OView-AI Supporter for Classifying Pneumonia, Pneumothorax, Tuberculosis, Lung Cancer Chest X-ray Images Using Multi-Stage Superpixels Classification.

The deep learning approach has recently attracted much attention for its outstanding performance to assist in clinical diagnostic tasks, notably in computer-aided solutions. Computer-aided solutions are being developed using chest radiography to identify lung diseases. A chest X-ray image is one of the most often utilized diagnostic imaging modalities in computer-aided solutions since it produces non-invasive standard-of-care data. However, the accurate identification of a specific illness in chest X-ray images still poses a challenge due to their high inter-class similarities and low intra-class variant abnormalities, especially given the complex nature of radiographs and the complex anatomy of the chest. In this paper, we proposed a deep-learning-based solution to classify four lung diseases (pneumonia, pneumothorax, tuberculosis, and lung cancer) and healthy lungs using chest X-ray images. In order to achieve a high performance, the EfficientNet B7 model with the pre-trained weights of ImageNet trained by Noisy Student was used as a backbone model, followed by our proposed fine-tuned layers and hyperparameters. Our study achieved an average test accuracy of 97.42%, sensitivity of 95.93%, and specificity of 99.05%. Additionally, our findings were utilized as diagnostic supporting software in OView-AI system (computer-aided application). We conducted 910 clinical trials and achieved an AUC confidence interval (95% CI) of the diagnostic results in the OView-AI system of 97.01%, sensitivity of 95.68%, and specificity of 99.34%.

Ensuring Taiwan patient safety culture survey is free from differential item functioning.

BACKGROUND: Differential item functioning (DIF) means the interference of some demographic characteristic or grouping of the tight relationship between trait levels. DIF threatens precise interpretations of survey results and makes them unreliable. The aim of this study was to examine whether the succinct version of Taiwan Patient Safety Culture (TPSC-S) survey is free from DIF and to mitigate its impact if needed. METHODS: The TPSC-S survey results of 2964 respondents in a public hospital in Taiwan were analyzed. The existence, type, and effect size of DIF were examined for each TPSC-S item using a proportional-odds logistic regression method between characteristic groups, including gender, work experience, job types, management roles, employment status, and safety reporting experiences. RESULTS: The study results revealed that several items of TPSC-S showed statistically significant DIF between characteristic groups. Nevertheless, the magnitude of these DIF was small, and their influence to TPSC-S survey was not significant. The domain-level DIF impact was completely insignificant for all characteristic groups. CONCLUSION: This study revealed that the 24-item TPSC-S survey was free from DIF in six characteristic groups. The difference in survey scores between groups stems from the real difference that hospital safety managers want to measure.