Quantitative pivot shift assessment using combined inertial and magnetic sensing

Multiclass Support Vector Machine improves the Pivot-shift grading from Gerdy's acceleration resultant prior to the acute Anterior Cruciate Ligament surgery

INTRODUCTION

Rotatory laxity acceleration still lacks objective classification due to interval grading superposition, resulting in a biased pivot shift grading prior to the Anterior Cruciate Ligament (ACL) reconstruction. However, data analysis might help improve data grading in the operative room. Therefore, we described the improvement of the pivot-shift categorization in Gerdy's acceleration under anesthesia prior to ACL surgery using a support vector machine (SVM) classification, surgeon, and literature reference.

METHODS

Seventy-five patients (aged 30.3 ± 10.2 years, and IKDC 52.0 ± 16.5 points) with acute ACL rupture under anesthesia prior to ACL surgery were analyzed. Patients were graded with pivot-shift sign glide (+), clunk (++), and (+++) gross by senior orthopedic surgeons. At the same time, the tri-axial tibial plateau acceleration was measured. Categorical data were statistically described, and the accelerometry and categorical data were associated (α = 5%). A multiclass SVM kernel with the best accuracy trained by orthopedic surgeons and assisted from literature for missing data was compared with experienced surgeons and literature interval grading. The cubic SVM classifier achieved the best grading.

RESULTS

The intra-group proportions were different for each grading in the three compared strategies (p < 0.001). The inter-group proportions were different for all comparisons (p < 0.001). There were significant (p < 0.001) associations (Tau: 0.69, -0.28, and -0.50) between the surgeon and SVM, the surgeon and interval grading, and the interval and SVM, respectively.

CONCLUSION

The multiclass SVM classifier improves the acceleration categorization of the (+), (++), and (+++) pivot shift sign prior to the ACL surgery in agreement with surgeon criteria.

A comparison of the outcomes of anterior curciate ligament reconstruction with large-size graft versus reconstruction with average-size graft combined with extraarticular tenodesis

INTRODUCTION

Many patients who have had anterior cruciate ligament (ACL) reconstruction (R) complain of instability, inability to return to previous levels of sports activity, and possible ACL graft failure. Graft size was discovered to be an important factor in lowering ACL failure rates. Also, extraarticular tenodesis decreases recurrent instability, A comparative study was done to compare the effect of graft size and lateral external tenodesis on the recurrence of instability after ACL-R.

PATIENTS AND METHODS

A Prospective Blinded Randomized Controlled study included 100 consecutive patients who underwent ACL-R with hamstring tendon grafts in our Hospital. The patients were allocated into two groups (Group A and B) with randomization; group A received ACL-R with a large-size ACL-graft diameter of 6 strands, and group B received ACL-R of 4 strands combined with lateral extraarticular tenodesis (LET) (Modified Lemaire). Each group had fifty patients. The follow-up time was two years. They were examined for graft failure, anterolateral rotatory instability with the pivot shift test, and clinical outcomes, which were evaluated with the International Knee Documentation Committee score (IKDC) both subjective and objective.

RESULTS

In this study; group A, graft failure occurred in three (6.3%) patients, a positive pivot shift test grade I was detected in eight (17.8%) patients, grade II in three (6.7%) patients, and grade III in one (2.2%) patient. The subjective IKDC score was 87.9 (± 7.19) points. The objective IKDC score was normal or nearly normal in 43 (93.4%) patients. In group B, one (2.1%) patient had graft failure, five (10.9%) had a positive pivot shift test grade I, one (2.1%) had a grade II, and no patient had a grade III. The subjective IKDC score was 91.9 (± 8.9) points. The objective IKDC score was normal or nearly normal in 44 (95.6%) patients. As regard the subjective IKDC score, there was a non-significant difference between both groups (p value = 0.465).

CONCLUSION

Both groups showed a low ACL-graft failure rate, low anterolateral rotatory instability, and a good clinical outcome. Although there was no significant difference in subjective IKDC score between both groups, the failure rate and anterolateral rotatory instability were significantly lower in the ACL-R (4 strands) with LET combination group than in the group with the large-diameter (6 strands) graft.

LEVEL OF EVIDENCE

Level 1; Randomized Comparative Study.

