Artificial Intelligence and Machine Learning in Lower Extremity Arthroplasty: A Review

Haeberle, Heather S.; Helm, J. Matthew; Navarro, Sergio M.; Karnuta, Jaret M.; Schaffer, Jonathan; Callaghan, John J.; Mont, Michael A.; Kamath, Atul F.; Krebs, Viktor E.; Ramkumar, Prem N.

doi:10.1016/j.arth.2019.05.055

Cited by 113 publications

(94 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Compared with the previous pilot study [ 30 ], a new concept was introduced (namely, the classification for the type of prosthesis) and an extension of the algorithms and the features to predict the BMD was performed (namely, the features regarding the measurements of bone and function by CT scans and the EMG evaluations). These analyses fit with the idea of Haeberle et al, who considered ML not only for the classification of images but also as a valuable tool for moving in the direction of personalized care [ 23 ].…”

Section: Discussionmentioning

confidence: 68%

“…Many applications are present in the literature representing the implementation of ML algorithms with healthcare data: Ricciardi et al applied it to study fetal well-being [ 18 ], Stanzione et al and Romeo et al applied ML in radiomics processes [ 19 , 20 ], and Ricciardi et al performed ML studies for the diagnosis and prognosis of patients affected by coronary artery disease [ 21 , 22 ]. Haeberle et al, recently, conducted a review of ML in the orthopedic field, as well as Cabitza et al, who stated that there has been a 10-fold increase in reports mentioning ML in the last 20 years [ 23 , 24 ]. Different applications have been found in the orthopedic field and, especially, for the lower extremities: image-based analysis, mobile health technologies and value-based patients’ models.…”

Section: Introductionmentioning

confidence: 99%

“…Ramkumar et al developed and validated a predictive machine learning model using preoperative patient demographics for estimating the length of stay after primary THA as the first step in identifying a patient-specific payment model [ 27 , 28 ], while Harris et al developed predictive models for mortality and major complications after elective total joint arthroplasty that can be used to inform preoperative discussions and decisions in diverse healthcare settings [ 29 ]. However, there is also evidence from literature reviews that the advancement and employment of ML provides the opportunity to provide data-driven, high-performance medicine that can rapidly improve the knowledge, economics and delivery of lower extremity arthroplasty [ 23 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving Prosthetic Selection and Predicting BMD from Biometric Measurements in Patients Receiving Total Hip Arthroplasty

et al. 2020

View full text Add to dashboard Cite

There are two surgical approaches to performing total hip arthroplasty (THA): a cemented or uncemented type of prosthesis. The choice is usually based on the experience of the orthopaedic surgeon and on parameters such as the age and gender of the patient. Using machine learning (ML) techniques on quantitative biomechanical and bone quality data extracted from computed tomography, electromyography and gait analysis, the aim of this paper was, firstly, to help clinicians use patient-specific biomarkers from diagnostic exams in the prosthetic decision-making process. The second aim was to evaluate patient long-term outcomes by predicting the bone mineral density (BMD) of the proximal and distal parts of the femur using advanced image processing analysis techniques and ML. The ML analyses were performed on diagnostic patient data extracted from a national database of 51 THA patients using the Knime analytics platform. The classification analysis achieved 93% accuracy in choosing the type of prosthesis; the regression analysis on the BMD data showed a coefficient of determination of about 0.6. The start and stop of the electromyographic signals were identified as the best predictors. This study shows a patient-specific approach could be helpful in the decision-making process and provide clinicians with information regarding the follow up of patients.

show abstract

Section: Discussionmentioning

confidence: 68%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving Prosthetic Selection and Predicting BMD from Biometric Measurements in Patients Receiving Total Hip Arthroplasty

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Moreover, HFMM can support future temporal-spatial analysis for multiple foot and ankle motion patterns. By analyzing gait patterns in the future from big data will help us identify a pattern of ligament injuries and be applied to intelligent diagnosis for the patients with lateral ankle ligaments injury, which can automatically, accurately and immediately detect the injuries in acute phase and rehabilitation process (21,22).…”

