Key takeaway
In this systematic review, studies pairing AI with wearable inertial measurement units (IMUs) had a median dataset of only 50 participants; 76% used traditional machine learning, 93% used supervised learning and 65% focused on neurological problems. The abstract does not give the number of studies reviewed or how well the models performed, so it describes research habits, not how well the tools work.
Study design
Evidence review
Reading basis
Published abstract
Reading focus
Design & applicability
The research question
Wearable motion sensors (accelerometers and gyroscopes, known as IMUs) combined with AI are expected to change patient care, but the research base is not well mapped. The authors set out to chart which medical fields use these tools, which models are applied, and what the datasets look like.
Who and how
Systematic review following PRISMA reporting guidelines, built around three questions: which medical fields research AI with IMU data, which models analyse the data, and what the datasets are like. The abstract does not report the databases searched, the number of included studies, or the dates covered.
What it found
The authors’ reported results. Read each estimate with its population and uncertainty.
- 1The median dataset size was 50 participants, which the authors see as a serious limit for AI models that need large datasets to train and generalize.
- 2Machine learning dominated in 76% of the surveyed studies, mainly traditional models such as linear regression, support vector machine and random forest, with room for more deep learning.
- 3Supervised learning was used in 93% of studies, so unsupervised methods for finding hidden patterns are little used.
- 4Most studies took place in clinical settings (77%) rather than in real life, and 65% focused on neurological problems, leaving areas such as musculoskeletal care less explored.
Limits & uncertainty
- 1The abstract reports no number of included studies, search dates or quality assessment, so the strength of the evidence base is unclear.
- 2The review maps what researchers have done; it does not test whether any AI-plus-IMU tool improves patient outcomes.
- 3The authors themselves name small datasets and the clinic-only setting as limits on practical applicability. This reading is based on the abstract only.
What to take from it
For readers, the main message is that most AI work on wearable motion data is still early: small samples, clinic-based and focused on neurological conditions. Claims that a consumer wearable can diagnose conditions from movement data should be treated with caution until tested in larger, real-life groups.
Reading your own data
Phone and watch accelerometer data, such as step counts and activity minutes, are the everyday cousin of the IMU signals studied here. Use them as personal trends on one device, not as a diagnostic of movement disorders.
How to read this evidence
Check which designs were included, how searches and bias assessment were conducted, and the last search date. Publication date alone does not make the underlying evidence current.
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
Artificial intelligence (AI) has already revolutionized the analysis of image, text, and tabular data, bringing significant advances across many medical sectors. Now, by combining with wearable inertial measurement units (IMUs), AI could transform health care again by opening new opportunities in patient care and medical research.
Objective
This systematic review aims to evaluate the integration of AI models with wearable IMUs in health care, identifying current applications, challenges, and future opportunities. The focus will be on the types of models used, the characteristics of the datasets, and the potential for expanding and enhancing the use of this technology to improve patient care and advance medical research.
Methods
This study examines this synergy of AI models and IMU data by using a systematic methodology, following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, to explore 3 core questions: (1) Which medical fields are most actively researching AI and IMU data? (2) Which models are being used in the analysis of IMU data within these medical fields? (3) What are the characteristics of the datasets used for in this fields?
Results
The median dataset size is of 50 participants, which poses significant limitations for AI models given their dependency on large datasets for effective training and generalization. Furthermore, our analysis reveals the current dominance of machine learning models in 76% on the surveyed studies, suggesting a preference for traditional models like linear regression, support vector machine, and random forest, but also indicating significant growth potential for deep learning models in this area. Impressively, 93% of the studies used supervised learning, revealing an underuse of unsupervised learning, and indicating an important area for future exploration on discovering hidden patterns and insights without predefined labels or outcomes. In addition, there was a preference for conducting studies in clinical settings (77%), rather than in real-life scenarios, a choice that, along with the underapplication of the full potential of wearable IMUs, is recognized as a limitation in terms of practical applicability. Furthermore, the focus of 65% of the studies on neurological issues suggests an opportunity to broaden research scope to other clinical areas such as musculoskeletal applications, where AI could have significant impacts.
Conclusions
In conclusion, the review calls for a collaborative effort to address the highlighted challenges, including improvements in data collection, increasing dataset sizes, a move that inherently pushes the field toward the adoption of more complex deep learning models, and the expansion of the application of AI models on IMU data methodologies across various medical fields. This approach aims to enhance the reliability, generalizability, and clinical applicability of research findings, ultimately improving patient outcomes and advancing medical research.
Sources & attribution
The Use of Artificial Intelligence and Wearable Inertial Measurement Units in Medicine: Systematic Review.
Smits Serena R, Hinterwimmer F, Burgkart R, von Eisenhart-Rothe R, Rueckert D.
JMIR mHealth and uHealth · 2025-01-29
DOI: 10.2196/60521 ↗PubMed · 39880389 ↗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
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
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
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
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

