Deep learning generated lower extremity radiographic measurements are adequate for quick assessment of knee angular alignment and leg length determination.

PURPOSE: Angular and longitudinal deformities of leg alignment create excessive stresses across joints, leading to pain and impaired function. Multiple measurements are used to assess these deformities on anteroposterior (AP) full-length radiographs. An artificial intelligence (AI) software automatically locates anatomical landmarks on AP full-length radiographs and performs 13 measurements to assess knee angular alignment and leg length. The primary aim of this study was to evaluate the agreements in LLD and knee alignment measurements between an AI software and two board-certified radiologists in patients without metal implants. The secondary aim was to assess time savings achieved by AI. METHODS: The measurements assessed in the study were hip-knee-angle (HKA), anatomical-tibiofemoral angle (aTFA), anatomical-mechanical-axis angle (AMA), joint-line-convergence angle (JLCA), mechanical-lateral-proximal-femur-angle (mLPFA), mechanical-lateral-distal-femur-angle (mLDFA), mechanical-medial-proximal-tibia-angle (mMPTA), mechanical-lateral-distal-tibia- angle (mLDTA), femur length, tibia length, full leg length, leg length discrepancy (LLD), and mechanical axis deviation (MAD). These measurements were performed by two radiologists and the AI software on 164 legs. Intraclass-correlation-coefficients (ICC) and Bland-Altman analyses were used to assess the AI's performance. RESULTS: The AI software set incorrect landmarks for 11/164 legs. Excluding these cases, ICCs between the software and radiologists were excellent for 12/13 variables (11/13 with outliers included), and the AI software met performance targets for 11/13 variables (9/13 with outliers included). The mean reading time for the AI algorithm and two readers, respectively, was 38.3, 435.0, and 625.0 s. CONCLUSION: This study demonstrated that, with few exceptions, this AI-based software reliably generated measurements for most variables in the study and provided substantial time savings.

Correlation Between Traditional Anteroposterior Radiographic Measurements With Lateral Radiographic Measurements Following Triplanar Correction of Hallux Valgus and With Patient-Reported Outcomes From a Prospective Multicenter Trial.

Hallux valgus (HV) is a common condition in which the first ray is deformed, leading to pain and altered joint mechanics. A variety of radiographic measurements are used to evaluate HV. Little is known about measurements used in the assessment of HV on lateral radiographs compared to anteroposterior (AP) radiographs. The primary aim of this study was to correlate lateral measurements with AP measurements pre and postoperatively. The secondary aim was to correlate lateral measurements with patient-reported outcome measures (PROMs) pre and postoperatively. One hundred eighty-three patients were initially enrolled in the study. Two fellowship-trained musculoskeletal radiologists independently performed all measurements. On AP radiographs, hallux valgus angle (HVA) and intermetatarsal angle (IMA) were measured. On lateral radiographs, sagittal IMA, Meary's angle, and sagittal first ray length were measured. Measurements were recorded at baseline and 6, 12, and 24 months postoperatively. Intraclass correlation coefficients (ICCs) were used for inter-reader analysis. ICCs were moderate to very strong among readers. There were significant but weak correlations between lateral measurements and AP measurements. For at least 1 timepoint, IMA correlated with sagittal IMA, sagittal first ray length, and Meary's angle. HVA only correlated with sagittal first ray length. These correlations were all weak in magnitude. There were a few significant but weak correlations between the measurements in the study and PROMs. This study showed that sagittal IMA, sagittal first ray length, and Meary's angle are not predictive of AP measurements or patient outcomes and are not useful in preoperative assessment of HV.

Interreader reliability assessment of hallux valgus evaluation on dorsoplantar weightbearing radiographs from a prospective multi-center trial and correlation with patient-reported outcome measures.

OBJECTIVE: To determine inter-reader reliability (IRR) of hallux valgus (HV) related parameters, i.e. intermetatarsal angle (IMA), hallux valgus angle (HVA), lateral round sign of the first metatarsal, tibial sesamoid position (TSP), metatarsus adductus angle (MAA), transverse osseous foot width, 1st MT length, MTP osteoarthritis (OA), and distal metatarsal articular angle (DMAA). These were correlated with patient-reported outcome measures (PROMs). MATERIALS AND METHODS: A prospective single-arm Level 3 multicenter clinical trial in which standardized radiographs and PROMs were collected at the time of the initial patient visit for pre-operative assessment. Two musculoskeletal radiologists performed measurements blinded to each other's reads and clinical information. Intraclass coefficient and kappa were obtained for inter-reader analysis. A partial spearman rank order was used to correlate the measurements with PROMs. RESULTS: The final cohort size of 183 patients had mean age of 40.77 years, mean body mass index was 26.11 kg/m2, with 91.2% females and 8.7% males. There was excellent IRR for HVA (0.96, CI: [0.94,0.97]), IMA (0.92, CI: [0.89,0.94]), transverse osseous foot width (0.99, CI: [0.98,1.00]), and DMAA (0.80, CI: [0.74, 0.85]), good agreement for TSP (0.73, CI:[0.67,0.79]) and MAA (0.67, CI: [0.16, 0.84]), fair agreement for MTP OA (0.48, CI: [0.36,0.59]), and poor agreement for lateral round sign (0.32, CI: [0.11, 0.52]. The negative correlation of increasing transverse osseous foot width with worsening PROMIS physical but better MOxFQ and VAS scores is likely spurious. CONCLUSION: Good to excellent inter-reader reliability was observed for the most often used measurements for HV assessment without major trends in their correlations with PROMs. Lateral round sign is not a reliable finding in HV deformity.

