Flare Prediction Research Articles

Solar Flare Forecasting Using Hybrid Neural Networks

Abstract Solar flares are one of the most intense solar activities, the result of a sudden large-scale release of magnetic energy in the form of electromagnetic radiation and energetic particles. Intense solar flares can severely threaten communication and navigation systems, oil pipelines, and power grids on Earth. Therefore, it is crucial to establish highly accurate solar flare prediction models to enable humans to anticipate solar flare eruptions in advance, thereby reducing human and economic losses. In this paper, we utilized the solar active region (AR) magnetogram provided by the Solar Dynamics Observatory’s Helioseismic and Magnetic Imager and the associated feature parameters of the magnetic field; specifically, the feature vectors of the magnetic field’s spatial structure characteristics and the magnetic field feature parameters are fused to predict solar flares. We built two solar flare prediction models based on a combination of convolutional neural networks (CNN) and a temporal convolutional network (TCN), called CNN-TCN, and predicted whether a ≥C- or ≥M-class flare event would erupt in ARs in the next 24 hr, respectively. Then, after training and testing our model, we focused on the true skill statistic (TSS). Through the model superiority discussion, the model obtained high average TSS values, with the ≥C and ≥M models achieving TSS scores of 0.798 ± 0.032 and 0.850 ± 0.074, respectively, suggesting that our models have good forecasting performance. We speculate that some key features automatically extracted by our model may not have been previously identified, and these features could provide important clues for studying the mechanisms of flares.

P0267 Proactive Remote Monitoring of Inflammatory Bowel Disease for Improved Outcomes and Flare Prediction

Abstract Background This study evaluated a remote monitoring program for IBD patients, using a mobile app to track disease activity and improve patient-provider communication. The app included disease activity questionnaires, quality of life assessments, and home-based calprotectin tests. we aimed to develop a data-driven, patient-reported care management system for early detection of clinical flares in IBD patients, enabling timely treatment adjustments. Methods A 12-month prospective cohort study included 100 adult IBD patients. Participants completed monthly online questionnaires via the “DATOS” platform, assessing disease activity (PRO2/SCCAI), quality of life (PROMIS-10, SIBDQ), emotional state (DASS-21), and perceived disease control (IBD CONTROL). Home calprotectin tests were performed at baseline, 6 months, and 12 months. Data from 533 monthly observations were used to develop a machine learning model to predict flares. Results Among 100 patients (74% Crohn’s, 26% ulcerative colitis; median age 31 years), 94% were on biological therapy. Adherence to the remote platform declined over time (86% at 0 months, 53% at 6 months, 30% at 12 months). Over the study period, 40 flares, 14 hospitalizations, 6 surgeries, and 31 changes in biological therapy occurred. Patients experiencing a flare had significantly higher fecal calprotectin levels (mean: 901.8 vs. 330.6 mg/kg, p=0.044), as well as increased anxiety, depression, and stress (DASS-21, p<0.05), poorer quality of life (PROMIS-10, p=0.005; SIBDQ, p<0.001), and reduced perceived disease control (IBD-Control, p<0.001). A machine learning model incorporating calprotectin and patient-reported outcomes demonstrated a 0.85 accuracy in predicting flares. Conclusion This study demonstrates the feasibility of a remote monitoring program for IBD patients. Although the program facilitated streamlined patient follow-up, long-term adherence was challenging, highlighting the need for improvements in system usability and patient engagement. The machine-learning model, which combined fecal calprotectin and patient-reported outcomes, showed good accuracy in identifying patients at risk of flares. These findings suggest that remote monitoring, supported by machine learning, could enhance IBD management.

