Constructed Temporal Features for Longitudinal Classification of Human Ageing Data

Ribeiro, Caio; Freitas, Alex A.

doi:10.1109/ichi52183.2021.00027

Cited by 2 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several possible approaches for considering temporal patterns in supervised machine learning problems [Ribeiro et al, 2017], such as creating temporal features in a preprocessing step [Ribeiro and Freitas, 2021a], Structural Pattern Detection [Morid et al, 2020], Recurrent Neural Networks (often Long-Short Term Memory) [Aghili et al, 2018], and Deep Learning [Luo et al, 2020]. In this section we focus on decision tree-based classifiers, which are popular in biomedical applications and are the focus of our proposed algorithm adaptation for longitudinal classification.…”

Section: Related Workmentioning

confidence: 99%

A lexicographic optimisation approach to promote more recent features on longitudinal decision-tree-based classifiers: Applications to the English Longitudinal Study of Ageing

Ribeiro

Freitas

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Supervised machine learning algorithms rarely cope directly with the temporal information inherent to longitudinal datasets, which have multiple measurements of the same feature across several time points and are often generated by large health studies. In this paper we report on experiments which adapt the feature-selection function of decision tree-based classifiers to consider the temporal information in longitudinal datasets, using a lexicographic optimisation approach. This approach gives higher priority to the usual objective of maximising the information gain ratio, and it favours the selection of features more recently measured as a lower priority objective. Hence, when selecting between features with equivalent information gain ratio, priority is given to more recent measurements of biomedical features in our datasets. We performed experiments with 20 longitudinal datasets created from a human ageing study, and concluded from our results that this lexicographic optimisation approach is worthwhile and computationally inexpensive. In addition to a slight improve in predictive accuracy, the changed feature-selection function promotes models based on information that is more directly related to the subject's current biomedical situation and, thus, more actionable.

show abstract

Section: Related Workmentioning

confidence: 99%

A lexicographic optimisation approach to promote more recent features on longitudinal decision-tree-based classifiers: Applications to the English Longitudinal Study of Ageing

Ribeiro

Freitas

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

A lexicographic optimisation approach to promote more recent features on longitudinal decision-tree-based classifiers: applications to the English Longitudinal Study of Ageing

Ribeiro,

Freitas

2024

Artif Intell Rev

View full text Add to dashboard Cite

Supervised machine learning algorithms rarely cope directly with the temporal information inherent to longitudinal datasets, which have multiple measurements of the same feature across several time points and are often generated by large health studies. In this paper we report on experiments which adapt the feature-selection function of decision tree-based classifiers to consider the temporal information in longitudinal datasets, using a lexicographic optimisation approach. This approach gives higher priority to the usual objective of maximising the information gain ratio, and it favours the selection of features more recently measured as a lower priority objective. Hence, when selecting between features with equivalent information gain ratio, priority is given to more recent measurements of biomedical features in our datasets. To evaluate the proposed approach, we performed experiments with 20 longitudinal datasets created from a human ageing study. The results of these experiments show that, in addition to an improvement in predictive accuracy for random forests, the changed feature-selection function promotes models based on more recent information that is more directly related to the subject’s current biomedical situation and, thus, intuitively more interpretable and actionable.

show abstract

Constructed Temporal Features for Longitudinal Classification of Human Ageing Data

Abstract: The version in the Kent Academic Repository may differ from the final published version. Users are advised to check http://kar.kent.ac.uk for the status of the paper. Users should always cite the published version of record.

Cited by 2 publications

References 15 publications

A lexicographic optimisation approach to promote more recent features on longitudinal decision-tree-based classifiers: Applications to the English Longitudinal Study of Ageing

A lexicographic optimisation approach to promote more recent features on longitudinal decision-tree-based classifiers: Applications to the English Longitudinal Study of Ageing

A lexicographic optimisation approach to promote more recent features on longitudinal decision-tree-based classifiers: applications to the English Longitudinal Study of Ageing

Contact Info

Product

Resources

About