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.

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 individual's 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 person's 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 person's 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.

Inclusion Criteria: Grup Forensic Medicine

1. Applying to the Department of Forensic Medicine to determine the disability rate,
2. Antalgic gait evaluation performed within the scope of traffic accident or disability reporting,
3. Having a history of unilateral lower extremity fracture,
4. Not having any orthopedic or neurological problems that may affect walking, other than fractures,
5. At least 6 months after surgical treatment,
6. Scoring 24 or more from the Standardized Mini Mental Test
7. Male individuals between the ages of 18-40

Inclusion Criteria: Grup Orthopedics and Traumatology

1. Having a history of unilateral lower extremity fracture,
2. Not in a position of disability or compensation after the fracture,
3. Treated in the Orthopedics and Traumatology Department
4. Similar to the participants in the Group Forensic Medicine in terms of demographic characteristics,
5. No orthopedic or neurological problems other than fractures that would affect walking,
6. At least 6 months after surgical treatment,
7. Scoring 24 or above from the Standardized Mini Mental Test,
8. Male individuals between the ages of 18-40

Inclusion Criteria: Grup Healthy

1. Healthy participants who have compatible demographic characteristics of the patient groups,
2. Scoring 24 or more from the Standardized Mini Mental Test,
3. Male individuals between the ages of 18-40.

Exclusion Criteria:

1. Having any problems or pain in the upper extremities and/or trunk,
2. Having problems in both lower extremities,
3. Treatment is ongoing,
4. Patients who do not have the ability to walk independently,
5. Having a Body Mass Index of 30 kg/m² and above.

The male participants will be included in the study.

The participants will be included via invitation.

There is not a plan to make IPD available.