Effectiveness of remote monitoring and feedback on objective compliance with a mandibular advancement device for treatment of obstructive sleep apnea.

Compliance with a mandibular advancement device is important for the optimal treatment of obstructive sleep apnea. Recent advances in information and communication technology-based monitoring and intervention for chronic diseases have enabled continuous monitoring and personalized management. Self-evaluation and self-regulation through objective monitoring and feedback may improve compliance. The aim of this study was to evaluate the effects of information and communication technology-based remote monitoring and feedback services, using a smartphone application, on the objective compliance with a mandibular advancement device in patients with obstructive sleep apnea. Forty individuals who were diagnosed with obstructive sleep apnea by polysomnography were randomly assigned to groups A and B. During an initial 6-week evaluation period, the mandibular advancement device-wearing time was monitored with the smartphone application in group B, but not in group A. The two groups then switched the monitoring procedures during the second 6-week period (the smartphone application was then used by group B, but not by group A). If no input data were indicated on the cloud server of the smartphone application during the monitored period, push notifications were provided twice daily. Objective compliance, monitored by a micro-recorder within the mandibular advancement device, was noted and compared based on whether the monitoring service was provided. The number of mandibular advancement device-wearing days was significantly higher in the monitored period than in the unmonitored period. The mandibular advancement device-wearing time did not differ significantly between the two groups. In conclusion, information and communication technology-based remote monitoring and feedback services demonstrated a potential to increase the objective measures of compliance with mandibular advancement devices.

Application of Machine Learning to Identify Clinically Meaningful Risk Group for Osteoporosis in Individuals Under the Recommended Age for Dual-Energy X-Ray Absorptiometry.

Dual-energy X-ray absorptiometry (DXA) is the gold standard for diagnosing osteoporosis; it is generally recommended in men ≥ 70 and women ≥ 65 years old. Therefore, assessment of clinical risk factors for osteoporosis is very important in individuals under the recommended age for DXA. Here, we examine the diagnostic performance of machine learning-based prediction models for osteoporosis in individuals under the recommended age for DXA examination. Data of 2210 men aged 50-69 and 1099 women aged 50-64 obtained from the Korea National Health and Nutrition Examination Survey IV-V were analyzed. Extreme gradient boosting (XGBoost) was used to find relevant clinical features and applied to three machine learning models: XGBoost, logistic regression, and a multilayer perceptron. For the prediction of osteoporosis, the XGBoost model using the top 20 features extracted from XGBoost showed the most reliable performance with area under the receiver operating characteristic curve (AUROC) of 0.73 and 0.79 in men and women, respectively. We compared the diagnostic accuracy of the Shapley additive explanation values based on a risk-score model obtained from XGBoost and conventional osteoporosis risk assessment tools for prediction of osteoporosis using optimal cut-off values for each model. We observed that a cut-off risk score of ≥ 28 in men and ≥ 47 in women was optimal to classify a positive screening for osteoporosis (an AUROC of 0.86 in men and 0.91 in women). The XGBoost-based osteoporosis-prediction model outperformed conventional risk assessment tools. Therefore, machine learning-based prediction models are a more suitable option than conventional risk assessment methods for screening osteoporosis in individuals under the recommended age for DXA examination.

Simple oral exercise with chewing gum for improving oral function in older adults.

BACKGROUND: As general and oral health are closely interrelated, promoting oral health may extend a healthy life expectancy. AIMS: To evaluate the long-term effects of simple oral exercise (SOE) and chewing gum exercise on mastication, salivation, and swallowing function in adults aged ≥ 65 years. METHODS: Ninety-six participants were assigned to control, SOE, and GOE (chewing gum exercise with SOE) groups. The SOE comprised exercises to improve mastication, salivation, and swallowing function. Control group participants performed no exercises. The intervention period was 8 weeks, followed by a 3-week maintenance period. The Mixing Ability Index (MAI), occlusal force, unstimulated saliva, and repetitive saliva swallowing test were evaluated at baseline and 2, 5, 8, and 11 weeks later. Self-reported discomfort was re-evaluated after 8 weeks. RESULTS: After 8 weeks, mean MAI differences from baseline significantly increased in both groups; the increase in the GOE group was largest and four times higher than in the control group. Mean differences of occlusal force from baseline increased by 56 N (SOE group) and 60 N (GOE group). The increase of salivation was greater in the SOE (3.6-fold) and GOE (2.2-fold) groups than in the control group. Furthermore, 27% and 18% of SOE and GOE group participants, respectively, were re-categorized as having good swallowing function. Participants reported less discomfort as oral functions improved. DISCUSSION: These findings may facilitate the development of clinical practice guidelines for optimal oral care in older adults. CONCLUSION: While both SOE and GOE may improve oral function in older adults, GOE is recommended for those with impaired mastication. TRIAL REGISTRATION: KCT0003305, retrospectively registered 31/10/2018.