Smart Brace for Static and Dynamic Knee Laxity Measurement

Every year in Europe more than 500 thousand injuries that involve the anterior cruciate ligament (ACL) are diagnosed. The ACL is one of the main restraints within the human knee, focused on stabilizing the joint and controlling the relative movement between the tibia and femur under mechanical stress (i.e., laxity). Ligament laxity measurement is clinically valuable for diagnosing ACL injury and comparing possible outcomes of surgical procedures. In general, knee laxity assessment is manually performed and provides information to clinicians which is mainly subjective. Only recently quantitative assessment of knee laxity through instrumental approaches has been introduced and become a fundamental asset in clinical practice. However, the current solutions provide only partial information about either static or dynamic laxity. To support a multiparametric approach using a single device, an innovative smart knee brace for knee laxity evaluation was developed. Equipped with stretchable strain sensors and inertial measurement units (IMUs), the wearable system was designed to provide quantitative information concerning the drawer, Lachman, and pivot shift tests. We specifically characterized IMUs by using a reference sensor. Applying the Bland–Altman method, the limit of agreement was found to be less than 0.06 m/s² for the accelerometer, 0.06 rad/s for the gyroscope and 0.08 μT for the magnetometer. By using an appropriate characterizing setup, the average gauge factor of the three strain sensors was 2.169. Finally, we realized a pilot study to compare the outcomes with a marker-based optoelectronic stereophotogrammetric system to verify the validity of the designed system. The preliminary findings for the capability of the system to discriminate possible ACL lesions are encouraging; in fact, the smart brace could be an effective support for an objective and quantitative diagnosis of ACL tear by supporting the simultaneous assessment of both rotational and translational laxity. To obtain reliable information about the real effectiveness of the system, further clinical validation is necessary.

Is the KiRA Device Useful in Quantifying the Pivot Shift in Anterior Cruciate Ligament-Deficient Knees?

Background:

Various technologies have been developed to quantify the pivot shift, as it is regarded as a key indicator of anterolateral rotatory laxity of the knee.

Purpose:

To determine the usefulness of a commercially available triaxial accelerometer (Kinematic Rapid Assessment [KiRA]) in numerically quantifying the pivot shift in patients under anesthesia with an anterior cruciate ligament (ACL)–deficient knee.

Study Design:

Cohort study (diagnosis); Level of evidence, 3.

Methods:

Both knees of 50 patients (26 male [mean age, 30.4 years], 24 female [mean age, 26.6 years]) under anesthesia were assessed immediately before unilateral ACL reconstruction by an orthopaedic fellow and 1 of 3 experienced knee surgeons. The pivot-shift grade and 2 KiRA outputs (range of acceleration and slope of acceleration change) were compared.

Results:

The surgeon and fellow recorded the same pivot-shift grade for 45 of 50 patients (90%). Data from the 5 patients with no agreement and 1 patient with extreme outlying data were excluded from subsequent analysis. Using the KiRA range and slope data, the surgeon identified the injured knee in 74% and 76% of patients, respectively, while the fellow’s rate of injured knee identification was 74% and 80%, respectively. A correlation could be found only between pivot-shift grade and surgeon-derived range data (ρ = 0.40; P < .01) but not slope data or any fellow-derived outputs. Using the surgeon-derived range data, there was a significant difference between a grade 3 pivot (>5 m/s²) and a grade 1 or 2 pivot (<5 m/s²) (P = .01).

Conclusion:

Although a correlation between KiRA output data and pivot-shift grade was found when the device was used by an experienced surgeon, there was no correlation when used by a well-trained but less experienced orthopaedic fellow. Furthermore, the KiRA output data identified the ACL-deficient knee correctly in only 74% of patients. Although a threshold acceleration range value could be identified, above which the value was associated with a grade 3 pivot shift, this was dependent on the examiner, and distinction between other grades could not be made.

Anterior tibial loading on the calf enhances anterior tibial translation in the anterior cruciate ligament deficient knee in the anterior gravity radiographic view

BACKGROUND

Lateral radiograph in the prone position with the knee flexed at 15° (anterior gravity view (AGV)) is useful as a screening for anterior cruciate ligament (ACL) injuries, while it is sometimes difficult to find the side-to-side difference (SSD) in anterior tibial translation. Thus, we applied a weight (three kilograms) around the lower leg to increase anterior tibial translation. We aimed to determine whether weight load confers an advantage in visualizing anterior knee laxity in ACL injuries.

METHODS

Fifty-eight patients with confirmed unilateral ACL tears from February 2012 to April 2014 had consented to participate in this study. Lateral radiographs for both knees were taken in AGV and in AGV with a three-kilogram weight load applied to the proximal lower leg. Then, the SSD of tibial position related to the femur was measured in these radiographs.

