ClinicalTrials.gg
RecruitingNCT07580612AID-FOGUpdated May 12, 2026

AID-FOG: Artificial Intelligence-Driven Freezing of Gait Detection in the Home

An observational study in Parkinson Disease, Idiopathic, Freezing of Gait and Validation, sponsored by KU Leuven. Recruiting at 3 sites in 3 countries. Open to participants aged 18 Years and older, including healthy volunteers. Per ClinicalTrials.gov, last updated 2026-05-12.

Sponsored by KU Leuven · Observational

How we know

From the registry’s dates

  • Started Sep 2025; still recruiting 1 year 2 months later.

Help build ClinicalTrials.gg — short surveys, remote interviews or testing, in your language. Take part →

Study type
Observational
Model
Cohort
Time perspective
Prospective
Enrollment
126
Ages
18 Years and older
Sex
All
01

Where this study stands

Counted across the records on this site · 2026-11-22

Among 17 studies in Parkinson Disease by KU Leuven — 2 open to participants now, 3 under way, none of them phase 3. Parkinson Disease · KU Leuven.

Started
2025
the only one that year
Observational
3 of 17
2 open now
Registered
17th of 17
by date

Among the 17 studies in Parkinson Disease by KU Leuven, this one is the only one that started in 2025, is one of 3 observational ones, and was the 17th registered.

Parkinson Disease

4,583 studies on the registry are indexed under Parkinson Disease; 1,086 are open to participants now.

Browse Parkinson Disease studies →

Open to participants now

2 of the 17 studies in Parkinson Disease by KU Leuven are open now, in 3 countries. Recruiting first, the newest first:

By country, each count listing its studies:

All 2 open studies →

Where they have run

Who these studies take

Of the 752 Parkinson Disease studies recruiting now, 314 (42%) set no upper age limit and 127 (17%) stop at 75 or younger; 64 take children under 18; 189 take healthy volunteers.

This study: 18 Years and older · all sexes · healthy volunteers too.

The full table on the hub →

This tab as a report to print or save as PDF → With an account.

Was this useful?
Get alerts for this landscapeDownload CSVNarrow it in search →With an account: a weekly mail of what changed among 17 studies in Parkinson Disease by KU Leuven, or all of them as a file.
02

Study summary

Freezing of gait (FOG) is a debilitating symptom of Parkinson's disease increases the risk of falling. Despite being a common symptom, it is still difficult to evaluate freezing of gait quickly and accurately. Currently, the gold-standard method to determine the severity of FOG is a manual analysis of video footage by an experienced assessor, collected during standardized FOG-provoking walking tests. Because this is a very time-intensive process, where different assessors sometimes obtain different results, our team at KU Leuven have developed an artificial-intelligent (AI) algorithm trained to identify FOG episodes based on wearable inertial measurement unit (IMU) sensor data. The AI algorithm has already undergone initial validation during laboratory testing, yielding promising results. The aim of this study is to investigate whether the AI algorithm can accurately detect FOG episodes in a less controlled environment, namely the home environment. In a second phase, the investigators will also use the collected data to improve the AI algorithm for automated FOG detection in the home. Finally, the investigators want to explore whether the AI algorithm can detect FOG in real-time.

03

Conditions studied

  • Parkinson Disease, Idiopathic
  • Freezing of Gait
  • Validation
  • Wearable Sensors
  • Artifical Intelligence

Browse trials for

04

Who can participate

Ages eligible
18 Years and older
Sexes eligible
All
Accepts healthy volunteers
Yes
Sampling method
Non-probability sample

Study population

People with PD and healthy age-matched controls will be recruited from three primary sites, namely KU Leuven, Hamburg Medical Center, and Tel-Aviv Sourasky Medical Center.

Go through the criteria one by one — yes, no or not sure — and take the list to your doctor or the study team. Kept in this browser only.

Inclusion criteria

For all participants

  • Voluntary written of the participant has been obtained prior to any study-related procedures, except the non-recorded pre-screening questions;
  • At least 18 years of age at the time of signing the Informed Consent Form (ICF);
  • Person is cognitively able to follow and understand instructions and provide voluntary written informed consent;
  • Person is able to walk for short distances (± 10 meters) independently, with- or without use of a walking aid;
  • Person does not live in a temporary or permanent care facility.

