Application of electrophysiology-based machine learning in identifying driving fatigue / 环境与职业医学

Road traffic accidents (RTA) can cause a large number of casualties and property losses. Driving fatigue is one of the important factors leading to RTA. Electrophysiological signals, as a kind of information feedback for the nervous system to regulate body functions, can reflect drivers’ fatigue state. However, there is a lack of systematic reviews on the current research on electrophysiological signals as information input of machine learning methods for driving fatigue recognition. By investigating fatigue-related literature, the current paper summarized the neural regulation mechanism of fatigue, clarified that driving fatigue is caused by both psychological and physiological loads, recognized inducing factors related to driving fatigue, and summed up electrophysiological signals now in use of driving fatigue recognition, as well as their physiological mechanisms and related indicators. Machine learning algorithms are widely used in identifying driving fatigue. Based on existing studies that used electrophysiological signals as information input source and applied various machine learning algorithms to build driving fatigue identification models, this paper compared the effectiveness of various machine learning algorithms, and described the advantages and disadvantages of supervised machine learning. It is pointed out that suitable classification algorithms should be selected according to sample conditions and model eigenvalues when applied to driving fatigue recognition. In addition, a variety of electrophysiological signals as information sources can help improve the accuracy of a fatigue recognition model, but the increase of model input eigenvalues cannot. Finally, the research progress of identification methods based on electrophysiological signals provided new opportunities for identifying driving fatigue.

Biomechanical Response of Macrophages/Microglia Cells to Blast Shock Injury in Mice / 医用生物力学

Objective To establish a blast injury experimental model using a shock tube at lateral lying position of C57BL/6 mice, investigate biomechanical responses of macrophages/microglia cells in the heart, lung and brain tissues to mechanical damage by shock wave within 24 hours. Methods Shock tube was employed to generate a shock wave to C57BL/6 mice. Firstly, the weight changes of mice were measured at different time points after the shock. Then the cardiac, pulmonary and whole brain tissue samples were dissected after anesthesia. Pathological sections were stained with HE staining to detect structural damage; the TUNEL staining method was used to mark and count the proportion of dead cells in each tissue. Microglial cells were labeled with fluorescent antibody, while responses and changes of macrophages/microglia after shock loading were analyzed. Results The shock tube exerted 179 kPa overpressure shock wave upon sideway of the mouse, and lethal rate of the mouse was 3.33%. Compared with normal control group, the mice in experimental group had a significant weight loss within 24 hours after loading shock. Pathological sections showed rupture of lung tissues after shock, accompanied by alveolar protein deposition, pulmonary bulla and other diseases. Fluorescence staining showed that lung tissue was recruited and activated in a large amount within 24 hours. The proportion of dead cells cleared rebounded to normal level within 24 hours. The heart was highly tolerant to shock, and macrophages appeared near the large blood vessels. The brain showed unilateral aggregation of microglia due to the impact posture, mainly due to prolonged inflammation and a higher proportion of dead cells at the junction of gray and white matter. Conclusions A blast shock model at lateral lying position of the mouse was established. Within 24 hours, macrophages/microglia were recruited quickly to the injury site after being impacted, which mediated strong immune stress, and might participate in the immune response to trigger a second long-term inflammatory injury. The results of the study provide experimental basis for the evaluation of primary impact injury, such as dose-effect relationship and tissue damage difference.

Time-dependent expression of FZD4 in contused skeletal muscle of rat used for wound age estimation / 中国法医学杂志

Objective Take frizzled class receptor 4(FZD4) as an example for exploring whether the transmembrane receptor protein is a suitable marker for wound age estimation. Methods A total of 78 Sprague-Dawley rats were divided randomly into the control group and the contusion groups of 4h, 8h, 12h, 16h, 20h, 24h, 28h, 32h, 36h, 40h, 44h, and 48h after injury (n=6). Using a drop-ball technique, a contusion was produced in the right lamb of rats. The samples were dissected from injury zones. Then the expression of FZD4 was detected using immunofluorescence, real-time PCR and western blot, respectively. Results FZD4 was located on the membrane of skeletal muscle cells. Compared to the control group, FZD4 mRNA showed a signiifcant increase (over 2-fold) in 8h, 12h, 36h, and 40h after injury by Real-time PCR (P<0.05), and FZD4 protein showed a statistical up-regulation (less than 2-fold) in 8h, 36h, 40h, 44h, and 48h post contusion by western blotting (P<0.05). Conclusion The expression of FZD4 mRNA and protein are both time-dependent during contused skeletal muscle repair. To some degree, FZD4 mRNA was more suitable than corresponding protein for determining wound age.

Expression of SFRP5 mRNA in Rat Skeletal Muscle after Contusion / 法医学杂志

Objective T o investigate the relationship betw een the expression of secreted frizzled-related protein 5 (SFR P5) m RNA and the tim e interval after skeletal m uscle injury in rats by real-tim e PC R . Methods A total of ninety SD rats w ere random ly divided into the contusion groups at different tim es including 4 h, 8 h, 12 h, 16 h, 20 h, 24 h, 28 h, 32 h, 36 h, 40 h, 44 h, 48 h after contusion, incision groups at different tim es including 4h and 8h after incision and the control group. T he sam ples w ere taken from the contused zone at different tim e points. T he total RNA w as isolated from the sam ples and re-versely transcribed to analyze the expression levels of SFRP5 m RNA . Results C om pared to the control group, the expression of SFRP5 m RNA in contusion groups w ere dow n-regulated w ithin 48 h after con-tusion and reached the low est level at 20 h, and the expression of SFRP5 m RNA gradually increased from 20 h to 48 h after contusion. T he expression of SFRP5 m RNA in the incised groups w ere signifi-cantly low er than that of the contusion groups at 4 h after injury. A t the tim e of 8 h, the expression levels betw een the contusion and incision groups show ed no statistically significant difference. Conclusion It is suggested that SFRP5 m RNA analysis m ay show regular expression and can be a m arker for estim ation of skeletal m uscle injury age.