Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Network architecture for the two types of AE used in the analysis.

(a) Single hidden layer and (b) Two-hidden layers. In both cases, xi represent elements of the input as well as the output vector. zi represents elements of the learned lower dimensional representation. (a) Shallow autoencoder architecture and (b) Deeper autoencoder architecture.

More »

Fig 1 Expand

Fig 2.

Flow diagram of the MCA data analysis pipeline.

MCA on all features after numerical feature categorisation.

More »

Fig 2 Expand

Fig 3.

Flow diagram of the MCA/PCA data analysis pipeline.

MCA on categorical and PCA on numerical features.

More »

Fig 3 Expand

Fig 4.

Flow diagram of the MCA/PCA/PCA data analysis pipeline.

MCA on categorical and PCA on numerical features followed by PCA on resulting components of both methods.

More »

Fig 4 Expand

Fig 5.

Flow diagram of the AE data analysis pipeline.

Feature scaling followed by application multiple layer autoencoder neural network.

More »

Fig 5 Expand

Table 1.

Characteristics of the COPD cohort (overall, training and test sets) used for measuring patient similarity.

Mean value and standard deviation are presented for continuous feature.

More »

Table 1 Expand

Table 2.

Features ranked by degree of influence on the resulting similarity according to each pipeline.

Bolded entries indicate numerical features.

More »

Table 2 Expand

Table 3.

Clustering results comparison for COPD cohort—different k values presented above and below diagonal as indicated by backslash “\”.

The values of the diagonals represent averaged results obtained from 10% bootstrapped sampling and re-clustering.

More »

Table 3 Expand

Fig 6.

Patient similarity rankings as assigned by two clinician raters for each pipeline.

More »

Fig 6 Expand

Table 4.

Summary of evaluation results, including importance of features, cluster tendency and clinical expert evaluation for all four data processing pipelines.

More »

Table 4 Expand

Table 5.

Rater agreement metrics.

Raw (%) agreement and kappa coefficient calculated on the basis of 1–2 as well as binary (best/worst) rankings.

More »

Table 5 Expand