For participants with PD:

  • Clinical diagnosis of Parkinson's disease (PD) made by a neurologist according to the Movement Disorders Society guidelines;
  • Person self-reports to experience daily FOG (for recruitment of freezers only);
  • Person is willing to temporarily delay the morning anti-Parkinsonian medication during the standardized assessment visit.

Exclusion criteria

Exclusion criteria:

  • Occurrence of any of the following within 3 months prior to : myocardial infarction, hospitalization for unstable angina, stroke, coronary artery bypass graft (CABG), percutaneous coronary intervention (PCI), implantation of a cardiac resynchronization therapy device (CRTD), active treatment for cancer or other malignant disease, uncontrolled congestive heart disease ( class >3), acute psychosis or major psychiatric disorders or continued substance abuse, other neurological (than PD) or orthopaedic impairment that significantly impacts on gait;
  • Participant self-reports daily falls;
  • Participation in another interventional study, with or without an medicinal product (IMP) or device (IMD)
Terms in these criteria, in plain language(3)

Underlined terms in the criteria open these too. Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.

Informed consent

Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorized to decide for you.

You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.

NYHA class (heart failure)

The New York Heart Association’s four classes of how much heart failure limits physical activity.

I
No limits: ordinary activity causes no undue tiredness or breathlessness.
II
Slight limits: comfortable at rest, ordinary activity causes symptoms.
III
Marked limits: comfortable at rest, less than ordinary activity causes symptoms.
IV
Symptoms even at rest; any activity makes them worse.

Studies set their own limit — many outside heart failure leave out class III–IV, while heart failure studies may ask for a particular class. Check the class this study names.

Investigational drug or device

A drug or device being studied in a clinical trial.

It may be new, or already approved and being studied for another use, dose or form. Criteria often leave out people who took part in another study of one within a recent period, commonly 30 days or five half-lives.

05

Study design

Observational model
Cohort
Time perspective
Prospective
Enrollment
126 participants (estimated)
Patient registry
No

Groups and cohorts

  • Freezers

    Patients with Parkinson's disease who self-report to experience Freezing of Gait daily.

  • Non-freezers

    Patients with Parkinson's disease who do not experience Freezing of Gait.

  • Healthy controls

    Healthy older adults

06

What researchers measure

Primary outcomes

  1. Comparing the agreement between AID-FOG and gold-standard expert annotation to detect the percentage of time spent with freezing of gait (FOG) in relation to total time duration (%TF).

    The primary outcome (percentage of time spent with FOG in relation to total task duration = %TF) will be established by manual annotations of video footage by an experienced assessor (=gold-standard reference) and by the automated AID-FOG algorithm v1.0 applied post-hoc (i.e. offline) to IMU data collected during the same walking tasks. This will be calculated for standardized walking tasks on which the AID-FOG algorithm has been trained, standardized walking tasks on which the AID-FOG algorithm was not trained, and a free-living walking condition on which the AID-FOG algorithm was not trained.

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

Secondary outcomes

  1. F1-score

    Same as primary outcome, but now for the F1-score (rather than percent TF). F1 scores range between 0 and 1, the higher the score the better.

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  2. Number of FOG episodes

    Same as primary outcome, but now for the absolute number of FOG episodes.

    Time frame: T0: free-living gait (5 hours), T1: free-living gait (5 hours) and T2: standardized gait (4 hours)

  3. The performance of the AID-FOG algorithm to differentiate between the FOG manifestations.

    Freezing of gait (FOG) manifests in multiple forms, including akinetic and kinetic subtypes, which may be associated with trembling or occur without it. This study investigates the performance of AID-FOG in discriminating between these manifestations, using expert annotations as the reference standard.

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  4. Comparing performance of AID-FOG to detect freezing in OFF and ON medication states.

    The FOG outcomes as obtained by the human expert and the offline AID-FOG algorithm v1.0 will be calculated for both the OFF and ON medication states. These scores will be compared to evaluate the change in algorithm performance depending on medication status. The FOG outcomes will be the percentage TF which ranges between 0-100 percent. The higher the percentage the more freezing the patient has. But also the F1-score which ranges between 0-1. The higher the score the more overlap there is between the expert and the algorithm.

