Flare Prediction Research Articles

P197 Exploring diet categorisations and their influence on flare prediction in IBD, using Sparse Group LASSO

Abstract Background Diet is an important environmental factor that may affect flare occurrence in inflammatory bowel disease (IBD), but analyses are hindered by its complexity. Different a priori and a posteriori dietary assessment tools can be used, such as dietary quality scores and dietary pattern analyses. The Sparse Group LASSO (SGL) might be a novel method combining an a priori and an a posteriori approach. In this study, we aim to explore the SGL method to study whether different food categorisations, representing different dietary patterns, can predict flares in patients with IBD. Methods Baseline data on habitual dietary intake and longitudinal data on disease course was collected over a period of 24 months from two cohorts from the Northern and Southern provinces of the Netherlands. Collected food items were classified into 22 food groups. These were further classified into 3 diet categorisations, representing different dietary patterns: model 1. Plant vs animal vs mixed; model 2. Potentially healthy vs neutral vs potentially unhealthy; model 3. Ultra-processed vs not ultra-processed. The SGL parameter ‘lambda’ identifies important groups using a priori group information, while allowing for only a subset of variables within a group to be important predictors. Results Of 724 eligible patients, 427 were in remission at baseline and could be included in the SGL analyses. 106 patients (65.1% female, 34% ulcerative colitis, mean age 43.3 ± 14.7 years) developed a flare within 11.2 ± 6.6 months of follow-up. There was a significant higher crude food intake of red meat (p=0.028) and vegetables (p=0.027) in patients who developed a flare compared to those remaining in remission. Prediction models were moderate with AUC varying between 0.425 and 0.542 for model 1, 0.512 and 0.562 for model 2 and 0.451 and 0.612 for model 3 (Table 1). All models showed red meat, legumes and vegetables as the first selected predicting variables. Unexpectedly, legumes and vegetables predicted a higher risk on flares independently of their categorisation. This was robust in our data and confirmed by Kaplan-Meier survival analyses. Notably, clinical confounders sex and kilocalorie intake had the highest predictive values in all 3 models. Conclusion Categorisation of the same food groups and food items in different ways influences the predictive value of the SGL method. For the present study, categorising according to ultra-processed and not ultra-processed achieved the best prediction model, though still moderate. The current exploration of the SGL method showed that food might not be the most important predictor of flares in IBD. However, red meat, legumes and vegetables were the most important dietary influencers in these cohorts.

S21 APEX Score Prospective Validation: An Excellent Predictor of Flares in Small Bowel Crohn’s Disease After Mucosal Healing

S21 APEX Score Prospective Validation: An Excellent Predictor of Flares in Small Bowel Crohn’s Disease After Mucosal Healing

Solar active region magnetogram image dataset for studies of space weather

In this dataset we provide a comprehensive collection of line-of-sight (LOS) solar photospheric magnetograms (images quantifying the strength of the photospheric magnetic field) from the National Aeronautics and Space Administration’s (NASA’s) Solar Dynamics Observatory (SDO). The dataset incorporates data from three sources and provides SDO Helioseismic and Magnetic Imager (HMI) magnetograms of solar active regions (regions of large magnetic flux, generally the source of eruptive events) as well as labels of corresponding flaring activity. This dataset will be useful for image analysis or solar physics research related to magnetic structure, its evolution over time, and its relation to solar flares. The dataset will be of interest to those researchers investigating automated solar flare prediction methods, including supervised and unsupervised machine learning (classical and deep), binary and multi-class classification, and regression. This dataset is a minimally processed, user configurable dataset of consistently sized images of solar active regions that can serve as a comprehensive image dataset of LOS photospheric magnetograms for solar flare prediction research.

Tracking of Systemic Lupus Erythematosus (SLE) Longitudinally Using Biosensor and Patient-Reported Data: A Report on the Fully Decentralized Mobile Study to Measure and Predict Lupus Disease Activity Using Digital Signals-The OASIS Study.

(1) Objective: Systemic lupus erythematosus (SLE) is a complex disease involving immune dysregulation, episodic flares, and poor quality of life (QOL). For a decentralized digital study of SLE patients, machine learning was used to assess patient-reported outcomes (PROs), QOL, and biometric data for predicting possible disease flares. (2) Methods: Participants were recruited from the LupusCorner online community. Adults self-reporting an SLE diagnosis were consented and given a mobile application to record patient profile (PP), PRO, and QOL metrics, and enlisted participants received smartwatches for digital biometric monitoring. The resulting data were profiled using feature selection and classification algorithms. (3) Results: 550 participants completed digital surveys, 144 (26%) agreed to wear smartwatches, and medical records (MRs) were obtained for 68. Mining of PP, PRO, QOL, and biometric data yielded a 26-feature model for classifying participants according to MR-identified disease flare risk. ROC curves significantly distinguished true from false positives (ten-fold cross-validation: p < 0.00023; five-fold: p < 0.00022). A 25-feature Bayesian model enabled time-variant prediction of participant-reported possible flares (P(true) > 0.85, p < 0.001; P(nonflare) > 0.83, p < 0.0001). (4) Conclusions: Regular profiling of patient well-being and biometric activity may support proactive screening for circumstances warranting clinical assessment.