RESULTS

The SSD with the weight was significantly greater than that without the weight (5.9 ± 2.1 and 3.5 ± 1.6 mm, respectively, p < 0.01). The ratio of patients with SSD of three millimeters or more in AGV with the weight was also significantly larger than that without the weight (p < 0.01).

CONCLUSIONS

The anterior laxity in AGV with the three-kilogram weight is larger than that without the weight. Thus, the AGV with the weight could be one of the helpful radiographic technique for auxiliary diagnosis of ACL injury. Level of evidence Cohort study, Level IV.

Quantitative assessment of the pivot shift test with smartphone accelerometer

PURPOSE

The pivot shift (PS) test is commonly used to diagnose and evaluate the dynamic instability of the knee joint in cases of anterior cruciate ligament (ACL) tear. There is a need of a reliable and inexpensive tool which is easily available to measure PS objectively in a clinical setting. The purpose of this study was to evaluate the use of a smartphone, which is readily available, to assess the PS phenomenon.

METHODS

Seventeen patients with unilateral ACL-injured knees, undergoing ACL reconstruction, were enrolled in the study. PS was initially graded according to the International Knee Documentation Committee classification by two observers. The PS test was then performed by them in normal and injured knees under anaesthesia using a smartphone attached to Gerdy's tubercle. Acceleration changes during the PS test were recorded using the smartphone accelerometer application. Intra-observer and inter-observer reliability of the test among the two observers were evaluated. Acceleration changes were compared between the injured and normal knees, and also between the clinical grades of PS. Diagnostic utility of the smartphone accelerometer was examined by a receiver operating characteristic curve analysis.

RESULTS

Intra-observer and inter-observer reliability were high for the smartphone accelerometer. The acceleration change was higher in the ACL-injured knees than in normal knees. The mean acceleration change was 2.54 m/s² (SD = 0.97) in ACL-injured knees and 0.73 m/s² (SD = 0.19) in normal knees (p < 0.001). The mean acceleration change of Grade 1 knees was 1.89 m/s² (SD = 0.57), and that of knees of Grade 2 and above were 2.99 m/s² (SD = 0.95) (p < 0.05). Sensitivity was 94% and specificity was 100% for the acceleration change required to detect ACL injury, i.e., 1.24 m/s².

CONCLUSIONS

The results show that a smartphone can be used to evaluate the PS quantitatively and reliably, in the diagnosis of ACL injury.

LEVEL OF EVIDENCE

II.

Contribution of Additional Anterolateral Structure Augmentation to Controlling Pivot Shift in Anterior Cruciate Ligament Reconstruction

BACKGROUND

Several types of anterolateral structure (ALS) augmentation procedures in anterior cruciate ligament (ACL) reconstruction have been reported. However, information is limited regarding the effect of additional ALS augmentation on rotatory stability in a clinical setting.

PURPOSE/HYPOTHESIS

This study aimed to investigate the contribution of additional ALS augmentation in ACL reconstruction in cases with a high risk of residual pivot shift. The 2 hypotheses were as follows. First, additional ALS augmentation would improve rotatory stability as compared with solely reconstructing the ACL. Second, graft tension changes would be different between the ACL and ALS during knee range of motion and against anterior or rotatory loads.

STUDY DESIGN

Controlled laboratory study.

METHODS

Fifteen patients who met at least 1 of the following criteria were included: (1) revision ACL reconstruction, (2) preoperative high-grade pivot shift, or (3) hyperextended knee. The pivot-shift test was performed preoperatively and during surgery after ACL reconstruction and after additional ALS augmentation with acceleration measurements from a triaxial accelerometer. The tension changes of the ACL and ALS grafts were also measured during knee range of motion and against manual maximum anterior tibial translation, internal rotation, and external rotation.

RESULTS

After ACL reconstruction, the pivot-shift acceleration was still greater than that of the uninjured knee. However, additional ALS augmentation further reduced acceleration when compared with ACL reconstruction alone in both primary and revision cases (P < .05 vs preoperative, P < .05 vs ACL). During knee flexion-extension, the tension of the ACL increased as the knee was extended, whereas that of the ALS did not change. Graft tension of the ACL and ALS became higher with internal rotation and lower with external rotation as compared with the neutral position. Tension of the ACL was significantly increased against anterior tibial translational loads, whereas that of the ALS was not.