Effects of Depression, Anxiety, and Pain Catastrophizing on Total Hip Arthroplasty Patient Activity Level.

BACKGROUND: Improvements in psychological factors are strongly associated with increased physical activity in the general population. The effects of depression, anxiety, and pain catastrophizing on activity level have not been thoroughly explored in patients undergoing total hip arthroplasty (THA). Mental health markedly influences patient perspectives on treatment success and quality of life. We hypothesized that improvements in screenings for depression, anxiety, and catastrophizing correlate with improvements in activity levels after THA. METHODS: Two hundred ninety two patients (313 hips) who underwent THA with a minimum 1-year (mean 615 ± 270 days) follow-up completed preoperative and postoperative surveys containing the University of California Los Angeles (UCLA) Activity Score, Hospital Anxiety Depression Scale (HADS), Pain Catastrophizing Scale (PCS), and Depression Anxiety Stress Scale-21 (DASS). Wilcoxon signed-rank tests were performed between preoperative and postoperative times for outcome measures. Partial Spearman's rank-order correlations were performed between the change in UCLA Score and the change in HADS, PCS, and DASS. RESULTS: There were significant improvements in UCLA Score (P value < .0001) and every subscale of PCS, HADS, and DASS (P values < .0001). Significant negative correlations existed between change in UCLA Score and change in HADS-anxiety (rs = -0.21, P value < .001), change in HADS-depression (rs = -0.23, P value < .001), and change in DASS-anxiety (rs = -0.22, P value = .004) following THA. Weaker significant negative correlations existed between change in UCLA Score and change in the remaining PCS (P values = .006) and DASS-depression(P value = .037) subscales. CONCLUSION: Improvements in patient-reported depression, anxiety, and pain catastrophizing screenings following THA were associated with increased activity levels. Patients who were screened for catastrophizing, depression, and anxiety achieved statistically and clinically meaningful improvements in symptoms following THA. Addressing patient mental health provides another avenue for holistic care of THA patients.

Does Preoperative Activity Level Affect Postoperative Outcomes Following Total Hip Arthroplasty?

BACKGROUND: Many patients electing to undergo total hip arthroplasty (THA) value continuing active lifestyles when considering treatment options. Addressing these concerns requires evaluating the effect of preoperative activity level on patient-reported outcomes and improvement following THA. METHODS: Three hundred thirty-five patients (368 hips) who underwent THA with a minimum 6-month (mean 533 ± 271 days) follow-up completed preoperative and postoperative University of California, Los Angeles (UCLA) activity score along with various patient-reported measures of function, pain, and mental state. Preoperative UCLA score divided patients into inactive, mild, and active groups. Analysis of covariance controlling for age, sex, body mass index, surgical approach, implant, bilateral cases, conversions, and follow-up time evaluated differences among groups for postoperative outcomes with subsequent Tukey-Kramer pairwise comparisons. RESULTS: Mildly active patients (73:139 male:female) had better postoperative outcomes than inactive patients (40:70 male:female) for UCLA score, EuroQol Visual Analog Scale (EQVAS), Hip Outcome Score (HOS), 12-item Short-Form (SF-12) Physical, and Visual Analog Pain Scale (average/now/worst) (P values <0.001/<0.001/<0.001/<0.001/0.003/<0.001/<0.001). Active patients (32:14 male:female) had better postoperative outcomes than inactive patients for UCLA score, EQVAS, HOS, SF-12 Physical, and Visual Analog Pain Scale Worst (P values <0.001/0.024/0.001/0.001/0.017). No postoperative outcome differences existed between active and mild patients. Inactive patients displayed greater outcome improvements than mildly active patients for UCLA score, Harris Hip Score, and International Hip Outcome Tool (P values <0.001/<0.001/0.013) and active patients for UCLA score, EQVAS, HOS, International Hip Outcome Tool, and SF-12 Physical (P values <0.001/0.008/0.013/0.022/0.004). CONCLUSIONS: Inactive patients achieve greater measure improvements following THA. Active patients achieve better absolute outcomes than inactive patients; however, increasing activity levels do not incrementally improve patient-reported outcome measures. Patients similarly improve pain and mental health regardless of activity level.

In Vitro Investigation of Column Fixation Constructs for Periacetabular Osteotomy: Which Provide the Greatest Stiffness and Strength?

