Transcranial direct current stimulation (TDCS) is a clinically safe and effective method of delivering weak electric current to modulate cortical activities. And based on the cumulating scientific evidences, the method is recommended to treat major depressive disorder (MDD) and other psychiatric disorders. In this paper, we review the development of TDCS in the rising field of neuromodulation. Then with suggested biochemical and physical mechanism of TDCS, we summarize the reported cases of using TDCS to alleviate major neuropsychiatric disorders. And, in particular, the treatment of MDD is highlighted as an illustrative example of using TDCS. We discuss here the therapeutic potentials of this method in psychiatry. And in closing remarks, we evaluate the current technical limitations and suggest the future directions of this method in both the clinical and research aspects.
Depressive Disorder, Major ; Methods ; Transcranial Direct Current Stimulation

Purpose: Accurate prediction of blood glucose variability is crucial for effective diabetes management, as both hypoglycemia and hyperglycemia are associated with increased morbidity and mortality. However, conventional predictive models rely primarily on patient-specific biometric data, often neglecting the influence of patient–provider interactions, which can significantly impact outcomes. This study introduces Cyclic Dual Latent Discovery (CDLD), a deep learning framework that explicitly models patient–provider interactions to improve prediction of blood glucose levels. By leveraging a real-world intensive care unit (ICU) dataset, the model captures latent attributes of both patients and providers, thus improving forecasting accuracy. Methods: ICU patient records were obtained from the MIMIC-IV v3.0 critical care database, including approximately 5,014 instances of patient–provider interaction. The CDLD model uses a cyclic training mechanism that alternately updates patient and provider latent representations to optimize predictive performance. During preprocessing, all numeric features were normalized, and extreme glucose values were capped at 500 mg/dL to mitigate the effect of outliers. Results: CDLD outperformed conventional models, achieving a root mean square error of 0.0852 on the validation set and 0.0899 on the test set, which indicates improved generalization. The model effectively captured latent patient–provider interaction patterns, yielding more accurate glucose variability predictions than baseline approaches. Conclusion Integrating patient–provider interaction modeling into predictive frameworks can increase blood glucose prediction accuracy. The CDLD model offers a novel approach to diabetes management, potentially paving the way for artificial intelligence-driven personalized treatment strategies.

Purpose: Accurate prediction of blood glucose variability is crucial for effective diabetes management, as both hypoglycemia and hyperglycemia are associated with increased morbidity and mortality. However, conventional predictive models rely primarily on patient-specific biometric data, often neglecting the influence of patient–provider interactions, which can significantly impact outcomes. This study introduces Cyclic Dual Latent Discovery (CDLD), a deep learning framework that explicitly models patient–provider interactions to improve prediction of blood glucose levels. By leveraging a real-world intensive care unit (ICU) dataset, the model captures latent attributes of both patients and providers, thus improving forecasting accuracy. Methods: ICU patient records were obtained from the MIMIC-IV v3.0 critical care database, including approximately 5,014 instances of patient–provider interaction. The CDLD model uses a cyclic training mechanism that alternately updates patient and provider latent representations to optimize predictive performance. During preprocessing, all numeric features were normalized, and extreme glucose values were capped at 500 mg/dL to mitigate the effect of outliers. Results: CDLD outperformed conventional models, achieving a root mean square error of 0.0852 on the validation set and 0.0899 on the test set, which indicates improved generalization. The model effectively captured latent patient–provider interaction patterns, yielding more accurate glucose variability predictions than baseline approaches. Conclusion Integrating patient–provider interaction modeling into predictive frameworks can increase blood glucose prediction accuracy. The CDLD model offers a novel approach to diabetes management, potentially paving the way for artificial intelligence-driven personalized treatment strategies.

Purpose: Accurate prediction of blood glucose variability is crucial for effective diabetes management, as both hypoglycemia and hyperglycemia are associated with increased morbidity and mortality. However, conventional predictive models rely primarily on patient-specific biometric data, often neglecting the influence of patient–provider interactions, which can significantly impact outcomes. This study introduces Cyclic Dual Latent Discovery (CDLD), a deep learning framework that explicitly models patient–provider interactions to improve prediction of blood glucose levels. By leveraging a real-world intensive care unit (ICU) dataset, the model captures latent attributes of both patients and providers, thus improving forecasting accuracy. Methods: ICU patient records were obtained from the MIMIC-IV v3.0 critical care database, including approximately 5,014 instances of patient–provider interaction. The CDLD model uses a cyclic training mechanism that alternately updates patient and provider latent representations to optimize predictive performance. During preprocessing, all numeric features were normalized, and extreme glucose values were capped at 500 mg/dL to mitigate the effect of outliers. Results: CDLD outperformed conventional models, achieving a root mean square error of 0.0852 on the validation set and 0.0899 on the test set, which indicates improved generalization. The model effectively captured latent patient–provider interaction patterns, yielding more accurate glucose variability predictions than baseline approaches. Conclusion Integrating patient–provider interaction modeling into predictive frameworks can increase blood glucose prediction accuracy. The CDLD model offers a novel approach to diabetes management, potentially paving the way for artificial intelligence-driven personalized treatment strategies.