P0393 Radiological healing in perianal fistulising Crohn’s disease: MRI predictors and disease course

Abstract Background Perianal fistulising Crohn’s disease (CD) is a disabling condition affecting up to 30% of patients. Studies suggest that greater fibrosis in the fistula tract is linked to improved clinical outcomes. This study aims to describe the natural history of perianal fistulising CD, including MRI parameters, and to identify clinical and radiological predictors of relapse and radiological healing Methods Pelvic MRIs for perianal fistula performed at CHU Liège, Belgium, from 2018 to 2023 were collected. MRI protocols used 1.5T [Siemens Aera/Sola] or 3T [Siemens Vida] machines, with sequences including T2 TSE, T2 TSE FS, and T1 TSE FS before and after gadolinium injection. The MAGNIFI-CD and modified Van Assche (VA) indices were assessed for each patient. Two blinded radiologists evaluated fistula tract fibrosis. For patients with perianal flare, only the first MRI was analysed (MRI 1). For others, the first and last MRI (MRI 2) within the study period were assessed. Perianal flare was defined as abscess drainage or stoma creation for active perianal CD, and radiological healing as ≥80% fistula fibrosis or a MAGNIFI-CD score of 0. Results A total of 102 pelvic MRIs from 84 patients were included. The median patient age was 39 years (31–51), with 40% female. The median duration of perianal CD was 52 months (2–144); 26% had a seton at MRI 1, 7% had a stoma, and 41% were on anti-TNF therapy. During follow-up, 22% required abscess drainage. No clinical factors were associated with perianal flare. Univariate analysis identified several MRI 1 radiologic predictors of flare: fibrosis percentage (OR=0.72, p=0.033), VA hyperintensity T2 (OR=3.22, p=0.028), VA rectal involvement (OR=1.75, p=0.040), VA inflammatory mass (OR=1.42, p=0.022), VA T1 post-contrast hyperintensity (OR=3.68, p=0.045), MAGNIFI-CD score (OR=1.13, p=0.022), MAGNIFI T1 post-contrast hyperintensity (OR=1.77, p=0.031), and MAGNIFI inflammatory mass (OR=1.40, p=0.033). In multivariate analysis, only MAGNIFI T1 post-contrast hyperintensity remained significant (OR=1.77, p=0.031). Radiological healing was achieved in 30% at MRI 1 (25/84) and 44% at MRI 2 (8/18). No factors at MRI 1 predicted healing at MRI 2, though T1 post-contrast hyperintensity at MRI 1 showed a trend towards predicting lack of healing (OR=0.11, p=0.071). Conclusion One-fifth of patients experienced perianal flare during follow-up. Clinical and therapeutic factors did not predict outcomes; only persistent MRI inflammation and low fistula fibrosis were linked to future abscess drainage. Specific MRI features may serve as therapeutic targets in perianal CD management, pending validation in a prospective cohort.

Analysis of related factors for systemic lupus erythematosus flare after SARS-Cov-2 infection: A retrospective cohort study.

Since COVID-19 infections are more common in systemic lupus erythematosus (SLE) patients, most recent research has focused on the outcome of COVID-19, with fewer studies on disease activity in SLE. This research aims to evaluate flares in SLE with COVID-19 infection while investigating predictive factors. A questionnaire survey was conducted to collect information on patients with previously diagnosed SLE from multi-center. SLE patients infected with COVID-19 after December 7, 2022, were selected. Detailed information covering demographic characteristics, SLE and COVID-19 clinical features, disease activity, and medication was collected through an electronic questionnaire. A multivariate logistic regression model was constructed to evaluate the predictive factors for SLE disease onset after COVID-19 infection. A total of 240 patients were finally included in our analysis. Thirty (12.5%) of those enrolled reported an SLE flare. Multivariate analysis with logistic models confirmed that SLE in the active stage (OR 2.617, 95% CI 1.008-6.514, p = .041) and COVID-19 duration (OR 4.140, 95% CI 1.412-11.694, p = .008) were predictors for flare in SLE patients with Covid-19 infection. In contrast, immunosuppressants were associated with a low incidence of flare of SLE (OR 0.138, 95% CI 0.042-0.46, p = .005). The active phase of SLE and the progression of COVID-19 were the main risk factors for disease exacerbation in SLE patients, while the use of immunosuppressive medications was associated with a lower risk of flare-ups. These findings provide valuable insights for managing SLE patients during the COVID-19 pandemic.

