Browsing by Author "Vukićević, Arso (55568836700)"

Hanging is one of the most common suicide methods worldwide. Neck injuries that occur upon such neck compression – fractures of the thyrohyoid complex and cervical spine, occupy forensic pathologists for a long time. However, research failed to identify particular patterns of these injuries corresponding to the force distribution a ligature applies to the neck: the issue of reconstructing the knot in a noose position persists. So far, machine learning (ML) models were not utilized to classify knot positions and reconstruct this event. We conducted a single-institutional, retrospective study on 1235 autopsy cases of suicidal hanging, developed several ML models, and assessed their classification performance in a stepwise manner to discriminate between: 1. typical (‘posterior) and atypical (‘anterior’ and ‘lateral’) hangings, 2. anterior and lateral hangings, and 3. left and right lateral hangings. The variable coding was based on the presence/absence of fractures of greater hyoid bone horns (GHH), superior thyroid cartilage horns (STH), and cervical spine. Subject age was considered. The models’ parameters were optimized by the Genetic Algorithm. The accuracy of ML models in the first step was very modest (c. 60%) but increased subsequently: Multilayer Perceptron – Artificial Neural Network and k-Nearest Neighbors performed excellently discriminating between left and right lateral hangings (accuracy 91.8% and 90.6%, respectively). The latter is of great importance for clarifying probable hanging fracture biomechanics. Alongside the conventional inferential statistical analysis we performed, our results further indicate the association of the knot position with ipsilateral GHH and contralateral STH fractures in lateral hangings. Moreover, odds for unilateral GHH fracture, simultaneous GHH and STH fractures, and cervical spine fracture were significantly higher in atypical (‘anterior’ and ‘lateral’) hangings, compared to typical (‘posterior’) hangings. © 2024 Elsevier B.V.

Introduction/Objective Finite element analysis (FEA) is mathematical method which can be used for the assessment of biomechanical behavior of dento-alveolar complex. The objectives were to analyze biomechanical behavior changes of teeth and supporting tissues under occlusal load in cases of horizontal and vertical alveolar bone loss, to assess potential impact of tooth displacement and altered stress distribution on further damage, and to evaluate the impact of regenerative periodontal therapy. Methods Three patient-specific three-dimensional finite element (3D FE) models were developed from the acquired cone beam computed tomography, comprising the patient’s upper left canine, first and second premolar, and adjacent bone. Model 1 represented horizontal bone loss. Model 2 included intrabony defect along distal aspect of tooth #24. Model 3 represented situation six months after the regenerative periodontal surgery. Displacement, Von Mises, and principal stresses were evaluated through FEA, under moderate vertical occlusal load. Results FEA demonstrated that in the model with vertical bone loss significant tooth displacement was present, even though the clinically evident tooth mobility was absent. Biomechanical behavior and stress distribution of teeth and surrounding tissues under moderate occlusal load was much more altered in case with vertical bone loss in comparison with horizontal bone loss. Six months following the regenerative therapy, the values of all evaluated parameters were noticeable reduced. Conclusion Regenerative periodontal therapy improved the biomechanical characteristics of the affected teeth and the related periodontal structures. © 2021, Serbia Medical Society. All rights reserved.

The thyrohyoid complex and cervical spine fracture distribution patterns may reflect the knot position as the force distribution by the noose to different neck regions may vary depending on it. Recently, machine learning models (MLm) were used to classify knot position through these fractures. The contribution of aging on the fracture susceptibility is better demonstrated, but data on body weight (BW) and height (BH) significance on this is more doubtful and MLm did not consider them. A retrospectively obtained autopsy data on sex, age, BW, BH and distribution of greater hyoid bone horn (GHH), superior thyroid cartilage horn (STH), and cervical spine fractures in 368 suicidal hangings were analyzed by standard statistics to determine association of the anthropometrics (age, BW, and BH) with the fracture occurrence, and by machine learning algorithms to determine if body weight and height improved MLm classification of hanging cases with typical and atypical knot positions. In the sample, unilateral GHH fracture was significantly more common in atypical hangings, while isolated STH fractures were more common in typical hangings. Age was a predictor of GHH fractures and BW of STH fractures, but BW poorly correlated with their number. BH was not a predictor of any thyrohyoid fracture. On the ROC curve analysis, the MLm that considered BW and BH did not perform statistically better than MLm that did not consider them. The study indicates that body weight and height are of no detrimental value in assessing the thyrohyoid and cervical spine fracture patterns in suicidal hangings. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

The authors regret the second paragraph of the section 2.4.1. Machine learning algorithm models development and analyses (starting with: “The following ML models were assessed: Multilayer Perceptron Artificial Neural Network (MLP–ANN) [50], Decision Tree (DT) [51], K-Nearest Neighbors (k-NN) [52], and Naïve Bayes (NB)… and ending with: “…reported in the Results section.”) is misleading and incomplete, and requires a corrigendum to explain the exact machine learning models development, program use, and to enable results reproducibility. The paragraph should read as follows: “The following ML models were assessed: Multilayer Perceptron Artificial Neural Network (MLP–ANN) [50], Decision Tree (DT) [51], K-Nearest Neighbors (k-NN) [52], and Naïve Bayes (NB) [53,54]. The finetuning of the MLP-ANN algorithms hyperparameters was done in Matlab, in an evolutionary manner, by using the Genetic algorithm (GA) [55], that starts a model optimization from an initial guess of hyperparameters (initial population), which are used as inputs for the objective function (OF). The OF ensembles the model with respect to the current guess of hyperparameters and computers the model accuracy – which needs to be maximized [55–58]. The hyperparameters of MLP-ANN considered for GA optimization were similar as in our previous work [56]. MLP-ANN algorithms with similar, corresponding accuracies to previously mentioned, and DT, K-NN, and NB algorithms were then developed all by automatic or repeated manual hyperparameter adjustments in SPSS. The settings and performances of algorithms developed in SPSS are reported in the Results section.” Figure 3 should be interpreted in accordance with this. We are truly sorry and apologize for any inconvenience caused by the mistake. © 2024 Elsevier B.V.