, 28.5 years old), and quadriceps tendon autograft in 1.3% (n = 24; mean age, 24.1 years old). Among the included patients, 99.1% (n = 1781) reported successful RTW after surgery. The mean time to RTW was 84.2 days (range, 31.4-107.1 days) for HT and 69.5 days (range, 49-56.6 days) for allograft. Conclusion: While data regarding work intensity before and after ACL injury were absent, our study results suggested that patients most often RTW within 90 days of surgery. Patients with allograft ACLR may RTW earlier than patients undergoing ACLR with HT autograft.
RESUMO
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.
RESUMO
This narrative review examines the current literature for the influence of the surgical timing in the setting of anterior cruciate ligament (ACL) reconstruction on various outcomes. Although the exact definition of early and delayed ACL reconstruction (ACLR) is a subject of controversy, surgical timing influences arthrofibrosis and postoperative stiffness, quadriceps strength, postoperative knee function, and the incidence of intra-articular injuries to the menisci and cartilage. Additionally, there is a shortage of evidence regarding the role of ACLR timing in the setting of multiligament knee injury and when concurrent procedures are performed during the operative treatment of the ACL-injured knee.
Assuntos
Lesões do Ligamento Cruzado Anterior , Reconstrução do Ligamento Cruzado Anterior , Humanos , Reconstrução do Ligamento Cruzado Anterior/métodos , Lesões do Ligamento Cruzado Anterior/cirurgia , Fatores de Tempo , Complicações Pós-OperatóriasRESUMO
Deep 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.
Assuntos
Aprendizado Profundo , Cirurgiões Ortopédicos , Humanos , Inteligência Artificial , Privacidade , Sistema de RegistrosRESUMO
This study explored professional wrestlers' experiences of the consequences of an anterior cruciate ligament (ACL) injury and their perception of whether the ACL injury could have been prevented. We interviewed 10 professional wrestlers (60% women, age range 21-34) treated with ACL reconstruction with semistructured interviews. Transcripts were analysed using qualitative content analysis: One major theme, 'Wrestling with a ghost: facing an opponent I can neither see nor clinch', supported by five main categories, emerged from the collected data. The five main categories were: My ACL injury: bad luck or bad planning?; The way back: a fight to return to sport; Only performance counts; The injury's impact on life: a wrestling with emotions; In hindsight, personal growth. Professional wrestlers who experienced an ACL injury expressed that not only the injury itself but also the subsequent recovery posed major challenges that they did not know how to deal with and that, in some cases, ended the athletes' wrestling careers. Professional wrestlers attributed their ACL injuries to bad luck or large training loads and wished that they had more support from the wrestling community when injured.
RESUMO
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.