Prediction of Large Solar Flares Based on SHARP and High-energy-density Magnetic Field Parameters

The existing flare prediction primarily relies on photospheric magnetic field parameters from the entire active region (AR), such as Space-Weather HMI Activity Region Patches (SHARP) parameters. However, these parameters may not capture the details of the AR evolution preceding flares. The magnetic structure within the core area of an AR is essential for predicting large solar flares. This paper utilizes the area of high photospheric free energy density (high-energy-density, hereafter HED, region) as a proxy for the AR core region. We construct two data sets: SHARP and HED data sets. The ARs contained in both data sets are identical. Furthermore, the start and end times for the same AR in both data sets are identical. We develop six models for 24 hr solar flare forecasting, utilizing SHARP and HED data sets. We then compare their categorical and probabilistic forecasting performance. Additionally, we conduct an analysis of parameter importance. The main results are as follows: (1) Among the six solar flare prediction models, the models using HED parameters outperform those using SHARP parameters in both categorical and probabilistic prediction, indicating the important role of the HED region in the flare initiation process. (2) The transformer flare prediction model stands out significantly in true skill statistic and Brier skill score, surpassing the other models. (3) In parameter importance analysis, the total photospheric free magnetic energy density (E free) within the HED parameters excels in both categorical and probabilistic forecasting. Similarly, among the SHARP parameters, the R_VALUE stands out as the most effective parameter for both categorical and probabilistic forecasting.

131 and 304 Å Emission Variability Increases Hours Prior to Solar Flare Onset

Abstract Thermal changes in coronal loops are well studied, both in quiescent active regions and in flaring scenarios. However, relatively little attention has been paid to loop emission in the hours before the onset of a solar flare; here, we present the findings of a study of over 50 off-limb flares of Geostationary Operational Environmental Satellite class C5.0 and above. We investigated the integrated emission variability for Solar Dynamics Observatory Atmospheric Imaging Assembly channels 131, 171, 193, and 304 Å for 6 hr before each flare and compared these quantities to the same time range and channels above active regions without proximal flaring. We find significantly increased emission variability in the 2–3 hr before flare onset, particularly for the 131 and 304 channels. This finding suggests a potential new flare prediction methodology. The emission trends between the channels are not consistently well correlated, suggesting a somewhat chaotic thermal environment within the coronal portion of the loops that disturbs the commonly observed heating and cooling cycles of quiescent active region loops. We present our approach and the resulting statistics and discuss the implications for heating sources in these preflaring active regions.

OP03 Redesigning the patient management pathway through prediction of flares in axial spondyloarthritis using a machine learning approach to improve care

Abstract Background and aims Treatment of axial spondyloarthritis (axSpA) involves the management of flares which can be unpredictable. ASAS developed a data-driven definition of flares/disease worsening as an increase in ASDAS-CRP of at least 0.9 points, for use in axSpA clinical trials (1). With the current pressures on clinic capacity, there is a challenge to see flare patients in a timely manner. Artificial intelligence (AI) and natural language processing (NLP) methods provide algorithms for learning systems to recognise disease-related terms and classify clinical phenotypes using large datasets, which may support early identification of patients with a risk of having a flare. In previous work, we presented an approach using NLP to identify patients who may have rheumatic disease with predictors to discriminate patients with diagnosed inflammatory arthritis from controls with non-inflammatory arthritis. With the same aim, we extended the panel of predictors by combining clinical and laboratory data to predict flares in axSpA. Methods 282 axSpA patients seen between January 2016 to May 2024 were included in the study. There are 100 flare and 182 non-flare patients studied. We utilised patient blood test results, demographic information, electronic patient-reported outcomes scores, comorbidity, weight and height. We developed a time series dataset and applied Long Short-Term Memory (LSTM) networks and neural networks (NN) to forecast the risk of flare before their future clinics. Results We conducted predictive modelling to forecast flare and non-flare events using data collected prior to patients upcoming clinic appointments. The dataset was split into training and testing sets based on observations taken 2 months before the clinic visit. Our LSTM model achieved 90.25% accuracy, 0.89 sensitivity, 0.96 specificity, 0.93 precision and 0.98 Area Under the Receiver Operating Characteristic Curve (AUROC) predicting flare and non-flare events 2 months before the clinics. The results are summarized in Table 1. OP03 Table 1.Performance of Long Short-Term Memory (LSTM) and neural networks (NN) on data from 2 months before the clinic visit.AVG ACCURACYAVG SENSITIVITYAVG SPECIFICITYAVG PRECISIONAVG AUROCLSTM (2 months before the next clinics)90.25%0.890.960.930.98NEURAL NETWORK (2 months before the next clinics)71.90%0.910.010.610.5 Conclusions The presented combination of clinical and laboratory data shows promising results for the prediction of flare in axSpA and may in the future assist clinicians in seeing the right patient in the right clinic. A study is planned not only to confirm the results but also to refine the machine learning (ML) models developed and specify disease attributes. In the service redesign, patients identified as at risk of flares will be booked and seen in routine clinics at the right time to prevent flares. This process in the long-term will reduce the reliance on flare and urgent clinics.

