Machine Learning-Assisted Decision Making in Orthopaedic Oncology.

¼ Artificial intelligence is an umbrella term for computational calculations that are designed to mimic human intelligence and problem-solving capabilities, although in the future, this may become an incomplete definition. Machine learning (ML) encompasses the development of algorithms or predictive models that generate outputs without explicit instructions, assisting in clinical predictions based on large data sets. Deep learning is a subset of ML that utilizes layers of networks that use various inter-relational connections to define and generalize data.¼ ML algorithms can enhance radiomics techniques for improved image evaluation and diagnosis. While ML shows promise with the advent of radiomics, there are still obstacles to overcome.¼ Several calculators leveraging ML algorithms have been developed to predict survival in primary sarcomas and metastatic bone disease utilizing patient-specific data. While these models often report exceptionally accurate performance, it is crucial to evaluate their robustness using standardized guidelines.¼ While increased computing power suggests continuous improvement of ML algorithms, these advancements must be balanced against challenges such as diversifying data, addressing ethical concerns, and enhancing model interpretability.

Radiographic parameters of pelvic and proximal femoral morphology do not predict outcomes for direct anterior total hip arthroplasty.

BACKGROUND: Radiographic predictors of outcomes associated with direct anterior approach (DAA) total hip arthroplasty (THA) are largely unknown. Anecdotally, some surgeons limit surgery to patients with low body mass index (BMI) or "favorable" bony morphology. Objective data on the impact of these factors is limited. We sought to determine radiographic and demographic predictors of outcomes after DAA arthroplasty. METHODS: A consecutive series of patients undergoing unilateral, elective DAA THA, who had linked pre- and post-operative patient reported outcome scores, from January 1, 2017 to March 30, 2019 were included. Radiographic measurements, including proxies for pelvic overhang, femoral canal access, acetabular morphologic changes, and markers of disease severity, were performed on calibrated radiographs. Intra-observer consistency was also evaluated. Outcome measures included disease specific and general health patient-reported outcomes scores, while surgical difficulty was approximated by estimated blood loss and surgical time. Multivariate analyses were performed to determine statistically significant correlations. RESULTS: 168 patients were included. Overall, patients experienced significant improvement in outcome scores (mean ∆ HOOS-JR 39.4, PROMIS-physical 12.3). There were two reoperations (1.2%), for recurrent dislocation. Female sex (p = 0.015) and increasing age (p == 0.019) were associated with shorter surgical times. No statistically significant correlations were found between the radiographic parameters and outcome measures. Intraclass correlation coefficients of the radiographic measurements were overall strong (0.73-1.0). CONCLUSION: We demonstrated consistent results in this series of patients despite variation in bony morphology. Our findings suggest that DAA THA can be safely performed on a broader patient population.

Corrective Osteotomy and Physeal Bar Resection for Distal Radial Physeal Arrest After Flexible Nailing: A Case Report.

CASE: A 9-year-old girl developed a physeal bar after flexible nailing for a proximal radius fracture. The patient presented 2 years after initial injury with gross deformity of the wrist with confirmed physeal bar. The patient underwent physeal bar resection, cement interposition, and corrective osteotomy with improvement of radial height, wrist deformity, and function. CONCLUSION: This case illustrates the importance of meticulous flexible nail insertion technique and the subsequent, successful treatment for the complication.