Balance and gait algorithms on a smartphone

Balance and gait algorithms on a smartphone use built-in inertial sensors (accelerometer and gyroscope) to collect and analyze movement data:

• by applying signal processing and machine learning techniques, the algorithms can quantify stability during standing and extract key metrics during walking, such as stride length, step time, and walking speed

The raw data for these algorithms are collected from the smartphone's internal Inertial Measurement Unit (IMU), which includes:

• accelerometer: a triaxial sensor that measures linear acceleration along the x, y, and z axes
  • during gait analysis, it can detect the impact of footsteps and the up-and-down motion of the body's center of mass
• gyroscope: a triaxial sensor that measures angular velocity, or rotational speed, around the x, y, and z axes
  • this data is crucial for analyzing body sway during balance tasks and rotational movements during turns while walking

The raw sensor data is filtered and processed using algorithms to produce clinically relevant gait and balance parameters. Gait analysis algorithms

1. signal filtering: raw sensor data contains noise from body tremors and device movement - a Butterworth or Kalman filter is often used to smooth the signal and remove noise before analysis
2. gait event detection: algorithms identify key events in the gait cycle, such as heel strike and toe-off, by detecting specific peaks and troughs in the filtered acceleration and angular velocity signals

Parameter extraction: Once gait events are identified, the algorithm calculates spatiotemporal parameters, including:

• Cadence: The number of steps per minute
• Step time: The time between consecutive steps
• Step length: Estimated by double-integrating the acceleration data
  • sophisticated algorithms may also use a double-pendulum model to improve accuracy
• Walking speed: The average distance covered over a specific time
• Symmetry and variability: Metrics calculated by comparing left and right step timings and lengths, which can indicate gait abnormalities

Evidence shows that smartphone-based assessment was valid and reliable method to assess standing balance (1).

With respect to the Apple Health (Walking Steadiness) (2):

This built-in feature on iPhone 8 or later is the most widely discussed and validated app for gait analysis.

• Key metrics tracked: When carried in a pocket or near the waist, the Health app monitors a variety of mobility metrics, including:
  • Walking Speed
  • Walking Asymmetry (balance between steps)
  • Double Support Time (how long both feet are on the ground)
  • Walking Step Length

Provides a "Fall risk assessment": provides a predictive "Walking Steadiness" score (High, OK, or Low) that estimates your fall risk over the next 12 months

• users can receive notifications if their score is low

With respect to the validity of using the "walking steadiness" indicator on the iPhone (2):

• twenty-seven children, 28 adults and 28 seniors equipped with an iPhone completed a 6-min walk test (6MWT)
  • gait speed (GS), step length (SL), and double support time (DST) were extracted from the gait recordings of the Health app
  • gait parameters were simultaneously collected with an inertial sensors system (APDM Mobility Lab) to assess concurrent validity
  • showed that agreement of the Health App with the APDM Mobility Lab was good for GS in all age groups and for SL in adults/seniors, but poor to moderate for DST in all age groups and for SL in children
  • consistency between repeated measurements was good to excellent for all gait parameters in adults/seniors, and moderate to good for GS and DST but poor for SL in children
  • study authors concluded that:
    • the Health app on iPhone is reliable and valid for measuring GS and SL in adults and seniors
    • careful interpretation is required when using the Health app in children and when measuring DST in general, as both have shown limited validity and/or reliability

Use of smartphone to assess gait in patients with cerebral small vessel disease (CSVD)

• study assessed the ability to detect gait events using a smartphone combined with deep learning and evaluate the remote effects and clinical significance of this method in different elderly populations and patients with cerebral small vessel disease (CSVD) (3):
  • the study authors showed that
    • this method can effectively differentiate gait differences between healthy older adults, individuals with mild cognitive impairment, Parkinson’s disease, and cerebral small vessel disease patients during single-task and dual-task walking
    • proposed that the smartphone-based gait analysis method proposed in this study is easy to operate, has a low cost, and promotes detection, showing promise for applications in remote rehabilitation management, clinical assessment, and other fields

Reference:

1. Prato TA, Lynall RC, Howell DR, Lugade V. Validity and Reliability of an Integrated Smartphone Measurement Approach for Balance. J Sport Rehabil. 2024 Nov 18;34(2):177-183.
2. Werner, C., Hezel, N., Dongus, F. et al. Validity and reliability of the Apple Health app on iPhone for measuring gait parameters in children, adults, and seniors. Sci Rep 2023;13: 5350.
3. Xu, K.; Yu, W.; Yu, S.; Zheng, M.; Zhang, H. The Detection of Gait Events Based on Smartphones and Deep Learning. Bioengineering;2025: 12(5):491.