Clinical course and flare predictors in patients with rheumatoid arthritis in low disease activity and ultrasound remission monitored by ultrasound yearly and on-demand: A prospective 2-year observation study

Introduction and objectivesUltrasound (US) remission in rheumatoid arthritis (RA) targets synovitis absence. Tenosynovitis triggers flares. Despite increased ultrasound use, flare patterns among patients with low disease activity (LDA) and ultrasound remission, especially in real-world settings, are poorly understood. This study examined flare rates and predictors of US remission in patients without synovitis or tenosynovitis. Materials and methodsIn a study of 88 patients achieving US remission and LDA, the focus was on the time to the first flare over a 2-year follow-up. US remission, indicated by the absence of active synovitis and tenosynovitis based on a power Doppler (US-PD) score of 0, was assessed on various joints. Flares are defined by the need for additional medication or encountering a US-PD flare. They were monitored at the baseline, 1-year, and 2-year visits with further US evaluation at clinical flare-ups. Baseline factors linked to a shorter time to flare were analyzed. ResultsAt 1 year, LDA and US remission rates were 75% and 92%, respectively, and at 2 years, 73% and 87% respectively. Over the 2 years, 40% experienced flare, occurring on average at 11.7±7.0 months. Notably, 5.7% have US-PD flares without clinical signs. Analysis revealed Stage III disease and CRP as factors linked to a shorter time to flare. Discussion and conclusionsIn patients with RA achieving LDA and US remission, frequent flares were observed with US remission over 2 years, but most maintained sustained remission. Baseline factors are essential for predicting flares, emphasizing continuous monitoring and personalized treatment to sustain remission and minimize flare risks in RA management.

MSR151 Replicability and Deployment of a Systemic Lupus Erythematosus Flare Prediction Model From Administrative Claims to Electronic Medical Records

MSR151 Replicability and Deployment of a Systemic Lupus Erythematosus Flare Prediction Model From Administrative Claims to Electronic Medical Records

An observational study of ultrasound semiquantitative scoring for predicting the risk of gout flare.

An observational study was conducted to determine whether semiquantitative scoring of ultrasound signs of gout predicted flare over 12months. Gout patients were enrolled consecutively in this 12-month prospective observational single-center study. Ultrasound evaluation and clinical assessment were performed at baseline. All patients were examined bilaterally evaluating 14joints (knee, ankle, metatarsophalangeal joints 1-5) and 10tendons (posterior tibial, quadriceps, peroneus longus and brevis scored as one, patellar, and Achilles tendons). The following ultrasound features were examined and semiquantitative scoring was performed: DC sign, aggregates, tophi, bone erosion, synovial hypertrophy, PD activity, and tenosynovitis. Patients were divided into two groups, one with flares during the follow-up period and the other without flares. Atotal of 119 participants completed the study; 61(51.3%) participants experienced at least one flare over 12months, with amedian of 2.0flares. The ultrasound findings indicative of DC sign, aggregate, tophi, bone erosion, and PD activity at baseline were significantly correlated with the development of gout flares over 12months. Logistic regression analysis suggested that DC sign score (OR:2.41, 95% CI: 0.92-4.37; P = 0.02), tophi score (OR:1.87, 95% CI: 0.65-2.28; P = 0.04), and PD activity score (OR:1.93, 95% CI: 0.58-3.26; P = 0.03) were independent predictors of flare. ROC curve analysis to assess ultrasound semiquantitative scoring has good sensitivity and specificity for the prediction of gout flares. Ultrasound semiquantitative scoring can predict the risk of flare, and ultrasound findings indicative of DC sign, tophi, and PD activity are independent predictors of gout flares over 12months.

