Using deep learning and image processing technology, a standardized automatic quantitative analysis systerm of lumbar disc degeneration based on T2MRI is proposed to help doctors evaluate the prognosis of intervertebral disc (IVD) degeneration. A semantic segmentation network BianqueNet with self-attention mechanism skip connection module and deep feature extraction module is proposed to achieve high-precision segmentation of intervertebral disc related areas. A quantitative method is proposed to calculate the signal intensity difference (SI) in IVD, average disc height (DH), disc height index (DHI), and disc height-to-diameter ratio (DHR). According to the correlation analysis results of the degeneration characteristic parameters of IVDs, 1051 MRI images from four hospitals were collected to establish the quantitative ranges for these IVD parameters in larger population around China. The average dice coefficients of the proposed segmentation network for vertebral bodies and intervertebral discs are 97.04% and 94.76%, respectively. The designed parameters of intervertebral disc degeneration have a significant negative correlation with the Modified Pfirrmann Grade. This procedure is suitable for different MRI centers and different resolution of lumbar spine T2MRI (ICC=.874~.958). Among them, the standard of intervertebral disc signal intensity degeneration has excellent reliability according to the modified Pfirrmann Grade (macroF1=90.63%~92.02%). we developed a fully automated deep learning-based lumbar spine segmentation network, which demonstrated strong versatility and high reliability to assist residents on IVD degeneration grading by means of IVD degeneration quantitation.
Patient satisfaction is an important outcome measure after total knee arthroplasty (TKA) and is the ultimate goal of surgery. However, patient satisfaction reflects a complex construct of the patient's personal expectations and preferences in addition to subjective evaluation of outcome after TKA. Multiple studies have found a patient dissatisfaction rate of approximately 20% at 1 year after TKA. The purpose of this study is to determine whether there is an association between a single-item validated TKA satisfaction score and patient-reported outcome measures (PROMs) at 3 time points (1, 2, and 5 years after TKA) and to determine if dissatisfaction rate after TKA varies over time. A multi-center, prospective cohort of 12,952 patients (8,078 patients were assessed at 1-year, 702 patients at 2-year, and 4,172 patients at 5-year) undergoing primary TKA were enrolled by 230 surgeons in 28 states between 2012–2015. Surgeons practices varied in size, reimbursement models, and geographic setting ensuring that the cohort included diverse patient populations and delivery models. Surgeons agreed to invite all TKA patients to participate and sporadic audits of surgical logs validated that all patients were invited and > 90% of patients were included. Demographic and clinical data [age, gender, body mass index (BMI), and modified Charlson co-morbidity index (CCI)] were collected. Patient-reported outcome measures (PROMs) were collected pre-op and post-op at 1, 2, and 5 years using an internet-based platform including the KOOS (total score, and pain, ADL, QoL sub scores), KOOS Jr, SF-36 (PCS and MCS). We used the single-item satisfaction scale which was tested and validated by the Swedish Knee Arthroplasty Registry. The patients' responses were made on 5-point Likert scale (very satisfied, somewhat satisfied, neutral, somewhat dissatisfied, very dissatisfied). Patients were classified into 2 categories: satisfied group for patients who answered satisfied or very satisfied and dissatisfied group for patients answered neutral, somewhat dissatisfied, or very dissatisfied. Univariate analysis of the difference between the satisfied and dissatisfied patients' groups was performed using Mann-Whitney U test for continuous variables and chi-square test for categorical variables. Logistic regression model was performed to study the correlation between the satisfaction and PROMs with 95% confidence interval.Introduction
Methods
US payers offer incentives to hospitals to report patient-reported outcomes measures (PROMs) for total hip arthroplasty (THA). We report THA norms for pre-op and one-year PROMs in a large multi-center cohort and compare global, hip specific scores, and abbreviated PROM measures acceptable to meet payer requirements. The HOOS 12 is a new form of the HOOS containing 12 questions that allows separate determination of pain and ADL sub-scores in addition to the total score. Between 2011–2015, 7895 primary elective THA patients enrolled in the FORCE-TJR research consortium from over 200 surgeons in 28 states. Patients completed pre-op demographics, clinical risks, PROMs, and one-year outcomes. Over 95% completed pre-op PROMs; 83% post-op. Generic and hip specific (HOOS full and HOOS-12 sub-scores, and HOOS JR global) PROMs were compared.Introduction
Methods
Historically, US arthroplasty revision rates are based on CMS data that cannot verify initial surgery date in patients under 65 years or laterality of revision. We calculated US one-year revision rates for primary total hip replacement (THR) using a representative cohort. Reasons for revision were documented. A multi-center cohort from US surgeons in 28 states collected sociodemographic data; medical, emotional, musculoskeletal comorbidities; BMI; and patient-reported pain and function (SF36, HOOS) for elective THR patients. Cases in 2011–2013 were matched with CMS data to ascertain 1 year revision through 2014. Predictors of revision were identified. Chart reviews to verify reasons for revision were performed.Introduction
Methods
