Skip to content
Wearables & measurementResearch article3 min read

Wrist-sensor data, mainly HRV, predicted executive function scores in mild cognitive impairment

MoveVitals Editorial Collective · Study published · Reading updated

Original paper:Predicting cognitive scores from wearable-based digital physiological features using machine learning: data from a clinical trial in mild cognitive impairment. · BMC medicine · 2024 · Original paper ↗

Key takeaway

In a 10-week trial of 30 older adults with mild cognitive impairment, machine learning on wrist-sensor features, mainly HRV, predicted executive function scores with r = 0.69 and within-person changes with r = 0.61. Only 17 individuals and 96 data intervals were analyzed, so the model is a promising proof of concept, not a validated tool.

Study design

Research article

Reading basis

Published abstract

Reading focus

Design & applicability

The research question

Tracking thinking skills in mild cognitive impairment (MCI) normally needs inconvenient neuropsychological tests. The authors tested whether physiological signals from a wrist wearable can serve as a proxy for cognitive test scores.

Who and how

Secondary analysis of a 10-week single-arm clinical trial in adults aged 50-70 with amnestic MCI (N = 30) who received a digitally delivered multidomain intervention. Cognition was tested before and after with the Neuropsychological Test Battery (NTB), giving composite scores for executive function, processing speed, immediate memory, delayed memory and global cognition. An Empatica E4 wrist device recorded blood volume pulse, electrodermal activity and skin temperature, from which features were extracted. NTB scores were interpolated to 10-day intervals, and personal-baseline-centered data were also used. Supervised machine learning predicted scores from physiological features and demographics, with leave-one-subject-out and leave-one-interval-out cross-validation.

What it found

The authors’ reported results. Read each estimate with its population and uncertainty.

  1. 1
    The final sample was 96 aggregated data intervals from 17 individuals, with 106 digital physiological features extracted.
  2. 2
    Physiological features, especially HRV measures, correlated most strongly with executive function compared with the other cognitive composites.
  3. 3
    The model predicted actual executive function scores with correlation r = 0.69 and intra-individual changes in executive function with r = 0.61.
  4. 4
    The authors conclude that wearable-based physiological measures, mainly HRV, could help with continuous assessment of cognition in MCI.

Limits & uncertainty

  1. 1
    The final analysis used only 17 of the 30 enrolled individuals and 96 intervals, so the model could be overfitted and may not generalize.
  2. 2
    NTB scores were interpolated between two tests to fill 10-day intervals, so the cognitive targets are estimates, not measured values.
  3. 3
    There was a single-arm design with a medical-grade Empatica E4, not a consumer watch, and the trial intervention may have changed both cognition and physiology.
  4. 4
    The abstract gives correlations only, with no error or confidence intervals. This reading rests on the abstract only.

What to take from it

The work hints that HRV from a wrist device could one day help monitor cognition in people with MCI, especially to follow changes over time. It does not show that your own HRV can estimate your memory or thinking ability. Concerns about memory should be assessed by a clinician with proper tests.

Reading your own data

HRV is the signal this study leans on, and consumer watches also report it, but a medical-grade research device is not the same as a consumer one. Track your own HRV against your own baseline under the same conditions, and do not treat it as a stand-in for a cognitive test.

How to read this evidence

The index does not establish a precise design. Read the methods before making causal claims; check population, comparator, outcomes and uncertainty in the source.

Authors’ structured abstract English

The attributed English abstract is reproduced under the recorded open licence. It is source material, not a MoveVitals interpretation. The prepared analysis above separates the authors’ findings from our interpretation.

Background

Continuous assessment and remote monitoring of cognitive function in individuals with mild cognitive impairment (MCI) enables tracking therapeutic effects and modifying treatment to achieve better clinical outcomes. While standardized neuropsychological tests are inconvenient for this purpose, wearable sensor technology collecting physiological and behavioral data looks promising to provide proxy measures of cognitive function. The objective of this study was to evaluate the predictive ability of digital physiological features, based on sensor data from wrist-worn wearables, in determining neuropsychological test scores in individuals with MCI.