Abstract 5 — Prediction of Flare Following Glucocorticoids Withdrawal in Rheumatoid Arthritis Patients with Continuation of csDMARDs: A Real-Life Study

Background In patients with rheumatoid arthritis (RA), glucocorticoids (GC) should be firstly discontinued before considering tapering conventional synthetic disease-modifying anti-rheumatic drugs (csDMARD) or other biological agents. We aim to determine risk factors for flare after GC withdrawal in RA patients undergoing csDMARDs. Method RA patients who discontinued GC with continuation of csDMARD were selected from a longitudinal real-world cohort. Established RA was defined as disease duration over 12 months. Dissatisfied RA control was defined as the proportion of simplified disease activity index (SDAI)-based remission time to total time from GC initiation to discontinuation less than 50%. Logistic regression was used to analyze the independent risk factors for flare after GC discontinuation and results were expressed as odds ratio (OR). Results There were 115 eligible RA patients discounted GC with continuation of csDMARDs (methotrexate: 80%; hydroxychloroquine: 61%; csDMARDs combination: 79%). Of these, 24 patients experienced flare after GC discontinuation. Compared with relapse-free patients, flare patients were more likely to have established RA (75% vs. 49%, p=0.025), higher median cumulative prednisolone dosages (3.3g vs. 2.2g, p=0.004), and higher proportion of dissatisfied RA control during GC usage (66% vs. 33%, p=0.038). In multivariate analysis, significantly increased flare risk was predicted by established RA (OR 2.93 [1.02-8.43]), cumulative prednisolone dose &gt; 2.5g (OR 3.69 [1.34-10.19]) and dissatisfied RA control (OR 3.00 [1.09-8.30]). Flare risk was increased with increases in number of risk factors, with highest OR of 11.56 in patients with three risk factors (p for trend=0.002). Conclusions Flare following GC withdrawal is not common in RA patients with undergoing csDMARDs therapy. Established RA, higher cumulative GC dose and dissatisfied RA control before GC discontinuation are important factors associated with flare after GC withdrawal.

The existence of hot X-ray onsets in solar flares

Context. It is well known among the scientific community that solar flare activity often begins well before the main impulsive energy release. However, a consistent explanation for this phenomenon has not yet been established. Aims. Our aim is to investigate the earliest phase of four distinct flares observed by Solar Orbiter/STIX and determine the relationships of the newly heated plasma to flare structure and dynamics. Methods. The analysis focuses on four events that were observed from both Earth and Solar Orbiter, which allows for a comparison of STIX observations with those of GOES/XRS and SDO/AIA. The early phases of the events were studied using STIX and GOES spectroscopic analysis to investigate the evolution of the physical parameters of the plasma, including the isothermal temperature and emission measure. Furthermore, to determine the location of the heated plasma, STIX observations were combined with AIA images. Results. The events with clear emission prior to the impulsive phase show elevated temperatures (&gt; 10 MK) from the very beginning, which indicates that energy release started before any detection by STIX. Although the temperature shows little variation during the initial phase, the emission measure increases by about two orders of magnitude, implying a series of incrementally greater energy releases. The spectral analysis of STIX and GOES from the very first time bins suggests that the emission has a multi-thermal nature, with a hot component of more than 10 MK. Alternative heating mechanisms may be more significant during this phase, since nonthermal emission, as observed by STIX, is only detected later. STIX and AIA images reveal the presence of more compact sources of hot plasma early in the flare that originate from different locations with respect to the standard loop-top source that is observed later in the flare. However, because extended bremsstrahlung sources are much more difficult to detect than compact sources, there might be additionally heated plasma in the loop-top during hot onsets. Conclusions. This analysis confirms the existence of “hot onsets”, with STIX detecting the hot onset pattern even earlier than GOES. These elevated temperatures imply that energy release actually begins well before any detection by STIX. Therefore, hot onsets may be significant in the initiation, early development, or even prediction of solar flares.

