ABSTRACT
BACKGROUND: EXCOR Pediatric is one of the most commonly used ventricular assist devices (VAD) for small children; it requires visual inspection of the diaphragm movement to assess its operating status. Although this visual inspection can only be performed by trained medical professionals, it can also be attempted by the recent advances in computer vision technology. METHODS: Movement of the diaphragm in the operating EXCOR VAD was recorded as movies and annotated frame-by-frame in three classes according to the state of the diaphragm: "fill," "mid," and "empty." Three models, MobileNetV3, EfficientNetV2, and MobileViT, were trained using the frames, and their performance was evaluated based on the accuracy and area under the receiver operating characteristic curve (AROC). RESULTS: A total of 152 movies were available from two participants. Only the 10 mL pumps were used. Ninety-eight movies were used for annotation and frame extraction, and 7949 frames per class were included in the analysis. The macro-average accuracies of the three models were 0.88, 0.91, and 0.93, and the AROC were 0.99, 0.98, and 0.99 for MobileNetV3, EfficientNetV2, and MobileViT, respectively. CONCLUSION: Image recognition models based on lightweight deep neural networks could detect the diaphragm state of EXCOR VAD with sufficient accuracy, although there were limited variations in the dataset. This suggests the potential of computer vision for the automated monitoring of the EXCOR diaphragm position.
ABSTRACT
BACKGROUND & AIMS: Sarcopenia is a serious problem in adults and children. However, limited modalities are available for diagnosing pediatric sarcopenia. The serum creatinine to cystatin C ratio (Cre/CysC ratio) is a promising method for muscle quantification, although its clinical significance in the pediatric population is unknown. This study aimed to evaluate the relationship between the Cre/CysC ratio and physical performance. METHODS: This was a single-center retrospective study. Patients aged <15 years who had visited the University of Tokyo Hospital for measurements of serum creatinine and cystatin C levels, body height, and body weight were included. The patients were assigned according to their age (<2 or ≥2 years), and the relationship between the Cre/CysC ratio and physical performance at the time of measurement was analyzed. RESULTS: We included 266 patients, revealing a significant relationship between Cre/CysC ratio and physical performance in children aged ≥2 years (p < 0.001) but not in children aged <2 years (p = 0.42). The repeater-operator curve analysis of Cre/CysC to predict bedridden status showed good performance (the area under the curve was 0.82 (95% CI, 0.75-0.89)) and the cut-off value 0.44 had good accuracy (sensitivity 0.87, specificity 0.61). CONCLUSIONS: The Cre/CysC ratio was a significant marker of impaired physical performance, and a Cre/CysC ratio <0.44 accurately predicted bedridden status in children aged >2 years.
