Bronchopulmonary dysplasia (BPD) in preterm infants is a major concern in neonatal intensive care, necessitating early and accurate detection for improved outcomes. Despite the use of clinical information in previous studies to assess BPD severity, there is a gap in early prediction through imaging techniques. This paper proposed a novel method using convolutional neural networks (CNNs) for the early prediction of BPD from neonatal chest X-rays. We employed two strategies: first, analyzing chest X-ray images taken on specific days post-birth to evaluate day-wise BPD predictive performance using CNN models; and second, aggregating these images to enhance the training dataset. Thirteen specific CNN architectures were evaluated using a five-fold cross-validation method on a dataset acquired at four distinct time points: 3, 7, 14, and 28-days post-birth. The dataset included 115 preterm infants, 51 with BPD and 64 normal, classified based on their condition at 36 weeks of post-menstrual age. MobileNetV2 demonstrated consistent and fairly above-moderate performance among the networks used, with calculated metrics showing an accuracy of 0.665 ± 0.045, an AUC of 0.736 ± 0.053, a recall of 0.635 ± 0.042, a precision of 0.647 ± 0.046, and an F1-score of 0.641 ± 0.042. The results highlight the potential of CNNs in enhancing early diagnostic accuracy for BPD in neonatal patients using chest X-ray images.

Ureteral stones, a prevalent type of urinary stone, form within the ureter, causing severe pain and hematuria. Extracorporeal shock wave lithotripsy (ESWL) and transurethral lithotripsy (TUL) are the primary treatments. Although ESWL is less invasive and requires shorter hospital stays, its lower success rate compared to TUL, often necessitates additional treatments, increasing both the physical and financial burdens on patients. This study aims to enhance the accuracy of predicting ESWL outcomes by using advanced machine learning methods to analyze both CT and X-ray images together with clinical findings. Particularly, X-ray images, which have been less frequently in past studies, are anticipated to provide detailed analytical features. Addressing the limitations of current predictive methods, which often suffer from excessive irrelevant features and low interpretability, this study introduces three sophisticated feature selection approaches: P-value, AUC, and SHAP value. These approaches aim to enhance both model interpretability and predictive performance. Several machine learning algorithms were evaluated, including decision tree, K-nearest neighbors, random forest, logistic regression, SVM, adaboost, and Gaussian NB. Results from 139 subjects with ESWL show that logistic regression and SVM perform optimally, with SHAP-based feature selection significantly boosting outcomes, demonstrated by the increase in the AUC from 0.791 to 0.845 for logistic regression, and from 0.750 to 0.764 for SVM. Furthermore, the study decreases the number of features used in the model from 55 to 19, simplifying the prediction process. However, features extracted from X-ray images showed limited effectiveness.

The incidence of falls in hospital facilities is high and can lead to a decrease in patients' quality of life and an increase in medical expenses. Therefore, the development of a system that can predict getting-up from a bed is necessary. This study proposes a get-up detecting sensor using 6-axis inertial sensor. This system can detect getting-up from a bed in real-time using machine learning with Edge AI. To evaluate the basic performance of the proposed system, a protocol was applied for four subjects, and data were collected. Alert accuracy rate and false alert rate were used as evaluation metrics, and a model was built using data from three of the subjects and evaluated with the remaining subject, which was repeated for all four subjects. For high-risk bed-leaving behavior, medium-risk pre-bed-leaving behavior, and low-risk get-up behavior, the alert accuracy rate (i.e., Recall) was 89.4%, 97.5%, and 86.3%, respectively, and the false alert rate (1-Precision) was 6.3%, 10.2%, and 0.0%, respectively. This confirmed the possibility of predicting rising behavior with high accuracy. Furthermore, as a proof of concept, a real-time get-up detection system was developed, and its practicality was demonstrated. Future challenges include reevaluating feature extraction and evaluating the performance of the proposed system with a diverse range of subjects of different ages, genders, and health statuses.

Chronic lung disease (CLD) is the most common and serious lung disease in premature infants. In this study, we predict the severity (mild or severe) of neonatal chest X-ray images using a convolutional neural network (CNN) to enable early intervention to provide personalized treatment and improve prognosis. Thirty subjects were tested in a leave-one-out cross validation experiment using 30 chest X-ray images of 11 patients with mild disease and 19 patients with severe disease at 7 days of age. To improve the prediction accuracy, we proposed to limit the input image of the CNN to the lung field region and to use a pre-training model for transfer learning. Four different experiments were conducted, comparing the results with different input images (whole image or lung field region) and with and without transfer learning. The results showed that the best accuracy was obtained when the entire image was used as input and no transfer learning was performed, with an Accuracy of 0.667.

Baseball elbow is a pitching elbow disorder caused by repeated pitching movements. Osteochondritis dissecans (OCD) is one of baseball elbow disorders, and is an intractable osteochondral injury that tends to occur in elementary and junior high school students. If it can be found in the early stages, it will be completely cured by conservative treatment, which is to set a period to stop playing baseball. Since there is almost no pain in the early stage, the hurdles for consultation are high and there are many cases in which the condition becomes severe. Periodical medical check of baseball elbow is effective, however, the number of implementations is several times a year due to the shortage of specialists who can make a diagnosis. In this study, for the purpose of developing computer-aided diagnosis (CADx) of early-stage OCD, we propose an OCD detection method using ultrasound images of the elbow. The proposed method first segments the humerus capitellum using fully convolutional network (FCN). Secondly, the segmented region is classified into OCD +/- classes using fine-tuning VGG16 to detect OCD. The proposed method was applied to 125 child baseball players including 61 OCD children and 64 healthy children. 5-fold cross-validation was conducted. The average detection results were 76.8% for accuracy, 100% for precision, 52.3% for recall, F1-score was 0.673, and AUC was 0.851.