scholarly journals Predicting Subjective Failure of ACL Reconstruction: A Machine Learning Analysis of the Norwegian Knee Ligament Register and Patient Reported Outcomes

2022 ◽  
Author(s):  
R. Kyle Martin ◽  
Solvejg Wastvedt ◽  
Ayoosh Pareek ◽  
Andreas Persson ◽  
Håvard Visnes ◽  
...  
Keyword(s):  
Machine Learning ◽  
Acl Reconstruction ◽  
Patient Reported Outcomes ◽  
Knee Ligament ◽  
Patient Reported ◽  
Learning Analysis

scholarly journals Acute ACL reconstruction shows superior clinical results and can be performed safely without an increased risk of developing arthrofibrosis

2019 ◽  
Vol 28 (7) ◽  
pp. 2036-2043 ◽  
Author(s):  
Christoffer von Essen ◽  
Karl Eriksson ◽  
Björn Barenius
Keyword(s):  
Range Of Motion ◽  
Acl Reconstruction ◽  
Patient Reported Outcomes ◽  
Activity Level ◽  
Knee Ligament ◽  
Acute Group ◽  
Increased Risk ◽  
Significant Difference ◽  
Patient Reported ◽  
Delayed Group

Abstract Purpose To compare acute ACL reconstruction (ACLR) within 8 days of injury with delayed reconstruction after normalized range of motion (ROM), 6–10 weeks after injury. It was hypothesized that acute ACL reconstruction with modern techniques is safe and can be beneficial in terms of patient-reported outcomes and range of motion. Methods The effect of acute and delayed ACLR was randomized studied on 70 patients with high recreational activity level, Tegner level 6 or more, between 2006 and 2013. Patient-reported outcomes, objective IKDC, KOOS, and manual stability measurements were documented during the 24-month follow-up period. Results The acute ACLR group did not result in increased stiffness and showed superior outcome regarding strength and how the patient felt their knee functioning at 24 months. In addition, the acute group was not inferior to the delayed group in any assessment. Regarding patient-related outcomes in KOOS, both groups showed significant improvements in all subscales, but no difference was found between the groups. Functional return (FR) rate was almost double compared to the Swedish knee ligament register and treatment failure (TF) rate was reduced by half, no significant difference between the groups. No difference regarding cyclops removal, re-injury of ACL or meniscus was found between the two surgical timing groups. Conclusion Acute ACLR within 8 days of injury does not appear to adversely affect ROM or result in increased stiffness in the knee joint and was not inferior to the delayed group in any assessment when compared to delayed surgery. Level of evidence I.

scholarly journals Electronic patient-reported outcomes and machine learning in predicting immune-related adverse events of immune checkpoint inhibitor therapies

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Sanna Iivanainen ◽  
Jussi Ekstrom ◽  
Henri Virtanen ◽  
Vesa V. Kataja ◽  
Jussi P. Koivunen
Keyword(s):  
Machine Learning ◽  
Early Detection ◽  
Adverse Events ◽  
Cancer Patients ◽  
Immune Checkpoint ◽  
Patient Reported Outcomes ◽  
Prediction Models ◽  
Accuracy Score ◽  
Patient Reported ◽  
Auc Value

Abstract Background Immune-checkpoint inhibitors (ICIs) have introduced novel immune-related adverse events (irAEs), arising from various organ systems without strong timely dependency on therapy dosing. Early detection of irAEs could result in improved toxicity profile and quality of life. Symptom data collected by electronic (e) patient-reported outcomes (PRO) could be used as an input for machine learning (ML) based prediction models for the early detection of irAEs. Methods The utilized dataset consisted of two data sources. The first dataset consisted of 820 completed symptom questionnaires from 34 ICI treated advanced cancer patients, including 18 monitored symptoms collected using the Kaiku Health digital platform. The second dataset included prospectively collected irAE data, Common Terminology Criteria for Adverse Events (CTCAE) class, and the severity of 26 irAEs. The ML models were built using extreme gradient boosting algorithms. The first model was trained to detect the presence and the second the onset of irAEs. Results The model trained to predict the presence of irAEs had an excellent performance based on four metrics: accuracy score 0.97, Area Under the Curve (AUC) value 0.99, F1-score 0.94 and Matthew’s correlation coefficient (MCC) 0.92. The prediction of the irAE onset was more difficult with accuracy score 0.96, AUC value 0.93, F1-score 0.66 and MCC 0.64 but the model performance was still at a good level. Conclusion The current study suggests that ML based prediction models, using ePRO data as an input, can predict the presence and onset of irAEs with a high accuracy, indicating that ePRO follow-up with ML algorithms could facilitate the detection of irAEs in ICI-treated cancer patients. The results should be validated with a larger dataset. Trial registration Clinical Trials Register (NCT3928938), registration date the 26th of April, 2019

scholarly journals Streamlining the KOOS Activities of Daily Living Subscale Using Machine Learning

