Free-living wrist and hip accelerometry forecast cognitive decline among older adults without dementia over 1- or 5-years in two distinct observational cohorts

Abstract

The prevalence of major neurocognitive disorders is expected to rise over the next 3 decades as the number of adults ≥65 years old increases. Noninvasive screening capable of flagging individuals most at risk of subsequent cognitive decline could trigger closer monitoring and preventive strategies. In this study, we used free-living accelerometry data to forecast cognitive decline within 1- or 5-years in older adults without dementia using two cohorts. The first cohort, recruited in the south side of Chicago, wore hip accelerometers for 7 continuous days. The second cohort, nationally recruited, wore wrist accelerometers continuously for 72 h. Separate classifier models forecasted 1-year cognitive decline with over 85% accuracy using hip data and forecasted 5-year cognitive decline with nearly 70% accuracy using wrist data, significant improvements compared to demographics and comorbidities alone. The proposed models are readily translatable to clinical practices serving ageing populations.

Fig. 1. Confusion matrix and ROC-AUC curve summarizing experiments with data recorded for the hip accelerometry cohort.

The figure shows a confusion matrix and b ROC-AUC curve for the held-out sample.

Fig. 2. Relative importance of predictive features in CDPred-4+ experiments with the hip accelerometry cohort.

The features are listed in the order of decreasing importance, from top to bottom of the graph.

Fig. 3. Confusion matrix and ROC-AUC curve summarizing experiments with data recorded for the wrist accelerometry cohort.

The figure shows a confusion matrix and b ROC-AUC curve for the held-out sample.

Fig. 4. Relative importance of predictive features in CDPred-4+ experiments with the wrist accelerometry cohort.

The features are listed in the order of decreasing importance, from top to bottom of the graph.

Fig. 5. Distribution of CPM₇₅/VMC₇₅ over cohorts.

Hip/Wrist accelerometry cohorts distribution of CPM₇₅/VMC₇₅. Red dashed line represents Q1 quantiles on inactive: [0, 25%]; Green dashed line represents Q2 quantiles on moderately active [25–50%]; Blue dashed line represents Q3 quantiles on active [50–75%], and above Q3 represents extremely active [75–100%].

Fig. 6. Includes animations illustrating the entropy, skewness, harmonics, kurtosis, and amplitude accelerometry features used in our analysis (we did not illustrate more standard statistics, such as mean and variance of measurements).

a Differential entropy: Differential entropy is the highest for a uniform distribution of activity (for example, when a person stays inactive 24 h a day, so there are no bursts of activity). When a person is more active through the day and inactive at night, the entropy of activity drops, because the daytime activity exceeds the night-time activity average. b Fast Fourier transform (FFT): The fast Fourier transform refers to the number of harmonics that can be used to describe a curve. Any curve can be decomposed into a spectrum of harmonics. In this case, the hypothetical activity curve shown in red is the sum of 3 harmonics with nonzero amplitude: one with four cycles a day, one with a single full cycle a day, and one with a two-day cycle. In real accelerometry data, the number of accelerometry harmonics composing a 24-h circadian pattern is typically over 15 harmonics. c Skewness is a statistic characterizing the asymmetry of the distribution of activity; it can be applied to entire device wear time or to smaller intervals of accelerometry readings. d Excess kurtosis is a statistic indicating deviation of a distribution from a normal distribution. Kurtosis is zero for a normal distribution, positive for distributions with heavier (than normal) tails, such as t-distribution, and negative for distributions that have lighter tails, such as Beta with parameters (2,2). e Amplitude: The amplitude of each harmonic in an FFT reflects the distance between minimum and maximum activity values. For non-essential (noise-level) harmonics in FFT, the amplitude is close to zero.