Deep learning-based relapse prediction of neuromyelitis optica spectrum disorder with anti-aquaporin-4 antibody.

Objective: We previously identified the independent predictors of recurrent relapse in neuromyelitis optica spectrum disorder (NMOSD) with anti-aquaporin-4 antibody (AQP4-ab) and designed a nomogram to estimate the 1- and 2-year relapse-free probability, using the Cox proportional hazard (Cox-PH) model, assuming that the risk of relapse had a linear correlation with clinical variables. However, whether the linear assumption fits real disease tragedy is unknown. We aimed to employ deep learning and machine learning to develop a novel prediction model of relapse in patients with NMOSD and compare the performance with the conventional Cox-PH model. Methods: This retrospective cohort study included patients with NMOSD with AQP4-ab in 10 study centers. In this study, 1,135 treatment episodes from 358 patients in Huashan Hospital were employed as the training set while 213 treatment episodes from 92 patients in nine other research centers as the validation set. We compared five models with added variables of gender, AQP4-ab titer, previous attack under the same therapy, EDSS score at treatment initiation, maintenance therapy, age at treatment initiation, disease duration, the phenotype of the most recent attack, and annualized relapse rate (ARR) of the most recent year by concordance index (C-index): conventional Cox-PH, random survival forest (RSF), LogisticHazard, DeepHit, and DeepSurv. Results: When including all variables, RSF outperformed the C-index in the training set (0.739), followed by DeepHit (0.737), LogisticHazard (0.722), DeepSurv (0.698), and Cox-PH (0.679) models. As for the validation set, the C-index of LogisticHazard outperformed the other models (0.718), followed by DeepHit (0.704), DeepSurv (0.698), RSF (0.685), and Cox-PH (0.651) models. Maintenance therapy was calculated to be the most important variable for relapse prediction. Conclusion: This study confirmed the superiority of deep learning to design a prediction model of relapse in patients with AQP4-ab-positive NMOSD, with the LogisticHazard model showing the best predictive power in validation.

Comparison of Long-Term Use of Low Dose Rituximab and Mycophenolate Mofetil in Chinese Patients With Neuromyelitis Optica Spectrum Disorder.

Background: Several studies have reported the efficacy and safety of rituximab (RTX) and mycophenolate mofetil (MMF) in neuromyelitis optica spectrum disorder (NMOSD). This study aimed to evaluate the efficacy and safety of long-term use of low-dose RTX and MMF in Chinese patients with NMOSD. Methods: We retrospectively reviewed data from patients with NMOSD in our hospital. The enrolled patients were administrated different immunosuppressive agents. We accessed annual relapse rate (ARR), neurological disability (Expanded Disability Status Scale, EDSS), time to the next relapse, and adverse events. Results: EDSS and ARR were both reduced after RTX and MMF treatment. Kaplan-Meier analysis indicated that patients treated with RTX had a longer time to next relapse compared other immunosuppressive agents before RTX (log-rank test: p < 0.001). Furthermore, we evaluated the change of EDSS and ARR in RTX and MMF, and patients treated with RTX showed a better reduction. Eleven relapses from seven patients in group RTX and 20 relapses from 14 patients in group MMF were reported during follow-up. Conclusion: Long-term using of low dose of RTX and MMF were effective and tolerable in Chinese patients with NMOSD. Compared with MMF, RTX showed a better way to reduce the ARR.

Neuromyelitis Optica Spectrum Disorder With Anti-Aquaporin-4 Antibody: Outcome Prediction Models.

Background: Recognizing the predictors of disease relapses in patients with anti-aquaporin-4 antibody (AQP4-ab)-positive neuromyelitis optica spectrum disorder (NMOSD) is essential for individualized treatment strategy. We aimed to identify the factors that predicted relapses among patients with AQP4-ab-positive NMOSD, develop outcome prediction models, and validate them in a multicenter validation cohort. Methods: Between January 2015 and December 2020, 820 patients with NMOSD were registered at Huashan Hospital. We retrospectively reviewed their medical records, and included 358 AQP4-ab-positive patients with 1135 treatment episodes. Univariate and multivariate analyses were used to explore the predictors of relapse, severe visual or motor disability during follow-up. A model predicting the 1- and 2-year relapse-free probability was developed and validated in an external validation cohort of 92 patients with 213 treatment episodes. Results: Lower serum AQP4-ab titer (< 1:100), higher Expanded Disability Status Scale (EDSS) score at onset (≥ 2.5), and use of intravenous methylprednisolone (IVMP) at the first attack predicted an overall lower annualized relapse rate. Older age (> 48 years), optic neuritis at onset, and higher onset EDSS score (≥ 2.5) significantly increased the risk for blindness, while IVMP at the first attack and maintenance therapy reduced the risk for blindness. Myelitis at onset increased the possibility of motor disability (EDSS ≥ 6.0), severe motor disability or death (EDSS ≥ 8.0), while maintenance therapy reduced these possibilities. Anderson and Gill model identified that the risk factors predicting recurrent relapses under certain treatment status were female gender, high AQP4-ab titer (≥ 1:100), previous attack under same therapy, lower EDSS score at treatment initiation (< 2.5), and no maintenance therapy or oral prednisone lasting less than 6 months. A nomogram using the above factors showed good discrimination and calibration abilities. The concordance indexes in the primary and validation cohort were 0.66 and 0.65, respectively. Conclusion: This study reports the demographic, clinical and therapeutic predictors of relapse, and severe visual or motor disability in NMOSD. Early identification of patients at risk of unfavorable outcomes is of paramount importance to inform treatment decisions.

