.2023 Feb;45(1):491-505.

doi: 10.1007/s11357-022-00657-6. Epub 2022 Sep 15.

Bioenergetic and vascular predictors of potential super-ager and cognitive decline trajectories-a UK Biobank Random Forest classification study

Parvin Mohammadiarvejeh^#¹, Brandon S Klinedinst^#², Qian Wang³, Tianqi Li⁴, Brittany Larsen⁵, Amy Pollpeter⁶, Shannin N Moody⁷, Sara A Willette⁸, Jon P Mochel⁹, Karin Allenspach¹⁰, Guiping Hu¹, Auriel A Willette^{11 12 13 14 15}

Affiliations

¹ Department of Industrial and Manufacturing Systems Engineering, Iowa State University, Ames, IA, USA.
² Department of Medicine, University of Washington, Seattle, WA, USA.
³ Department of Food Science and Human Nutrition, Iowa State University, 1109 HSNB, 2302 Osborn Drive, Ames, IA, 50011-1078, USA.
⁴ Genetics and Genomics Graduate Program, Iowa State University, Ames, IA, USA.
⁵ Neuroscience Graduate Program, Iowa State University, Ames, IA, USA.
⁶ Bioinformatics and Computational Biology Graduate Program, Iowa State University, Ames, IA, USA.
⁷ Department of Human Development and Family Studies, Iowa State University, Ames, IA, USA.
⁸ IAC Tracker Inc, Ames, IA, USA.
⁹ Department of Biomedical Sciences, Iowa State University, Ames, IA, USA.
¹⁰ Department of Veterinary Clinical Sciences, Iowa State University, Ames, IA, USA.
¹¹ Department of Food Science and Human Nutrition, Iowa State University, 1109 HSNB, 2302 Osborn Drive, Ames, IA, 50011-1078, USA. awillett@iastate.edu.
¹² Genetics and Genomics Graduate Program, Iowa State University, Ames, IA, USA. awillett@iastate.edu.
¹³ Bioinformatics and Computational Biology Graduate Program, Iowa State University, Ames, IA, USA. awillett@iastate.edu.
¹⁴ IAC Tracker Inc, Ames, IA, USA. awillett@iastate.edu.
¹⁵ Department of Neurology, University of Iowa, Iowa City, IA, USA. awillett@iastate.edu.

^# Contributed equally.

PMID:36104610
PMCID: PMC9886787
DOI: 10.1007/s11357-022-00657-6

Bioenergetic and vascular predictors of potential super-ager and cognitive decline trajectories-a UK Biobank Random Forest classification study

Parvin Mohammadiarvejeh et al. Geroscience.2023 Feb.

.2023 Feb;45(1):491-505.

doi: 10.1007/s11357-022-00657-6. Epub 2022 Sep 15.

Authors

Affiliations

¹ Department of Industrial and Manufacturing Systems Engineering, Iowa State University, Ames, IA, USA.
² Department of Medicine, University of Washington, Seattle, WA, USA.
³ Department of Food Science and Human Nutrition, Iowa State University, 1109 HSNB, 2302 Osborn Drive, Ames, IA, 50011-1078, USA.
⁴ Genetics and Genomics Graduate Program, Iowa State University, Ames, IA, USA.
⁵ Neuroscience Graduate Program, Iowa State University, Ames, IA, USA.
⁶ Bioinformatics and Computational Biology Graduate Program, Iowa State University, Ames, IA, USA.
⁷ Department of Human Development and Family Studies, Iowa State University, Ames, IA, USA.
⁸ IAC Tracker Inc, Ames, IA, USA.
⁹ Department of Biomedical Sciences, Iowa State University, Ames, IA, USA.
¹⁰ Department of Veterinary Clinical Sciences, Iowa State University, Ames, IA, USA.
¹¹ Department of Food Science and Human Nutrition, Iowa State University, 1109 HSNB, 2302 Osborn Drive, Ames, IA, 50011-1078, USA. awillett@iastate.edu.
¹² Genetics and Genomics Graduate Program, Iowa State University, Ames, IA, USA. awillett@iastate.edu.
¹³ Bioinformatics and Computational Biology Graduate Program, Iowa State University, Ames, IA, USA. awillett@iastate.edu.
¹⁴ IAC Tracker Inc, Ames, IA, USA. awillett@iastate.edu.
¹⁵ Department of Neurology, University of Iowa, Iowa City, IA, USA. awillett@iastate.edu.

^# Contributed equally.