A real-world 2-year prospective study of medication tapering in patients with well-controlled rheumatoid arthritis within the rheumatoid arthritis medication tapering (RHEUMTAP) cohort.

This study had two aims: (i) to investigate outcomes of medication tapering in stable RA patients on biologic or targeted synthetic disease-modifying anti-rheumatic drugs (bDMARDs/tsDMARDs) and conventional synthetic DMARDs (csDMARDs) in a real-world prospective cohort; and (ii) to evaluate possible predictors of flare with medication taper. A prospective cohort of patients with RA in sustained remission or low disease activity while on stable bDMARD/tsDMARDs +/- csDMARDs for at least 6 months underwent medication tapering/stopping and was tracked for 2 years. Patients were evaluated for flares in four groups: no taper, only bDMARD/tsDMARD taper, only csDMARD taper and both csDMARD and bDMARD/tsDMARD taper. The RHEUMTAP cohort included 131 patients that met eligibility criteria, of which 52 patients underwent a medication taper. Flare was experienced by 15 patients in the taper and twoin the no-taper groups. Patients undergoing any taper/stop overall were 10 times more likely to experience a flare compared with those not tapered (HR 10.43, 95% CI 2.98-36.53, P = 0.0002). The group tapering bDMARD/tsDMARD had 31 times higher risk of flare (HR 31.43, 95% CI 6.35-155.55, P<0.0001) than the no-taper group. Patients tapering both csDMARDs and bDMARD/tsDMARDs had 18 times higher risk of flare than the no-taper group (HR 18.45, 95% CI 2.55-133.37, P = 0.0039). The only csDMARD taper group had a 91% lower risk of flare than the bDMARD/tsDMARD taper group (HR 0.09, 95% CI 0.01-0.69, P = 0.0213). In our real-world prospective RHEUMTAP cohort study on the outcomes of different medication tapering groups in well-controlled RA, patients who tapered or stopped bDMARDs/tsDMARDs with or without background therapy were more likely to experience a flare than patients that did not taper any medications and those that tapered only csDMARDs.

Occurrence and prediction of flare after tapering of TNF inhibitors in patients with axial spondyloarthritis.

Patients with axial spondyloarthritis (axSpA) in clinical remission tapered Tumor Necrosis Factor inhibitor (TNFi) therapy according to a clinical guideline. During 2-years' follow-up, we aimed to investigate flare frequency, dose at which flare occurred, type of flare and predictors thereof. Patients in clinical remission (Bath ankylosing spondylitis disease activity index (BASDAI)<40, physician global score<40 and without disease activity the previous year) tapered TNFi to 2/3 standard dose at baseline, 1/2 at week (w) 16, 1/3 at w32 and discontinuationed at w48. Flare was defined as: BASDAI flare (BASDAI≥40 and Δ≥20) and/or clinical flare (development of inflammatory back pain, musculoskeletal or extra-articular manifestations and/or ASDAS-CRP increase ≥0.9) and/or MRI flare (≥2 new/worsened inflammatory lesions). Of 108 patients, 106 (99%) flared before 2 years: 29 patients (27%) at 2/3 standard dose, 21 (20%) at 1/2 dose, 29 (27%) at 1/3 dose and 27 (25%) after discontinuation. One-hundred-and-five (99%) had clinical flare, 25 (24%) BASDAI flare and 23 (29% of patients with MRI) MRI flare. Forty-one patients (41%) fulfilled the ASAS-definition of clinically important worsening (≥0.9 increase since baseline). Higher baseline physician global score was an independent predictor of flare after tapering to 2/3 (Odds ratio=1.19 (95% Confidence Interval=1.05-1.41);p=0.011). Changes in clinical and/or imaging variables in the 16 weeks prior to tapering did not predict flare. Almost all (99%) axSpA patients in clinical remission flared during tapering to discontinuation, but above half not before receiving 1/3 dose or less. Higher physician global score was an independent predictor of flare.

Factors contributing to flares of ulcerative colitis in North India- a case-control study

