OrthoSensor (United States)

Aims The use of technology to assess balance and alignment during total knee surgery can provide an overload of numerical data to the surgeon. Meanwhile, this quantification holds the potential to clarify and guide the surgeon through the surgical decision process when selecting the appropriate bone recut or soft tissue adjustment when balancing a total knee. Therefore, this paper evaluates the potential of deploying supervised machine learning (ML) models to select a surgical correction based on patient-specific intra-operative assessments. Methods Based on a clinical series of 479 primary total knees and 1,305 associated surgical decisions, various ML models were developed. These models identified the indicated surgical decision based on available, intra-operative alignment, and tibiofemoral load data. Results With an associated area under the receiver-operator curve ranging between 0.75 and 0.98, the optimized ML models resulted in good to excellent predictions. The best performing model used a random forest approach while considering both alignment and intra-articular load readings. Conclusion The presented model has the potential to make experience available to surgeons adopting new technology, bringing expert opinion in their operating theatre, but also provides insight in the surgical decision process. More specifically, these promising outcomes indicated the relevance of considering the overall limb alignment in the coronal and sagittal plane to identify the appropriate surgical decision.

This study is a systematic review of all reported synovial fluid markers for the diagnosis of periprosthetic joint infection and a meta-analysis of the most frequently reported markers to identify those of greatest diagnostic utility. A search of six databases was conducted to identify all studies evaluating the utility of synovial fluid markers in the diagnosis of periprosthetic joint infection. Two observers assessed methodologic quality and extracted data independently. A meta-analysis of the most frequently reported markers was performed. Twenty-three studies were included in the meta-analysis. The most common markers (and their respective area under the curve) were interleukin-17 (0.974), leukocyte esterase (0.968), α-defensin (0.958), interleukin-6 (0.956), interleukin-1β (0.948), and C-reactive protein (0.927). Among these markers, α-defensin had the highest diagnostic odds ratio but did not achieve statistically significant superiority. The most frequently studied synovial fluid markers for the diagnosis of periprosthetic joint infection are C-reactive protein, leukocyte esterase, interleukin-6, interleukin-1β, α-defensin, and interleukin-17, all of which have high diagnostic utility. Level II.

Recently, technological advances have made it possible to quantify pounds of pressure across the bearing surface during TKA. This multicenter evaluation, using intraoperative sensors, was performed for two reasons: 1) to define “balance” 2) to determine if patients with balanced knees exhibit improved short-term clinical outcomes. Outcomes scores were compared between “balanced” and “unbalanced” patients. At 6-months, the balanced cohort scored 172.4 and 14.5 in KSS and WOMAC, respectively; the unbalanced cohort scored 145.3 and 23.8 in KSS and WOMAC (P<0.001). Out of all confounding variables, balanced joints were the most significant contributing factor to improved postoperative outcomes (P<0.001). Odds ratios demonstrate that balanced joints are 2.5, 1.3, and 1.8 times more likely to achieve meaningful improvement in KSS, WOMAC, and activity level, respectively.