Machine Learning Models for Prediction of Sex Based on Lumbar Vertebral Morphometry.

BACKGROUND: Identifying skeletal remains has been and will remain a challenge for forensic experts and forensic anthropologists, especially in disasters with multiple victims or skeletal remains in an advanced stage of decomposition. This study examined the performance of two machine learning (ML) algorithms in predicting the person's sex based only on the morphometry of L1-L5 lumbar vertebrae collected recently from Romanian individuals. The purpose of the present study was to assess whether by using the machine learning (ML) techniques one can obtain a reliable prediction of sex in forensic identification based only on the parameters obtained from the metric analysis of the lumbar spine. METHOD: This paper built and tuned predictive models with two of the most popular techniques for classification, RF (random forest) and XGB (xgboost). Both series of models used cross-validation and a grid search to find the best combination of hyper-parameters. The best models were selected based on the ROC_AUC (area under curve) metric. RESULTS: The L1-L5 lumbar vertebrae exhibit sexual dimorphism and can be used as predictors in sex prediction. Out of the eight significant predictors for sex, six were found to be particularly important for the RF model, while only three were determined to be important by the XGB model. CONCLUSIONS: Even if the data set was small (149 observations), both RF and XGB techniques reliably predicted a person's sex based only on the L1-L5 measurements. This can prove valuable, especially when only skeletal remains are available. With minor adjustments, the presented ML setup can be transformed into an interactive web service, freely accessible to forensic anthropologists, in which, after entering the L1-L5 measurements of a body/cadaver, they can predict the person's sex.

The Vital Role of Thanatochemistry in the Postmortem Diagnostic of Diabetic Ketoacidosis-Case Report.

Diabetic ketoacidosis (DKA) is a lethal acute hyperglycemic complication of diabetes mellitus (DM) and it represents the initial manifestation of DM in about 15-20% of cases in adults and about 30-40% of cases in children. Postmortem diagnosis of DKA can only be made by applying thanatochemistry. Biochemistry applied postmortem is viewed with skepticism by many practitioners in the forensic field, completely lacking in many forensic services around the world, and especially in the national ones. This article aims to underline the importance of the postmortem application of biochemistry by reviewing the case of a person in the third decade of life who died suddenly at home due to diabetic ketoacidosis (DKA), whose autopsy was performed at an early PMI of approximately 24 h. Routine postmortem examinations (macroscopic, anatomopathological, and toxicological) could not establish a clear cause of death. When attention was turned to biochemical determinations (i.e., determination of glycated hemoglobin, glucose and ketone bodies (acetone, beta-hydroxybutyrate) in the blood, vitreous humor, and cerebrospinal fluid), the identified values clarified the thanatogenic mechanisms by establishing the diagnosis of DKA.

Toxic Blood Hydrogen Cyanide Concentration as a Vital Sign of a Deceased Room Fire Victim-Case Report.

Carbon monoxide (CO) and hydrogen cyanide (HCN) are two common toxic products of combustion. HCN concentrations of fire victims are not routinely determined in most legal medicine services in Romania. We present the case of a room fire victim in which we evaluated the concentrations of HCN and carboxyhemoglobin (COHb), their contribution to the mechanism of death, and the possibility that HCN concentration can be interpreted as vital sign. COHb was determined by spectrophotometry. HCN was spectrophotometrically determined with ninhydrin in postmortem blood samples after its removal with 20% phosphoric acid and uptake into a solution of potassium carbonate. The presence of ethyl alcohol was determined by gas chromatography. The COHb concentration was 6.15%, while the blood HCN concentration was 1.043 µg × mL-1 and the total HCN was 1.904 µg × ml-1. A blood alcohol content of 4.36 g‰ and a urine alcohol content of 5.88 g‰ were also found. Although the fire produced a considerable amount of soot, and there were signs of inhalation of soot particles, the COHb level cannot be interpreted as a vital sign. Toxic concentrations of HCN and total HCN can be interpreted as a vital sign and indicates a contributive effect of HCN in the mechanism of death.

Hydrogen cyanide and carboxyhemoglobin assessment in an open space fire-related fatality.

Hydrogen cyanide (HCN) can be a major contributory factor in death from fire-related inhalation injury. Although carbon monoxide (CO) is considered the lethal agent of smoke in fires, its liability as a cause of death is sometimes debatable. The purpose of this report is to present the case of an 80-year-old man with locomotor disabilities who died due to an open space fire of vegetation debris and household waste in his yard. We evaluated here the concentrations of HCN and carboxyhemoglobin (COHb) and their contribution to the mechanism of death. In addition, the risk factors and the contributing effect of the factors that compose the complex toxic environment that develops in fires were discussed. COHb was determined by spectrophotometry as recommended by Katsumata et al. in 1982. HCN was determined with ninhydrin in postmortem blood samples after removal with 20% phosphoric acid and capture in a potassium carbonate solution. A toxic concentration of 1.3 µg ml-1 HCN and a lethal COHb level of 73.7% were determined in the blood samples. Although death was mainly attributed to CO poisoning and extremely severe burns in this open space burning case, the additive effect of HCN in the mechanism of death was also highlighted. The results suggested the possibility that the man's clothing may have played an important role in the production of HCN in this open space fire, as well as other types of garbage that were burned.