Methods

We used the dataset collected from a 10-week single-arm clinical trial in older adults (50-70 years old) diagnosed with amnestic MCI (N = 30) who received a digitally delivered multidomain therapeutic intervention. Cognitive performance was assessed before and after the intervention using the Neuropsychological Test Battery (NTB) from which composite scores were calculated (executive function, processing speed, immediate memory, delayed memory and global cognition). The Empatica E4, a wrist-wearable medical-grade device, was used to collect physiological data including blood volume pulse, electrodermal activity, and skin temperature. We processed sensors' data and extracted a range of physiological features. We used interpolated NTB scores for 10-day intervals to test predictability of scores over short periods and to leverage the maximum of wearable data available. In addition, we used individually centered data which represents deviations from personal baselines. Supervised machine learning was used to train models predicting NTB scores from digital physiological features and demographics. Performance was evaluated using "leave-one-subject-out" and "leave-one-interval-out" cross-validation.

Results

The final sample included 96 aggregated data intervals from 17 individuals. In total, 106 digital physiological features were extracted. We found that physiological features, especially measures of heart rate variability, correlated most strongly to the executive function compared to other cognitive composites. The model predicted the actual executive function scores with correlation r = 0.69 and intra-individual changes in executive function scores with r = 0.61.

Conclusions

Our findings demonstrated that wearable-based physiological measures, primarily HRV, have potential to be used for the continuous assessments of cognitive function in individuals with MCI.

Sources & attribution

Predicting cognitive scores from wearable-based digital physiological features using machine learning: data from a clinical trial in mild cognitive impairment.

Rykov YG, Patterson MD, Gangwar BA, Jabar SB, Leonardo J, Ng KP, Kandiah N.

BMC medicine · 2024-01-25

DOI: 10.1186/s12916-024-03252-y ↗PubMed · 38273340 ↗Europe PMC · Recorded licence: cc by ↗

Abstract © the original authors, reproduced under the recorded open licence. Translations support reading; use the English record to check terminology and numerical results. Our methodological interpretation is separate from the authors’ conclusions.

MoveVitals editorial interpretation · educational content · no individual clinical review recorded

Sources checked 2026-11-01

Practical guides

Read in context

·Cohort study

Activity–stroke and heart attack curves differ by accelerometer processing method

Among 90,237 UK Biobank adults free of cardiovascular disease at baseline, followed until December 2022 for 1,298 strokes and 2,031 myocardial infarctions, the shape of the link between moderate-vigorous physical activity (MVPA) and each outcome depended on how the accelerometer data were processed. For stroke, hazard fell in a straight line only with the machine-learning metric; for myocardial infarction, two metrics gave a curved decline and activity counts a straight one. The abstract gives no hazard ratios, so it shows that methods disagree, not which one is right, and the findings are observational associations.

Preventive Medicine

In-depth explainersRead study →
·Validation study/review

Smartwatch data as forensic evidence: heart rate is best validated, the rest uneven

A systematic review and meta-analysis of studies on smartwatches from four major brands, framed around digital forensics, found that heart rate was both the most studied and the most accurate measure. Step count, distance, energy expenditure, activity classification and sleep were less consistently validated, and results varied by brand, protocol and reporting. The abstract gives no pooled numbers, and most studies were run in healthy people in laboratories, so it cannot say how a particular watch performs for a particular person in daily life.

Forensic Science International

In-depth explainersRead study →
·Overview of reviews

Activity trackers: about 1,800 more steps a day, but small effects on other outcomes

An umbrella review of 39 systematic reviews and meta-analyses, covering 163,992 participants, found that activity trackers were associated with more physical activity (SMD 0.3–0.6), equating to about 1,800 extra steps and 40 minutes more walking per day, and with a bodyweight reduction of about 1 kg. Effects on blood pressure, cholesterol, glycosylated haemoglobin, quality of life and pain were typically small and often non-significant. The abstract does not say what else came with the trackers in these programs or how much the reviews overlap, so the gains cannot be credited to the device alone.

The Lancet Digital Health

In-depth explainersRead study →
·Validation study/review

Seven sleep trackers: good at spotting sleep, weak on wake and sleep stages

In a sleep laboratory, 34 healthy young adults wore a subset of seven consumer sleep trackers for three nights. Against polysomnography every device detected sleep very well (sensitivity 0.93 or higher) but caught wake poorly (specificity 0.18–0.54), and five of the seven matched or beat research actigraphy (specificity 0.39). Sleep-stage estimates were inconsistent, and the participants were healthy adults aged 18 to 35 in a fixed 8-hour bed window, with each device tested in only 11 to 20 of them, so the results say little about people with sleep problems.

Sleep

In-depth explainersRead study →
Wearables & measurement →