PMID:36104610
PMCID: PMC9886787
DOI: 10.1007/s11357-022-00657-6

Abstract

Aging has often been characterized by progressive cognitive decline in memory and especially executive function. Yet some adults, aged 80 years or older, are "super-agers" that exhibit cognitive performance like younger adults. It is unknown if there are adults in mid-life with similar superior cognitive performance ("positive-aging") versus cognitive decline over time and if there are blood biomarkers that can distinguish between these groups. Among 1303 participants in UK Biobank, latent growth curve models classified participants into different cognitive groups based on longitudinal fluid intelligence (FI) scores over 7-9 years. Random Forest (RF) classification was then used to predict cognitive trajectory types using longitudinal predictors including demographic, vascular, bioenergetic, and immune factors. Feature ranking importance and performance metrics of the model were reported. Despite model complexity, we achieved a precision of 77% when determining who would be in the "positive-aging" group (n = 563) vs. cognitive decline group (n = 380). Among the top fifteen features, an equal number were related to either vascular health or cellular bioenergetics but not demographics like age, sex, or socioeconomic status. Sensitivity analyses showed worse model results when combining a cognitive maintainer group (n = 360) with the positive-aging or cognitive decline group. Our results suggest that optimal cognitive aging may not be related to age per se but biological factors that may be amenable to lifestyle or pharmacological changes.

Keywords: Bioenergetics; Biomarkers; Cognitive decline; Metabolism; Super-agers; Vascular.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

**Fig. 1**
The relative feature score of the top fifteen features in the Random Forest model. Colors represent different feature classes (i.e., “factor type”). For a given feature, the “I” and “II” symbols represent variables collected either at baseline or on a subsequent visit respectively. No features were multicollinear (e.g., r > 0.80)

**Fig. 2**
These partial dependence plots illustrate changes in the relationship between a given vascular feature and the probability of being either in the cognitive decline group (0–0.49) or positive-aging group (0.50–1.00). The purple dotted line signifies the 0.50 threshold distinguishing between the cognitive decline and positive-aging groups

**Fig. 3**
These partial dependence plots illustrate changes in the relationship between a given bioenergetics feature and the probability of being either in the cognitive decline group (0–0.49) or positive-aging group (0.50–1.00). The purple dotted line signifies the 0.50 threshold distinguishing between the cognitive decline and positive-aging groups

**Fig. 4**
These partial dependence plots illustrate changes in the relationship between the neutrophil II feature and the probability of being either in the cognitive decline group (0–0.49) or positive-aging group (0.50–1.00). The purple dotted line signifies the 0.50 threshold distinguishing between participants in the cognitive decline and positive-aging groups

**Fig. 5**
Distributions for the top fifteen features to use in the final Random Forest model, to predict positive-aging versus cognitive-decline groups. Features are aggregated by each feature class (i.e., “factor type”) for ease of interpretation of common features

**Fig. 6**
Receiver operation characteristic (ROC) curve showing the final model fit of 42 features for distinguishing between positive-ager and cognitive decliner groups. The diagonal line represents “at-chance” prediction. The “true positive rate” and “false positive rate” correspond to sensitivity and 1-specificity. AUC, area under the curve

See this image and copyright information in PMC

References

1. Dempster FN. The rise and fall of the inhibitory mechanism: Toward a unified theory of cognitive development and aging. Dev Rev. 1992;1;12(1):45–75. 10.1016/0273-2297(92)90003-K.
1. Parkin AJ, Walter BM. Recollective experience, normal aging, and frontal dysfunction. Psychol Aging. 1992;7(2):290. 10.1037/0882-7974.7.2.290. - PubMed
1. Salthouse TA. When does age-related cognitive decline begin? Neurobiol Aging. 2009;30(4):507–514. doi: 10.1016/j.neurobiolaging.2008.09.023. - DOI - PMC - PubMed
1. Singh-Manoux A, Kivimaki M, Glymour MM, Elbaz A, Berr C, Ebmeier KP, Ferrie JE, Dugravot A. Timing of onset of cognitive decline: results from Whitehall II prospective cohort study. BMJ. 2012;344. 10.1136/bmj.d7622. - PMC - PubMed
1. Jensen, Arthur R. Abilities: their structure, growth, and action. Am J Psychol. 1974;290–6. 10.2307/1422024.

Publication types

Actions
Actions

MeSH terms

Actions
Actions
Actions
Actions
Actions
Actions

Grants and funding

LinkOut - more resources

Full Text Sources
Other Literature Sources
- The Lens - Patent Citations Database

Movatterモバイル変換

Account

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

Full text links

Actions

Bioenergetic and vascular predictors of potential super-ager and cognitive decline trajectories-a UK Biobank Random Forest classification study

Affiliations

Bioenergetic and vascular predictors of potential super-ager and cognitive decline trajectories-a UK Biobank Random Forest classification study

Authors

Affiliations

Abstract

Conflict of interest statement

Figures

References

Publication types

MeSH terms

Grants and funding

LinkOut - more resources

Full Text Sources

Other Literature Sources