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  5. Consistency of FOG detection with AID-FOG compared between two free-living assessments

    The agreement in FOG detection (%TF, F1-score) between the AID-FOG algorithm and the gold-standard human annotations will be compared between the two free-living test days.

    Time frame: T0= test day 1: free-living gait (5 hours) and T1= test day 2: free-living gait (5 hours)

  6. The number of false detections of FOG episodes during free-living

    The absolute sum of false detections made by the algorithm.

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  7. Comparing AID-FOG with subjective FOG

    The FOG outcomes obtained with AID-FOG will be correlated to the total score of the New Freezing of Gait Questionnaire (NFOGQ) and Patient Reported Outcomes of FOG (PRO).

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  8. Performance of automated FOG detection during free-living mobility

    The FOG outcomes obtained with AID-FOG offline will be calculated from multiple days of free-living mobility IMU data. These outcomes will be correlated to FOG severity as determined during the observed walking tasks of the project and self-reported FOG severity.

    Time frame: 1 week of free-living mobility with IMU

Other outcomes

  1. AID-FOG version 2.0 (percentage TF)

    The data obtained in the study will be used to train the AID-FOG algorithm v1.0. This trained AID-FOG algorithm v2.0 will be evaluated using the same listed outcome measures, using a leave-one-subject-out approach. Percentage of time spent with FOG in relation to total task duration (= %TF) will be established by manual annotations of video footage by an experienced assessor (=gold-standard reference) and by the automated AID-FOG algorithm v2.0 applied post-hoc (i.e. offline) to IMU data collected during the same walking tasks. This will be calculated for standardized walking tasks on which the AID-FOG algorithm has been trained, standardized walking tasks on which the AID-FOG algorithm was not trained, and a free-living walking condition on which the AID-FOG algorithm was not trained.

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  2. AID-FOG version 2.0 (F1-score)

    The data obtained in the study will be used to train the AID-FOG algorithm v1.0. This trained AID-FOG algorithm v2.0 will be evaluated using the same listed outcome measures, using a leave-one-subject-out approach. Same as percentage TF, but now for the F1-score (rather than percent TF). F1 scores range between 0 and 1, the higher the score the better.

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  3. AID-FOG version 2.0 (Number of FOG episodes)

    The data obtained in the study will be used to train the AID-FOG algorithm v1.0. This trained AID-FOG algorithm v2.0 will be evaluated using the same listed outcome measures, using a leave-one-subject-out approach. Same as percentage TF, but now for the absolute number of FOG episodes.

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  4. AID-FOG version 2.0 (FOG manifestations)

    The data obtained in the study will be used to train the AID-FOG algorithm v1.0. This trained AID-FOG algorithm v2.0 will be evaluated using the same listed outcome measures, using a leave-one-subject-out approach. The performance of the AID-FOG algorithm v2.0 to discriminate between the FOG manifestations. Freezing of gait (FOG) manifests in multiple forms, including akinetic and kinetic subtypes, which may be associated with trembling or occur without it. This study investigates the performance of AID-FOG in discriminating between these manifestations, using expert annotations as the reference standard.

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  5. AID-FOG version 2.0 (OFF/ON medication)

    The data obtained in the study will be used to train the AID-FOG algorithm v1.0. This trained AID-FOG algorithm v2.0 will be evaluated using the same listed outcome measures, using a leave-one-subject-out approach. Comparing performance of AID-FOG v2.0 to detect freezing in OFF and ON medication states. The FOG outcomes as obtained by the human expert and the offline AID-FOG algorithm v2.0 will be calculated for both the OFF and ON medication states. These scores will be compared to evaluate the change in algorithm performance depending on medication status. The FOG outcomes will be the percentage TF which ranges between 0-100 percent. The higher the percentage the more freezing the patient has. But also the F1-score which ranges between 0-1. The higher the score the more overlap there is between the expert and the algorithm.

