EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable machine learning framework to predict personalized physiological aging

David Bernard, Emmanuel Doumard, Isabelle Ader, Philippe Kemoun, Jean-Christophe Pagès, Anne Galinier, Sylvain Cussat-Blanc, Felix Furger, Luigi Ferrucci iD, Julien Aligon, Cyrille Delpierre, Luc Pénicaud und 2 weitere

Aging Cell · 2023-08 · 22 (8)

DOI: 10.1111/acel.13872 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Aging Cell, online erschienen am 10.06.2023. Verfasst von David Bernard und 13 weiteren Autor:innen. Beteiligte Einrichtung: RESTORE Research Center, Université de Toulouse, INSERM 1301, CNRS 5070, EFS, ENVT, France. Hauptthemen laut MEDLINE: Algorithms, Health Status. Die Arbeit wurde bisher 109-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agence Nationale de la Recherche, Inserm transfert, European Regional Development Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Attaining personalized healthy aging requires accurate monitoring of physiological changes and identifying subclinical markers that predict accelerated or delayed aging. Classic biostatistical methods most rely on supervised variables to estimate physiological aging and do not capture the full complexity of inter‐parameter interactions. Machine learning (ML) is promising, but its black box nature eludes direct understanding, substantially limiting physician confidence and clinical usage. Using a broad population dataset from the National Health and Nutrition Examination Survey (NHANES) study including routine biological variables and after selection of XGBoost as the most appropriate algorithm, we created an innovative explainable ML framework to determine a Personalized physiological age (PPA). PPA predicted both chronic disease and mortality independently of chronological age. Twenty‐six variables were sufficient to predict PPA. Using SHapley Additive exPlanations (SHAP), we implemented a precise quantitative associated metric for each variable explaining physiological (i.e., accelerated or delayed) deviations from age‐specific normative data. Among the variables, glycated hemoglobin (HbA1c) displays a major relative weight in the estimation of PPA. Finally, clustering profiles of identical contextualized explanations reveal different aging trajectories opening opportunities to specific clinical follow‐up. These data show that PPA is a robust, quantitative and explainable ML‐based metric that monitors personalized health status. Our approach also provides a complete framework applicable to different datasets or variables, allowing precision physiological age estimation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsHealth StatusNutrition SurveysMachine Learning

Stichwörter der Autor:innen

ExplainabilityRejuvenative therapyartificial intelligencebiological agehealthy agingmachine learningpersonalized medicinephysiological age

Autor:innen und Institutionen

  • RESTORE Research Center, Université de Toulouse, INSERM 1301, CNRS 5070, EFS, ENVT, France.
  • Université Toulouse 1 - Capitole, Institute of Research in Informatics (IRIT) of Toulouse, CNRS, Toulouse, France.
  • Oral Medicine Department and Hospital of Toulouse, Toulouse Institute of Oral Medicine and Science, CHU de Toulouse, Toulouse, France.
  • UFR Santé, Département Médecine, Institut Fédératif de Biologie, CHU de Toulouse, Toulouse, France.
  • Artificial and Natural Intelligence Toulouse Institute ANITI, Toulouse, France.
  • Biomedical Research Centre, National Institute on Aging, NIH, Baltimore, Maryland, USA.

ORCID-Profile: Luigi Ferrucci, Paul Monsarrat

Förderung

  • Agence Nationale de la Recherche
  • Inserm transfert
  • European Regional Development Fund

Zitieren

APA

Bernard, D., Doumard, E., Ader, I., Kemoun, P., Pagès, J. C., Galinier, A., Cussat-Blanc, S., Furger, F., Ferrucci, L., Aligon, J., Delpierre, C., Pénicaud, L., Monsarrat, P., & Casteilla, L. (2023). Explainable machine learning framework to predict personalized physiological aging. Aging Cell, 22(8). https://doi.org/10.1111/acel.13872

Vancouver

Bernard D, Doumard E, Ader I, Kemoun P, Pagès JC, Galinier A, et al. Explainable machine learning framework to predict personalized physiological aging. Aging Cell. 2023;22(8). doi:10.1111/acel.13872

BibTeX
@article{Bernard2023,
  author = {Bernard, David and Doumard, Emmanuel and Ader, Isabelle and Kemoun, Philippe and Pagès, Jean-Christophe and Galinier, Anne and Cussat-Blanc, Sylvain and Furger, Felix and Ferrucci, Luigi and Aligon, Julien and Delpierre, Cyrille and Pénicaud, Luc and Monsarrat, Paul and Casteilla, Louis},
  title = {Explainable machine learning framework to predict personalized physiological aging},
  journal = {Aging Cell},
  year = {2023},
  volume = {22},
  number = {8},
  doi = {10.1111/acel.13872}
}
Kostenlos starten →