2020 ◽  
Vol 8 (3) ◽  
pp. 232596712091044 ◽  
Author(s):  
Ashim Gupta ◽  
Ajish S.R. Potty ◽  
Deepak Ganta ◽  
R. Justin Mistovich ◽  
Sreeram Penna ◽  
...  
Keyword(s):  
Machine Learning ◽  
Activities Of Daily Living ◽  
Functional Outcome ◽  
Acl Reconstruction ◽  
Daily Living ◽  
High Accuracy ◽  
Quality Data ◽  
Specific Patient ◽  
Patient Reported ◽  
Essential Questions

Background: Functional outcome scores provide valuable data, yet they can be burdensome to patients and require significant resources to administer. The Knee injury and Osteoarthritis Outcome Score (KOOS) is a knee-specific patient-reported outcome measure (PROM) and is validated for anterior cruciate ligament (ACL) reconstruction outcomes. The KOOS requires 42 questions in 5 subscales. We utilized a machine learning (ML) algorithm to determine whether the number of questions and the resultant burden to complete the survey can be lowered in a subset (activities of daily living; ADL) of KOOS, yet still provide identical data. Hypothesis: Fewer questions than the 17 currently provided are actually needed to predict KOOS ADL subscale scores with high accuracy. Study Design: Cohort study (diagnosis); Level of evidence, 2. Methods: Pre- and postoperative patient-reported KOOS ADL scores were obtained from the Surgical Outcome System (SOS) data registry for patients who had ACL reconstruction. Categorical Boosting (CatBoost) ML models were built to analyze each question and its value in predicting the patient’s actual functional outcome (ie, KOOS ADL score). A streamlined set of minimal essential questions were then identified. Results: The SOS registry contained 6185 patients who underwent ACL reconstruction. A total of 2525 patients between the age of 16 and 50 years had completed KOOS ADL scores presurgically and 3 months postoperatively. The data set consisted of 51.84% male patients and 48.16% female patients, with a mean age of 29 years. The CatBoost model predicted KOOS ADL scores with high accuracy when only 6 questions were asked ( R2 = 0.95), similar to when all 17 questions of the subscale were asked ( R2 = 0.99). Conclusion: ML algorithms successfully identified the essential questions in the KOOS ADL questionnaire. Only 35% (6/17) of KOOS ADL questions (descending stairs, ascending stairs, standing, walking on flat surface, putting on socks/stockings, and getting on/off toilet) are needed to predict KOOS ADL scores with high accuracy after ACL reconstruction. ML can be utilized successfully to streamline the burden of patient data collection. This, in turn, can potentially lead to improved patient reporting, increased compliance, and increased utilization of PROMs while still providing quality data.

Psychosocial profiles and their predictors in epilepsy using patient‐reported outcomes and machine learning

Epilepsia ◽  
2020 ◽  
Vol 61 (6) ◽  
pp. 1201-1210 ◽  
Author(s):  
Colin B. Josephson ◽  
Jordan D. T. Engbers ◽  
Meng Wang ◽  
Kevin Perera ◽  
Pamela Roach ◽  
...  
Keyword(s):  
Machine Learning ◽  
Patient Reported Outcomes ◽  
Patient Reported ◽  
Psychosocial Profiles

scholarly journals Poor Associations Between Radiographic Tibiofemoral Osteoarthritis and Patient-Reported Outcomes at 16 Years After Anterior Cruciate Ligament Reconstruction

2020 ◽  
Vol 8 (9) ◽  
pp. 232596712095117
Author(s):  
Fredrik Identeg ◽  
Eric Hamrin Senorski ◽  
Eleonor Svantesson ◽  
Kristian Samuelsson ◽  
Ninni Sernert ◽  
...  
Keyword(s):  
Acl Reconstruction ◽  
Patient Reported Outcomes ◽  
Cruciate Ligament ◽  
Patient Reported ◽  
Long Term Follow Up ◽  
Ikdc Score ◽  
Anterior Cruciate ◽  
Grade 3