BackgroundUlcerative colitis is a relapsing and remitting disease that may be associated with flares. The causes of flares in the Indian setting are not well recognized.MethodsThe present prospective case-control study was conducted at a single center in North India. Cases were defined as patients admitted for flare of ulcerative colitis, while controls were patients in remission enrolled from the outpatient department. The basis of the diagnosis of flare was a simple clinical colitis activity index (SCCAI) of ≥ 5 and endoscopic activity, while remission was based on SCCAI < 4 and a normal fecal calprotectin. A questionnaire evaluating recent infections, stress, drug intake (antibiotics, pain medication), adherence to therapy, and use of complementary and alternative therapy (CAM) was administered.ResultsWe included 84 patients (51 with flare and 33 in remission) with a median age of 38 years, of whom 47 (55.9%) were males. The two groups were similar for baseline parameters, including age (38, 23–50 and 38, 25.5–48.5 years), male gender (52.9% and 60.6%), extent of disease, extraintestinal manifestations (21.6% and 12.1%), use of 5-aminosalicylates (76.5% and 90.9%). The thiopurine use was lower in those having a flare (15.7% and 36.4%). Amongst the predictors of flare, the recent infections (39.2% and 30.3%), recent travel (31.4 and 27.3%), eating outside food (47.1% and 39.4%), consumption of milk products (88.2% and 75.8%), use of pain medication (43.1% and 33.3%) and recent stress (62.7% and 60.6%) were similar between cases and controls. The rates of antibiotic use (29.4% and 6.1%), lack of adherence (50.9% and 15.2%), and intake of CAM (70.6% and 33.3%) were higher in those with flare. Patients attributed a lack of adherence to the cost of therapy, presumed cure (due to lack of symptoms), and fear of adverse effects.ConclusionLack of adherence to inflammatory bowel disease therapies and recent CAM and antibiotic intake was higher in patients with flares of UC. The study makes ground for educational intervention(s) promoting knowledge and adherence to IBD therapies.

Capsule Endoscopy in Inflammatory Bowel Disease: A Systematic Review

AbstractThe role of video capsule endoscopy (VCE) in inflammatory bowel disease (IBD) has evolved from small bowel to a panenteric evaluation tool over the past two decades. We systematically reviewed the techniques, applications, outcomes, and complications of VCE in IBD. A systematic literature search was performed using PubMed, Embase, and Medline. All relevant original articles involving VCE in IBD were included from 2003 to July 2022. After screening 3,089 citations, finally 201 references were included. The diagnostic yield of VCE in suspected Crohn's disease (CD) was highly variable (6–80%) with excellent sensitivity (77–93%) and specificity (80–89%). The diagnostic yield in known CD was 52 to 88.3% leading to a change in management (26–75%) and disease reclassification with variable retention rates. VCE was superior to small bowel series, computed tomography (CT) and could be better than magnetic resonance enterography (MRE), especially for proximal and superficial lesions. Colon or panenteric VCE has strong correlation to ileo-colonoscopy (IC) and combined magnetic resonance imaging and IC, respectively. The VCE retention rate in CD is higher in known CD which significantly decreases after the negative patency capsule test or CT/MRE. VCE can identify lesions beyond the reach of IC in postoperative CD. Colon Capsule Endoscopy is a noninvasive monitoring tool in ulcerative colitis (UC) having a strong correlation with IC and may uncover small bowel involvement. VCE is specifically useful in IBD-unclassified (IBD-U) which can lead to the diagnosis of CD in 16.7 to 61.5%. Various scoring systems have been established and validated for small bowel CD (Lewis score and capsule endoscopy CD activity index—CECDAI), UC (capsule scoring of UC: Capsule Scoring of Ulcerative Colitis), panenteric evaluation (Capsule Endoscopy Crohn's Disease Activity Index, Elaikim score), and flare prediction (APEX score). Technological advances include double head, three-dimensional reconstruction, sampling system, panoramic view (344 and 360 degree lateral), and panenteric capsule. Artificial intelligence and software like TOP100 and Quickview can help reduce capsule reading time with excellent sensitivity and specificity. VCE in IBD has widespread application in suspected and known small bowel CD, monitoring of UC, postoperative CD, IBD-U, and for panenteric evaluation. Patency capsule testing helps to reduce retention rates significantly. Artificial intelligence and technical advances can help evolve this novel technology.

Operational prediction of solar flares using a transformer-based framework

Solar flares are explosions on the Sun. They happen when energy stored in magnetic fields around solar active regions (ARs) is suddenly released. Solar flares and accompanied coronal mass ejections are sources of space weather, which negatively affects a variety of technologies at or near Earth, ranging from blocking high-frequency radio waves used for radio communication to degrading power grid operations. Monitoring and providing early and accurate prediction of solar flares is therefore crucial for preparedness and disaster risk management. In this article, we present a transformer-based framework, named SolarFlareNet, for predicting whether an AR would produce a gamma-class flare within the next 24 to 72 h. We consider three gamma classes, namely the geM5.0 class, the geM class and the geC class, and build three transformers separately, each corresponding to a gamma class. Each transformer is used to make predictions of its corresponding gamma-class flares. The crux of our approach is to model data samples in an AR as time series and to use transformers to capture the temporal dynamics of the data samples. Each data sample consists of magnetic parameters taken from Space-weather HMI Active Region Patches (SHARP) and related data products. We survey flare events that occurred from May 2010 to December 2022 using the Geostationary Operational Environmental Satellite X-ray flare catalogs provided by the National Centers for Environmental Information (NCEI), and build a database of flares with identified ARs in the NCEI flare catalogs. This flare database is used to construct labels of the data samples suitable for machine learning. We further extend the deterministic approach to a calibration-based probabilistic forecasting method. The SolarFlareNet system is fully operational and is capable of making near real-time predictions of solar flares on the Web.