Predicting Immune Flares in Untreated Chronic Hepatitis B Patients Using Novel Risk Factors and the FLARE-B Score.

Risk factors of chronic hepatitis B (CHB) immune flares are poorly understood. The primary aim of this study was to discover predictors of the CHB flare in non-cirrhotic, untreated CHB patients and develop a simple risk-stratifying score to predict the CHB flare. The secondary aim was to compare different machine learning methods for prediction. A retrospective cohort of untreated, non-cirrhotic CHB patients with normal baseline ALT was followed up over time until an immune flare as defined by ALT twice the upper limit of normal. Statistical learning and machine learning algorithms were used to develop predictive models using baseline variables. Bootstrap validation was used to internally validate the models. Of 405 patients (median age 44y; 41% male, 10% HBeAg positive), 67 (17%) experienced an immune flare by 5 years (annual incidence 4.0%). Predictors of flare included raised serum globulin, younger age, HBeAg positive status, higher viral load and raised liver stiffness. A simple predictive model "FLARE-B" had optimism-adjusted 1, 3 and 5-year AUCs of 0.813, 0.728 and 0.702, respectively. The random survival forest algorithm had the highest optimism-adjusted AUCs of 0.861, 0.766 and 0.725, respectively. New, novel predictors of the CHB flare include a raised serum globulin and possibly raised liver stiffness and the absence of liver steatosis. FLARE-B can be used to risk-stratify individuals and potentially guide personalized management strategies such as monitoring schedules and proactive antiviral treatment in high-risk patients.

Solar active region evolution and imminent flaring activity through color-coded visualization of photospheric vector magnetograms

Context. The emergence of magnetic flux, its transition to complex configurations, and the pre-eruptive state of active regions are probed using photospheric magnetograms. Aims. Our aim is to pinpoint different evolutionary stages in emerging active regions, explore their differences, and produce parameters that could advance flare prediction using color-coded maps of the photospheric magnetic field. Methods. The three components of the photospheric magnetic field vector are combined to create color-combined magnetograms (COCOMAGs). From these, the areas occupied by different color hues are extracted, creating appropriate time series (color curves). These COCOMAGs and color curves are used as proxies of the active region evolution and its complexity. Results. The morphology of COCOMAGs showcases typical features of active regions, such as sunspots, plages, and sheared polarity inversion lines. The color curves represent the area occupied by photospheric magnetic field of different orientation and contain information pertaining to the evolutionary stages of active regions. During emergence, most of the region area is dominated by horizontal or highly inclined magnetic field, which is gradually replaced by more vertical magnetic field. In complex regions, large parts are covered by highly inclined magnetic fields, appearing as abrupt color changes in COCOMAGs. The decay of a region is signified by a domination of vertical magnetic field, indicating a gradual relaxation of the magnetic field configuration. The color curves exhibit a varying degree of correlation with active region complexity. Particularly the red and magenta color curves, which represent strong, purely horizontal magnetic field, are good indicators of future flaring activity. Conclusions. Color-combined magnetograms facilitate a comprehensive view of the evolution of active regions and their complexity. They offer a framework for the treatment of complex observations and can be used in pattern recognition, feature extraction, and flare-prediction schemes.

