Digital biomarkers

There are 53 papers on digital biomarkers in aging research: 1 trial and 14 observational studies in people, 35 reviews. The newest story, Nov 13, 2026: “Peak step rates were lower in symptom-free mutation carriers”.

Biomarker

53 papers study it268 more mention it15 findings

25 new papers in 30 daysSee all 321 papers on digital biomarkers

“RouterSense successfully identified key digital biomarkers associated with ADRD.”
RouterSense: A Passive, Network‐Based Health Monitoring System for In‐Home PatientsAAIC 2025 abstract2025doi:10.1002/alz70863_110660
  • Human trial1
  • Humans14
  • In silico2

Effects

5

Sarcopenia monitoring

upin humans1

1 study
  1. Digital biomarkers improve sarcopenia monitoring in sarcopenia monitoring.

    “digital biomarker technologies including smart watch, smart insoles, surface electromyography, and markerless motion analysis via OpenPose enable objective, continuous, real-world monitoring of sarcopenia”

    Reviewin sarcopenia monitoring

    Development and Clinical Application of Digital Biomarkers for Sarcopenia

    Journal of bone metabolism

Early detection of neurodegenerative disease

upin reviews1

1 study
  1. Digital biomarkers improve early detection of neurodegenerative disease.

    “we highlight the potential of DBMs to transform clinical monitoring, early detection and therapeutic interventions in these disorders”

    Review

    A framework of digital biomarkers for neurodegenerative diseases

    Nature reviews bioengineering

Remote patient assessment

upin reviews1

1 study
  1. Digital biomarkers improve remote patient assessment.

    “offer fresh opportunities for remote patient assessment, personalized care and large-scale biomedical research”

    Review

    A framework of digital biomarkers for neurodegenerative diseases

    Nature reviews bioengineering

Cross-center classification accuracy

upin silico1

1 study
  1. Digital biomarkers improve cross-center classification accuracy in silico (77-78% vs 56-65%).

    “Moreover, they achieve accurate and consistent cross-center classification (77-78% accuracy), while standard biomarkers perform poorly in the generalization attempt (56-65%).”

    In silico

    Digital twins support cross-modal and cross-centric classification of mild cognitive impairment

    Communications medicine

Mild cognitive impairment classification accuracy

upin silico1

1 study
  1. Digital biomarkers improve mild cognitive impairment classification accuracy in silico (83% vs 58% for EEG, 75% vs 68% for MEG).

    “Digital biomarkers outperform standard biomarkers in the MCI vs healthy classification in both separate datasets (83% vs 58% for EEG dataset and 75% vs 68% for MEG dataset).”

    In silico

    Digital twins support cross-modal and cross-centric classification of mild cognitive impairment

    Communications medicine

Upstream

1

Amyloid beta burden

no changein humans1

1 study
  1. Amyloid beta burden showed no clear effect on digital biomarkers in humans (at baseline between amyloid-positive and amyloid-negative patients).

    “There were no differences in DBs during the baseline period.”

    Human trialat baseline between amyloid-positive and amyloid-negative patients

    DETECT‐AD (Digital Evaluations and Technologies Enabling Clinical Translation for Alzheimer’s Disease): Baseline results of a simulated anti‐amyloid clinical trial using digital biomarkers

    AAIC 2025 abstract

Associations

8

Frailty

upin humans2

2 studies
  1. Digital biomarkers predict frailty in humans (wearable device monitoring) (AUC 0.73-0.94).

    “Validation performance, where comparable, ranged from ICC 0.70-0.98 (reliability vs reference systems) and AUC 0.73-0.94 for fall/frailty discrimination”

    Reviewwearable device monitoring

    Wearable-Derived Digital Biomarkers for Mobility Assessment and Risk Stratification in Older Adults: A Scoping Review

    Gerontology

  2. Digital biomarkers predict frailty in humans (classify robust and pre-frailty/frailty participants) (sensitivity 0.78 (95% CI: 0.70-0.86), specificity 0.79 (95% CI: 0.72-0.86)).

    “Meta-analysis further revealed pooled sensitivity of 0.78 [95% confidence interval (CI): 0.70-0.86] and specificity of 0.79 (95% CI: 0.72-0.86) to classify robust and pre-frailty/frailty participants.”

    Reviewclassify robust and pre-frailty/frailty participants

    Digital biomarkers for real-life, home-based monitoring of frailty: a systematic review and meta-analysis

    Age and ageing

Fall risk

mixedin humans1

1 study
  1. Digital biomarkers are associated with fall risk in humans (Community samples).

