Development of a Non-Contact Sensor System for Converting 2D Images into 3D Body Data: A Deep Learning Approach to Monitor Obesity and Body Shape in Individuals in Their 20s and 30s.

This study demonstrates how to generate a three-dimensional (3D) body model through a small number of images and derive body values similar to the actual values using generated 3D body data. In this study, a 3D body model that can be used for body type diagnosis was developed using two full-body pictures of the front and side taken with a mobile phone. For data training, 400 3D body datasets (male: 200, female: 200) provided by Size Korea were used, and four models, i.e., 3D recurrent reconstruction neural network, point cloud generative adversarial network, skinned multi-person linear model, and pixel-aligned impact function for high-resolution 3D human digitization, were used. The models proposed in this study were analyzed and compared. A total of 10 men and women were analyzed, and their corresponding 3D models were verified by comparing 3D body data derived from 2D image inputs with those obtained using a body scanner. The model was verified through the difference between 3D data derived from the 2D image and those derived using an actual body scanner. Unlike the 3D generation models that could not be used to derive the body values in this study, the proposed model was successfully used to derive various body values, indicating that this model can be implemented to identify various body types and monitor obesity in the future.

AI-based betting anomaly detection system to ensure fairness in sports and prevent illegal gambling.

This study develops a solution to sports match-fixing using various machine-learning models to detect match-fixing anomalies, based on betting odds. We use five models to distinguish between normal and abnormal matches: logistic regression (LR), random forest (RF), support vector machine (SVM), the k-nearest neighbor (KNN) classification, and the ensemble model-a model optimized from the previous four. The models classify normal and abnormal matches by learning their patterns using sports betting odds data. The database was developed based on the world football league match betting data of 12 betting companies, which offered a vast collection of data on players, teams, game schedules, and league rankings for football matches. We develop an abnormal match detection model based on the data analysis results of each model, using the match result dividend data. We then use data from real-time matches and apply the five models to construct a system capable of detecting match-fixing in real time. The RF, KNN, and ensemble models recorded a high accuracy, over 92%, whereas the LR and SVM models were approximately 80% accurate. In comparison, previous studies have used a single model to examine football match betting odds data, with an accuracy of 70-80%.

The Effects of an App-Based Physical Activity Program on Colorectal Cancer Patients Undergoing Chemotherapy: A Randomized Controlled Trial.

BACKGROUND: Colorectal cancer is one of the most common malignancies worldwide. Oxaliplatin, which is used as adjuvant chemotherapy, affects quality of life by causing oxaliplatin-induced peripheral neuropathy in colorectal cancer patients. OBJECTIVES: This study examined the effects of an application (app)-based physical activity program for alleviating peripheral neuropathy symptoms in colorectal cancer patients undergoing chemotherapy. METHODS: This was a randomized controlled study that included 34 patients undergoing chemotherapy after being diagnosed with colorectal cancer. Outcomes were compared between patients who participated in a 6-week app-based physical activity program (experimental group; n = 17) and who received standard booklet education (control group; n = 17). Data were collected using questionnaires, and exercise time was recorded to evaluate intervention adherence. RESULTS: Significant differences were observed between the groups in peripheral neuropathy symptoms (F = 8.93, P = .002), interference with activities (Z = -2.55, P = .011), and quality of life (F = 7.65, P = .003). The experimental group showed significantly higher average exercise times at 1 to 4 weeks (Z = -2.10, P = .026), 5 to 6 weeks (Z = -4.02, P < .001), and 1 to 6 weeks (Z = -3.40, P = .001) than the control group. CONCLUSIONS: The app-based physical activity program had a positive effect on participants' exercise adherence and reduced peripheral neuropathy symptoms. Thus, we propose the adoption of a mobile health app that can be used at any time or place as an intervention for preventing or alleviating adverse effects during the treatment of cancer patients. IMPLICATIONS FOR PRACTICE: An app-based physical activity program using the mobile health app can be used as a nursing intervention to manage symptoms and increase the health behavior adherence in cancer patients.

Efficacy and Safety of Low-Dose Intravesical OnabotulinumtoxinA Injections in Female Patients With Detrusor Overactivity With Detrusor Underactivity.

PURPOSE: We assessed the effectiveness and safety of using intravesical onabotulinumtoxinA (onabotA; BOTOX) injection with a low dose (75 units) for treating urinary storage symptoms in patients with detrusor overactivity with detrusor underactivity (DODU) compared to using the standard 100 units of onabotA in patients with overactive bladder (OAB). METHODS: This ambidirectional study included 121 female patients who received intravesical onabotA injections at our hospitals. A total of 87 patients with OAB and 34 patients with DODU were reviewed using a 3-day voiding diary, uroflowmetry, and questionnaires including the International Prostate Symptom Score (IPSS), Overactive Bladder Symptom Score, and Patient Perception of Bladder Condition. Patients were evaluated at baseline, within 2 weeks of treatment, and beyond 3 months after treatment. RESULTS: Questionnaire scores of the DODU group demonstrated significant improvement in the short term, with a subsequent decline, but an overall improvement compared to baseline in the long term. Notably, the DODU group exhibited enhanced IPSS voiding scores after the treatment. In the OAB group, most questionnaire scores, excluding the IPSS voiding score, showed significant posttreatment improvement, which was sustained to some extent in the long term. Voiding diary parameters related to storage symptoms were enhanced in both groups. The maximum and mean flow rates decreased in the OAB group but increased in the DODU group, particularly in the short term (P=0.000). The postvoid residual volume increased in both groups after posttreatment, with a mitigated change in the long term. Safety assessments revealed manageable adverse events in both groups with comparable frequencies. CONCLUSION: Low-dose intravesical onabotA for DODU demonstrated a relatively shorter duration of efficacy than OAB. Nonetheless, the treatment improved both storage and voiding symptoms in patients with DODU without significant adverse effects.

EarlyTect BCD, a Streamlined PENK Methylation Test in Urine DNA, Effectively Detects Bladder Cancer in Patients with Hematuria.

The current noninvasive diagnostic approaches for detecting bladder cancer (BC) often exhibit limited clinical performance, especially for the initial diagnosis. This study aims to evaluate the validity of a streamlined urine-based PENK methylation test called EarlyTect BCD in detecting BC in patients with hematuria scheduled for cystoscopy in Korean and American populations. The test seamlessly integrates two steps, linear target enrichment and quantitative methylation-specific PCR within a single closed tube. The detection limitation of the test was approximately two genome copies of methylated PENK per milliliter of urine. In the retrospective training set (n = 105), an optimal cutoff value was determined to distinguish BC from non-BC, resulting in a sensitivity of 87.3% and a specificity of 95.2%. In the prospective validation set (n = 210, 122 Korean and 88 American patients), the overall sensitivity for detecting all stages of BC was 81.0%, with a specificity of 91.5% and an area under the curve value of 0.889. There was no significant difference between the two groups. The test achieved a sensitivity of 100% in detecting high-grade Ta and higher stages of BC. The negative predictive value of the test was 97.7%, and the positive predictive value was 51.5%. The findings of this study demonstrate that EarlyTect BCD is a highly effective noninvasive diagnostic tool for identifying BC among patients with hematuria.