Abstract
Amyotrophic Lateral Sclerosis (ALS) is an inexorably progressive neurodegenerative condition with no effective disease modifying therapies. The development and validation of reliable prognostic models is a recognised research priority. We present a prognostic model for survival in ALS where result uncertainty is taken into account. Patient data were reduced and projected onto a 2D space using Uniform Manifold Approximation and Projection (UMAP), a novel non-linear dimension reduction technique. Information from 5,220 patients was included as development data originating from past clinical trials, and real-world population data as validation data. Predictors included age, gender, region of onset, symptom duration, weight at baseline, functional impairment, and estimated rate of functional loss. UMAP projection of patients shows an informative 2D data distribution. As limited data availability precluded complex model designs, the projection was divided into three zones with relevant survival rates. These rates were defined using confidence bounds: high, intermediate, and low 1-year survival rates at respectively 90% (pm 4%), 80% (pm 4%) and 58% (pm 4%). Predicted 1-year survival was estimated using zone membership. This approach requires a limited set of features, is easily updated, improves with additional patient data, and accounts for results uncertainty.
Highlights
Amyotrophic Lateral Sclerosis (ALS) is a relentlessly progressive neurodegenerative condition involving both upper and lower motor neurons, leading to progressive limb weakness and bulbar dysfunction
Our study demonstrated the utility of Uniform Manifold Approximation and Projection (UMAP) for survival analysis in ALS
We have successfully applied this non-linear dimension reduction method to ALS clinical trial data to predict overall survival, 1-year survival and 1-year functional loss
Summary
Amyotrophic Lateral Sclerosis (ALS) is a relentlessly progressive neurodegenerative condition involving both upper and lower motor neurons, leading to progressive limb weakness and bulbar dysfunction. The disease is characterised by considerable clinical h eterogeneity[2] and differences in progression r ate[3], with some patients surviving 10 years or more[4,5]. Disease heterogeneity is a recognised barrier to successful clinical trials in A LS6, and accurate prognosis prediction would improve patient stratification. Westeneng et al.[17] presented an externally validated Royston-Parmar regression prediction model of survival in a large European ALS population. A neighbourhood-based approach takes full advantage of patient similarity for prognosis modelling and can unravel relevant correlations between predictors and outcomes. The main objective of our study was to evaluate a UMAP based 1-year survival prediction model in ALS, designed using three clinical trial datasets, and validated by a Real-World (RW) dataset. Taking advantage of the UMAP projection, other prognosis outcomes and different time frames can be explored
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