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  6. AID-FOG version 2.0 (consistency of detection during two free-living assessments)

    The data obtained in the study will be used to train the AID-FOG algorithm v1.0. This trained AID-FOG algorithm v2.0 will be evaluated using the same listed outcome measures, using a leave-one-subject-out approach. Consistency of FOG detection with AID-FOG v2.0 compared between two free-living assessments. The agreement in FOG detection (%TF, F1-score) between the AID-FOG algorithm v2.0 and the gold-standard human annotations will be compared between the two free-living test days.

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  7. AID-FOG version 2.0 (number of false positives)

    The data obtained in the study will be used to train the AID-FOG algorithm v1.0. This trained AID-FOG algorithm v2.0 will be evaluated using the same listed outcome measures, using a leave-one-subject-out approach. The number of false detections (AID-FOG v2.0) of FOG episodes during free-living

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  8. AID-FOG version 2.0 (subjective FOG)

    The data obtained in the study will be used to train the AID-FOG algorithm v1.0. This trained AID-FOG algorithm v2.0 will be evaluated using the same listed outcome measures, using a leave-one-subject-out approach. Comparing AID-FOG v2.0 with subjective FOG. The FOG outcomes obtained with AID-FOG v2.0 will be correlated to the total score of the New Freezing of Gait Questionnaire (NFOGQ) and Patient Reported Outcomes of FOG (PRO).

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  9. AID-FOG online (percentage TF)

    The AID-FOG algorithm will be modified for real-time FOG detection. Performance of this AID-FOG online algorithm will be compared with AID-FOG offline versions, using the same listed outcomes. Percentage of time spent with FOG in relation to total task duration (= %TF) will be established by manual annotations of video footage by an experienced assessor (=gold-standard reference) and by the automated AID-FOG online to IMU data collected during the same walking tasks. This will be calculated for standardized walking tasks on which the AID-FOG algorithm has been trained, standardized walking tasks on which the AID-FOG algorithm was not trained, and a free-living walking condition on which the AID-FOG algorithm was not trained.

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  10. AID-FOG online (F1-score)

    The AID-FOG algorithm will be modified for real-time FOG detection. Performance of this AID-FOG online algorithm will be compared with AID-FOG offline versions, using the same listed outcomes. Same as percentage TF, but now for the F1-score (rather than percent TF). F1 scores range between 0 and 1, the higher the score the better.

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  11. AID-FOG online (number of FOG episodes)

    The AID-FOG algorithm will be modified for real-time FOG detection. Performance of this AID-FOG online algorithm will be compared with AID-FOG offline versions, using the same listed outcomes. Same as percentage TF, but now for the absolute number of FOG episodes.

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  12. AID-FOG online (FOG manifestations)

    The AID-FOG algorithm will be modified for real-time FOG detection. Performance of this AID-FOG online algorithm will be compared with AID-FOG offline versions, using the same listed outcomes. The performance of the AID-FOG online algorithm to discriminate between the FOG manifestations.

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  13. AID-FOG online (OFF/ON medication)

    The AID-FOG algorithm will be modified for real-time FOG detection. Performance of this AID-FOG online algorithm will be compared with AID-FOG offline versions, using the same listed outcomes. The FOG outcomes as obtained by the human expert and the offline AID-FOG online algorithm will be calculated for both the OFF and ON medication states. These scores will be compared to evaluate the change in algorithm performance depending on medication status. The FOG outcomes will be the percentage TF which ranges between 0-100 percent. The higher the percentage the more freezing the patient has. But also the F1-score which ranges between 0-1. The higher the score the more overlap there is between the expert and the algorithm.

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  14. AID-FOG online (agreement of the detection between two free-living test days)

    The AID-FOG algorithm will be modified for real-time FOG detection. Performance of this AID-FOG online algorithm will be compared with AID-FOG offline versions, using the same listed outcomes. The agreement in FOG detection (%TF, F1-score) between the AID-FOG online algorithm and the gold-standard human annotations will be compared between the two free-living test days.

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  15. AID-FOG online (number false positives)

    The AID-FOG algorithm will be modified for real-time FOG detection. Performance of this AID-FOG online algorithm will be compared with AID-FOG offline versions, using the same listed outcomes. The absolute sum of false detections made by the online algorithm.

