Robust training of recurrent neural networks to handle missing data for disease progression modeling
Publikation: Konferencebidrag › Paper › Forskning
Standard
Robust training of recurrent neural networks to handle missing data for disease progression modeling. / Mehdipour Ghazi, Mostafa; Nielsen, Mads; Pai, Akshay Sadananda Uppinakudru; Cardoso, Manuel Jorge; Modat, Marc; Ourselin, Sebastien; Sørensen, Lauge.
2018. Paper præsenteret ved 1st Conference on Medical Imaging with Deep Learning (MIDL 2018), Amsterdam, Holland.Publikation: Konferencebidrag › Paper › Forskning
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - CONF
T1 - Robust training of recurrent neural networks to handle missing data for disease progression modeling
AU - Mehdipour Ghazi, Mostafa
AU - Nielsen, Mads
AU - Pai, Akshay Sadananda Uppinakudru
AU - Cardoso, Manuel Jorge
AU - Modat, Marc
AU - Ourselin, Sebastien
AU - Sørensen, Lauge
PY - 2018
Y1 - 2018
N2 - Disease progression modeling (DPM) using longitudinal data is a challenging task in machine learning for healthcare that can provide clinicians with better tools for diagnosis and monitoring of disease. Existing DPM algorithms neglect temporal dependencies among measurements and make parametric assumptions about biomarker trajectories. In addition, they do not model multiple biomarkers jointly and need to align subjects' trajectories. In this paper, recurrent neural networks (RNNs) are utilized to address these issues. However, in many cases, longitudinal cohorts contain incomplete data, which hinders the application of standard RNNs and requires a pre-processing step such as imputation of the missing values. We, therefore, propose a generalized training rule for the most widely used RNN architecture, long short-term memory (LSTM) networks, that can handle missing values in both target and predictor variables. This algorithm is applied for modeling the progression of Alzheimer's disease (AD) using magnetic resonance imaging (MRI) biomarkers. The results show that the proposed LSTM algorithm achieves a lower mean absolute error for prediction of measurements across all considered MRI biomarkers compared to using standard LSTM networks with data imputation or using a regression-based DPM method. Moreover, applying linear discriminant analysis to the biomarkers' values predicted by the proposed algorithm results in a larger area under the receiver operating characteristic curve (AUC) for clinical diagnosis of AD compared to the same alternatives, and the AUC is comparable to state-of-the-art AUC's from a recent cross-sectional medical image classification challenge. This paper shows that built-in handling of missing values in LSTM network training paves the way for application of RNNs in disease progression modeling.
AB - Disease progression modeling (DPM) using longitudinal data is a challenging task in machine learning for healthcare that can provide clinicians with better tools for diagnosis and monitoring of disease. Existing DPM algorithms neglect temporal dependencies among measurements and make parametric assumptions about biomarker trajectories. In addition, they do not model multiple biomarkers jointly and need to align subjects' trajectories. In this paper, recurrent neural networks (RNNs) are utilized to address these issues. However, in many cases, longitudinal cohorts contain incomplete data, which hinders the application of standard RNNs and requires a pre-processing step such as imputation of the missing values. We, therefore, propose a generalized training rule for the most widely used RNN architecture, long short-term memory (LSTM) networks, that can handle missing values in both target and predictor variables. This algorithm is applied for modeling the progression of Alzheimer's disease (AD) using magnetic resonance imaging (MRI) biomarkers. The results show that the proposed LSTM algorithm achieves a lower mean absolute error for prediction of measurements across all considered MRI biomarkers compared to using standard LSTM networks with data imputation or using a regression-based DPM method. Moreover, applying linear discriminant analysis to the biomarkers' values predicted by the proposed algorithm results in a larger area under the receiver operating characteristic curve (AUC) for clinical diagnosis of AD compared to the same alternatives, and the AUC is comparable to state-of-the-art AUC's from a recent cross-sectional medical image classification challenge. This paper shows that built-in handling of missing values in LSTM network training paves the way for application of RNNs in disease progression modeling.
M3 - Paper
T2 - 1st Conference on Medical Imaging with Deep Learning (MIDL 2018)
Y2 - 4 July 2018 through 6 July 2018
ER -
ID: 199022614