Prediction of radiographic progression pattern in patients with ankylosing spondylitis using group-based trajectory modeling and decision trees.

Objective: This study aimed to identify trajectories of radiographic progression of the spine over time and use them, along with associated clinical factors, to develop a prediction model for patients with ankylosing spondylitis (AS). Methods: Data from the medical records of patients diagnosed with AS in a single center were extracted between 2001 and 2018. Modified Stoke Ankylosing Spondylitis Spinal Scores (mSASSS) were estimated from cervical and lumbar radiographs. Group-based trajectory modeling classified patients into trajectory subgroups using longitudinal mSASSS data. In multivariate analysis, significant clinical factors associated with trajectories were selected and used to develop a decision tree for prediction of radiographic progression. The most appropriate group for each patient was then predicted using decision tree analysis. Results: We identified three trajectory classes: class 1 had a uniformly increasing slope of mSASSS, class 2 showed sustained low mSASSS, and class 3 showed little change in the slope of mSASSS but highest mSASSS from time of diagnosis to after progression. In multivariate analysis for predictive factors, female sex, younger age at diagnosis, lack of eye involvement, presence of peripheral joint involvement, and low baseline erythrocyte sedimentation rate (log) were significantly associated with class 2. Class 3 was significantly associated with male sex, older age at diagnosis, presence of ocular involvement, and lack of peripheral joint involvement when compared with class 1. Six clinical factors from multivariate analysis were used for the decision tree for classifying patients into three trajectories of radiographic progression. Conclusion: We identified three patterns of radiographic progression over time and developed a decision tree based on clinical factors to classify patients according to their trajectories of radiographic progression. Clinically, this model holds promise for predicting prognosis in patients with AS.

A pilot study on deep learning-based grading of corners of vertebral bodies for assessment of radiographic progression in patients with ankylosing spondylitis.

Background: Radiographs are widely used to evaluate radiographic progression with modified stoke ankylosing spondylitis spinal score (mSASSS). Objective: This pilot study aimed to develop a deep learning model for grading the corners of the cervical and lumbar vertebral bodies for computer-aided detection of mSASSS in patients with ankylosing spondylitis (AS). Methods: Digital radiographic examination of the spine was performed using Discovery XR656 (GE Healthcare) and Digital Diagnost (Philips). The disk points were detected between the bodies using a key-point detection deep learning model from the image obtained in DICOM (digital imaging and communications in medicine) format from the cervical and lumbar spinal radiographs. After cropping the vertebral regions around the disk point, the lower and upper corners of the vertebral bodies were classified as grade 3 (total bony bridges) or grades 0, 1, or 2 (non-bridges). We trained a convolutional neural network model to predict the grades in the lower and upper corners of the vertebral bodies. The performance of the model was evaluated in a validation set, which was separate from the training set. Results: Among 1280 patients with AS for whom mSASSS data were available, 5,083 cervical and 5245 lumbar lateral radiographs were reviewed. The total number of corners where mSASSS was measured in the cervical and lumbar vertebrae, including the upper and lower corners, was 119,414. Among them, the number of corners in the training and validation sets was 110,088 and 9326, respectively. The mean accuracy, sensitivity, and specificity for mSASSS scoring in one corner of the vertebral body were 0.91604, 0.80288, and 0.94244, respectively. Conclusion: A high-performance deep learning model for grading the corners of the vertebral bodies was developed for the first time. This model must be improved and further validated to develop a computer-aided tool for assessing mSASSS in the future.

Comparative Cost-Effectiveness of Tofacitinib With Continuing Conventional Synthetic Disease-Modifying Anti-Rheumatic Drugs for Active Rheumatoid Arthritis in South Korea.

INTRODUCTION: The objective of this study was to evaluate the cost-effectiveness of initiating treatment with tofacitinib and subsequently incorporating it into a conventional synthetic disease-modifying anti-rheumatic drug (csDMARD) treatment sequence and to compare the cost-effectiveness of this sequence with that of continuing csDMARDs alone in patients with active rheumatoid arthritis (RA). METHODS: A cohort-based Markov model was used to evaluate the cost-effectiveness of two tofacitinib treatment sequences compared with that of continuing the csDMARD treatment sequence over a lifetime. Of the two tofacitinib sequences, the first consisted of initial tofacitinib treatment followed by biologic DMARDs (bDMARDs) and the second consisted of csDMARD treatments followed by tofacitinib. A third treatment sequence, continuing the csDMARD treatment sequence before starting bDMARDs, was used as a comparator. Efficacy was assessed using the American College of Rheumatology (ACR) response rates (ACR 20, ACR 50, and ACR 70) after 6 months, which were converted to changes in the health assessment questionnaire-disability index (HAQ-DI) score. Utility was estimated by mapping from the HAQ-DI score, costs were analyzed from a Korean societal perspective, and outcomes were considered in terms of quality-adjusted life-years (QALYs). One-way sensitivity analysis and probabilistic sensitivity analysis were performed to assess the robustness of the model. RESULTS: The incremental cost-effectiveness ratios over a lifetime for starting with tofacitinib and incorporating tofacitinib into the csDMARD treatment sequence versus continuing csDMARDs only were US$14,537 per QALY and US$7,086 per QALY, respectively. One-way sensitivity analysis and probabilistic sensitivity analysis confirmed the robustness of these results. CONCLUSION: Starting with tofacitinib and incorporating it into a csDMARDs treatment sequence is cost-effective compared to continuing csDMARDs alone in patients with RA.

Dose Reduction of Tumor Necrosis Factor Inhibitor and its Effect on Medical Costs for Patients with Ankylosing Spondylitis.

INTRODUCTION: Tumor necrosis factor inhibitors (TNFis) may be administered at a reduced dose to patients with ankylosing spondylitis (AS) for various reasons. However, in practice, there is insufficient evidence of how the dose reduction of TNFi is implemented and the amount of medical costs it reduces. In this study, we investigated treatment patterns among patients with AS who were administered various TNFis. The effect on medical costs related to AS was also investigated using Korea's insurance claims database. METHODS: From the insurance claims database of the Health Insurance Review & Assessment Service in South Korea, patients with AS newly treated with TNFis (etanercept, adalimumab, golimumab, and infliximab) between July 1, 2013, and June 30, 2016, were enrolled. Patients treated with the TNFis were followed up for 2 years. Treatment patterns (continuation and discontinuation of TNFi) and dose reduction (< 50% of recommended dose) in patients who continued treatment were analyzed and compared among the TNFi groups using the Chi-square test. Healthcare costs between the dose reduction and maintenance groups were compared using general linear modeling. RESULTS: Of 1352 patients, 764 (56.51%) continued using TNFis for 2 years, and 17.8% of these were administered reduced doses. TNFi dose reduction was the most frequent in 36 (24.83%) patients using etanercept, followed by those using adalimumab (21.97%), golimumab (11.70%), and infliximab (11.98%) (p = 0.0028). For each TNFi group, the total healthcare cost significantly decreased, that is, by 24.85% for adalimumab, 31.80% for etanercept, 26.34% for golimumab, and 35.52% for infliximab (p < 0.0001). CONCLUSIONS: TNFi dose reduction was identified in 17.8% of the patients with AS, and the patterns were different for each TNFi. Additionally, the dose reductions significantly reduced the medical costs associated with AS, that is, from 24.85 to 35.52% of the total medical expenditure.