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

  16. AID-FOG online (subjective FOG)

    The AID-FOG algorithm will be modified for real-time FOG detection. Performance of this AID-FOG online algorithm will be compared with AID-FOG offline versions, using the same listed outcomes. Comparing AID-FOG online with subjective FOG. The FOG outcomes obtained with AID-FOG online will be correlated to the total score of the New Freezing of Gait Questionnaire (NFOGQ) and Patient Reported Outcomes of FOG (PRO).

    Time frame: T0=test day 1: free-living gait assessment (5 hours), T1=test day 2: free-living gait (5 hours) and T2= test day 3: standardized gait (4 hours)

07

Study locations

1 of 3 sites recruiting
08

References and documents

Publications

  • Yang PK, Filtjens B, Ginis P, Goris M, Nieuwboer A, Gilat M, Slaets P, Vanrumste B. Freezing of gait assessment with inertial measurement units and deep learning: effect of tasks, medication states, and stops. J Neuroeng Rehabil. 2024 Feb 13;21(1):24. doi: 10.1186/s12984-024-01320-1. PubMed 38350964 ↗
  • Yang PK, Filtjens B, Ginis P, Goris M, Nieuwboer A, Gilat M, Slaets P, Vanrumste B. Automatic Detection and Assessment of Freezing of Gait Manifestations. IEEE Trans Neural Syst Rehabil Eng. 2024;32:2699-2708. doi: 10.1109/TNSRE.2024.3431208. Epub 2024 Jul 31. PubMed 39028610 ↗

Individual participant data

Plan to share: Undecided — The datasets could be made available under restricted access after publication of the results, following ethical approval and a data-transfer agreement. GDPR and privacy regulations will be adhered to.

09

Timeline

Tracking since Sep 25, 2026
ElapsedEstimatedEstimated, not yet reachedSimilar studies: half by the dot; the band is the middle halfHalf of similar studies reached it by the dot; the band is the middle half, from a quarter to three quarters

Started Sep 2025 (actual). Primary completion is estimated for Jun 2027, 21 months after the start.

Of 381 non-industry observational studies under Parkinson Disease, half reached primary completion within 48 months of starting (the median), counting those still running; a quarter within 22 and three quarters within 133. This study's planned 21 months is below that.

Counting every sponsor, half of 441 studies reached it within 47 months; a quarter within 22 and three quarters within 114.

How these figures are worked out, and which studies are left out of them.

Registered
Apr 2, 2026
First posted
May 12, 2026
StartActual
Sep 22, 2025
Primary completionEst.
Jun 2027
CompletionEst.
Jun 2027
Last update
May 12, 2026
What these dates mean
Start.
When the first participant enrolled; while estimated, when the study expects to open to recruitment.
Primary completion.
When the last participant was examined or treated to collect data for the study's main question, its primary outcome. A study that stopped early gives the date its data collection stopped.
Completion.
When the last participant's last visit took place, for every outcome, secondary ones and side effects included: the end of the study. Often later than primary completion, sometimes the same day.
Actual and Est.
Actual means the registry says the date has happened. Est. (estimated) is a date the sponsor plans or expects. It can still move, and the sponsor is expected to change it to actual once it has passed.
No changes since tracking began. The registry record was last updated on May 12, 2026, before this site started recording changes on Sep 25, 2026. Its history is on ClinicalTrials.gov ↗
10

Registry details

Key details

Study ID
NCT07580612
Lead sponsor
KU Leuven
Collaborators
Michael J. Fox Foundation for Parkinson's Research, Tel Aviv Medical Center, Medical School Hamburg
Responsible party
Moran Gilat (Prof, KU Leuven) — Principal investigator
First posted
May 12, 2026
Start date
Sep 22, 2025
Primary completion
Jun 2027 (estimated)
Completion
Jun 2027 (estimated)
Last update
May 12, 2026

Oversight

Data monitoring committee
No
FDA-regulated drug
No
FDA-regulated device
No
View the source record on ClinicalTrials.gov ↗

Interested in this study?

Eligibility is decided by the study team. Share this record with your doctor or contact the team directly.

No contact was published for this record. The registry link below has the sponsor’s details.

Follow this study

Get an email when the registry record changes — status, dates, results — or when someone posts here.

Sign in to follow

Discussion

Questions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.

Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.

Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.

Start the discussion