Multimodal Artificial Intelligence Based Fall Risk Prediction in Parkinson's Disease

NCT07058714 | Completed

• 1 other identifier: BiruniUniverc
• Study Type: observational
• Target: 30
• Locations: 1 country
• Sites: 1

Brief Summary

Parkinson's disease (PD) is characterized by motor symptoms such as bradykinesia, tremor, rigidity, and postural instability, often leading to gait disturbances and a high risk of falls. Dual-task walking assessments-requiring simultaneous motor and cognitive engagement-have gained importance in evaluating real-life mobility impairments in PD, as they more accurately reflect challenges faced during daily activities. While clinical tools such as the Timed Up and Go (TUG), Four Square Step Test (FSST), and Mini-BESTest are widely used, their in-person application may not always be feasible for individuals with mobility or access limitations. Telehealth-based assessment methods, therefore, offer practical alternatives. Recently, the integration of artificial intelligence (AI), particularly machine learning (ML), into clinical assessments has opened new possibilities for fall risk prediction by enabling the simultaneous analysis of motor, cognitive, and balance-related parameters. This study aims to predict fall risk in individuals with PD using AI-based models that incorporate multiple data sources. Furthermore, it compares the predictive accuracy of models derived from single-task and dual-task conditions, with the goal of developing a more precise and clinically useful decision-support tool for early intervention.

Conditions

Parkinson Disease

Keywords

fall risk; dual-task; machine learning; artificial intelligence; balance evaluation; Parkinson's Disease

Outcome Measures

Primary Outcomes (2)

• Mini-Balance Evaluation Systems Test (Mini-BESTest)

  The Mini-BESTest is a 14-item balance assessment tool designed to evaluate dynamic balance, including postural responses, sensory orientation, and dynamic gait. The final section allows for assessment of dual-task performance within the context of a mobility test involving cognitive load. Each item is scored on a scale from 0 to 2, where 0 indicates inability to complete the task and 2 indicates normal performance. The maximum total score is 28. It is a unidimensional measure that takes approximately 15 minutes to complete and is considered valid and reliable for use in individuals with Parkinson's disease.

  Mini-BESTest will be administered once during a single assessment session, which is expected to last approximately 10-15 minutes.

• Four Square Step Test (FSST)

  This test evaluates the ability to step over obstacles in multiple directions. At the start, the participant stands in the top left square (Square 1) and faces Square 2. The stepping sequence begins clockwise through Squares 2, 4, and 3, and then continues counterclockwise through Squares 3, 4, 2, and back to 1. The clinician demonstrates the sequence, and the participant is allowed to practice. If the participant fails to complete the sequence correctly, loses balance, or touches the aid, the test is repeated. Two trials are performed, and the best time is recorded. Timing begins when the leading foot contacts Square 2 and ends when the trailing foot returns to Square 1. During this test, participants' stepping and changing direction movements will be recorded on video.

  will be administered once during a single assessment session, which is expected to last approximately 10 minutes.

Secondary Outcomes (6)

• Digit Span Test

  The Digit Span Test will be administered once during a single session and is expected to take approximately 5 minutes to complete.

• Verbal fluency task

  The phonemic verbal fluency task will be administered once during a single session and is expected to take approximately 3 minutes (1 minute per letter).

• Mental Flexibility Task

  The mental flexibility task will be performed once in a single session, taking approximately 2-3 minutes depending on the participant's cognitive status

• Dual-Task Questionnaire

  The dual-task questionnaire will be completed once during the assessment session and will require approximately 3-5 minutes to complete.

• Gait parameters

  Video-based gait assessment will be conducted once per participant during a single session. The walking task and data recording are expected to take approximately 5-7 minutes, including marker placement and calibration.

Other Outcomes (1)

• Parkinson's Disease-Specific Quality of Life Questionnaire

  This self-report questionnaire will be completed once by each participant and is expected to take approximately 5-7 minutes.

Eligibility Criteria

• Age: 40 Years - 75 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

This study was designed as a cross-sectional study. Patients diagnosed with Idiopathic Parkinson's Disease who applied to the Neurology clinic of Bakırköy Prof. Dr. Mazhar Osman Training and Research Hospital and were referred from there will be included in the study.