Background: Radiographic tibiofemoral (TF) osteoarthritis (OA) is common in patients after anterior cruciate ligament (ACL) reconstruction at long-term follow-up. The association between radiographic OA and patient-reported outcomes has not been thoroughly investigated. Purpose: To determine the association between radiographic TF OA and patient-reported outcome measure (PROM) scores at 16 years after ACL reconstruction. Study Design: Case-control study; Level of evidence, 3. Methods: This study was based on 2 randomized controlled studies comprising 193 patients who underwent unilateral ACL reconstruction. A long-term follow-up was carried out at 16.4 ± 1.7 years after surgery and included a radiographic examination of the knee and recording of PROM scores. Correlation analyses were performed between radiographic OA (Kellgren-Lawrence [K-L], Ahlbäck, and cumulative Fairbank grades) and the PROMs of the International Knee Documentation Committee (IKDC) subjective knee form, Lysholm score, and Tegner activity scale. A linear univariable regression model was used to assess how the IKDC score differed with each grade of radiographic OA. Results: Of 193 patients at baseline, 147 attended the long-term follow-up. At long-term follow-up, 44.2% of the patients had a K-L grade of ≥2 in the injured leg, compared with 6.8% in the uninjured leg. The mean IKDC score at follow-up was 71.2 ± 19.9. Higher grades of radiographic OA were significantly correlated with lower IKDC and Lysholm scores ( r = –0.36 to –0.22). Patients with a K-L grade of 3 to 4 had significantly lower IKDC scores compared with patients without radiographic OA (K-L grade 0-1). Adjusted beta values were –15.7 (95% CI, –27.5 to –4.0; P = .0093; R 2 = 0.09) for K-L grade 3 and –25.2 (95% CI, –41.7 to –8.6; P = .0033; R 2 = 0.09) for K-L grade 4. Conclusion: There was a poor but significant correlation between radiographic TF OA and more knee-related limitations, as measured by the IKDC form and the Lysholm score. Patients with high grades of radiographic TF OA (K-L grade 3-4) had a statistically significant decrease in IKDC scores compared with patients without radiographic TF OA at 16 years after ACL reconstruction. No associations were found between radiographic TF OA and the Tegner activity level.

scholarly journals Knee Kinematics Are Related to Patient-Reported Outcomes 6 Months After Anatomic ACL Reconstruction

2015 ◽  
Vol 3 (7_suppl2) ◽  
pp. 2325967115S0003 ◽  
Author(s):  
Jay Kalawadia ◽  
Eric Thorhauer ◽  
Fabio Vicente Arilla ◽  
Amir Ata Rahnemai Azar ◽  
Caiyan Zhang ◽  
...  
Keyword(s):  
Acl Reconstruction ◽  
Patient Reported Outcomes ◽  
Knee Kinematics ◽  
Anatomic Acl Reconstruction ◽  
Patient Reported

scholarly journals Development of the KOOSglobal Platform to Measure Patient-Reported Outcomes After Anterior Cruciate Ligament Reconstruction

2018 ◽  
Vol 46 (12) ◽  
pp. 2915-2921 ◽  
Author(s):  
Cale A. Jacobs ◽  
Michael R. Peabody ◽  
Christian Lattermann ◽  
Jose F. Vega ◽  
Laura J. Huston ◽  
...  
Keyword(s):  
Psychometric Properties ◽  
Acl Reconstruction ◽  
Relative Efficiency ◽  
Convergent Validity ◽  
Patient Reported Outcomes ◽  
Short Form ◽  
Cruciate Ligament ◽  
Patient Reported ◽  
Anterior Cruciate