CONCLUSION

Additional ALS augmentation further improved the rotatory stability during ACL reconstruction in patients with a high risk of residual pivot shift at the time of surgery. Significant differences in graft tension changes were also observed between the ACL and ALS against different loads. Additional ALS augmentation may be considered to eliminate the pivot shift in patients with a high risk of residual pivot shift.

Preoperative laxity in ACL-deficient knees increases with posterior tibial slope and medial meniscal tears

PURPOSE

The aim of this study was to determine patient and anatomic factors that influence anteroposterior and rotational laxity in knees with ACL tears. Based on the findings of biomechanical studies, we hypothesized that static and dynamic anterior tibial translation (ATT) as well as positive pivot shift would increase with female gender, tibial slope, and meniscal tears.

METHODS

The authors prospectively collected preoperative data and intraoperative findings of 417 patients that underwent ACL reconstruction. The exclusion criteria were: revision ACL procedures (n = 53), other surgical antecedents (n = 27), prior osteotomies (n = 7) or concomitant ligament tears on the ipsilateral knee (n = 34), and history of ACL tears in the contralateral knee (n = 45), leaving a study cohort of 251 patients. Their preoperative anteroposterior knee laxity was assessed objectively using 'static' monopodal weight-bearing radiographs and 'dynamic' instrumented differential measurements of ATT. Rotational laxity was assessed subjectively using the pivot shift test.

RESULTS

Multivariable regression showed that static ATT increases only with tibial slope (β = 0.30; p < 0.001), but dynamic ATT increases with tibial slope (β = 0.19; p = 0.041), medial meniscal tears (β = 1.27; p = 0.007), complete ACL tears (β = 2.06; p < 0.001), and to decrease with age (β = - 0.09; p < 0.001). Multivariable regression also indicated that high-grade pivot shift decreases with age (OR 0.94; p < 0.001) and for women (OR 0.25; p < 0.001), and to be higher for knees with complete ACL tears (OR 3.04; p = 0.002) or medial meniscal tears (OR 2.28; p = 0.010).

CONCLUSION

Contrary to expectations based on biomechanical studies, static ATT was only affected by high posterior tibial slope, while dynamic ATT was affected by both high posterior tibial slopes and medial meniscal tears, but not by gender or lateral meniscal tears. Likewise, pivot shift was affected by gender and medial meniscal tears, but not lateral meniscal tears or posterior tibial slope. These findings are relevant to guide surgeons in optimizing their surgical procedures, such as conserving the menisci when possible, and rehabilitation protocols, by delaying full weight-bearing and return to sports in patients with anatomic and lesional risk factors.

LEVEL OF EVIDENCE

Cohort study, Level IV.

Comparison of quantitative evaluation between cutaneous and transosseous inertial sensors in anterior cruciate ligament deficient knee: A cadaveric study

BACKGROUND

Recently several authors have reported on the quantitative evaluation of the pivot-shift test using cutaneous fixation of inertial sensors. Before utilizing this sensor for clinical studies, it is necessary to evaluate the accuracy of cutaneous sensor in assessing rotational knee instability. To evaluate the accuracy of inertial sensors, we compared cutaneous and transosseous sensors in the quantitative assessment of rotational knee instability in a cadaveric setting, in order to demonstrate their clinical applicability.

METHODS

Eight freshly frozen human cadaveric knees were used in this study. Inertial sensors were fixed on the tibial tuberosity and directly fixed to the distal tibia bone. A single examiner performed the pivot shift test from flexion to extension on the intact knees and ACL deficient knees. The peak overall magnitude of acceleration and the maximum rotational angular velocity in the tibial superoinferior axis was repeatedly measured with the inertial sensor during the pivot shift test. Correlations between cutaneous and transosseous inertial sensors were evaluated, as well as statistical analysis for differences between ACL intact and ACL deficient knees.

RESULTS

Acceleration and angular velocity measured with the cutaneous sensor demonstrated a strong positive correlation with the transosseous sensor (r = 0.86 and r = 0.83). Comparison between cutaneous and transosseous sensor indicated significant difference for the peak overall magnitude of acceleration (cutaneous: 10.3 ± 5.2 m/s², transosseous: 14.3 ± 7.6 m/s², P < 0.01) and for the maximum internal rotation angular velocity (cutaneous: 189.5 ± 99.6 deg/s, transosseous: 225.1 ± 103.3 deg/s, P < 0.05), but no significant difference for the maximum external rotation angular velocity (cutaneous: 176.1 ± 87.3 deg/s, transosseous: 195.9 ± 106.2 deg/s, N.S).

