Characterization of hidden rules linking symptoms and selection of acupoint using an artificial neural network model / 医学前沿

Comprehension of the medical diagnoses of doctors and treatment of diseases is important to understand the underlying principle in selecting appropriate acupoints. The pattern recognition process that pertains to symptoms and diseases and informs acupuncture treatment in a clinical setting was explored. A total of 232 clinical records were collected using a Charting Language program. The relationship between symptom information and selected acupoints was trained using an artificial neural network (ANN). A total of 11 hidden nodes with the highest average precision score were selected through a tenfold cross-validation. Our ANN model could predict the selected acupoints based on symptom and disease information with an average precision score of 0.865 (precision, 0.911; recall, 0.811). This model is a useful tool for diagnostic classification or pattern recognition and for the prediction and modeling of acupuncture treatment based on clinical data obtained in a real-world setting. The relationship between symptoms and selected acupoints could be systematically characterized through knowledge discovery processes, such as pattern identification.

Evaluation of skeletal maturity in the cervical vertebrae and hand-wrist in relation to vertical facial types / 대한치과교정학회지

OBJECTIVE@#To evaluate differences in skeletal maturity in relation to vertical facial types and to compare differences in the skeletal maturity of the cervical vertebrae and hand-wrist in females.@*METHODS@#This study included 59 females aged 7 to 9 years with skeletal Class I malocclusion. The participants were categorized into three groups (low, normal, and high) according to the mandibular plane angle. Skeletal maturity was measured using skeletal maturity indicators (SMIs) and the Tanner–Whitehouse III (TW3) method on hand-wrist radiographs and by using cervical vertebrae maturation indicators (CVMIs) on lateral cephalometric radiographs.@*RESULTS@#The SMI was higher in the high-angle group than in the low-angle group (p = 0.014). The median TW3 bone age was 11.4 months higher in the high-angle group than in the low-angle group (p = 0.032). There was no significant difference in CVMI among the three groups. Skeletal maturity showed a weakly positive correlation with the mandibular plane angle (SMI, r = 0.391; TW3, r = 0.333; CVMI, r = 0.259).@*CONCLUSIONS@#The skeletal maturity of the hand-wrist in females with a high mandibular plane angle was higher than that in females with a low mandibular plane angle. Obtaining additional hand-wrist radiographs may facilitate evaluation of skeletal maturity of females. In females with a high mandibular angle, the time to commence orthodontic treatment may be earlier than that in females with a low mandibular angle.

Effect of Food Deprivation on a Delayed Nonmatch-to-place T-maze Task

Food deprivation can affect performance on difficult cognitive task, such as the delayed nonmatch-to-place T-maze task (DNMT). The importance of food deprivation on maintaining high motivation for DNMT task has been emphasized, but not many studies have investigated the optimal conditions for depriving rodents to maximize performance. Establishing appropriate conditions for food deprivation is necessary to maintain DNMT task motivation. We applied different conditions of food deprivation (1-h food restriction vs. 1.5-g food restriction; single caging vs. group caging) and measured body weight and the number of correct choices that 8-week-old C57BL/6J mice made during the DNMT task. The 1.5-g food restriction group maintained 76.0+/-0.6% of their initial body weight, but the final body weight of the 1-h food restriction condition group was reduced to 62.2+/-0.8% of their initial body weight. These results propose that 1.5-g food restriction condition is effective condition for maintaining both body weight and motivation to complete the DNMT task.