Prediction of flare following glucocorticoids withdrawal in rheumatoid arthritis patients with continuation of csDMARDs: a real-life study.

To determine the risk factors for flare after glucocorticoids (GC) withdrawal in rheumatoid arthritis (RA) patients with undergoing conventional synthetic disease-modifying anti-rheumatic drugs (csDMARDs). RA patients who discontinued GC with continuation of csDMARD were selected from a longitudinal real-world cohort. Established RA was defined as disease duration over 12months. Dissatisfied RA control was defined as the proportion of simplified disease activity index (SDAI)-based remission time to total time from GC initiation to discontinuation less than 50%. Logistic regression was used to analyze the independent risk factors for flare after GC discontinuation and results were expressed as odds ratio (OR). There were 115 eligible RA patients discounted GC with continuation of csDMARDs (methotrexate: 80%; hydroxychloroquine: 61%; csDMARDs combination: 79%). Of these, 24 patients experienced flare after GC discontinuation. Compared with relapse-free patients, flare patients were more likely to have established RA (75% vs 49%, p = 0.025), higher median cumulative prednisolone dosages (3.3 vs 2.2g, p = 0.004), and higher proportion of dissatisfied RA control during GC usage (66% vs 33%, p = 0.038). In multivariate analysis, significantly increased flare risk was predicted by established RA (OR 2.93 [1.02-8.43]), cumulative prednisolone dose > 2.5g (OR 3.69 [1.34-10.19]) and dissatisfied RA control (OR 3.00 [1.09-8.30]). Flare risk was increased with increases in number of risk factors with highest OR of 11.56 in patients with three risk factors (p for trend = 0.002). Flare following GC withdrawal is not common in RA patients with undergoing csDMARDs therapy. Established RA, higher cumulative GC dose and dissatisfied RA control before GC discontinuation are important factors associated with flare after GC withdrawal.

Comparative analysis of machine learning models for solar flare prediction

Comparative analysis of machine learning models for solar flare prediction

Outcomes in children with rheumatic diseases following COVID-19 vaccination and infection: data from a large two-center cohort study in Thailand.

Vaccination against coronavirus disease 2019 (COVID-19) is effective in protecting patients from severe COVID-19 infection. Disease flare-up following immunization in children with rheumatic disorders may result in patient reluctance to receive the vaccine. Underlying rheumatic diseases or the use of immunosuppressive drugs may influence the outcomes of COVID-19 vaccination and infection. We aimed to describe outcomes in children with rheumatic diseases following COVID-19 immunization and infection. This retrospective study was performed at two large academic centers in Thailand. During the COVID-19 pandemic, all patients were routinely queried about COVID-19-related conditions. We included patients with rheumatic diseases aged <18 years who received at least one dose of a COVID-19 vaccine or had a history of COVID-19 infection with more than 6 months of recorded follow-up after the last vaccine dose or COVID-19 illness. Demographic information and data on clinical symptoms, disease activity, treatment, outcomes, and COVID-19 vaccination and infection were collected. A total of 479 patients were included. Most (229; 47.81%) patients had juvenile idiopathic arthritis, followed by connective tissue diseases (189; 39.46%), vasculitis syndromes (42; 8.76%), and other rheumatic diseases (19; 3.97%). Approximately 90% of patients received at least one dose of COVID-19 vaccination, and half of the patients had COVID-19 infection. Among patients, 10.72% and 3.27% developed a flare after COVID-19 vaccination and COVID-19 illness, respectively. Flare severity after COVID immunization and infection was mainly mild to moderate. The predictor of flare after COVID-19 vaccination was the use of prednisolone ≥10 mg/day before vaccination (hazard ratio: 2.04, 95% confidence interval: 1.05-3.97, p = 0.037). Inactive disease before receiving the COVID-19 vaccination was a predictor of inactive status after a flare (hazard ratio: 2.95, 95% confidence interval: 1.04-8.40; p = 0.043). Overall, 3.36% and 1.61% of patients experienced a new onset of rheumatic disease after receiving the COVID-19 vaccine and after COVID-19 infection, respectively. The COVID-19 vaccine is recommended for children with rheumatic disease, particularly those who are in stable condition. After COVID-19 vaccination, patients-especially those with active disease before vaccination or those receiving concurrent prednisolone doses of ≥10 mg/day-should be closely monitored.