Purpose: Accurate prediction of blood glucose variability is crucial for effective diabetes management, as both hypoglycemia and hyperglycemia are associated with increased morbidity and mortality. However, conventional predictive models rely primarily on patient-specific biometric data, often neglecting the influence of patient–provider interactions, which can significantly impact outcomes. This study introduces Cyclic Dual Latent Discovery (CDLD), a deep learning framework that explicitly models patient–provider interactions to improve prediction of blood glucose levels. By leveraging a real-world intensive care unit (ICU) dataset, the model captures latent attributes of both patients and providers, thus improving forecasting accuracy. Methods: ICU patient records were obtained from the MIMIC-IV v3.0 critical care database, including approximately 5,014 instances of patient–provider interaction. The CDLD model uses a cyclic training mechanism that alternately updates patient and provider latent representations to optimize predictive performance. During preprocessing, all numeric features were normalized, and extreme glucose values were capped at 500 mg/dL to mitigate the effect of outliers. Results: CDLD outperformed conventional models, achieving a root mean square error of 0.0852 on the validation set and 0.0899 on the test set, which indicates improved generalization. The model effectively captured latent patient–provider interaction patterns, yielding more accurate glucose variability predictions than baseline approaches. Conclusion Integrating patient–provider interaction modeling into predictive frameworks can increase blood glucose prediction accuracy. The CDLD model offers a novel approach to diabetes management, potentially paving the way for artificial intelligence-driven personalized treatment strategies.

Purpose: Accurate prediction of blood glucose variability is crucial for effective diabetes management, as both hypoglycemia and hyperglycemia are associated with increased morbidity and mortality. However, conventional predictive models rely primarily on patient-specific biometric data, often neglecting the influence of patient–provider interactions, which can significantly impact outcomes. This study introduces Cyclic Dual Latent Discovery (CDLD), a deep learning framework that explicitly models patient–provider interactions to improve prediction of blood glucose levels. By leveraging a real-world intensive care unit (ICU) dataset, the model captures latent attributes of both patients and providers, thus improving forecasting accuracy. Methods: ICU patient records were obtained from the MIMIC-IV v3.0 critical care database, including approximately 5,014 instances of patient–provider interaction. The CDLD model uses a cyclic training mechanism that alternately updates patient and provider latent representations to optimize predictive performance. During preprocessing, all numeric features were normalized, and extreme glucose values were capped at 500 mg/dL to mitigate the effect of outliers. Results: CDLD outperformed conventional models, achieving a root mean square error of 0.0852 on the validation set and 0.0899 on the test set, which indicates improved generalization. The model effectively captured latent patient–provider interaction patterns, yielding more accurate glucose variability predictions than baseline approaches. Conclusion Integrating patient–provider interaction modeling into predictive frameworks can increase blood glucose prediction accuracy. The CDLD model offers a novel approach to diabetes management, potentially paving the way for artificial intelligence-driven personalized treatment strategies.

OBJECTIVES: The primary objective of this study was to determine if the number of missing teeth could be predicted by oral disease pathogens, and the secondary objective was to assess whether deep learning is a better way of predicting the number of missing teeth than multivariable linear regression (MLR).METHODS: Data were collected through review of patient’s initial medical records. A total of 960 participants were cross-sectionally surveyed. MLR analysis was performed to assess the relationship between the number of missing teeth and the results of real-time PCR assay (done for quantification of 11 oral disease pathogens). A convolutional neural network (CNN) was used as the deep learning model and compared with MLR models. Each model was performed five times to generate an average accuracy rate and mean square error (MSE). The accuracy of predicting the number of missing teeth was evaluated and compared between the CNN and MLR methods.RESULTS: Model 1 had the demographic information necessary for the prediction of periodontal diseases in addition to the red and the orange complex bacteria that are highly predominant in oral diseases. The accuracy of the convolutional neural network in this model was 65.0%. However, applying Model 4, which added yellow complex bacteria to the total bacterial load, increased the expected extractions of dental caries to 70.2%.On the other hand, the accuracy of the MLR was about 50.0% in all models. The mean square error of the CNN was considerably smaller than that of the MLR, resulting in better predictability.CONCLUSIONS: Oral disease pathogens can be used as a predictor of missing teeth and deep learning can be a more accurate analysis method to predict the number of missing teeth as compared to MLR.
Bacteria ; Bacterial Load ; Citrus sinensis ; Dental Caries ; Hand ; Learning ; Linear Models ; Medical Records ; Methods ; Periodontal Diseases ; Periodontitis ; Pilot Projects ; Real-Time Polymerase Chain Reaction ; Tooth

