Westeneng HJ, Debray TPA, Visser AE, van Eijk RPA, Rooney JPK, Calvo A, Martin S, McDermott CJ, Thompson AG, Pinto S, Kobeleva X, Rosenbohm A, Stubendorff B, Sommer H, Middelkoop BM, Dekker AM, van Vugt JJFA, van Rheenen W, Vajda A, Heverin M, Kazoka M, Hollinger H, Gromicho M, Körner S, Ringer TM, Rödiger A, Gunkel A, Shaw CE, Bredenoord AL, van Es MA, Corcia P, Couratier P, Weber M, Grosskreutz J, Ludolph AC, Petri S, de Carvalho M, Van Damme P, Talbot K, Turner MR, Shaw PJ, Al-Chalabi A, Chiò A, Hardiman O, Moons KGM, Veldink JH, van den Berg LH
BACKGROUND: Amyotrophic lateral sclerosis (ALS) is a relentlessly progressive, fatal motor neuron disease with a variable natural history. There are no accurate models that predict the disease course and outcomes, which complicates risk assessment and counselling for individual patients, stratification of patients for trials, and timing of interventions. We therefore aimed to develop and validate a model for predicting a composite survival endpoint for individual patients with ALS.
METHODS: We obtained data for patients from 14 specialised ALS centres (each one designated as a cohort) in Belgium, France, the Netherlands, Germany, Ireland, Italy, Portugal, Switzerland, and the UK. All patients were diagnosed in the centres after excluding other diagnoses and classified according to revised El Escorial criteria. We assessed 16 patient characteristics as potential predictors of a composite survival outcome (time between onset of symptoms and non-invasive ventilation for more than 23 h per day, tracheostomy, or death) and applied backward elimination with bootstrapping in the largest population-based dataset for predictor selection. Data were gathered on the day of diagnosis or as soon as possible thereafter. Predictors that were selected in more than 70% of the bootstrap resamples were used to develop a multivariable Royston-Parmar model for predicting the composite survival outcome in individual patients. We assessed the generalisability of the model by estimating heterogeneity of predictive accuracy across external populations (ie, populations not used to develop the model) using internal-external cross-validation, and quantified the discrimination using the concordance (c) statistic (area under the receiver operator characteristic curve) and calibration using a calibration slope.
FINDINGS: Data were collected between Jan 1, 1992, and Sept 22, 2016 (the largest data-set included data from 1936 patients). The median follow-up time was 97.5 months (IQR 52.9-168.5). Eight candidate predictors entered the prediction model: bulbar versus non-bulbar onset (univariable hazard ratio [HR] 1.71, 95% CI 1.63-1.79), age at onset (1.03, 1.03 - 1.03), definite versus probable or possible ALS (1.47, 1.39-1.55), diagnostic delay (0.52, 0.51-0.53), forced vital capacity (HR 0.99, 0.99-0.99), progression rate (6.33, 5.92-6.76), frontotemporal dementia (1.34, 1.20-1.50), and presence of a C9orf72 repeat expansion (1.45, 1.31-1.61), all p<0.0001. The c statistic for external predictive accuracy of the model was 0.78 (95% CI 0.77-0.80; 95% prediction interval [PI] 0.74-0.82) and the calibration slope was 1.01 (95% CI 0.95-1.07; 95% PI 0.83-1.18). The model was used to define five groups with distinct median predicted (SE) and observed (SE) times in months from symptom onset to the composite survival outcome: very short 17.7 (0.20), 16.5 (0.23); short 25.3 (0.06), 25.2 (0.35); intermediate 32.2 (0.09), 32.8 (0.46); long 43.7 (0.21), 44.6 (0.74); and very long 91.0 (1.84), 85.6 (1.96).
INTERPRETATION: We have developed an externally validated model to predict survival without tracheostomy and non-invasive ventilation for more than 23 h per day in European patients with ALS. This model could be applied to individualised patient management, counselling, and future trial design, but to maximise the benefit and prevent harm it is intended to be used by medical doctors only.