Details

Autor(en) / Beteiligte

• Sevilla-Salcedo, Carlos
• Imani, Vandad
• M． Olmos, Pablo
• Gómez-Verdejo, Vanessa
• Tohka, Jussi

Titel

Multi-task longitudinal forecasting with missing values on Alzheimer’s disease

Ist Teil von

• Computer methods and programs in biomedicine, 2022-11, Vol.226, p.107056-107056, Article 107056

Ort / Verlag

Elsevier B.V

Erscheinungsjahr

2022

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• •Novel Bayesian variational inference framework for multisource longitudinal data with multitask classification/regression in dementia.•Semi-supervised formulation to handle high number of missing values and exploit temporal data structure.•Latent representations to combine time-stamps and obtain interpretable results.•Performance improvement over baselines in the simultaneous prediction of diagnosis, ventricle volume and ADAS13 score. [Display omitted] Background and Objective:Machine learning techniques typically used in dementia assessment are not able to learn multiple tasks jointly and deal with time-dependent heterogeneous data containing missing values. In this paper, we reformulate SSHIBA, a recently introduced Bayesian multi-view latent variable model, for jointly learning diagnosis, ventricle volume, and ADAS score in dementia on longitudinal data with missing values. Methods:We propose a novel Bayesian Variational inference framework capable of simultaneously imputing missing values and combining information from several views. This way, we can combine different data views from different time-points in a common latent space and learn the relationships between each time-point, using the semi-supervised formulation to fully exploit the temporal structure of the data and handle missing values. In turn, the model can combine all the available information to simultaneously model and predict multiple output variables. Results:We applied the proposed model to jointly predict diagnosis, ventricle volume, and ADAS score in dementia. The comparison of imputation strategies demonstrated the superior performance of the semi-supervised formulation of the model, improving the best baseline methods. Moreover, the performance in simultaneous prediction of diagnosis, ventricle volume, and ADAS score led to an improved prediction performance over the best baseline method. Conclusions:The results demonstrate that the proposed SSHIBA framework can learn an excellent imputation of the missing values and outperforming the baselines while simultaneously predicting three different tasks.