The upper lip is a functionally and aesthetically important area of the face. Therefore, reconstruction of an upper lip defect needs sufficient consideration to ensure functional and aesthetic recovery. Several methods, such as wedge resection, rotation flaps, advancement flaps, and myomucosal advancement flaps, have been used to reconstruct vermilion defects. However, it is challenging to reconstruct a vermilion defect because of the possibility of residual asymmetry or scars and restrictions to normal lip movement after the reconstruction. We present the case of a 51-year-old female that had an upper lip vermilion defect caused by a dog bite. The lip defect was reconstructed using a mucosal V-Y advancement flap. This mucosal flap was based on the orbicularis oris muscle with a branch of the superior labial artery to ensure sufficient blood supply. Therefore, flap survival was excellent, and there was no constriction of the flaps. Moreover, the color and contour were matched to the adjacent lip tissue, and re-establishment of the white roll and adequate lip volume were achieved. This mucosal V-Y advancement flap technique represents a reliable method to repair mucosal defects without vascular compromise of the flap.

Objectives: Botulinum toxin type A (BTX), a powerful neurotoxin, can be an effective treatment choice for diverse muscular disorders and can reduce abnormal muscle activities. Abnormal movements of the mandible can be caused by involuntary and uncontrolled contractions of the lateral pterygoid muscle (LP) in various pathological situations. Previous reports have shown that BTX can reduce abnormal contractions of the LP. However, needle placement into the LP for BTX injection requires skill, experience, and sufficient anatomical knowledge. To place the needle precisely into the LP, ultrasonography (USG) can be used as an effective needle-guidance modality. USG is a non-invasive imaging modality able to create real-time imageswithout any potential risks, including radiation exposure. Patients and Methods: The patients who had been performed USG-guided BTX injection into the LP using an intraoral approach were included in this study with a literature review and case presentations. Using the USG, four patients received BTX injections to treat recurrent temporomandibular dislocation and oromandibular dystonia resulting from involuntary LP activity.Result: Involuntary movements of the mandible were improved successfully in all patients, and showed satisfactory results without significant complication. Conclusion The intraoral approach could prevent potential complications during needle placement. USG-guided BTX injection is an effective, con-venient, and safe method that provides real-time imaging without unnecessary pain to the patient.

Background: The purpose of this study was to evaluate the pattern of predicted interosseous interference and to determine the influencing factor to volume of bony interference using a computer-assisted simulation system. This retrospective study recruited 116 patients with mandibular prognathism who had undergone sagittal split ramus osteotomy (SSRO) with or without maxillary osteotomy. The patients were divided into 3 groups accord‑ ing to the amount of menton (Me) deviation: less than 2 mm (Group 1), 2–4 mm (Group 2), and more than 4 mm (Group 3). Changes in the distal segments following BSSRO and the volume of the interosseous interference between the proximal and distal segments were simulated after matching preoperative occlusion and postoperative expected occlusion with the cone-beam computed tomography data. Ramal inclinations and other skeletal measure‑ ments were analyzed before surgery, immediately after surgery, and at least 6 months after surgery. Results: The anticipated interosseous interference was more frequently noted on the contralateral side of chin deviation (long side) than the deviated site (short side) in Groups 2 and 3. More interference volume was predicted at the long side (186 ± 343.9 ­mm 3 ) rather than the short side (54.4 ± 124.4 ­mm 3 ) in Group 3 (p = 0.033). The bilateral difference in the volume of the interosseous interference of the osteotomized mandible was significantly correlated with the Me deviation (r = − 0.257, p = 0.009) and bilateral ramal inclination (r= 0.361, p < 0.001). The predictor variable that affected the volume of the osseous interference at each side was the amount of Me deviation (p = 0.010). Conclusion By using the 3D simulation system, the potential site of bony collision could be visualized and success‑ fully reduced intraoperatively. Since the osseous interference can be existed on any side, unilaterally or bilaterally, 3D surgical simulation is necessary before surgery to predict the osseous interference and improve the ramal inclination.