Multimodal brain age prediction using machine learning: combining structural MRI and 5-HT2AR PET-derived features
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
Multimodal brain age prediction using machine learning : combining structural MRI and 5-HT2AR PET-derived features. / Dörfel, Ruben P.; Arenas-Gomez, Joan M.; Svarer, Claus; Ganz, Melanie; Knudsen, Gitte M.; Svensson, Jonas E.; Plavén-Sigray, Pontus.
I: GeroScience, 2024.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Multimodal brain age prediction using machine learning
T2 - combining structural MRI and 5-HT2AR PET-derived features
AU - Dörfel, Ruben P.
AU - Arenas-Gomez, Joan M.
AU - Svarer, Claus
AU - Ganz, Melanie
AU - Knudsen, Gitte M.
AU - Svensson, Jonas E.
AU - Plavén-Sigray, Pontus
N1 - Publisher Copyright: © The Author(s) 2024.
PY - 2024
Y1 - 2024
N2 - To better assess the pathology of neurodegenerative disorders and the efficacy of neuroprotective interventions, it is necessary to develop biomarkers that can accurately capture age-related biological changes in the human brain. Brain serotonin 2A receptors (5-HT2AR) show a particularly profound age-related decline and are also reduced in neurodegenerative disorders, such as Alzheimer’s disease. This study investigates whether the decline in 5-HT2AR binding, measured in vivo using positron emission tomography (PET), can be used as a biomarker for brain aging. Specifically, we aim to (1) predict brain age using 5-HT2AR binding outcomes, (2) compare 5-HT2AR-based predictions of brain age to predictions based on gray matter (GM) volume, as determined with structural magnetic resonance imaging (MRI), and (3) investigate whether combining 5-HT2AR and GM volume data improves prediction. We used PET and MR images from 209 healthy individuals aged between 18 and 85 years (mean = 38, std = 18) and estimated 5-HT2AR binding and GM volume for 14 cortical and subcortical regions. Different machine learning algorithms were applied to predict chronological age based on 5-HT2AR binding, GM volume, and the combined measures. The mean absolute error (MAE) and a cross-validation approach were used for evaluation and model comparison. We find that both the cerebral 5-HT2AR binding (mean MAE = 6.63 years, std = 0.74 years) and GM volume (mean MAE = 6.95 years, std = 0.83 years) predict chronological age accurately. Combining the two measures improves the prediction further (mean MAE = 5.54 years, std = 0.68). In conclusion, 5-HT2AR binding measured using PET might be useful for improving the quantification of a biomarker for brain aging.
AB - To better assess the pathology of neurodegenerative disorders and the efficacy of neuroprotective interventions, it is necessary to develop biomarkers that can accurately capture age-related biological changes in the human brain. Brain serotonin 2A receptors (5-HT2AR) show a particularly profound age-related decline and are also reduced in neurodegenerative disorders, such as Alzheimer’s disease. This study investigates whether the decline in 5-HT2AR binding, measured in vivo using positron emission tomography (PET), can be used as a biomarker for brain aging. Specifically, we aim to (1) predict brain age using 5-HT2AR binding outcomes, (2) compare 5-HT2AR-based predictions of brain age to predictions based on gray matter (GM) volume, as determined with structural magnetic resonance imaging (MRI), and (3) investigate whether combining 5-HT2AR and GM volume data improves prediction. We used PET and MR images from 209 healthy individuals aged between 18 and 85 years (mean = 38, std = 18) and estimated 5-HT2AR binding and GM volume for 14 cortical and subcortical regions. Different machine learning algorithms were applied to predict chronological age based on 5-HT2AR binding, GM volume, and the combined measures. The mean absolute error (MAE) and a cross-validation approach were used for evaluation and model comparison. We find that both the cerebral 5-HT2AR binding (mean MAE = 6.63 years, std = 0.74 years) and GM volume (mean MAE = 6.95 years, std = 0.83 years) predict chronological age accurately. Combining the two measures improves the prediction further (mean MAE = 5.54 years, std = 0.68). In conclusion, 5-HT2AR binding measured using PET might be useful for improving the quantification of a biomarker for brain aging.
KW - 5HT2A receptor
KW - Brain age
KW - Machine learning
KW - Magnetic resonance imaging
KW - Multimodal imaging
KW - Positron emission tomography
UR - http://www.scopus.com/inward/record.url?scp=85191325194&partnerID=8YFLogxK
U2 - 10.1007/s11357-024-01148-6
DO - 10.1007/s11357-024-01148-6
M3 - Journal article
C2 - 38668887
AN - SCOPUS:85191325194
JO - GeroScience
JF - GeroScience
SN - 0161-9152
ER -
ID: 392213451