A selective up-sampling method applied upon unbalanced data for flare prediction: potential to improve model performance

The Spaceweather HMI Active Region Patch (SHARP) parameters have been widely used to develop flare prediction models. The relatively small number of strong-flare events leads to an unbalanced dataset that prediction models can be sensitive to the unbalanced data and might lead to bias and limited performance. In this study, we adopted the logistic regression algorithm to develop a flare prediction model for the next 48 h based on the SHARP parameters. The model was trained with five different inputs. The first input was the original unbalanced dataset; the second and third inputs were obtained by using two widely used sampling methods from the original dataset, while the fourth input was the original dataset but accompanied by a weighted classifier. Based on the distribution properties of strong-flare occurrences related to SHARP parameters, we established a new selective up-sampling method and applied it to the mixed-up region (referred to as the confusing distribution areas consisting of both the strong-flare events and non-strong-flare events) to pick up the flare-related samples and add small random values to them and finally create a large number of flare-related samples that are very close to the ground truth. Thus, we obtained the fifth balanced dataset aiming to 1) promote the forecast capability in the mixed-up region and 2) increase the robustness of the model. We compared the model performance and found that the selective up-sampling method has potential to improve the model performance in strong-flare prediction with its F1 score reaching 0.5501 ± 0.1200, which is approximately 22% − 33% higher than other imbalance mitigation schemes.

Comparing feature sets and machine-learning models for prediction of solar flares

Context. Machine-learning methods for predicting solar flares typically employ physics-based features that have been carefully chosen by experts in order to capture the salient features of the photospheric magnetic fields of the Sun. Aims. Though the sophistication and complexity of these models have grown over time, there has been little evolution in the choice of feature sets, or any systematic study of whether the additional model complexity leads to higher predictive skill. Methods. This study compares the relative prediction performance of four different machine-learning based flare prediction models with increasing degrees of complexity. It evaluates three different feature sets as input to each model: a “traditional” physics-based feature set, a novel “shape-based” feature set derived from topological data analysis (TDA) of the solar magnetic field, and a combination of these two sets. A systematic hyperparameter tuning framework is employed in order to assure fair comparisons of the models across different feature sets. Finally, principal component analysis is used to study the effects of dimensionality reduction on these feature sets. Results. It is shown that simpler models with fewer free parameters perform better than the more complicated models on the canonical 24-h flare forecasting problem. In other words, more complex machine-learning architectures do not necessarily guarantee better prediction performance. In addition, it is found that shape-based feature sets contain just as much useful information as physics-based feature sets for the purpose of flare prediction, and that the dimension of these feature sets – particularly the shape-based one – can be greatly reduced without impacting predictive accuracy.

Predictors of severe lupus flare: a prospective follow-up study

BackgroundFlare-up of systemic lupus erythematosus (SLE) is a common characteristic that could have deleterious effects on patients’ outcome and survival. The aim of this study was to identify the predictors of severe lupus flare.Methods120 patients with SLE were enrolled and followed-up for 23 months. Demographic, clinical manifestations, laboratory parameters and disease activity were recorded at each visit. In addition, presence of severe lupus flare at each visit was evaluated by using the Safety of Estrogens in Lupus Erythematosus National Assessment (SELENA)-SLE disease activity index (SLEDAI) flare composite index. Predictors of severe lupus flare were obtained by backward logistic regression analyses. Predictors of SLEDAI were obtained by backward linear regression analyses.ResultsDuring the follow-up period, 47 patients had at least one episode of severe lupus flare. Mean (SD) age of patients with severe flare versus no flare was 31.7 (7.89) and 38.3 (8.24) years, respectively (P = 0.001). Ten (62.5%) out of 16 males and 37 (35.5%) out of 104 females had severe flare (P = 0.04). History of lupus nephritis (LN) was recorded in 76.5% and 44% of patients with severe flare and no severe flare, respectively (P = 0.001). Thirty-five (29.2%) patients with high anti-double-stranded DNA (anti-ds-DNA antibody) and 12 (10%) with negative anti-ds-DNA antibody had severe lupus flare (P = 0.02). By multivariable logistic regression analysis, younger age (OR = 0.87, 95% CI 0.80–0.94, P = 0.0001), history of LN (OR = 4.66, 95% CI 1.55–14.002, P = 0.006) and high SLEDAI at the first visit (OR = 1.19, 95% CI 1.026–1.38) were the main predictors of flare. When severe lupus flare after the first visit was used as the outcome variable, similar findings were observed but, SLEDAI, although left among the final predictors in the model, was not significant. SLEDAIs in future visits were mainly predicted by Anti-ds-DNA antibody, 24-h urine protein and arthritis at the first visit.ConclusionSLE patients with younger age, history of previous LN or high baseline SLEDAI, may need closer monitoring and follow up.

