Table 1.
Demographics of ADNI and AIBL datasets.
TM: trajectory modeling cohort, TP: trajectory prediction cohort. R: replication cohort.
Fig 1.
Analysis workflow of the longitudinal framework.
The workflow comprises two tasks, 1) trajectory modeling (TM), and 2) trajectory prediction (TP). Data from 69 ADNI-1 MCI subjects with 9 visits within 6 years are used for TM task using hierarchical clustering. 1116 ADNI subjects pooled from ADNI1, ADNIGO, and ADNI2 cohorts are used towards TP task. Data (CA: clinical attributes, CT: cortical thickness) from baseline and a follow-up timepoint is used towards trajectory prediction. The trained models from k-fold cross validation of ADNI subjects are then tested on 117 AIBL subjects as part of the replication analysis.
Fig 2.
A) 69 MCI subjects (rows) with six years of clinical scores (columns) were used as input to hierarchical clustering. The color indicates the clinical score at a given timepoint. Euclidean distance between score vectors was used as a similarity metric between two subjects. Ward’s method was used as a linkage criterion. B) Clinical score distribution at each timepoint of different trajectories (stable vs. decliners) derived from hierarchical clustering. Mean scores at each timepoints are used to build a template for each trajectory class.
Table 2.
Cluster demographics of ADNI trajectory prediction (TP) cohort based on MMSE.
Table 3.
Cluster demographics of ADNI trajectory prediction (TP) cohort based on ADAS-13.
Table 4.
Trajectory membership comparison between MMSE and ADAS-13 scales.
Note that MMSE only has single decline trajectory.
Fig 3.
Longitudinal Siamese network (LSN) model.
LSN consists of three stages. The first stage is a Siamese artificial neural network with twin weight-sharing branches. Weight-sharing implies identical weight configuration at each layer across two branches. These branches process an MR input (2 x 78 CT values) from the same subject at two timepoints and produce a transformed output that is representative of change (atrophy) over time. This change pattern is referred as “distance embedding”. In the second stage, this embedding is modulated by the APOE4 status with a multiplicative operation. Lastly, in the third stage, the modulated distance embedding is concatenated with the two clinical scores and age, and used towards final trajectory prediction. The weights (model parameters) of all operations are learned jointly in a single unified model framework.
Table 5.
Longitudinal Siamese network (LSN) architecture.
Fig 4.
Potential clinical workflow for subject specific decision-making.
The goal of this flowchart is to identify subjects benefitting from MR and additional timepoint information. Qualitatively, baseline edge-cases (BE) group includes subjects with very high or very low cognitive performance at baseline. Follow-up edge-cases (FE) group includes subjects with non-extreme cognitive performance at baseline but substantial change in performance at follow-up. And cognitively consistent (CC) group includes subjects with non-extreme cognitive performance at baseline and marginal change in performance at follow-up. The table shows the threshold values used for MMSE and ADAS-13 scales and corresponding trajectory class distribution within each group.
Fig 5.
MMSE prediction AUC and accuracy performance for ADNI dataset.
Top panel: Area under the ROC curve (AUC), Bottom panel: Accuracy. Results are stratified by groups defined by the clinical workflow. Abbreviations are as follows. BL: baseline visit, CA: clinical attributes, CT: cortical thickness. BE: baseline edge-cases, FE: follow-up edge-cases, CC: cognitively consistent. The statistical comparison of LSN against other models was performed using Mann-Whitney-U test. Note that only BL+followup, CA+CT input is relevant for this comparison. For AUC comparison, LSN offered significantly better performance over all four models for ‘All’, ‘BE’, and ‘CC’ subsets. LSN also offered statistically significant results over RF and ANN models for ‘FE’ subset. For accuracy comparison, LSN offered significantly better performance over SVM, RF, and ANN models for ‘All’, ‘FE’, and ‘CC’ subsets. No statistically significant results were obtained for ‘BE’ subset.
Fig 6.
MMSE prediction ROC curves for ADNI dataset.
Receiver operating characteristic curves for CA+CT input. Results are stratified by groups defined by the clinical workflow. Abbreviations are as follows. BL: baseline visit, CA: clinical attributes, CT: cortical thickness. BE: baseline edge-cases, FE: follow-up edge-cases, CC: cognitively consistent.
Fig 7.
ADAS-13 prediction accuracy performance for ADNI dataset.
Results are stratified by groups defined by the clinical workflow. Abbreviations are as follows. BL: baseline visit, CA: clinical attributes, CT: cortical thickness. BE: baseline edge-cases, FE: follow-up edge-cases, CC: cognitively consistent. The statistical comparison of LSN against other models was performed using Mann-Whitney-U test. Note that only BL+followup, CA+CT input is relevant for this comparison. For accuracy comparison, LSN offered significantly better performance over LR, SVM, RF, and ANN models for ‘All’, ‘FE’, ‘BE’, and ‘CC’ subsets.
Fig 8.
MMSE prediction AUC and accuracy performance for AIBL replication cohort.
Top pane: Area under the ROC curve (AUC), Bottom pane: Accuracy. Abbreviations are as follows. BL: baseline visit, CA: clinical attributes, CT: cortical thickness.
Fig 9.
MMSE prediction ROC curves for AIBL replication cohort.
Receiver operating characteristic curves for CA+CT input. Abbreviations are as follows. BL: baseline visit, CA: clinical attributes, CT: cortical thickness.