Evaluation of dental plaque reduction using microcurrent-emitting toothbrushes in orthodontic patients: a randomized, double-blind, crossover clinical trial.

This study aimed to compare the effectiveness of microcurrent-emitting toothbrushes (MCTs) and ordinary toothbrushes in reducing the dental plaque index (PI) and dental caries activity among orthodontic patients. The evaluation was performed using a crossover study design involving 22 orthodontic patients randomly assigned to the MCT or ordinary toothbrush groups. The participants used the designated toothbrush for 4 weeks and had a 1-week wash-out time before crossover to the other toothbrush. PI (Attin's index) and dental caries activity were measured at baseline and at the end of each 4-week period. Additionally, patients completed questionnaires to assess patient satisfaction for "freshness in mouth" and "cleansing degree." The results showed that the MCT group had a significant reduction in PI (p = 0.009), whereas the ordinary toothbrush group did not (p = 0.595). There was no significant difference in the dental caries activity between the two groups (p > 0.05). Patient satisfaction assessment revealed that 65% patients in the MCT group had more than "fair" experience of freshness, in contrast to 50% of patients in the ordinary toothbrush group. Satisfaction with cleansing degree was similar in both groups. Overall, these findings suggest that MCTs are more effective in reducing dental PI than ordinary toothbrushes.

Machine Learning Algorithms Predict Successful Weaning From Mechanical Ventilation Before Intubation: Retrospective Analysis From the Medical Information Mart for Intensive Care IV Database.

BACKGROUND: The prediction of successful weaning from mechanical ventilation (MV) in advance of intubation can facilitate discussions regarding end-of-life care before unnecessary intubation. OBJECTIVE: We aimed to develop a machine learning-based model that predicts successful weaning from ventilator support based on routine clinical and laboratory data taken before or immediately after intubation. METHODS: We used the Medical Information Mart for Intensive Care IV database, which is an open-access database covering 524,740 admissions of 382,278 patients in Beth Israel Deaconess Medical Center, United States, from 2008 to 2019. We selected adult patients who underwent MV in the intensive care unit (ICU). Clinical and laboratory variables that are considered relevant to the prognosis of the patient in the ICU were selected. Data collected before or within 24 hours of intubation were used to develop machine learning models that predict the probability of successful weaning within 14 days of ventilator support. Developed models were integrated into an ensemble model. Performance metrics were calculated by 5-fold cross-validation for each model, and a permutation feature importance and Shapley additive explanations analysis was conducted to better understand the impacts of individual variables on outcome prediction. RESULTS: Of the 23,242 patients, 19,025 (81.9%) patients were successfully weaned from MV within 14 days. Using the preselected 46 clinical and laboratory variables, the area under the receiver operating characteristic curve of CatBoost classifier, random forest classifier, and regularized logistic regression classifier models were 0.860 (95% CI 0.852-0.868), 0.855 (95% CI 0.848-0.863), and 0.823 (95% CI 0.813-0.832), respectively. Using the ensemble voting classifier using the 3 models above, the final model revealed the area under the receiver operating characteristic curve of 0.861 (95% CI 0.853-0.869), which was significantly better than that of Simplified Acute Physiology Score II (0.749, 95% CI 0.742-0.756) and Sequential Organ Failure Assessment (0.588, 95% CI 0.566-0.609). The top features included lactate and anion gap. The model's performance achieved a plateau with approximately the top 21 variables. CONCLUSIONS: We developed machine learning algorithms that can predict successful weaning from MV in advance to intubation in the ICU. Our models can aid the appropriate management for patients who hesitate to decide on ventilator support or meaningless end-of-life care.

Development and Verification of Time-Series Deep Learning for Drug-Induced Liver Injury Detection in Patients Taking Angiotensin II Receptor Blockers: A Multicenter Distributed Research Network Approach.