CONCLUSIONS

There is a positive correlation between cutaneous and transosseous inertial sensors. Therefore, this study indicated that the cutaneous inertial sensors could be used clinically for quantifying rotational knee instability, irrespective of the location of utilization.

Quantification of the pivot-shift test using a navigation system with non-invasive surface markers

PURPOSE

The purpose of this study was to validate the quantitation of the pivot-shift phenomenon by using a navigation system with non-invasive surface markers. Measurements obtained using this system were compared with those obtained using commercial pin-fixed markers.

METHODS

Seventy patients with anterior cruciate ligament (ACL) injuries were assessed under general anaesthesia. Knee kinematics during the pivot-shift test were recorded using an image-free navigation system with a commercial transmitter placed on the thigh and lower leg (surface markers) or those fixed to the femur and the tibia via metal pin fixators (pin-fixed markers). For quantitation of the pivot-shift phenomenon, posterior tibial reduction (PTR) was calculated using the two types of navigation system markers and were then compared. PTRs measured using the two types of markers were also compared with clinical grade of the pivot-shift test, as determined by an examiner.

RESULTS

The pivot-shift phenomenon could be identified in all patients on the navigation screen. The PTR measured using surface markers moderately correlated with that measured using pin-fixed markers (ρ = 0.524, p < 0.001). There were also moderate correlations between clinical grades and the PTRs measured using either the surface markers (ρ = 0.522, p < 0.001) or the pin-fixed markers (ρ = 0.645, p < 0.001).

CONCLUSIONS

The present study demonstrated that PTR, during the pivot-shift test, may be quantified in ACL-injured knees, using a navigation system with surface markers, and that the PTR measured with surface markers moderately correlated both with the PTR obtained using pin-fixed markers and with the clinical grade of the pivot-shift test. A customised method of fixing transmitters with reflective markers to patients' thighs and shins with Velcro straps is non-invasive and could assess and record the knee kinematics, especially the pivot-shift test, in ACL-injured and ACL-reconstructed knees before, during, and after surgery using a navigation system.

LEVEL OF EVIDENCE

Case series, Level IV.

Objective measures on knee instability: dynamic tests: a review of devices for assessment of dynamic knee laxity through utilization of the pivot shift test

Current reconstructive methods used after anterior cruciate ligament (ACL) injury do not entirely restore native knee kinematics. Evaluation of dynamic knee laxity is important to accurately diagnose ACL deficiency, to evaluate reconstructive techniques, and to construct treatment algorithms for patients with ACL injury. The purpose of this study is to present recent progress in evaluation of dynamic knee laxity through utilization of the pivot shift test. A thorough electronic search was performed and relevant studies were assessed. Certain dynamic knee laxity measurement methods have been present for over 10 years (Navigation system, Electromagnetic sensor system) while other methods (Inertial sensor, Image analysis system) have been introduced recently. Methods to evaluate dynamic knee laxity through the pivot shift test are already potent. However, further refinement is warranted. In addition, to correctly quantify the pivot shift test, the involved forces need to be controlled through either standardization or mechanization of the pivot shift test.

Assessment of the pivot shift using inertial sensors

The pivot shift test is an important clinical tool used to assess the stability of the knee following an injury to the anterior cruciate ligament (ACL). Previous studies have shown that significant variability exists in the performance and interpretation of this manoeuvre. Accordingly, a variety of techniques aimed at standardizing and quantifying the pivot shift test have been developed. In recent years, inertial sensors have been used to measure the kinematics of the pivot shift. The goal of this study is to present a review of the literature and discuss the principles of inertial sensors and their use in quantifying the pivot shift test.

Basic biomechanic principles of knee instability

Motion at the knee joint is a complex mechanical phenomenon. Stability is provided by a combination of static and dynamic structures that work in concert to prevent excessive movement or instability that is inherent in various knee injuries. The anterior cruciate ligament (ACL) is a main stabilizer of the knee, providing both translational and rotatory constraint. Despite the high volume of research directed at native ACL function, pathogenesis and surgical reconstruction of this structure, a gold standard for objective quantification of injury and subsequent repair, has not been demonstrated. Furthermore, recent studies have suggested that novel anatomic structures may play a significant role in knee stability. The use of biomechanical principles and testing techniques provides essential objective/quantitative information on the function of bone, ligaments, joint capsule, and other contributing soft tissues in response to various loading conditions. This review discusses the principles of biomechanics in relation to knee stability, with a focus on the objective quantification of knee stability, the individual contributions of specific knee structures to stability, and the most recent technological advances in the biomechanical evaluation of the knee joint.