You may qualify if:

• Clinical diagnosis of idiopathic Parkinson's disease
• Hoehn and Yahr stage between 1 and 3
• A score of at least 21 on the Montreal Cognitive Assessment (MoCA)
• Stable medication regimen during the past month
• Assessment conducted during the patient's "on" period
• Ability to walk independently on a flat surface (Functional Ambulation Classification ≥ 3)

You may not qualify if:

• Severe hearing or visual impairments
• Presence of other neurological, cardiovascular, or orthopedic conditions affecting gait
• Diagnosis of any other neurological disorder (e.g., dementia, cerebrovascular disease)
• Less than 5 years of formal education
• Presence of vascular pathology in the lower extremities

Sponsors & Collaborators

• Biruni University: lead

Study Sites (1)

Biruni University

Istanbul, Zeytinburnu, 34752, Turkey (Türkiye)

Location

Related Publications (6)

• Boddy A, Mitchell K, Ellison J, Brewer W, Perry LA. Reliability and validity of modified Four Square Step Test (mFSST) performance in individuals with Parkinson's disease. Physiother Theory Pract. 2023 May;39(5):1038-1043. doi: 10.1080/09593985.2022.2031360. Epub 2022 Jan 29.

  PMID: 35098864 BACKGROUND

• Caronni A, Amadei M, Diana L, Sangalli G, Scarano S, Perucca L, Rota V, Bolognini N. In Parkinson's disease, dual-tasking reduces gait smoothness during the straight-walking and turning-while-walking phases of the Timed Up and Go test. BMC Sports Sci Med Rehabil. 2025 Mar 7;17(1):42. doi: 10.1186/s13102-025-01068-8.

  PMID: 40055732 BACKGROUND

• Chen IC, Chuang IC, Chang KC, Chang CH, Wu CY. Dual task measures in older adults with and without cognitive impairment: response to simultaneous cognitive-exercise training and minimal clinically important difference estimates. BMC Geriatr. 2023 Oct 16;23(1):663. doi: 10.1186/s12877-023-04390-3.

  PMID: 37845603 BACKGROUND

• Dite W, Temple VA. A clinical test of stepping and change of direction to identify multiple falling older adults. Arch Phys Med Rehabil. 2002 Nov;83(11):1566-71. doi: 10.1053/apmr.2002.35469.

  PMID: 12422327 BACKGROUND

• Dou J, Wang J, Gao X, Wang G, Bai Y, Liang Y, Yang K, Yang Y, Zhang L. Effectiveness of Telemedicine Interventions on Motor and Nonmotor Outcomes in Parkinson Disease: Systematic Review and Network Meta-Analysis. J Med Internet Res. 2025 Jun 3;27:e71169. doi: 10.2196/71169.

  PMID: 40460428 BACKGROUND

• Silva-Batista C, de Almeida FO, Wilhelm JL, Horak FB, Mancini M, King LA. Telerehabilitation by Videoconferencing for Balance and Gait in People with Parkinson's Disease: A Scoping Review. Geriatrics (Basel). 2024 May 23;9(3):66. doi: 10.3390/geriatrics9030066.

  PMID: 38920422 BACKGROUND

MeSH Terms

Conditions

Parkinson Disease

Condition Hierarchy (Ancestors)

Parkinsonian Disorders; Basal Ganglia Diseases; Brain Diseases; Central Nervous System Diseases; Nervous System Diseases; Movement Disorders; Synucleinopathies; Neurodegenerative Diseases

Study Officials

• Guzin Kaya Aytutuldu

  Biruni University

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: CASE ONLY
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Assistant Professor

Study Record Dates

• First Submitted: July 1, 2025
• First Posted: July 10, 2025
• Study Start: July 1, 2025
• Primary Completion: July 15, 2025
• Study Completion: September 15, 2025
• Last Updated: September 19, 2025

Record last verified: 2025-09

Data Sharing

• IPD Sharing: Will not share

Locations

TU (1)