OBJECTIVES: The objective of this study was to develop and validate a multicenter-based, multi-model, time-series deep learning model for predicting drug-induced liver injury (DILI) in patients taking angiotensin receptor blockers (ARBs). The study leveraged a national-level multicenter approach, utilizing electronic health records (EHRs) from six hospitals in Korea. METHODS: A retrospective cohort analysis was conducted using EHRs from six hospitals in Korea, comprising a total of 10,852 patients whose data were converted to the Common Data Model. The study assessed the incidence rate of DILI among patients taking ARBs and compared it to a control group. Temporal patterns of important variables were analyzed using an interpretable timeseries model. RESULTS: The overall incidence rate of DILI among patients taking ARBs was found to be 1.09%. The incidence rates varied for each specific ARB drug and institution, with valsartan having the highest rate (1.24%) and olmesartan having the lowest rate (0.83%). The DILI prediction models showed varying performance, measured by the average area under the receiver operating characteristic curve, with telmisartan (0.93), losartan (0.92), and irbesartan (0.90) exhibiting higher classification performance. The aggregated attention scores from the models highlighted the importance of variables such as hematocrit, albumin, prothrombin time, and lymphocytes in predicting DILI. CONCLUSIONS: Implementing a multicenter-based timeseries classification model provided evidence that could be valuable to clinicians regarding temporal patterns associated with DILI in ARB users. This information supports informed decisions regarding appropriate drug use and treatment strategies.

Epigenetic Activation of Tensin 4 Promotes Gastric Cancer Progression.

Gastric cancer (GC) is a complex disease influenced by multiple genetic and epigenetic factors. Chronic inflammation caused by Helicobacter pylori infection and dietary risk factors can result in the accumulation of aberrant DNA methylation in gastric mucosa, which promotes GC development. Tensin 4 (TNS4), a member of the Tensin family of proteins, is localized to focal adhesion sites, which connect the extracellular matrix and cytoskeletal network. We identified upregulation of TNS4 in GC using quantitative reverse transcription PCR with 174 paired samples of GC tumors and adjacent normal tissues. Transcriptional activation of TNS4 occurred even during the early stage of tumor development. TNS4 depletion in GC cell lines that expressed high to moderate levels of TNS4, i.e., SNU-601, KATO III, and MKN74, reduced cell proliferation and migration, whereas ectopic expression of TNS4 in those lines that expressed lower levels of TNS4, i.e., SNU-638, MKN1, and MKN45 increased colony formation and cell migration. The promoter region of TNS4 was hypomethylated in GC cell lines that showed upregulation of TNS4. We also found a significant negative correlation between TNS4 expression and CpG methylation in 250 GC tumors based on The Cancer Genome Atlas (TCGA) data. This study elucidates the epigenetic mechanism of TNS4 activation and functional roles of TNS4 in GC development and progression and suggests a possible approach for future GC treatments.

Impact of image compression on deep learning-based mammogram classification.

Image compression is used in several clinical organizations to help address the overhead associated with medical imaging. These methods reduce file size by using a compact representation of the original image. This study aimed to analyze the impact of image compression on the performance of deep learning-based models in classifying mammograms as "malignant"-cases that lead to a cancer diagnosis and treatment-or "normal" and "benign," non-malignant cases that do not require immediate medical intervention. In this retrospective study, 9111 unique mammograms-5672 normal, 1686 benign, and 1754 malignant cases were collected from the National Cancer Center in the Republic of Korea. Image compression was applied to mammograms with compression ratios (CRs) ranging from 15 to 11 K. Convolutional neural networks (CNNs) with three convolutional layers and three fully-connected layers were trained using these images to classify a mammogram as malignant or not malignant across a range of CRs using five-fold cross-validation. Models trained on images with maximum CRs of 5 K had an average area under the receiver operating characteristic curve (AUROC) of 0.87 and area under the precision-recall curve (AUPRC) of 0.75 across the five folds and compression ratios. For images compressed with CRs of 10 K and 11 K, model performance decreased (average 0.79 in AUROC and 0.49 in AUPRC). Upon generating saliency maps that visualize the areas each model views as significant for prediction, models trained on less compressed (CR < = 5 K) images had maps encapsulating a radiologist's label, while models trained on images with higher amounts of compression had maps that missed the ground truth completely. In addition, base ResNet18 models pre-trained on ImageNet and trained using compressed mammograms did not show performance improvements over our CNN model, with AUROC and AUPRC values ranging from 0.77 to 0.87 and 0.52 to 0.71 respectively when trained and tested on images with maximum CRs of 5 K. This paper finds that while training models on images with increased the robustness of the models when tested on compressed data, moderate image compression did not substantially impact the classification performance of DL-based models.

Prediction of Prolonged Length of Hospital Stay After Cancer Surgery Using Machine Learning on Electronic Health Records: Retrospective Cross-sectional Study.