    “identifying digital biomarkers associated with fall risk”

    ReviewCommunity samples

    Beyond the sensory organization test: A portable scalable virtual reality platform for precision assessment of postural control

    Communications in Kinesiology

Cognitive impairment

upin humans1

1 study
  1. Digital biomarkers predict cognitive impairment in humans (older adults with or at risk of cognitive impairment) (AUC 0.59-0.95).

    “digital biomarkers (AUC: 0.59-0.95)”

    Reviewolder adults with or at risk of cognitive impairment

    Digital tools and biomarkers for cognitive screening: A systematic review

    Digital health

More on Cognitive impairment

Cognitive function

upin silico1

1 study
  1. Digital biomarkers predict cognitive function in silico (p < 0.01).

    “Additionally, digital biomarkers reliably predict global cognitive status across clinics across both datasets ( p < 0.01), while standard biomarkers present no correlation.”

    In silico

    Digital twins support cross-modal and cross-centric classification of mild cognitive impairment

    Communications medicine

Routersense

upin humans1

1 study
  1. Routersense predicts digital biomarkers in humans.

    “RouterSense successfully identified key digital biomarkers associated with ADRD.”

    Humans72 hoursn = 3

    RouterSense: A Passive, Network‐Based Health Monitoring System for In‐Home Patients

    AAIC 2025 abstract

More on Routersense

Pre-frailty

upin humans1

1 study
  1. Digital biomarkers predict pre-frailty in-home detection (sensitivity 0.82 (95% CI: 0.74-0.88), specificity 0.82 (95% CI: 0.75-0.88)).

    “pooled sensitivities of 0.84 (95% CI: 0.79-0.88) and 0.82 (95% CI: 0.74-0.88) for in-home detection of MCI and PF, respectively, while pooled specificities were 0.85 (95% CI: 0.80-0.89) and 0.82 (95% CI: 0.75-0.88)”

    Reviewin-home detection

    Predictive Accuracy of Digital Biomarker Technologies for Detection of Mild Cognitive Impairment and Pre-Frailty Amongst Older Adults: A Systematic Review and Meta-Analysis

    IEEE journal of biomedical and health informatics

More on Pre-frailty

Mild cognitive impairment

upin humans1

1 study
  1. Digital biomarkers predict mild cognitive impairment in-home detection (sensitivity 0.84 (95% CI: 0.79-0.88), specificity 0.85 (95% CI: 0.80-0.89)).

    “Meta-analysis further revealed pooled sensitivities of 0.84 (95% CI: 0.79-0.88) and 0.82 (95% CI: 0.74-0.88) for in-home detection of MCI and PF, respectively”

    Reviewin-home detection

    Predictive Accuracy of Digital Biomarker Technologies for Detection of Mild Cognitive Impairment and Pre-Frailty Amongst Older Adults: A Systematic Review and Meta-Analysis

    IEEE journal of biomedical and health informatics

More on Mild cognitive impairment

WHODAS 2.0

upin humans1

1 study
  1. Digital biomarkers predict WHODAS 2.0 in humans (MAPE 14.86% to 27.21%).

    “predicting patients’ WHODAS functionality scores per domain achieved a mean absolute percentage error varying between 14.86% and 27.21% among the domains”

    Humansone month

    Assessing WHODAS 2.0 Scores from Behavioral Biomarkers: a Data-driven Approach (Preprint)

    Preprint

More on WHODAS 2.0

Funding

32 grants since 2020

National Institute on Aging$20.6MNational Cancer Institute$1.7MThe University of Texas Health Science Center at Houston$366K

Latest

Dec 2025: 33Jan 2026: 23Feb 2026: 20Mar 2026: 21Apr 2026: 13May 2026: 7Jun 2026: 7Jul 2026: 15Aug 2026: 20Sep 2026: 10Oct 2026: 22Nov 2026: 10201 papers in 12 months
Amyotrophic Lateral Sclerosis & Frontotemporal Degeneration

Peak step rates were lower in symptom-free mutation carriers

In a 28-day Fitbit study, 56 symptom-free people with a disease-linked gene expansion had lower peak step rates than 160 people without the mutation.In a 28-day Fitbit study, 56 symptom-free people with a disease-linked gene expansion had lower peak step rates than 160 people without the mutation.

Cross-sectional · 226 peopleBiomarkers

See all 321 papers on digital biomarkers