Variation in the Thickness of Knee Cartilage. The Use of a Novel Machine Learning Algorithm for Cartilage Segmentation of Magnetic Resonance Images

BackgroundThe variation in articular cartilage thickness (ACT) in healthy knees is difficult to quantify and therefore poorly documented. Our aims are to (1) define how machine learning (ML) algorithms can automate the segmentation and measurement of ACT on magnetic resonance imaging (MRI) (2) use ML to provide reference data on ACT in healthy knees, and (3) identify whether demographic variables impact these results.MethodsPatients recruited into the Osteoarthritis Initiative with a radiographic Kellgren-Lawrence grade of 0 or 1 with 3D double-echo steady-state MRIs were included and their gender, age, and body mass index were collected. Using a validated ML algorithm, 2 orthogonal points on each femoral condyle were identified (distal and posterior) and ACT was measured on each MRI. Site-specific ACT was compared using paired t-tests, and multivariate regression was used to investigate the risk-adjusted effect of each demographic variable on ACT.ResultsA total of 3910 MRI were included. The average femoral ACT was 2.34 mm (standard deviation, 0.71; 95% confidence interval, 0.95-3.73). In multivariate analysis, distal-medial (?0.17 mm) and distal-lateral cartilage (?0.32 mm) were found to be thinner than posterior-lateral cartilage, while posterior-medial cartilage was found to be thicker (0.21 mm). In addition, female sex was found to negatively impact cartilage thickness (OR, ?0.36; all values: P < .001).ConclusionML was effectively used to automate the segmentation and measurement of cartilage thickness on a large number of MRIs of healthy knees to provide normative data on the variation in ACT in this population. We further report patient variables that can influence ACT. Further validation will determine whether this technique represents a powerful new tool for tracking the impact of medical intervention on the progression of articular cartilage degeneration.     

After-Hours Calls in a Joint Replacement Practice

BackgroundEarly discharge after joint arthroplasty requires additional resources to manage patients safely after surgery. Patient concerns must be addressed during nonbusiness hours to keep patients out of the emergency department and avoid readmissions. The goal of our study was to determine how type of system is utilized in a busy early discharge joint replacement practice.MethodsIn our total joint program, we have utilized a Google phone number to give patients access to a member of the surgical team after business hours and on weekends. The duration, chief complaint, and resolution of from the phone calls were collected prospectively for 3 months (July 3, 2017-October 3, 2017).ResultsSixty-eight calls were received from 55 patients during the 3-month study period. Three hundred twenty-five cases were performed. The average duration of a call was 3.9 minutes. The average length of time from surgery to call was 17.5 days (range 0-442 days). Suboptimal health literacy was associated with increased calls within the first week after surgery (odds ratio = 4.1, 95% confidence interval = 1.2-14.5, P = .022). A chief complaint of pain was associated with primary versus revision surgery. (odds ratio = 3.23, 95% confidence interval = 1.08-9.86).DiscussionAn “after-hours” telephone contact service with a member of the surgical team may help avoid unnecessary emergency department visits. About one phone call was received per day, with an average duration of 3.9 minutes per call. These additional resources are necessary to maintain patient safety and satisfaction in early discharge joint replacement.     

Systematic Review and Meta-Analysis of Intrawound Vancomycin in Total Hip and Total Knee Arthroplasty: A Call for a Prospective Randomized Trial

BackgroundTopical intrawound vancomycin has been used extensively in spine surgery to decrease surgical site infections. However, the efficacy of intrawound vancomycin in total hip (THA) and total knee arthroplasty (TKA) to prevent periprosthetic joint infection (PJI) has not been established.MethodsThe PubMed and MEDLINE databases were searched to identify studies utilizing intrawound vancomycin in primary and revision THA and TKA. Data for postoperative infection were pooled using random effect models with results reported as odds ratios (ORs) and 95% confidence intervals. Studies were weighted by the inverse variance of their effect estimates.ResultsOf the 91 studies identified, 6 low-quality retrospective studies (level III) were pooled for further analysis. A total of 3298 patients were assessed, 1801 of which were treated with intrawound vancomycin. Overall, patients who received vancomycin had a decreased rate of PJI (OR 0.2530, P < .0001). When analyzed separately, TKA patients and THA patients who received intrawound vancomycin had lower rates of PJI (OR 0.3467, P = .0005 and OR 0.3672, P = .0072, respectively). Pooled primary TKA and THA patients receiving vancomycin saw the rate of PJI decrease (OR 0.4435, P = .0046). Pooled revision TKA and THA patients saw a similar decrease in infection rates (OR 0.2818, P = .0013). No apparent publication bias was observed; however, the results from this analysis are limited by the low quality of evidence and inherent potential for bias.ConclusionIntrawound vancomycin may reduce the risk of PJI in primary and revision TKA and THA. However, only low-quality evidence exists, highlighting the need for randomized controlled trials before broad adoption of this practice can be recommended given the potential implications of widespread use of vancomycin in hip and knee arthroplasty.