A divisive hierarchical clustering methodology for enhancing the ensemble prediction power in large scale population studies: the ATHLOS project

Petros Barmpas*, Sotiris Tasoulis, Aristidis G. Vrahatis, Spiros V. Georgakopoulos, Panagiotis Anagnostou, Matthew Prina, José Luis Ayuso-Mateos, Jerome Bickenbach, Ivet Bayes, Martin Bobak, Francisco Félix Caballero, Somnath Chatterji, Laia Egea-Cortés, Esther García-Esquinas, Matilde Leonardi, Seppo Koskinen, Ilona Koupil, Andrzej Paja̧k, Martin Prince, Warren SandersonSergei Scherbov, Abdonas Tamosiunas, Aleksander Galas, Josep Maria Haro, Albert Sanchez-Niubo, Vassilis P. Plagianakos, Demosthenes Panagiotakos

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

5 Citations (Scopus)

Abstract

The ATHLOS cohort is composed of several harmonized datasets of international groups related to health and aging. As a result, the Healthy Aging index has been constructed based on a selection of variables from 16 individual studies. In this paper, we consider additional variables found in ATHLOS and investigate their utilization for predicting the Healthy Aging index. For this purpose, motivated by the volume and diversity of the dataset, we focus our attention upon data clustering, where unsupervised learning is utilized to enhance prediction power. Thus we show the predictive utility of exploiting hidden data structures. In addition, we demonstrate that imposed computation bottlenecks can be surpassed when using appropriate hierarchical clustering, within a clustering for ensemble classification scheme, while retaining prediction benefits. We propose a complete methodology that is evaluated against baseline methods and the original concept. The results are very encouraging suggesting further developments in this direction along with applications in tasks with similar characteristics. A straightforward open source implementation for the R project is also provided (https://github.com/Petros-Barmpas/HCEP).

Original languageEnglish
Article number6
JournalHealth Information Science and Systems
Volume10
Issue number1
DOIs
Publication statusPublished - 18 Apr 2022

Keywords

  • ATHLOS cohort
  • Clustering
  • Ensemble methods
  • Prediction enhancement

Fingerprint

Dive into the research topics of 'A divisive hierarchical clustering methodology for enhancing the ensemble prediction power in large scale population studies: the ATHLOS project'. Together they form a unique fingerprint.

Cite this