Impacts of Data Preprocessing and Sampling Techniques on Solar Flare Prediction from Multivariate Time Series Data of Photospheric Magnetic Field Parameters

The accurate prediction of solar flares is crucial due to their risks to astronauts, space equipment, and satellite communication systems. Our research enhances solar flare prediction by employing sophisticated data preprocessing and sampling techniques for the Space Weather Analytics for Solar Flares (SWAN-SF) data set, a rich source of multivariate time series data of solar active regions. Our study adopts a multifaceted approach encompassing four key methodologies. Initially, we address over 10 million missing values in the SWAN-SF data set through our innovative imputation technique called fast Pearson correlation-based k-nearest neighbors imputation. Subsequently, we propose a precise normalization technique, called LSBZM normalization, tailored for time series data, merging various strategies (log, square root, Box–Cox, Z-score, and min–max) to uniformly scale the data set's 24 attributes (photospheric magnetic field parameters), addressing issues such as skewness. We also explore the “near decision boundary sample removal” technique to enhance the classification performance of the data set by effectively resolving the challenge of class overlap. Finally, a pivotal aspect of our research is a thorough evaluation of diverse oversampling and undersampling methods, including SMOTE, ADASYN, Gaussian noise injection, TimeGAN, Tomek links, and random undersampling, to counter the severe imbalance in the SWAN-SF data set, notably a 60:1 ratio of major (X and M) to minor (C, B, and FQ) flaring events in binary classification. To demonstrate the effectiveness of our methods, we use eight classification algorithms, including advanced deep-learning-based architectures. Our analysis shows significant true skill statistic scores, underscoring the importance of data preprocessing and sampling in time-series-based solar flare prediction.

Case Studies on Pre-eruptive X-class Flares using R-value in the Lower Solar Atmosphere

The R-value is a measure of the strength of photospheric magnetic polarity inversion lines in active regions (ARs). This work investigates the possibility of a relation between R-value variations and the occurrence of X-class flares in ARs, not in the solar photosphere, as usual, but above it in regions closer to where flares occur. The modus operandi is to extrapolate the Solar Dynamic Observatory’s Helioseismic and Magnetic Imager magnetogram data up to a height of 3.24 Mm above the photosphere and then compute the R-value based on the extrapolated magnetic field. Recent studies have shown that certain flare-predictive parameters such as the horizontal gradient of the vertical magnetic field and magnetic helicity may improve flare prediction lead times significantly if studied at a specific height range above the photosphere, called the optimal height range (OHR). Here, we define the OHR as a collection of heights where a sudden but sustained increase in R-value is found. For the eight case studies discussed in this paper, our results indicate that it is possible for OHRs to exist in the low solar atmosphere (between 0.36 and 3.24 Mm), where R-value spikes occur 48–68 hr before the first X-class flare of an emerging AR. The temporal evolution of R-value before the first X-class flare for an emerging AR is also found to be distinct from that of nonflaring ARs. For X-class flares associated with nonemerging ARs, an OHR could not be found.

Causal Attention Deep-learning Model for Solar Flare Forecasting

Solar flares originate from the sudden release of energy stored in the magnetic field of the active region on the Sun, but the trigger for flares is still uncertain. Currently, deep-learning-based solar flare prediction models have achieved good results and are widely recognized. However, these models focus more on data correlation rather than causality. An ideal flare prediction model should probe into the causes/triggers of solar flares, and diagnose the precursors of flares rather than just correlation analysis. To extract more informative precursors of flares from magnetograms, while suppressing the interference of confounding factors, a causal attention module is introduced to disentangle causal and confounder features from the input features. To address the problem of imbalanced positive and negative samples in the data set, an adaptive data set split mechanism is proposed. It divides the data set into several balanced subsets of positive and negative samples, and dynamically adjusts the subsets according to the model’s prediction results during the training process. The experimental results demonstrate that our proposed model achieves 4.08%, 8.38%, and 2.19% higher accuracy, true skill score, and area under the receiver operating characteristic curve than the baseline model. Additionally, the class-specific heatmaps by using the gradient-weighted class activation mapping method reveal that our proposed model generally focuses on the polarity inverse line of active regions, well in line with theoretical study.

Clinical characteristics and risk factors for lupus flares in sub-Saharan Africa-retrospective cross-sectional study.