BACKGROUND: Postoperative length of stay is a key indicator in the management of medical resources and an indirect predictor of the incidence of surgical complications and the degree of recovery of the patient after cancer surgery. Recently, machine learning has been used to predict complex medical outcomes, such as prolonged length of hospital stay, using extensive medical information. OBJECTIVE: The objective of this study was to develop a prediction model for prolonged length of stay after cancer surgery using a machine learning approach. METHODS: In our retrospective study, electronic health records (EHRs) from 42,751 patients who underwent primary surgery for 17 types of cancer between January 1, 2000, and December 31, 2017, were sourced from a single cancer center. The EHRs included numerous variables such as surgical factors, cancer factors, underlying diseases, functional laboratory assessments, general assessments, medications, and social factors. To predict prolonged length of stay after cancer surgery, we employed extreme gradient boosting classifier, multilayer perceptron, and logistic regression models. Prolonged postoperative length of stay for cancer was defined as bed-days of the group of patients who accounted for the top 50% of the distribution of bed-days by cancer type. RESULTS: In the prediction of prolonged length of stay after cancer surgery, extreme gradient boosting classifier models demonstrated excellent performance for kidney and bladder cancer surgeries (area under the receiver operating characteristic curve [AUC] >0.85). A moderate performance (AUC 0.70-0.85) was observed for stomach, breast, colon, thyroid, prostate, cervix uteri, corpus uteri, and oral cancers. For stomach, breast, colon, thyroid, and lung cancers, with more than 4000 cases each, the extreme gradient boosting classifier model showed slightly better performance than the logistic regression model, although the logistic regression model also performed adequately. We identified risk variables for the prediction of prolonged postoperative length of stay for each type of cancer, and the importance of the variables differed depending on the cancer type. After we added operative time to the models trained on preoperative factors, the models generally outperformed the corresponding models using only preoperative variables. CONCLUSIONS: A machine learning approach using EHRs may improve the prediction of prolonged length of hospital stay after primary cancer surgery. This algorithm may help to provide a more effective allocation of medical resources in cancer surgery.

Improvements in oral functions of elderly after simple oral exercise.

Purpose: Conventional oral exercises in previous studies are considered impractical for continuous use in the elderly because of the extended duration needed for effective outcomes. Therefore, in the present study, a simple oral exercise (SOE) was developed to reduce performance time, focusing on improvements in mastication, salivation, and swallowing functions. The aim of this study was to determine the short-term effects of the SOE with respect to improving mastication, salivation, and swallowing function in elderly subjects ≥65 years of age. Patients and methods: The study included 84 subjects, all of whom performed the SOE 2 times per day for 1 week. Masticatory performance was assessed using the mixing ability index (MAI). Unstimulated saliva and the degree of moisture of the tongue/buccal mucosa were evaluated, and the repetitive saliva swallowing test was performed. On the basis of each of these four measurements, subjects were dichotomized into two groups with high (good) and low (poor) conditions. The same evaluations were conducted before and immediately after intervention, as well as after 1 week of intervention. A subjective evaluation with questionnaires was performed after 1 week of intervention. The changes were analyzed using repeated-measures ANOVA, Cochran's Q test, and McNemar's test. Results: The mean MAI increased by 6% immediately after the intervention, and by 16% in the poor-chewing group. Similarly, the amount of unstimulated saliva increased by 0.1 ml/min immediately after the SOE, and by 29% in the poor-salivation group. The degree of tongue moisture increased by 3% and was maintained. In the poor-swallowing group, 25% and 40% of the subjects were upgraded to the good-swallowing group immediately after intervention, as well as after 1 week of intervention, respectively. The subjects experienced less discomfort as their oral function improved. Conclusion: The SOE was effective in immediately improving oral functions, and improvement was maintained for 1 week.

Preparation and properties of collagen/modified hyaluronic acid hydrogel for biomedical application.

Hydrogels composed of collagen and hyaluronic acid are types of crosslinked water-swellable polymers and possess vast potential for applications in the medical industry. Collagen (Co) is the major structural protein of connective tissues such as skin, tendon and cartilage. Hyaluronic acid (HA) is a non-immunogenic, non-adhesive glycosaminoglycan that has a high water absorption property and plays significant roles in several cellular processes. The purpose of this study is to prepare a collagen (Co)-modified hyaluronic acid (MHA) hydrogel and investigate its potential utility for biomedical products such as wound dressing materials. Collagen (Co, type I) was obtained from pig skin and mucopolysaccharide-HA was modified by a poly (ethylene glycol) diglycidyl ether (PEGDGE) crosslinker. Thermal stability, swelling behavior, and mechanical strength of Co-MHA hydrogel according to different mass ratios of Co and MHA in hydrogel networks were investigated. The physical properties of the hydrogel were measured by SEM, Differential Scanning Calorimetry (DSC), Thermal Gravity Analysis (TGA), and a Universal Testing Machine (UTM). The cell viability of Co-MHA hydrogel was also evaluated using an in vitro MTT assay.