MRI-based machine learning model: A potential modality for predicting cognitive dysfunction in patients with type 2 diabetes mellitus.

Background: Type 2 diabetes mellitus (T2DM) is a crucial risk factor for cognitive impairment. Accurate assessment of patients' cognitive function and early intervention is helpful to improve patient's quality of life. At present, neuropsychiatric screening tests is often used to perform this task in clinical practice. However, it may have poor repeatability. Moreover, several studies revealed that machine learning (ML) models can effectively assess cognitive impairment in Alzheimer's disease (AD) patients. We investigated whether we could develop an MRI-based ML model to evaluate the cognitive state of patients with T2DM. Objective: To propose MRI-based ML models and assess their performance to predict cognitive dysfunction in patients with type 2 diabetes mellitus (T2DM). Methods: Fluid Attenuated Inversion Recovery (FLAIR) of magnetic resonance images (MRI) were derived from 122 patients with T2DM. Cognitive function was assessed using the Chinese version of the Montréal Cognitive Assessment Scale-B (MoCA-B). Patients with T2DM were separated into the Dementia (DM) group (n = 40), MCI group (n = 52), and normal cognitive state (N) group (n = 30), according to the MoCA scores. Radiomics features were extracted from MR images with the Radcloud platform. The variance threshold, SelectKBest, and least absolute shrinkage and selection operator (LASSO) were used for the feature selection. Based on the selected features, the ML models were constructed with three classifiers, k-NearestNeighbor (KNN), Support Vector Machine (SVM), and Logistic Regression (LR), and the validation method was used to improve the effectiveness of the model. The area under the receiver operating characteristic curve (ROC) determined the appearance of the classification. The optimal classifier was determined by the principle of maximizing the Youden index. Results: 1,409 features were extracted and reduced to 13 features as the optimal discriminators to build the radiomics model. In the validation set, ROC curves revealed that the LR classifier had the best predictive performance, with an area under the curve (AUC) of 0.831 in DM, 0.883 in MIC, and 0.904 in the N group, compared with the SVM and KNN classifiers. Conclusion: MRI-based ML models have the potential to predict cognitive dysfunction in patients with T2DM. Compared with the SVM and KNN, the LR algorithm showed the best performance.

Impact of time on ultrasonic cavitation peening via detection of surface plastic deformation.

During ultrasonic cavitation peening, bubbles repeatedly form and collapse, which leads to high impact loads on the treated surface. At the initial stage of ultrasonic cavitation peening, the most obvious change is plastic deformation instead of mass loss on the treated specimen surface. Meanwhile the plastic deformation is beneficial for mechanical surface properties. As the cavitation exposure time increases, erosion and damage are inflicted on the metal surface due to the increase in the number of collapse events. In this respect, the treatment time is a key parameter to improve the specimen surface properties during this manufacturing process. However, the influence of treatment time on the surface properties has not yet been thoroughly investigated. In this paper, it is the first time to utilize the plastic deformation to evaluate the optimal treatment time at different input power. The plastic deformation can be deduced by the mass loss and the volume change on the treated specimen surface. Using plastic deformation, the modification of surface hardness and roughness are investigated at different cavitation exposure intervals and vibration amplitudes. It is found that significant improvement of the microhardness on the treated surface occurs at the end of incubation period. Higher vibration amplitudes of the horn tip lead to shorter incubation period and higher microhardness.

Effect of occlusal splints for the management of patients with myofascial pain: a randomized, controlled, double-blind study.

BACKGROUND: Occlusal splints have been the preferred modalities in the management of myofascial temporomandibular disorders (TMDs), but now controversy exists in reporting whether they are successful for TMDs treatments. The aim of this study was to give objective evidence to the assessment of treatment effect of occlusal splints for myofascial TMDs patients by clinical assessments and surface electromyography (sEMG) measurements of masseter muscles (MM). METHODS: Thirty-six patients (12 males and 24 females) aged 16 - 57 (38 ± 11) years participated in the study. All participants diagnosed with myofascial TMD were randomized into two groups (18 of each). Patients in the first group (A) were treated with occlusal splints for 1 month, while patients in the second group (B) were treated with placebo (non-occluding palatal) splints. Clinical assessments were performed at the beginning of the study and 1 month after treatment. sEMG measurements for MM were performed at mandibular postural position (MPP) and maximum intercuspal contacted position (ICP) 1 month after the treatment. The root mean square (RMS) and the median frequency (MF) as linear indices of sEMG data were used to demonstrate muscle activity and muscle fatigue. Data were analyzed by ANOVA and post hoc SNK test. The differences were considered significant at P < 0.05. RESULTS: It was found that 89% of group A either completely recovered (39%) or clinically improved (50%), while only 22% of group B had a spontaneous improvement. sEMG analysis showed that at MPP, the mean of RMS value of MM in group A was lower than that of group B, which shows statistical differences (P < 0.01). At ICP, the RMS value of MM in group A was higher than that of group B, which shows statistical differences (P < 0.01). At MPP, MF value of MM in group A was higher than that of group B (P < 0.05). At ICP, MF value of MM was lower than that of group B (P < 0.01). CONCLUSIONS: Occlusal splint could eliminate or improve the signs and symptoms of TMD patients with myofascial pain. sEMG analysis indicates that the wearing of occlusal splints may reduce the degree of fatigue of the masticatory muscles. The splint therapy outcome has a correlation with the electromyographic changes in the masticatory muscles.

[Differentiation and functional expression of highly purified osteoclast-like cells in vitro].

OBJECTIVE: To establish a culture method for a large amount of highly purified osteoclast-like cells in vitro. To investigate the gene expression of some osteoclast marker enzymes. To lay the foundation for the further study of the signal path on the differentiation and formation of osteoclast-like cells. METHODS: The bone marrow mononuclear cells of rat were treated with 30 ng/mL macrophagecolony-stimulating factor (M-CSF) and 50 ng/mL receptor activator of NF-kappaB ligand (RANKL) and cultured for 6 days. After culturing, cells were evaluated by morphology observation, tartrate-resistant acid phosphatase (TRAP) staining, Giemsa staining, pit staining, and the gene expression of some osteoclast marker enzymes. RESULTS: The TRAP-positive mononuclear cells were more frequently observed than the multinucleated cells and pit staining could be seen on the dentine slice. The transcription expression of TRAP, matrix metalloproteinase-9 (MMP-9), membrane-type1-matrix metalloproteinase (MT1-MMP) and cathepsin K were detected by RT-PCR. CONCLUSION: The cooperation of M-CSF and RANKL could induce a large amount of highly purified osteoclast-like cells formation in rat bone marrow culture. The typical characteristics of osteoclast-like cells were demonstrated and the enriched osteoclast-like cells expressed TRAP, MMP-9, MT1-MMP and cathepsin K.