Section: Discussionmentioning

confidence: 99%

Gait Kinematics of Patients with Lateral Collateral Ligament Injuries of Ankle

Zheng

Liu

Zhang

et al. 2020

Preprint

View full text Add to dashboard Cite

Background：Lateral collateral ligament (LCL) injuries of ankle are a common problem in sports medicine. The purpose of this study is to evaluate the walking kinematics in patients with LCL injuries of ankle for examining how ankle ligament injuries affect foot and ankle motion. The results will serve in precision assessment and computer-aided diagnosis.Methods：Kinematics of walking were assessed by the Heidelberg Foot Measurement Model (HFMM) in 6 adults (3 patients, 3 control subjects). We hypothesized that patients with ligament injury will: present a shorter stance phase, but longer swing phase; be observed with an increasing number of shank and foot adjustments during the stance phase; reduce velocity of foot during the early swing phase with an increasing variation. Velocity profiles and micro-adjustment of knee, ankle, and foot were calculated during different gait phases and compared between two different subject groups by independent-sample t-test with 95% confidence intervals and standard error of measurements.Results：In the gait cycle, 1 st rocker phase was 2.09% shorter (p < 0.001) and 2 nd rocker phase was 1.54% longer (p = 0.009) in patients than in controls. Compared to control subjects, the patients showed 89.1 mm shorter stride length (p<0.001), 0.10s slower stride (p<0.001) and 1.57 more complex micro-adjustments in 2 nd rocker phase than in other rocker/swing phases during natural walking (p=0.017). The mean velocity of knee (6.05 mm/10 -2 s vs. 4.74 mm/10 -2 s), ankle (0.85 mm/10 -2 s vs. 0.52 mm/10 -2 s), midfoot (0.79 mm/10 -2 s vs. 0.48 mm/10 -2 s) and forefoot (1.72 mm/10 -2 s vs. 0.97 mm/10 -2 s) in 2 nd rocker was significantly higher in patients (p<0.001). Conclusion:Our findings revealed the human motion compensatory mechanism. Patients with ligament injuries need more musculoskeletal adjustments to keeping body balance than control subjects. Precise descriptions of the kinematics are crucial for clinical assessment before and after surgical management. These results will also provide a foundation for computer-aided diagnosis in the future.

show abstract

“…5 Machine learning (ML) is a subset of AI that uses computational algorithms to analyze large data sets to classify and predict without explicit instructions. 5,6 In its most rudimentary form, ML models are given inputs and outputs of "training sets" using realworld data to determine relationships using pattern recognition. 6 As such, the model is dependent on the accuracy and biases of the given data set.…”

mentioning

confidence: 99%

Clinical and Research Medical Applications of Artificial Intelligence

Ramkumar

Kunze

Haeberle

et al. 2021

Arthroscopy: The Journal of Arthroscopic & Related Surgery

Self Cite

View full text Add to dashboard Cite

Artificial intelligence (AI), including machine learning (ML), has transformed numerous industries through newfound efficiencies and supportive decision-making. With the exponential growth of computing power and large datasets, AI has transitioned from theory to reality in teaching machines to automate tasks without human supervision. AI-based computational algorithms analyze "training sets" using pattern recognition and learning from inputted data to classify and predict outputs that otherwise could not be effectively analyzed with human processing or standard statistical methods. Though widespread understanding of the fundamental principles and adoption of applications have yet to be achieved, recent applications and research efforts implementing AI have demonstrated great promise in predicting future injury risk, interpreting advanced imaging, evaluating patient-reported outcomes, reporting value-based metrics, and augmenting telehealth. With appreciation, caution, and experience applying AI, the potential to automate tasks and improve data-driven insights may be realized to fundamentally improve patient care. The purpose of this review is to discuss the pearls, pitfalls, and applications associated with AI.

show abstract

Artificial Intelligence and Machine Learning in Lower Extremity Arthroplasty: A Review

Cited by 113 publications

References 14 publications

Improving Prosthetic Selection and Predicting BMD from Biometric Measurements in Patients Receiving Total Hip Arthroplasty

Improving Prosthetic Selection and Predicting BMD from Biometric Measurements in Patients Receiving Total Hip Arthroplasty

Gait Kinematics of Patients with Lateral Collateral Ligament Injuries of Ankle

Clinical and Research Medical Applications of Artificial Intelligence

Contact Info

Product

Resources

About