A model of healthy aging based on smartphone interactions reveals advanced behavioral age in neurological disease

Enea Ceolini; Iris Brunner; Johanna Bunschoten; Marian H J M Majoie; Roland D Thijs; Arko Ghosh

doi:10.1016/j.isci.2022.104792

A model of healthy aging based on smartphone interactions reveals advanced behavioral age in neurological disease

Enea Ceolini, Iris Brunner, Johanna Bunschoten, Marian H J M Majoie, Roland D Thijs, Arko Ghosh^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

Smartphones offer unique opportunities to trace the convoluted behavioral patterns accompanying healthy aging. Here we captured smartphone touchscreen interactions from a healthy population (N = 684, ∼309 million interactions) spanning 16 to 86 years of age and trained a decision tree regression model to estimate chronological age based on the interactions. The interactions were clustered according to their next interval dynamics to quantify diverse smartphone behaviors. The regression model well-estimated the chronological age in health (mean absolute error = 6 years, R2 = 0.8). We next deployed this model on a population of stroke survivors (N = 41) to find larger prediction errors such that the estimated age was advanced by 6 years. A similar pattern was observed in people with epilepsy (N = 51), with prediction errors advanced by 10 years. The smartphone behavioral model trained in health can be used to study altered aging in neurological diseases.

Original language	English
Article number	104792
Number of pages	12
Journal	iScience
Volume	25
Issue number	8
DOIs	https://doi.org/10.1016/j.isci.2022.104792
Publication status	Published - 19 Aug 2022

Access to Document

10.1016/j.isci.2022.104792Licence: CC BY

Cite this

@article{4d4a49852a3247f1992c98f1674f219b,

title = "A model of healthy aging based on smartphone interactions reveals advanced behavioral age in neurological disease",

abstract = "Smartphones offer unique opportunities to trace the convoluted behavioral patterns accompanying healthy aging. Here we captured smartphone touchscreen interactions from a healthy population (N = 684, ∼309 million interactions) spanning 16 to 86 years of age and trained a decision tree regression model to estimate chronological age based on the interactions. The interactions were clustered according to their next interval dynamics to quantify diverse smartphone behaviors. The regression model well-estimated the chronological age in health (mean absolute error = 6 years, R2 = 0.8). We next deployed this model on a population of stroke survivors (N = 41) to find larger prediction errors such that the estimated age was advanced by 6 years. A similar pattern was observed in people with epilepsy (N = 51), with prediction errors advanced by 10 years. The smartphone behavioral model trained in health can be used to study altered aging in neurological diseases.",

author = "Enea Ceolini and Iris Brunner and Johanna Bunschoten and Majoie, {Marian H J M} and Thijs, {Roland D} and Arko Ghosh",

note = "{\textcopyright} 2022 The Author(s).",

year = "2022",

month = aug,

day = "19",

doi = "10.1016/j.isci.2022.104792",

language = "English",

volume = "25",

journal = "iScience",

issn = "2589-0042",

publisher = "Elsevier Inc.",

number = "8",

}

TY - JOUR

T1 - A model of healthy aging based on smartphone interactions reveals advanced behavioral age in neurological disease

AU - Ceolini, Enea

AU - Brunner, Iris

AU - Bunschoten, Johanna

AU - Majoie, Marian H J M

AU - Thijs, Roland D

AU - Ghosh, Arko

PY - 2022/8/19

Y1 - 2022/8/19

N2 - Smartphones offer unique opportunities to trace the convoluted behavioral patterns accompanying healthy aging. Here we captured smartphone touchscreen interactions from a healthy population (N = 684, ∼309 million interactions) spanning 16 to 86 years of age and trained a decision tree regression model to estimate chronological age based on the interactions. The interactions were clustered according to their next interval dynamics to quantify diverse smartphone behaviors. The regression model well-estimated the chronological age in health (mean absolute error = 6 years, R2 = 0.8). We next deployed this model on a population of stroke survivors (N = 41) to find larger prediction errors such that the estimated age was advanced by 6 years. A similar pattern was observed in people with epilepsy (N = 51), with prediction errors advanced by 10 years. The smartphone behavioral model trained in health can be used to study altered aging in neurological diseases.

AB - Smartphones offer unique opportunities to trace the convoluted behavioral patterns accompanying healthy aging. Here we captured smartphone touchscreen interactions from a healthy population (N = 684, ∼309 million interactions) spanning 16 to 86 years of age and trained a decision tree regression model to estimate chronological age based on the interactions. The interactions were clustered according to their next interval dynamics to quantify diverse smartphone behaviors. The regression model well-estimated the chronological age in health (mean absolute error = 6 years, R2 = 0.8). We next deployed this model on a population of stroke survivors (N = 41) to find larger prediction errors such that the estimated age was advanced by 6 years. A similar pattern was observed in people with epilepsy (N = 51), with prediction errors advanced by 10 years. The smartphone behavioral model trained in health can be used to study altered aging in neurological diseases.

U2 - 10.1016/j.isci.2022.104792

DO - 10.1016/j.isci.2022.104792

M3 - Article

C2 - 36039359

SN - 2589-0042

VL - 25

JO - iScience

JF - iScience

IS - 8

M1 - 104792

ER -