Knee instability scores for ACL reconstruction

Despite abundant biological, biomechanical, and clinical research, return to sport after anterior cruciate ligament (ACL) injury remains a significant challenge. Residual rotatory knee laxity has been identified as one of the factors responsible for poor functional outcome. To improve and standardize the assessment of knee instability, a variety of instability scoring systems is available. Recently, devices to objectively quantify static and dynamic clinical exams have been developed to complement traditional subjective grading systems. These devices enable an improved evaluation of knee instability and possible associated injuries. This additional information may promote the development of new treatment algorithms and allow for individualized treatment. In this review, the different subjective laxity scores as well as complementary objective measuring systems are discussed, along with an introduction of injury to an individualized treatment algorithm.

A mechanical pivot-shift device for continuously applying defined loads to cadaveric knees

PURPOSE

Current techniques to study the biomechanics of the pivot-shift utilize either static or poorly defined loading conditions. Here, a novel mechanical pivot-shift device that continuously applies well-defined loads to cadaveric knees is characterized and validated against the manual pivot-shift.

METHODS

Six fresh-frozen human lower limb specimens were potted at the femur, mounted on a hinged testing base, and fitted with the mechanical device. Five mechanical and manual pivot-shift tests were performed on each knee by two examiners before and after transecting the ACL. Three-dimensional kinematics (anterior and internal-rotary displacements, and posterior and external-rotary velocities) and kinetics (forces and moments applied to the tibia by the device) were recorded using an optical navigation system and 6-axis load cell. Analysis of variance and Bland-Altman statistics were used to gauge repeatability within knees, reproducibility between knees, agreement between the mechanical and manual test methods, and agreement between examiners.

RESULTS

The forces and moments applied by the device were continuous and repeatable/reproducible to within 4/10 % of maximum recorded values. Kinematic variables (excluding external-rotary velocity) were qualitatively and quantitatively similar to manual pivot-shift kinematics, and were more repeatable and reproducible.

CONCLUSION

The presented device induces pivot-shift-like kinematics by applying highly repeatable three-dimensional loads to cadaver knees. It is based on a simple mechanical principle and designed using easily obtainable components. Consequently, the device enables orthopaedic biomechanists to easily and reliably quantify the effect of ACL injury and reconstruction on pivot-shift kinematics.

Use of inertial sensors to predict pivot-shift grade and diagnose an ACL injury during preoperative testing

BACKGROUND

The pivot-shift (PS) examination is used to demonstrate knee instability and detect anterior cruciate ligament (ACL) injury. Prior studies using inertial sensors identified the ACL-deficient knee with reasonable accuracy, but none addressed the more difficult problem of using these sensors to determine whether a subject has an ACL deficiency and to correctly assign a PS grade to a patient's knee.

HYPOTHESIS

Inertial sensor data recorded during a PS examination can accurately predict ACL deficiency and the PS score assigned by the examining physician.

STUDY DESIGN

Cohort study (diagnosis); Level of evidence, 2.

METHODS

A total of 32 patients with unilateral ACL deficiency and 29 with intact ACLs in both knees had inertial sensor modules strapped to the tibia and femur of each limb for preoperative PS testing under anesthesia. Support vector machine (SVM) methods assessed PS grades on the basis of these data, with the examiner's clinical grading shift used as ground truth. A fusion of regression and SVM classification techniques diagnosed ACL deficiency.

RESULTS

The clinically determined PS grades of all 122 knees were as follows: 0 (n = 69), +1 (n = 23), +2 (n = 27), and +3 (n = 3). The SVM classification analysis was 77% accurate in correctly classifying these grades, with 98% of computed PS grades falling within ±1 grade of the clinically determined value. The system fusion algorithm diagnosed ACL deficiency in an individual with an overall accuracy of 97%. This method yielded 6% false negatives and 0% false positives.

CONCLUSION

This study used inertial sensor technology with SVM algorithms to accurately determine clinically assigned PS grades in ACL-intact and ACL-deficient knees. By extending the assessment to a separate group of patients without ACL injury, the inertial sensor data demonstrated highly accurate diagnosis of ACL deficiency.