Systemic lupus erythematosus (SLE) is an autoimmune disease with a variable course with unpredictable flares. Identifying predictors of these flares is essential for monitoring and timely hospital care. To characterize the prevalence of flares within the first five years of SLE diagnosis and determine the clinical and immunological characteristics associated with flare development among patients attending the Rheumatology Clinic at Tikur Anbesa Specialized Hospital (TASH) and Lancet General Hospital. A multicenter, cross-sectional study was conducted from May 2023 to November 2023 at TASH and Lancet General Hospital. The data was collected from electronic medical records and analyzed using SPSS version 26. Logistic regressions were used to determine factors associated with lupus flare. Most patients with SLE were female (95.4%). The most common clinical presentations were musculoskeletal (71.8%), cutaneous (55%), and constitutional (22%). Almost half (44.3%) of the patients had comorbidity illness. Positive ANA test was found in 96.5% of the patients, whereas only 55% had positive anti-dsDNA test. The prevalence of SLE flare in the first five years of SLE diagnosis was 38.9%, and most flares occurred within the first year of diagnosis. Patients with the following characteristics were more likely to have flare-ups: younger age at diagnosis (less than 25years old), initial presentation with vasculitis, renal flare, and being on low-dose prednisolone. The most common clinical presentations were musculoskeletal, dermatologic, and constitutional manifestations. Age < 25years at diagnosis, initial clinical presentation with renal manifestation, and being on low-dose prednisolone were predictors of SLE flare. Key Points • This study found a significant gender disparity, with 95% female. • Nearly 39% of patients experienced an SLE flare within the first five years of diagnosis. • Over three-quarters (77%) of flares occurred within the first year of diagnosis. • Age less than 25years, initial presentation with vasculitis, renal involvement, and being on low-dose prednisolone were identified as predictors of flares.

Time Series of Magnetic Field Parameters of Merged MDI and HMI Space-weather Active Region Patches as Potential Tool for Solar Flare Forecasting

Solar flare prediction studies have been recently conducted with the use of Space-Weather MDI (Michelson Doppler Imager on board Solar and Heliospheric Observatory) Active Region Patches (SMARPs) and Space-Weather HMI (Helioseismic and Magnetic Imager on board Solar Dynamics Observatory) Active Region Patches (SHARPs), which are two currently available data products containing magnetic field characteristics of solar active regions (ARs). The present work is an effort to combine them into one data product, and perform some initial statistical analyses in order to further expand their application in space-weather forecasting. The combined data are derived by filtering, rescaling, and merging the SMARP and SHARP parameters, which can then be spatially reduced to create uniform multivariate time series. The resulting combined MDI–HMI data set currently spans the period between 1996 April 4 and 2022 December 13, and may be extended to a more recent date. This provides an opportunity to correlate and compare it with other space-weather time series, such as the daily solar flare index or the statistical properties of the soft X-ray flux measured by the Geostationary Operational Environmental Satellites. Time-lagged cross correlation indicates that a relationship may exist, where some magnetic field properties of ARs lead the flare index in time. Applying the rolling-window technique makes it possible to see how this leader–follower dynamic varies with time. Preliminary results indicate that areas of high correlation generally correspond to increased flare activity during the peak solar cycle.

Immunosuppressives discontinuation after renal response in lupus nephritis: predictors of flares, time to withdrawal and long-term outcomes.

The optimal duration of immunosuppressive (IS) treatment for lupus nephritis (LN) remains uncertain. We assessed the prevalence and predictors of IS tapering and discontinuation (D/C) in LN patients. Data from 137 inception cohort LN patients were analyzed. We examined determinants of flares during tapering and after IS D/C, D/C achievement and time to D/C, and adverse long-term outcomes applying logistic and linear regression models. IS tapering was attempted in 111 (81%) patients, and D/C was achieved in 67.5%. Longer time to achieve complete renal response (CR) (OR : 1.07, p= 0.046) and higher SLEDAI-2K at tapering initiation (OR : 2.57, p= 0.008) were correlated with higher risk of renal flares during tapering. Persistent hydroxychloroquine use (≥2/3 of follow-up) (OR : 0.28, p= 0.08) and lower SLEDAI-2K 12 months before IS D/C (OR : 1.70, p= 0.013) decreased the risk of post-D/C flares. Adverse outcomes (>30% eGFR decline, chronic kidney disease, end-stage renal disease, death) at the end of follow-up (median124 months) were more frequent in patients with flares during IS tapering (53% vs 16%, p< 0.0038) but did not differ between IS D/C achievers and non-achievers. In proliferative LN, differences mirrored those in entire cohort, except for time to D/C, which occurred 20 months earlier in membranous vs proliferative LN (β-coef=-19.8, p= 0.014). Earlier CR achievement and lower SLEDAI-2K at tapering initiation prevent flares during IS tapering, while persistent hydroxychloroquine use and lower SLEDAI-2K 12 months before IS D/C prevent post-D/C flares. Flares during tapering increase the risk of unfavorable long-term outcomes. Earlier IS D/C is feasible in membranous LN.

