Viewing Study NCT06057272



Ignite Creation Date: 2024-05-06 @ 7:33 PM
Last Modification Date: 2024-10-26 @ 3:09 PM
Study NCT ID: NCT06057272
Status: NOT_YET_RECRUITING
Last Update Posted: 2023-10-06
First Post: 2023-09-14

Brief Title: Lie Detector at the Gait Artificial Intelligence Model
Sponsor: Hacettepe University
Organization: Hacettepe University

Study Overview

Official Title: Determination of Walking Imitations With Artificial Intelligence Model in Forensic Medicine Lie Detector for Walking
Status: NOT_YET_RECRUITING
Status Verified Date: 2023-10
Last Known Status: None
Delayed Posting: No
If Stopped, Why?: Not Stopped
Has Expanded Access: False
If Expanded Access, NCT#: N/A
Has Expanded Access, NCT# Status: N/A
Acronym: None
Brief Summary: The goal of this clinical trial is to obtain more consistent results with the use of repetitive neural networks in gait models and classification approaches in individuals applying forensic sciences It was aimed to develop a decision support system for determining the walking imitations of individuals with explainable machine learning approaches on disability compensation in the field of Forensic Medicine

Participants will be assessed regarding kinematic and temporospatial gait parameters pain severity and fatigue level

Comparison group Researchers will compare the patients applying to the forensic medicine department to those applying to the orthopedic department and their healthy counterparts
Detailed Description: Walking is an autonomic process that involves repetitive cycles and occurs as a result of rhythmic alternating movements of the trunk upper and lower limbs and the forward displacement of the gravity center in the sagittal plane Gait assessments in locomotor diseases or situations that affect movements are based on the description of the individuals gait characteristics and comparison of reference data of individuals of similar age and sex

In some cases patients do not walk with their real gait pattern but may use imitation of some pathologic patterns for secondary financial expectations Generally this problem which can be experienced when determining the disability rate in the field of Forensic Medicine is carried out in order to deliberately deflect the persons walk and to achieve a higher disability rate Thus some unfair compensation gains may occur It is expected that there will be consistency in repetitive steps during a persons habitual gait however this consistency between steps is expected to differ if one wishes to imitate a gait If this issue will provide benefits especially in terms of disability compensation imitation is difficult to understand and proved with methodological designs developed for gait analysis and observational analysis and is often inadequate

In recent studies deep neural networks have been used to study the uniqueness of individual gait patterns by learning and classifying nonlinear systems from data collected from multiple sensors More successful results are obtained with 3-dimensional kinematic data instead of only 2-dimensional spatial-temporal relationship by using information obtained from many sensors in gait analysis with depth images and inertial measurement units Based on this within the scope of the study it is aimed to obtain more consistent results with the use of repetitive neural networks in gait models and classification approaches

It is especially important in clinical evaluations that the analysis and effective features of the models developed with the studies in the field of explainable artificial intelligence and present clear findings to the decision maker The only study that contains similarities about the study to be conducted is the use of layer-by-layer relationship propagation approach to explain walking patterns in individuals with deep learning methods Within the scope of this project it was aimed to develop a decision support system for determining the walking imitations of individuals with explainable machine learning approaches on disability compensation in the field of Forensic Medicine In this way regardless of the personal experience of the evaluator and the method it will be ensured that unfair compensation or lost rights gained by imitation walk is prevented and evidence-based information for the benefit of justice in judicial processes will be obtained

The study will make a significant contribution to the field and the literature as the first study in which artificial intelligence model is used in the determination of walking imitations in the field of Forensic Medicine and which creates a decision support system lie detector on the walk in this field The spatiotemporal characteristics and kinematic evaluations of gait in diseases affecting movement and in healthy individuals are frequently used in clinics and researches in medicine and health sciences but this project is for the first time in the field of medicine to use multiple gait data in an artificial intelligence model to distinguish imitation gaits With the creation of the artificial intelligence model it will contribute to academic studies and researcher training for the definition of disease specific gait patterns and the creation of norms in the following stages

Study Oversight

Has Oversight DMC: None
Is a FDA Regulated Drug?: False
Is a FDA Regulated Device?: False
Is an Unapproved Device?: None
Is a PPSD?: None
Is a US Export?: None
Is an FDA AA801 Violation?: None