RESUMEN
BACKGROUND: The radiographic assessment of bone morphology impacts implant selection and fixation type in total hip arthroplasty (THA) and is important to minimize the risk of periprosthetic femur fracture (PFF). We utilized a deep-learning algorithm to automate femoral radiographic parameters and determined which automated parameters were associated with early PFF. METHODS: Radiographs from a publicly available database and from patients undergoing primary cementless THA at a high-volume institution (2016 to 2020) were obtained. A U-Net algorithm was trained to segment femoral landmarks for bone morphology parameter automation. Automated parameters were compared against that of a fellowship-trained surgeon and compared in an independent cohort of 100 patients who underwent THA (50 with early PFF and 50 controls matched by femoral component, age, sex, body mass index, and surgical approach). RESULTS: On the independent cohort, the algorithm generated 1,710 unique measurements for 95 images (5% lesser trochanter identification failure) in 22 minutes. Medullary canal width, femoral cortex width, canal flare index, morphological cortical index, canal bone ratio, and canal calcar ratio had good-to-excellent correlation with surgeon measurements (Pearson's correlation coefficient: 0.76 to 0.96). Canal calcar ratios (0.43 ± 0.08 versus 0.40 ± 0.07) and canal bone ratios (0.39 ± 0.06 versus 0.36 ± 0.06) were higher (P < .05) in the PFF cohort when comparing the automated parameters. CONCLUSIONS: Deep-learning automated parameters demonstrated differences in patients who had and did not have early PFF after cementless primary THA. This algorithm has the potential to complement and improve patient-specific PFF risk-prediction tools.
RESUMEN
INTRODUCTION/AIMS: Hourglass-like constrictions (HGCs) of involved nerves in neuralgic amyotrophy (NA) (Parsonage-Turner syndrome) have been increasingly recognized with magnetic resonance neurography (MRN). This study sought to determine the sensitivity of HGCs, detected by MRN, among electromyography (EMG)-confirmed NA cases. METHODS: This study retrospectively reviewed records of patients with the clinical diagnosis of NA, and with EMG confirmation, who underwent 3-Tesla MRN within 90 days of EMG at a single tertiary referral center between 2011 and 2021. "Severe NA" positive cases were defined by a clinical diagnosis and specific EMG criteria: fibrillation potentials or positive sharp waves, along with motor unit recruitment (MUR) grades of "discrete" or "none." On MRN, one or more HGCs, defined as focally decreased nerve caliber or diffusely beaded appearance, was considered "imaging-positive." Post hoc inter-rater reliability for HGCs was measured by comparing the original MRN report against subsequent blinded interpretation by a second radiologist. RESULTS: A total of 123 NA patients with 3-Tesla MRN performed within 90 days of EMG were identified. HGCs were observed in 90.2% of all NA patients. In "severe NA" cases, based on the above EMG criteria, HGC detection resulted in a sensitivity of 91.9%. Nerve-by-nerve analysis (183 nerve-muscle pairs, nerves assessed by MRN, muscles assessed by EMG) showed a sensitivity of 91.0%. The second radiologist largely agreed with the original HGC evaluation, (94.3% by subjects, 91.8% by nerves), with no significant difference between evaluations (subjects: χ2 = 2.27, P = .132, nerves: χ2 = 0.98, P = .323). DISCUSSION: MRN detection of HGCs is common in NA.
RESUMEN
Purpose: The primary objective of this study is to determine if ultrasound-guided erector spinae plane blocks (ESPB) prior to thoracolumbar spinal fusion reduces opioid consumption in the first 24 hours postoperatively. Secondary objectives include ESPB effects on administration of opioids, utilization of intravenous patient-controlled analgesia (IV-PCA), pain scores, length of stay, and opioid related side effects. Methods: A retrospective cohort analysis was performed on consecutive, adult patients undergoing primary thoracolumbar fusion procedures. Demographic and baseline characteristics including diagnoses of chronic pain, anxiety, depression, and preoperative use of opioids were collected. Surgical data included surgical levels, opioid administration, and duration. Postoperative data included pain scores, opioid consumption, IV-PCA duration, opioid-related side effects, ESPB-related complications, and length of stay (LOS). Statistical analysis was performed using chi-squared and t-test analyses, multivariable analysis, and covariate adjustment with propensity score. Results: A total of 118 consecutive primary thoracolumbar fusions were identified between October 2019 and December 2021 (70 ESPB, 48 no-block [NB]). There were no significant demographic or surgical differences between groups. Median surgical time (262.50 mins vs 332.50 mins, p = 0.04), median intraoperative opioid consumption (8.11 OME vs 1.73 OME, p = 0.01), and median LOS (152.00 hrs vs 128.50 hrs, p = 0.01) were significantly reduced in the ESPB group. Using multivariable covariate adjustment with propensity score analysis only intraoperative opioid administration was found to be significantly less in the ESPB cohort. Conclusion: ESPB for thoracolumbar fusion can be performed safely in index cases. There was a reduction of intraoperative opioid administration in the ESPB group, however the care team was not blinded to the intervention. Extensive thoracolumbar spinal fusion surgery may require a different approach to regional anesthesia to be similarly effective as ESPB in isolated lumbar surgeries.
RESUMEN
BACKGROUND: Accurate and rapid identification of implant manufacturer and model is critical in the evaluation and management of patients requiring revision total shoulder arthroplasty (TSA). Failure to correctly identify implant designs in these circumstances may lead to delay in care, unexpected intraoperative challenges, increased morbidity, and excess health care costs. Deep learning (DL) permits automated image processing and holds the potential to mitigate such challenges while improving the value of care rendered. The purpose of this study was to develop an automated DL algorithm to identify shoulder arthroplasty implants from plain radiographs. METHODS: A total of 3060 postoperative images from patients who underwent TSA between 2011 and 2021 performed by 26 fellowship-trained surgeons at 2 independent tertiary academic hospitals in the Pacific Northwest and Mid-Atlantic Northeast were included. A DL algorithm was trained using transfer learning and data augmentation to classify 22 different reverse TSA and anatomic TSA prostheses from 8 implant manufacturers. Images were split into training and testing cohorts (2448 training and 612 testing images). Optimized model performance was assessed using standardized metrics including the multiclass area under the receiver operating characteristic curve (AUROC) and compared with a reference standard of implant data from operative reports. RESULTS: The algorithm classified implants at a mean speed of 0.079 seconds (±0.002 seconds) per image. The optimized model discriminated between 8 manufacturers (22 unique implants) with AUROCs of 0.994-1.000, accuracy of 97.1%, and sensitivities between 0.80 and 1.00 on the independent testing set. In the subset of single-institution implant predictions, a DL model identified 6 specific implants with AUROCs of 0.999-1.000, accuracy of 99.4%, and sensitivity >0.97 for all implants. Saliency maps revealed key differentiating features across implant manufacturers and designs recognized by the algorithm for classification. CONCLUSION: A DL model demonstrated excellent accuracy in identifying 22 unique TSA implants from 8 manufacturers. This algorithm may provide a clinically meaningful adjunct in assisting with preoperative planning for the failed TSA and allows for scalable expansion with additional radiographic data and validation efforts.
