Age Classification in Forensic Medicine Using Machine Learning Techniques.

The aim of the study was to assess the capabilities of age determination (age group) at death using classification techniques by histomorphometric characteristics of osseous and cartilaginous tissue aging. Materials and Methods: The study material was a database containing the findings of morphometric researches of osseous and cartilaginous tissue histologic specimens from 294 categorized male corpses aged 10-93 years. For data analysis and classification we used modern machine learning methods: k-NN, SVM, logistic regression, CatBoost, SGD, naive Bayes, random forest, nonlinear dimensionality reduction methods (t-SNE and uMAP), and recursive feature elimination for feature selection. Results: The used techniques (algorithms) provided effective representation of a complex data set (76 histomorphometric features), allowing to reveal the cluster structure inside the low dimensional feature space, thus fitting the classifier becomes even more reasonable. During feature selection, we estimated their importance for age group classification and studied the relationship between classification quality and the number of features inside the feature space. Data pre-processing made it possible to get rid of noise and keep most informative features, thereby accelerating a learning process and improving the classification quality. Data projection showed more well-defined cluster structure in the space of selected features. The accuracy of establishing certain groups was equal to 90%. It proves high efficiency of machine learning techniques used for forensic age diagnostics based on histomorphometric findings.

Age-related changes in cationic compositions of human cranial base bone apatite measured by X-ray energy dispersive spectroscopy (EDS) coupled with scanning electron microscope (SEM).

One of the most common scientific methods to study the chemical composition of bone matter is energy-dispersive X-ray spectroscopy (EDS). However, interpretation of the data obtained can be quite complicated and require a thorough understanding of bone structure. This is especially important when evaluating subtle changes of chemical composition, including the age-related ones. The aim of current study is to create a method of processing the obtained data that can be utilized in clinical medicine and use it to evaluate the age evolution of bone chemical composition. To achieve this goal, an elemental composition of 62 samples of cadaver compact bone, taken from the skull base (age: Me = 57.5; 21/91(min/max); Q1 = 39.5, Q3 = 73.75), was studied with EDS. We used the original method to estimate the amount of Mg2+ cations. We detected and confirmed an increase of Mg2+ cation formula amount in the bone apatite, which characterizes age-related resorption rate. Analysis of cation estimated ratio in a normative bone hydroxylapatite showed an increase of Mg2+ amount (R = 0.43, p = 0.0005). Also, Ca weight fraction was shown to decrease with age (R = - 0.43, p = 0.0005), which in turn confirmed the age-dependent bone decalcification. In addition, electron probe microanalysis (EPMA) and X-ray diffraction analysis (XRD) were performed. EDS data confirmed the EPMA results (R = 0.76, p = 0.001). In conclusion, the proposed method can be used in forensic medicine and provide additional data to the known trends of decalcification and change of density and crystallinity of mineral bone matter.

A full Bayesian calibration model for assessing age in adults by means of pulp/tooth area ratio in periapical radiography.

The Bayesian approach is being a fundamental tool in forensic and legal field where inferences and decisions are made. In this study, a full Bayesian calibration model was developed to make probabilistic inferences about age estimation in a reference sample of 891 periapical X-rays of upper and lower canines. These teeth belonged to both deceased and living adult subjects, aged between 20 and 86 years, coming from five different countries (Turkey, Italy, Portugal, Japan and Mexico). For this purpose, the narrowing of pulp chamber due to the apposition of secondary dentine was analysed by means of the pulp/tooth area ratio. To determine the agreement of the method, intra- and inter-observer differences for measuring process were calculated by means of the intraclass correlation coefficient (ICC) analysis. Observer error tests showed excellent agreement between observers and between repeated assessments. According to the results of the ANCOVA, neither nationality nor sex was associated to the secondary dentine apposition while it is associated with individual's age. The results of the present study indicated that the concept of probability is intrinsically linked to the assessment of age in a forensic context, and the Bayesian approach could be considered a robust tool to overtake the bias generated by traditional regression models, thus helping the decision-making process in a legal framework.

[Histometric symptoms of age-sensitive changes of bone tissue.]

The study presents the results of a complex histomorphometric research of the features of the age-related dynamics of bone tissue. As a study material we used samples of the distal epiphysis and diaphysis of the left tibia from 348 corpses of males with a known age from 0 to 90 years. A group of microosteometric features, that have the strongest correlation with age, is established in different age groups; their quantitative characteristics are given. It is clarified that the trends of age-related changes in the structural components of bone tissue correspond to the basic patterns of growth, remodeling, depend on the species and their localization. Conceptual positions of age involution of bone tissue are proposed.

Sudden death in cancer pathology forensic-medical characteristics.

The article presents a review of references on causes of sudden death of persons suffering from oncological diseases. The paper describes the main mechanisms of sudden death of persons with cancer who are subjected to forensic-medical research. Data on the structure of sudden death for the last 10 years are demonstrated. The authors have identified the increase of a number of sudden deaths in the group with oncological pathology 2. 2 times more in comparison with 2005. There are showed peculiarities of forensic-medical diagnostics of reasons of sudden death in cancer.

Cholinergic innervation of the endocrine cells of the blood vessels of the human brain.

In an immunochemical study of the melanocytes of the brain blood vessels in man, the presence of vasopressin has been demonstrated. The endings of cholinergic axons terminate on the surface of these cells. It is assumed that the melanocytes participate in regulation of the motility of the arteries of the brain.

Catecholamines and indolalkylamines of the pia mater and spinal cord in vertebrates.

Fluorimetric methods were used to determine adrenaline, dopamine, noradrenaline, serotonin and tryptamine in the pia mater of the brain and spinal cord of various vertebrates (fishes, birds, mammals) and of man. The histochemical method using glyoxylic acid showed the presence of biogenic monoamines in adrenergic nerve fibres and in the monoaminocytes. Their total amount in the pia mater is roughly the same, except in man, in whom it is significantly lower. From the higher adrenergic axon concentration on the one hand and the lower number of monoaminocytes on the other, it can be concluded that the neuronal factor has a more important role in the regulation of brain haemodynamics in man.