Comparison of Gout Flares With the Initiation of Treat-to-Target Allopurinol and Febuxostat: A Post-Hoc Analysis of a Randomized Multicenter Trial.

Initiating urate-lowering therapy (ULT) in gout can precipitate arthritis flares. There have been limited comparisons of flare risk during the initiation and escalation of allopurinol and febuxostat, administered as a treat-to-target strategy with optimal anti-inflammatory prophylaxis. This was a post-hoc analysis of a 72-week randomized, double-blind, placebo-controlled, noninferiority trial comparing the efficacy of allopurinol and febuxostat. For this analysis, the occurrence of flares was examined during weeks 0 to 24 when ULT was initiated and titrated to a serum urate (sUA) goal of less than 6 mg/dl (<5 mg/dl if tophi). Flares were assessed at regular intervals through structured participant interviews. Predictors of flare, including treatment assignment, were examined using multivariable Cox proportional hazards regression. Study participants (n = 940) were predominantly male (98.4%) and had a mean age of 62.1 years with approximately equal proportions receiving allopurinol or febuxostat. Mean baseline sUA was 8.5 mg/dl and all participants received anti-inflammatory prophylaxis (90% colchicine). In a multivariable model, there were no significant associations of ULT treatment (hazard ratio [HR] 1.17; febuxostat vs allopurinol), ULT-dose escalation (HR 1.18 vs no escalation), prophylaxis type, or individual comorbidity with flare and no evidence of ULT-dose escalation interaction. Factors independently associated with flare risk during ULT initiation/escalation included younger age, higher baseline sUA, and absence of tophi. These results demonstrate that gout flare risk during the initiation and titration of allopurinol is similar to febuxostat when these agents are administered according to a treat-to-target strategy using gradual ULT-dose titration and best practice gout flare prophylaxis.

A novel solar flare forecast model with deep convolution neural network and one-against-rest approach

We present a novel deep Convolutional Neural Network model with one-against-rest approach (OAR-CNN) and modify the hybrid Convolutional Neural Network (H-CNN) model of Zheng et al. (2019) for multiclass flare prediction to forecast whether an active region generates multiclass flare within 24 h. Additionally, in the OAR-CNN and H-CNN models, we employ the decision strategies of majority voting and probability threshold, respectively, comparing the prediction outcomes of these two strategies. Our models undergo training and testing on the same 10 cross-validation datasets as employed by Zheng et al. (2019), and then compare the results with previous studies using forecast verification metrics, with a focus on the true skill statistic (TSS). The major results are summarized as follows. (1) This is the first attempt to utilize the decision strategies of majority voting and probability threshold in the OAR-CNN model for multiclass solar flare prediction. (2) In both the OAR-CNN and H-CNN models, the predictive results with the probability threshold decision strategy are higher than those with majority voting across all six classes (i.e., No-flare, C, M, X, ⩾C, and ⩾M class), except for a slight decrease in the C class in the OAR-CNN model. (3) The OAR-CNN and modified H-CNN models with the probability threshold decision strategy demonstrate comparable statistical scores across all categories and outperform previous studies. (4) In the prediction of four-class flare, our proposed OAR-CNN model with the probability threshold decision strategy achieves relatively high mean TSS scores of 0.744, 0.429, 0.567, and 0.630 for No-flare, C, M, and X class, respectively, surpassing or comparable to results from prior studies. Furthermore, our model achieves high TSS scores of 0.744 ± 0.042 for ⩾C–class and 0.764 ± 0.089 for ⩾M-class predictions.