The Barcelona baseline risk score to predict long-term prognosis after a first demyelinating event: a prospective observational study

Abstract

Background: In multiple sclerosis (MS), predicting at symptom onset who will develop early and severe disability is an unmet need with significant therapeutic implications. Here we propose the Barcelona-Baseline Risk Score (BRS) model to predict long-term disease outcomes in a flexible and generalisable manner.

Methods: Using prospectively acquired data from the Barcelona first-attack cohort, we created the Barcelona-BRS model as a set of six Weibull survival models of time to an Expanded Disability Status Scale score of 3.0, built with flexible combinations of predictors, including sex, age at first attack, and number and topography of T2 lesions, among others, adaptable to data availability. Data-driven risk groups were identified and compared in terms of long-term clinical and MRI outcomes, including relapse-associated worsening (RAW), progression independent of relapse activity (PIRA), conversion to secondary progressive MS (SPMS), lesional and brain volumetric data, and patient-reported/administered clinical scores, through Kaplan-Meier and mixed-effects models. Finally, we externally validated our model in a completely unseen cohort.

Findings: We included 1074 patients (737 [69%] female, mean age: 31.7 years) with a first demyelinating attack. Over a median follow-up of 11.9 years, 375 (35%), 298 (28%), and 94 (8.8%) developed RAW, PIRA, and SPMS, respectively. Weibull models included age at first attack, number of brain T2 lesions, and disability at first visit as main predictors. Four data-driven groups of increasing risk of unfavourable outcomes were created: Light-Green-BRS (N = 258), Dark-Green-BRS (N = 319), Orange-BRS (N = 321), and Red-BRS (N = 176), which, over time, behaved significantly differently across disability, quality of life, and MRI measures, being the Red-BRS the group with worst outcomes (p < 0.01). The results in the external validation cohort (N = 139, 100 female [72%], 34 years) mirrored those of the original one.

Interpretation: The robustness, flexibility, and generalisability of the Barcelona-BRS model support its consideration as a ready-to-use tool for clinical practice.

Funding: None.

Keywords: Disease progression; MRI; Multiple sclerosis; Predictive model; Progression independent of relapse activity; Relapse-associated worsening.

Fig. 1

Study design. Schematic view of the path to creating the Barcelona-BRS umbrella model and obtaining the derived Barcelona-BRS risk groups. Abbreviations: BRS: baseline risk score; CELs: Contrast-enhancing lesions; EDSS: Expanded Disability Status Scale; IT: Infratentorial lesions; MRI: Magnetic Resonance Imaging; OBs: oligoclonal bands; SC: spinal cord.

Fig. 2

A. Patient Flowchart. Out of a total of 1561 patients with a first demyelinating attack seen at Cemcat, 1074 finally met our inclusion criteria. Abbreviations: IQR: interquartile range. B. This panel shows the most informative times (in years) to EDSS 3.0, which correspond to the median times (across bootstrap samples) of the most informative model for each patient (A). Fig. 3A also shows the data-driven thresholds to create risk groups, thanks to 2000 survival trees. As explained in the results section, we found three data-driven groups: Red BRS (estimated median time to EDSS 3.0 below or equal to 3.49 years, N = 176 [16.4%]), Orange BRS (estimated median time above 3.49 and below or equal 4.23 years, N = 321 [29.9%]), and green-BRS (median time above 4.23 years, N = 577 [53.7%]). C. Weibull model of time to EDSS 3.0 for the four Barcelona-BRS groups. D. Estimated EDSS trajectories over time for the four Barcelona-BRS risk groups. For visualisation purposes, this figure shows the trajectories using mixed splines models. However, regression estimates of the slopes over time have been obtained through linear mixed-effects models (see Supplementary Table S3). E. Estimated trajectories of cumulative number of new T2 lesions over time for each one of the four Barcelona-BRS risk groups from the first demyelinating attack (time = 0 years). As can be observed, and as also shown in Fig. 4 (heatmap for different outcomes), the light green-BRS group behaved very differently from the other three, and especially from the Orange BRS and Red BRS groups, which behaved almost identically. The regression estimates of the slopes over time have been obtained through linear mixed-effects models (see Supplementary Table S4). Abbreviations: BRS: baseline risk score; EDSS: Expanded Disability Status Scale.

Fig. 3

Heatmaps of binary disease outcomes. This figure shows the estimated probabilities of reaching each one of the clinical outcomes based on the Kaplan Meier models, for each one of the Barcelona-BRS risk groups. A. Whole cohort; B. Patients with early DMT exposure (within 12 months of CIS); C. Patients with late DMT exposure (after 3 years of CIS). Abbreviations: BRS: baseline risk score; CIS: clinically isolated syndrome; CSDW: confirmed and sustained disability worsening; DMT: disease-modifying treatment; EDSS: Expanded Disability Status Scale; PIRA: progression independent of relapse activity; RAW: relapse-associated worsening; SPMS: secondary progressive multiple sclerosis.

Fig. 4

Light green BRS group is used as reference. Please note the x-axis is displayed in logarithmic scale, for visualisation purposes. Also, the 95% CI have been truncated at 100 to avoid excessively large figure subpanels. Details on HR (95% CI) are shown in Supplementary Table S6. Abbreviations: BRS: Baseline Risk Score; CSDW: Confirmed and sustained disability worsening; EDSS: Expanded Disability Status Scale; PIRA: progression independent of relapse activity; RAW: relapse-associated worsening; SPMS: secondary progressive multiple sclerosis.