In the framework of precision medicine, we investigate the similarity of diabetic kidney disease (DKD) patients through longitudinal data clusters. Starting with insights from category theory, we build patients’ clusters according to the shapes of their trajectories, adopting the Fréchet distance. We group patients according to their behavior of the estimated glomerular filtration rate (eGFR), obtaining informative mean curves. Behavior pattern recognition can shed light on individualized treatments.
Clustering longitudinal data with category theory for diabetic kidney disease
Veronica Distefano;
2021-01-01
Abstract
In the framework of precision medicine, we investigate the similarity of diabetic kidney disease (DKD) patients through longitudinal data clusters. Starting with insights from category theory, we build patients’ clusters according to the shapes of their trajectories, adopting the Fréchet distance. We group patients according to their behavior of the estimated glomerular filtration rate (eGFR), obtaining informative mean curves. Behavior pattern recognition can shed light on individualized treatments.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