Efficacy and safety of azathioprine, mycophenolate mofetil, and reduced dose of rituximab in neuromyelitis optica spectrum disorder.

BACKGROUND AND PURPOSE: Data regarding the efficacy and safety of currently widely available preventive therapies in neuromyelitis optica spectrum disorder (NMOSD) are needed. We compared the efficacy and safety of azathioprine (AZA), mycophenolate mofetil (MMF), and reduced dose of rituximab (RTX) in NMOSD based on a large multicenter retrospective cohort. METHODS: Patients with aquaporin 4 (AQP4) antibody-positive NMOSD with AZA (n = 167), MMF (n = 131), or RTX (n = 55) as initial preventive treatment were included. The main outcome was the occurrence of relapse after the initiation of immunotherapy. Secondary outcomes were annual relapse rate, disability accumulation, drug persistence, and adverse events. RESULTS: The median follow-up time of the 353 patients was 30.3 months. The regimen of RTX was 100 mg on Day 1 and 500 mg on Day 2, followed by 500 mg every 6 months. The proportions of patients with concomitant steroid therapy at baseline were 96.4%, 95.4%, and 76.4% in the AZA, MMF, and RTX groups. Risk of relapse was significantly reduced in patients treated with RTX compared with those treated with AZA (hazard ratio [HR] = 4.40, 95% confidence interval [CI] = 1.41-13.80, p = 0.011) or MMF (HR = 5.20, 95% CI = 1.60-16.86, p = 0.006) after adjusting for potential confounding variables. Drug discontinuations were less likely on RTX than AZA (HR = 2.22, 95% CI = 1.34-3.66, p = 0.002). RTX exhibited lower incidence of adverse events (32.7%) than AZA (62.3%, p < 0.001). CONCLUSIONS: We provide Class III evidence that reduced dose of RTX is superior to AZA and MMF as initial treatment to reduce the risk of relapse and is better tolerated than AZA in Chinese patients with AQP4 antibody-positive NMOSD.

Incidence and risk factors for venous thromboembolism during an acute attack in patients with neuromyelitis optica spectrum disorders.

BACKGROUND: Neuromyelitis optica spectrum disorders (NMOSD) patients may be at increased risk of venous thromboembolism (VTE) during the acute attack, but evidence is limited. OBJECTIVE: To investigate the incidence of venous thromboembolism (VTE) in Neuromyelitis optica spectrum disorders (NMOSD) patients with an acute attack and to identify the potential risk factors for the development of VTE. METHODS: We conducted a retrospective study of NMOSD patients with an acute attack between January 1, 2015, and June 31, 2021. Diagnosis of DVT or PE was objectively confirmed by doppler ultrasound or computed tomographic pulmonary angiography (CTPA) during their acute hospital stay. RESULTS: We identified 184 attacks in 128 NMOSD patients with the mean age of 46.9 years at the time of the attack and female predominance (152/184, 83.2%). VTE occurred in 22 (12.0%) attacks. Among the 22 attacks, 20 presented with transverse myelitis (TM), 1 cerebral syndrome (CS), and 1 simultaneous TM and brainstem syndrome (BS). Multivariable logistic regression analysis showed that advanced age [odds ratio (OR) = 1.08, 95% confidence interval (CI) = 1.04-1.12, p = 0.000], Nadir Expanded Disability Status Scale (EDSS)>6.5(OR = 3.39, 95% CI = 1.22-10.10, p = 0.029) and intravenous immunoglobulin (IVIG) treatment (OR = 3.21, 95% CI = 1.15-8.91, p = 0.025) were independent risk factors for the development of VTE in the total NMOSD cohort. In the subgroup analysis of the NMOSD patients with TM, age at attack (OR = 1.07, 95% CI = 1.03-1.11, p = 0.002) and IVIG treatment (OR = 4.23, 95% CI = 1.44-12.45, p = 0.009) were independent risk factors for the development of VTE in the total NMOSD cohort, but Nadir EDSS>6.5 was not an independent risk factor. CONCLUSIONS: VTE is a frequent complication in NMOSD patients, especially in patients with TM. Advanced age and IVIG are independent risk factors for VTE. Immobilization is an independent risk factor for VTE in the total NMOSD cohort but not in the subgroup analysis of the patients with TM.

Intravenous immunoglobulin as the rescue treatment in NMOSD patients.

Intravenous immunoglobulin (IVIg) has been used for neuromyelitis optica spectrum disorder (NMOSD) patients to prevent relapses in several studies. However, efficacy of the rescue treatment of IVIG was just assessed in a small sample research. The aim of this study is to investigate the efficacy of IVIG in NMOSD as a rescue treatment and whether it could reduce the relapse rate. We retrospectively reviewed patients with NMOSD in the First and Second Affiliated Hospital of Wenzhou Medical University. Clinical parameters were extracted from the medical records, such as expanded disability scale score (EDSS) and time to next relapse. Thirty-one events of 20 NMOSD patients were included in the intravenous methylprednisolone (IVMT) + IVIG group and 72 events of 39 patients in the IVMT group. IVMT therapy combined with IVIG could improve the neurological disability when discharged (p < 0.001), whereas patients first attacked did not show a similar trend. Patients who were treated with IVMT + IVIG (17.39 ± 2.75 months) show a longer time to next relapse compared to patients who were treated with IVMT (9.50 ± 0.79 months) (log rank test p = 0.002), especially in relapsed patients or anti-aquaporin-4 antibody (AQP4-Ab) seropositive patients. IVIG might be helpful for NMOSD patients as the rescue treatment and might bring a longer remission, especially for patients with relapse and AQP4-ab seropositive patients.