Background: The Knee injury and Osteoarthritis Outcome Score (KOOS) has demonstrated inferior psychometric properties when compared with the International Knee Documentation Committee (IKDC) subjective knee form when assessing outcomes after anterior cruciate ligament (ACL) reconstruction. The KOOS, Joint Replacement (KOOS, JR) is a validated short-form instrument to assess patient-reported outcomes (PROs) after knee arthroplasty, and the purpose of this study was to determine if augmenting the KOOS, JR with additional KOOS items would allow for the creation of a short-form KOOS-based global knee score for patients undergoing ACL reconstruction, with psychometric properties similar to those of the IKDC. Hypothesis: An augmented version of the KOOS, JR could be created that would demonstrate convergent validity with the IKDC but avoid the ceiling effects and limitations previously noted with several of the KOOS subscales. Study Design: Cohort study (diagnosis); Level of evidence, 2. Methods: Based on preoperative and 2-year postoperative responses to the KOOS questionnaires from a sample of 1904 patients undergoing ACL reconstruction, an aggregate score combining the KOOS, JR and the 4 KOOS Quality of Life subscale questions, termed the KOOSglobal, was developed. Psychometric properties of the KOOSglobal were then compared with those of the IKDC subjective score. Convergent validity between the KOOSglobal and IKDC was assessed with a Spearman correlation (ρ). Responsiveness of the 2 instruments was assessed by calculating the pre- to postoperative effect size and relative efficiency. Finally, the presence of a preoperative floor or postoperative ceiling effect was defined with the threshold of 15% of patients reporting either the worst possible (0 for KOOSglobal and IKDC) or the best possible (100 for KOOSglobal and IKDC) scores, respectively. Results: The newly developed KOOSglobal was responsive after ACL reconstruction and demonstrated convergent validity with the IKDC. The KOOSglobal significantly correlated with the IKDC scores (ρ = 0.91, P < .001), explained 83% of the variability in IKDC scores, and was similarly responsive (relative efficiency = 0.63). While there was a higher rate of perfect postoperative scores with the KOOSglobal (213 of 1904, 11%) than with the IKDC (6%), the KOOSglobal was still below the 15% ceiling effect threshold. Conclusion: The large ceiling effects limit the ability to use several of the KOOS subscales with the younger, more active ACL population. However, by creating an aggregate score from the KOOS, JR and 4 KOOS Quality of Life subscale questions, the 11-item KOOSglobal offers a responsive PRO tool after ACL reconstruction that converges with the information captured with the IKDC. Also, by offering the ability to calculate multiple scores from a single questionnaire, the KOOSglobal may provide the orthopaedic community a single PRO platform to be used across knee-related subspecialties. Registration: NCT00478894 ( ClinicalTrials.gov identifier).

scholarly journals Machine learning algorithm to predict anterior cruciate ligament revision demonstrates external validity

2022 ◽  
Author(s):  
R. Kyle Martin ◽  
Solvejg Wastvedt ◽  
Ayoosh Pareek ◽  
Andreas Persson ◽  
Håvard Visnes ◽  
...  
Keyword(s):  
Machine Learning ◽  
Acl Reconstruction ◽  
External Validity ◽  
Learning Algorithm ◽  
Cruciate Ligament ◽  
External Validation ◽  
Model Performance ◽  
Knee Ligament ◽  
Graft Choice ◽  
Anterior Cruciate

Abstract Purpose External validation of machine learning predictive models is achieved through evaluation of model performance on different groups of patients than were used for algorithm development. This important step is uncommonly performed, inhibiting clinical translation of newly developed models. Machine learning analysis of the Norwegian Knee Ligament Register (NKLR) recently led to the development of a tool capable of estimating the risk of anterior cruciate ligament (ACL) revision (https://swastvedt.shinyapps.io/calculator_rev/). The purpose of this study was to determine the external validity of the NKLR model by assessing algorithm performance when applied to patients from the Danish Knee Ligament Registry (DKLR). Methods The primary outcome measure of the NKLR model was probability of revision ACL reconstruction within 1, 2, and/or 5 years. For external validation, all DKLR patients with complete data for the five variables required for NKLR prediction were included. The five variables included graft choice, femur fixation device, KOOS QOL score at surgery, years from injury to surgery, and age at surgery. Predicted revision probabilities were calculated for all DKLR patients. The model performance was assessed using the same metrics as the NKLR study: concordance and calibration. Results In total, 10,922 DKLR patients were included for analysis. Average follow-up time or time-to-revision was 8.4 (± 4.3) years and overall revision rate was 6.9%. Surgical technique trends (i.e., graft choice and fixation devices) and injury characteristics (i.e., concomitant meniscus and cartilage pathology) were dissimilar between registries. The model produced similar concordance when applied to the DKLR population compared to the original NKLR test data (DKLR: 0.68; NKLR: 0.68–0.69). Calibration was poorer for the DKLR population at one and five years post primary surgery but similar to the NKLR at two years. Conclusion The NKLR machine learning algorithm demonstrated similar performance when applied to patients from the DKLR, suggesting that it is valid for application outside of the initial patient population. This represents the first machine learning model for predicting revision ACL reconstruction that has been externally validated. Clinicians can use this in-clinic calculator to estimate revision risk at a patient specific level when discussing outcome expectations pre-operatively. While encouraging, it should be noted that the performance of the model on patients undergoing ACL reconstruction outside of Scandinavia remains unknown. Level of evidence III.

Sign in / Sign up

Export Citation Format

Share Document