Background: Periacetabular osteotomy (PAO) is an effective surgical procedure for managing acetabular dysplasia. The purpose of this study was to analyze the biomechanical properties of novel PAO constructs that incorporate orthopaedic trauma techniques. We hypothesize that these fixation methods will create a stiffer construct that tolerates higher loads to failure. Methods: Twenty bio-composite hemi-pelvises underwent PAO with the following fixation configurations: Group A: 4 iliac crest (IC) screws; Group B: 3 IC screws; Group C: 2 IC screws, 1 retrograde anterior column (AC) screw, and 1 lateral compression type-2 (LC2) screw directed from the anterior inferior iliac spine to the posterior inferior iliac spine; Group D: 1 AC screw, 1 LC2 screw, 1 posterior column screw; Group E: 2 LC2 screws, 1 AC screw. Constructs were loaded to failure on a material testing hydraulic press, and ultimate strength, stiffness, and osteotomy displacement were measured. Results: The highest load to failure was seen in group D (2511 N), which was significantly more than groups A (1528 N, P = .0114) and B (1348 N, P < .0001). The stiffest construct was group E (602 N/mm) compared to groups A (315 N/mm, P = .0439) and B (243 N/mm, P = .0008). Failure occurred most often with a fracture in the posterior column. Conclusions: This study supports column fixation methods used in orthopaedic trauma for PAO as biomechanically advantageous to traditional fixation techniques. These constructs may be beneficial to patients with weight-bearing concerns or early rehabilitation needs.

Reliability assessment of leg length and angular alignment on manual reads versus artificial intelligence-generated lower extremity radiographic measurements.

PURPOSE: Leg length discrepancy (LLD) and lower extremity malalignment can lead to pain and osteoarthritis. A variety of radiographic parameters are used to assess LLD and alignment. A 510(k) FDA approved artificial intelligence (AI) software locates landmarks on full leg standing radiographs and performs several measurements. The objective of this study was to assess the reliability of this AI tool compared to three manual readers. METHODS: A sample of 320 legs was used. Three readers' measurements were compared to AI output for hip-knee-angle (HKA), anatomical-tibiofemoral angle (aTFA), anatomical-mechanical-axis angle (AMA), joint-line-convergence angle (JLCA), mechanical-lateral-proximal-femur-angle (mLPFA), mechanical-lateral-distal-femur-angle (mLDFA), mechanical-medial-proximal-tibia-angle (mMPTA), mechanical-lateral-distal-tibia- angle (mLDTA), femur length, tibia length, full leg length, leg-length-discrepancy (LLD), and mechanical-axis-deviation (MAD). Intraclass correlation coefficients (ICCs) and Bland-Altman analysis were used to track performance. RESULTS: AI output was successfully produced for 272/320 legs in the study. The reader versus AI pairwise ICCs were mostly in the excellent range: 12/13, 12/13, and 9/13 variables were in the excellent range (ICC > 0.75) for readers 1, 2, and 3, respectively. There was better agreement for leg length, femur length, tibia length, LLD, and HKA than for other variables. The median reading times for the three readers and AI were 250, 282, 236, and 38 s, respectively. CONCLUSION: This study showed that AI-based software provides reliable assessment of LLD and lower extremity alignment with substantial time savings.

Artificial intelligence-generated hip radiological measurements are fast and adequate for reliable assessment of hip dysplasia : an external validation study.

AIMS: Hip dysplasia (HD) leads to premature osteoarthritis. Timely detection and correction of HD has been shown to improve pain, functional status, and hip longevity. Several time-consuming radiological measurements are currently used to confirm HD. An artificial intelligence (AI) software named HIPPO automatically locates anatomical landmarks on anteroposterior pelvis radiographs and performs the needed measurements. The primary aim of this study was to assess the reliability of this tool as compared to multi-reader evaluation in clinically proven cases of adult HD. The secondary aims were to assess the time savings achieved and evaluate inter-reader assessment. METHODS: A consecutive preoperative sample of 130 HD patients (256 hips) was used. This cohort included 82.3% females (n = 107) and 17.7% males (n = 23) with median patient age of 28.6 years (interquartile range (IQR) 22.5 to 37.2). Three trained readers' measurements were compared to AI outputs of lateral centre-edge angle (LCEA), caput-collum-diaphyseal (CCD) angle, pelvic obliquity, Tönnis angle, Sharp's angle, and femoral head coverage. Intraclass correlation coefficients (ICC) and Bland-Altman analyses were obtained. RESULTS: Among 256 hips with AI outputs, all six hip AI measurements were successfully obtained. The AI-reader correlations were generally good (ICC 0.60 to 0.74) to excellent (ICC > 0.75). There was lower agreement for CCD angle measurement. Most widely used measurements for HD diagnosis (LCEA and Tönnis angle) demonstrated good to excellent inter-method reliability (ICC 0.71 to 0.86 and 0.82 to 0.90, respectively). The median reading time for the three readers and AI was 212 (IQR 197 to 230), 131 (IQR 126 to 147), 734 (IQR 690 to 786), and 41 (IQR 38 to 44) seconds, respectively. CONCLUSION: This study showed that AI-based software demonstrated reliable radiological assessment of patients with HD with significant interpretation-related time savings.Cite this article: Bone Jt Open 2022;3(11):877-884.