Predicting future clinical changes of MCI patients using longitudinal and multimodal biomarkers

Abstract

Accurate prediction of clinical changes of mild cognitive impairment (MCI) patients, including both qualitative change (i.e., conversion to Alzheimer's disease (AD)) and quantitative change (i.e., cognitive scores) at future time points, is important for early diagnosis of AD and for monitoring the disease progression. In this paper, we propose to predict future clinical changes of MCI patients by using both baseline and longitudinal multimodality data. To do this, we first develop a longitudinal feature selection method to jointly select brain regions across multiple time points for each modality. Specifically, for each time point, we train a sparse linear regression model by using the imaging data and the corresponding clinical scores, with an extra 'group regularization' to group the weights corresponding to the same brain region across multiple time points together and to allow for selection of brain regions based on the strength of multiple time points jointly. Then, to further reflect the longitudinal changes on the selected brain regions, we extract a set of longitudinal features from the original baseline and longitudinal data. Finally, we combine all features on the selected brain regions, from different modalities, for prediction by using our previously proposed multi-kernel SVM. We validate our method on 88 ADNI MCI subjects, with both MRI and FDG-PET data and the corresponding clinical scores (i.e., MMSE and ADAS-Cog) at 5 different time points. We first predict the clinical scores (MMSE and ADAS-Cog) at 24-month by using the multimodality data at previous time points, and then predict the conversion of MCI to AD by using the multimodality data at time points which are at least 6-month ahead of the conversion. The results on both sets of experiments show that our proposed method can achieve better performance in predicting future clinical changes of MCI patients than the conventional methods.

Figure 1. Flowchart of the proposed method.

Figure 2. Illustration on longitudinal feature selection.

Figure 3. Average longitudinal changes of clinical scores in MCI patients.

Figure 4. Scatter plots of the predicated MMSE scores vs. the actual scores by six different methods.

Figure 5. Scatter plots of the predicated ADAS-Cog scores vs. the actual scores by six different methods.

Figure 6. Regression performance with respect to the use of different number of longitudinal time points by three different methods.

Figure 7. Regression performance of the proposed method on two sub-groups of MCI patients, when using different number of longitudinal time points.

Figure 8. Prediction of conversion of MCI patients under different conversion times.

Figure 9. Classification performance comparison between single-modality vs. multimodality based methods.

Figure 10. Top 20% brain regions detected by the longitudinal feature selection method on MRI images.

Figure 11. Top 20% brain regions detected by the longitudinal feature selection method on PET images.