OA29 Flares following COVID-19 vaccination in patients with idiopathic inflammatory myopathies: combined analysis from the COVID-19 Vaccination in Autoimmune Diseases (COVAD) studies

Abstract Background/Aims Flares following COVID-19 vaccination are an emerging concern among patients with rare rheumatic disease like idiopathic inflammatory myositis (IIMs), whereas data and understanding of this is rather limited. We aimed to study the prevalence, characteristics and determinants of IIM flares following COVID-19 vaccination. Methods CoVAD (COVID-19 Vaccination In Autoimmune Diseases) surveys are global patient self-reported e-surveys from 109 countries conducted in 2021 and 2022. Flares of IIM were defined by 4 definitions; a. patient self-reported, b. physician and immunosuppression (IS) denoted, c. sign directed (new erythematous rash, or worsening myositis or arthritis), d. MCID worsening of PROMISPF10a score between the patients who had taken both surveys. Descriptive statistics and multivariate regression were used to describe the predictors of flare. Cox-regression analysis was used to differentiate flares by IIM subtypes. Results Among the 1,278 IIM patients, aged 63 (50-71) years, 276 (21.5%) were dermatomyositis, 237 (18.5%) IBM, 899 (70.3%) were female and most were Caucasian (80.8%). Flares of IIM were seen in 123/1278 (9.6%), 163/1278 (12.7%), 112/1278 (8.7%), and 16/96 (19.6%) by definitions a-d respectively with median time to flare being 71.5 (10.7-235) days. Muscle weakness (69.1%), and fatigue (56.9%) were the most common symptoms of flare. The predictors of self-reported flare were: inactive/disease in remission prior to first dose of vaccine (OR = 4.3, 95%CI=2.4-7.6), and anxiety disorder (OR = 2.2, 95%CI=1.1-4.7). Rituximab use (OR = 0.3, 95%CI=0.1-0.7) and IBM (OR = 0.3, 95%CI=0.1-0.7) were protective. Physician defined flares were seen more often in females, mixed ethnicity, and those with asthma, ILD, and anxiety disorder (OR ranging 1.6-7.0, all p &amp;lt; 0.05). Notably, overlap myositis (OM) had higher HR for flare compared to polymyositis (HR = 2.3, 95%CI=1.2-4.4, p = 0.010). Conclusion Nearly one in ten individuals with IIM develop flares after vaccination, more so among women, those with overlap myositis, and inactive disease prior to vaccination. Formal definition of flares in IIM is needed. Disclosure L. Gupta: None. N. R: None. Z. Griger: None. V. Agarwal: None. P. Sen: None. M. Joshi: None. S. Saha: None. K. Jagtap: None. O. Distler: Honoraria; Abbvie, Acceleron, Alcimed, Amgen, AnaMar, Arxx, Baecon, Blade, Bayer, Boehringer Ingelheim, ChemomAb, Corbus, CSL Behring, Galapagos, Glenmark, GSK, Horizon (Curzion), Inventiva, iQvia, Kymera, Lupin, Medac, Medscape, Mitsubishi Tanabe, Novartis, Roche, Roivant, Sanofi, Serodapharm, Topadur and UCB. E. Nikiphorou: Honoraria; Celltrion, Pfizer, Sanofi, Gilead, Galapagos, AbbVie, and Lilly. Grants/research support; Pfizer and Lilly. A. Tan: Honoraria; Abbvie, Gilead, Janssen, Lilly, Novartis, Pfizer, and UCB. S. Shinjo: None. N. Ziade: Honoraria; Pfizer, Roche, Abbvie, Eli Lilly, NewBridge, Sanofi-Aventis, Boehringer Ingelheim, Janssen, and Pierre Fabre. M. Milchert: None. I. Parodis: Honoraria; Amgen, AstraZeneca, Aurinia Pharmaceuticals, Elli Lilly and Company, Gilead Sciences, GlaxoSmithKline, Janssen Pharmaceuticals, Novartis and F. Hoffmann-La Roche AG. M. Kuwana: None. A. Makol: None. J. Pauling: None. C. Wincup: None. J. Lilleker: Honoraria; Sanofi Genzyme, Roche, and Biogen. A. Nune: None. J. Day: Grants/research support; CSL Limited. H. Chinoy: Consultancies; Novartis, Eli Lilly, Orphazyme, Astra Zeneca. Honoraria; UCB, and Biogen. Grants/research support; Eli Lilly and UCB. V. Agarwal: None. R. Aggarwal: Consultancies; Bristol Myers-Squibb, Pfizer, Genentech, Octapharma, CSL Behring, Mallinckrodt, AstraZeneca, Corbus, Kezar, Abbvie, Janssen, Alexion, Argenx, Q32, EMD-Serono, Boehringer Ingelheim, and Roivant.

