Prognostic models based on patient snapshots and time windows: predicting disease progression to assisted ventilation in Amyotrophic Lateral Sclerosis

© 2015 Elsevier Inc. All rights reserved.
Amyotrophic Lateral Sclerosis (ALS) is a devastating disease and the most common neurodegenerative disorder of young adults. ALS patients present a rapidly progressive motor weakness. This usually leads to death in a few years by respiratory failure. The correct prediction of respiratory insufficiency is thus key for patient management. In this context, we propose an innovative approach for prognostic prediction based on patient snapshots and time windows. We first cluster temporally-related tests to obtain snapshots of the patient's condition at a given time (patient snapshots). Then we use the snapshots to predict the probability of an ALS patient to require assisted ventilation after k days from the time of clinical evaluation (time window). This probability is based on the patient's current condition, evaluated using clinical features, including functional impairment assessments and a complete set of respiratory tests. The prognostic models include three temporal windows allowing to perform short, medium and long term prognosis regarding progression to assisted ventilation. Experimental results show an area under the receiver operating characteristics curve (AUC) in the test set of approximately 79% for time windows of 90, 180 and 365 days. Creating patient snapshots using hierarchical clustering with constraints outperforms the state of the art, and the proposed prognostic model becomes the first non population-based approach for prognostic prediction in ALS. The results are promising and should enhance the current clinical practice, largely supported by non-standardized tests and clinicians' experience.
This work was supported by national funds through Fundação para a Ciência e a Tecnologia (FCT), under projects UID/CEC/50021/2013, NEUROCLINOMICS: Understanding NEUROdegenerative diseases through CLINical and OMICS data integration (PTDC/EIA-EIA/111239/2009), and a doctoral grant SFRH/BD/82042/2011 to AVC.