Identification of biomarkers that predict renal flare in childhood-onset lupus nephritis with mycophenolate acid.

Children-onset lupus nephritis (cLN) occurs>50% of patients with systemic lupus erythematosus. Mycophenolic acid (MPA) is the first-line agent for the induction and maintenance treatment of LN. This study was to explore the predictors of renal flare in cLN. Data from 90 patients were included in population pharmacokinetic (PK) models to predict MPA exposure. Cox regression models and restricted cubic spline were performed in 61 patients to identify the risk factors for renal flare, baseline clinical characteristics and MPA exposures as potential covariates. PK best fitted a two-compartment model of first-order absorption and linear elimination, with delayed absorption. Clearance increased with weight and immunoglobulin G (IgG), but decreased with albumin and serum creatinine. During follow-up of 1040 (658-1359) days, 18 patients experienced a renal flare, after a median time of 932.5 (663.5-1316) days. Each 1-mg·h/L increase of MPA-AUC was associated with a 6% decreased risk of an event (HR=0.94; 95% CI: 0.90-0.98), while IgG significantly increased this risk (HR=1.17; 95% CI: 1.08-1.26). ROC analysis showed that MPA-AUC0-12h<35mg·h/L and IgG>17.6g/L had a good prediction of renal flare. Of restricted cubic spline, the risk of renal flares decreased with higher MPA exposure but reached a plateau when AUC0-12h>55mg·h/L, while substantially increases when IgG is>18.2g/L. Monitoring MPA exposure together with IgG could be very useful during clinical practice to identify patients with a potential high risk of renal flare. This early risk assessment would allow for the treat-to-target and tailored medicine.

Flares in autoimmune rheumatic diseases in the post-COVID-19 vaccination period-a cross-sequential study based on COVAD surveys.

Flares of autoimmune rheumatic diseases (AIRDs) following COVID-19 vaccination are a particular concern in vaccine-hesitant individuals. Therefore, we investigated the incidence, predictors and patterns of flares following vaccination in individuals living with AIRDs, using global COVID-19 Vaccination in Autoimmune Diseases (COVAD) surveys. The COVAD surveys were used to extract data on flare demographics, comorbidities, COVID-19 history, and vaccination details for patients with AIRDs. Flares following vaccination were identified as patient-reported (a), increased immunosuppression (b), clinical exacerbations (c) and worsening of PROMIS scores (d). We studied flare characteristics and used regression models to differentiate flares among various AIRDs. Of 15 165 total responses, the incidence of flares in 3453 patients with AIRDs was 11.3%, 14.8%, 9.5% and 26.7% by definitions a-d, respectively. There was moderate agreement between patient-reported and immunosuppression-defined flares (K = 0.403, P = 0.022). Arthritis (61.6%) and fatigue (58.8%) were the most commonly reported symptoms. Self-reported flares were associated with higher comorbidities (P = 0.013), mental health disorders (MHDs) (P < 0.001) and autoimmune disease multimorbidity (AIDm) (P < 0.001).In regression analysis, the presence of AIDm [odds ratio (OR) = 1.4; 95% CI: 1.1, 1.7; P = 0.003), or a MHD (OR = 1.7; 95% CI: 1.1, 2.6; P = 0.007), or being a Moderna vaccine recipient (OR = 1.5; 95% CI: 1.09, 2.2; P = 0.014) were predictors of flares. Use of MMF (OR = 0.5; 95% CI: 0.3, 0.8; P = 0.009) and glucocorticoids (OR = 0.6; 95% CI: 0.5, 0.8; P = 0.003) were protective.A higher frequency of patients with AIRDs reported overall active disease post-vaccination compared with before vaccination (OR = 1.3; 95% CI: 1.1, 1.5; P < 0.001). Flares occur in nearly 1 in 10 individuals with AIRDs after COVID vaccination; people with comorbidities (especially AIDm), MHDs and those receiving the Moderna vaccine are particularly vulnerable. Future avenues include exploring flare profiles and optimizing vaccine strategies for this group.