RESUMEN
Objective.The trend in the medical field is towards intelligent detection-based medical diagnostic systems. However, these methods are often seen as 'black boxes' due to their lack of interpretability. This situation presents challenges in identifying reasons for misdiagnoses and improving accuracy, which leads to potential risks of misdiagnosis and delayed treatment. Therefore, how to enhance the interpretability of diagnostic models is crucial for improving patient outcomes and reducing treatment delays. So far, only limited researches exist on deep learning-based prediction of spontaneous pneumothorax, a pulmonary disease that affects lung ventilation and venous return.Approach.This study develops an integrated medical image analysis system using explainable deep learning model for image recognition and visualization to achieve an interpretable automatic diagnosis process.Main results.The system achieves an impressive 95.56% accuracy in pneumothorax classification, which emphasizes the significance of the blood vessel penetration defect in clinical judgment.Significance.This would lead to improve model trustworthiness, reduce uncertainty, and accurate diagnosis of various lung diseases, which results in better medical outcomes for patients and better utilization of medical resources. Future research can focus on implementing new deep learning models to detect and diagnose other lung diseases that can enhance the generalizability of this system.
Asunto(s)
Aprendizaje Profundo , Procesamiento de Imagen Asistido por Computador , Neumotórax , Neumotórax/diagnóstico por imagen , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Tomografía Computarizada por Rayos XRESUMEN
Primary spontaneous pneumothorax (PSP) primarily affects slim and tall young males. Exploring the etiological link between chest wall structural characteristics and PSP is crucial for advancing treatment methods. In this case-control study, chest computed tomography (CT) images from patients undergoing thoracic surgery, with or without PSP, were analyzed using Artificial Intelligence. Convolutional Neural Network (CNN) model of EfficientNetB3 and InceptionV3 were used with transfer learning on the Imagenet to compare the images of both groups. A heatmap was created on the chest CT scans to enhance interoperability, and the scale-invariant feature transform (SIFT) was adopted to further compare the image level. A total of 2,312 CT images of 26 non-PSP patients and 1,122 CT images of 26 PSP patients were selected. Chest-wall apex pit (CAP) was found in 25 PSP and three non-PSP patients (p < 0.001). The CNN achieved a testing accuracy of 93.47 % in distinguishing PSP from non-PSP based on chest wall features by identifying the existence of CAP. Heatmap analysis demonstrated CNN's precision in targeting the upper chest wall, accurately identifying CAP without undue influence from similar structures, or inappropriately expanding or minimizing the test area. SIFT results indicated a 10.55 % higher mean similarity within the groups compared to between PSP and non-PSP (p < 0.001). In conclusion, distinctive radiographic chest wall configurations were observed in PSP patients, with CAP potentially serving as an etiological factor linked to PSP. This study accentuates the potential of AI-assisted analysis in refining diagnostic approaches and treatment strategies for PSP.
RESUMEN
Background: The scarcity of medical resources and personnel has worsened due to COVID-19. Telemedicine faces challenges in assessing wounds without physical examination. Evaluating pressure injuries is time consuming, energy intensive, and inconsistent. Most of today's telemedicine platforms utilize graphical user interfaces with complex operational procedures and limited channels for information dissemination. The study aims to establish a smart telemedicine diagnosis system based on YOLOv7 and large language model. Methods: The YOLOv7 model is trained using a clinical data set, with data augmentation techniques employed to enhance the data set to identify six types of pressure injury images. The established system features a front-end interface that includes responsive web design and a chatbot with ChatGPT, and it is integrated with a database for personal information management. Results: This research provides a practical pressure injury staging classification model with an average F1 score of 0.9238. The system remotely provides real-time accurate diagnoses and prescriptions, guiding patients to seek various medical help levels based on symptom severity. Conclusions: This study establishes a smart telemedicine auxiliary diagnosis system based on the YOLOv7 model, which possesses capabilities for classification and real-time detection. During teleconsultations, it provides immediate and accurate diagnostic information and prescription recommendations and seeks various medical assistance based on the severity of symptoms. Through the setup of a chatbot with ChatGPT, different users can quickly achieve their respective objectives.
Asunto(s)
COVID-19 , Úlcera por Presión , Telemedicina , Humanos , Úlcera por Presión/diagnóstico , COVID-19/diagnóstico , SARS-CoV-2RESUMEN
The purposes of this study were to develop a latent human error analysis process, to explore the factors of latent human error in aviation maintenance tasks, and to provide an efficient improvement strategy for addressing those errors. First, we used HFACS and RCA to define the error factors related to aviation maintenance tasks. Fuzzy TOPSIS with four criteria was applied to evaluate the error factors. Results show that 1) adverse physiological states, 2) physical/mental limitations, and 3) coordination, communication, and planning are the factors related to airline maintenance tasks that could be addressed easily and efficiently. This research establishes a new analytic process for investigating latent human error and provides a strategy for analyzing human error using fuzzy TOPSIS. Our analysis process complements shortages in existing methodologies by incorporating improvement efficiency, and it enhances the depth and broadness of human error analysis methodology.
Asunto(s)
Aeronaves/normas , Lista de Verificación , Eficiencia Organizacional , Ergonomía/métodos , Humanos , Mantenimiento/métodos , Mantenimiento/normas , Control de Calidad , Análisis de Causa RaízRESUMEN
The Digital Accessible Information SYstem (DAISY) player is an assistive reading tool developed for use by persons with visual impairments. Certain problems have persisted in the operating procedure and interface of DAISY players, especially for their Chinese users. Therefore, the aim of this study was to redesign the DAISY player with increased usability features for use by native Chinese speakers. First, a User Centered Design (UCD) process was employed to analyze the development of the prototype. Next, operation procedures were reorganized according to GOMS (Goals, Operators, Methods, and Selection rules) methodology. Then the user interface was redesigned according to specific Universal Design (UD) principles. Following these revisions, an experiment involving four scenarios was conducted to compare the new prototype to other players, and it was tested by twelve visually impaired participants. Results indicate the prototype had the quickest operating times, the fewest number of operating errors, and the lowest mental workloads of all the compared players, significantly enhancing the prototype's usability. These findings have allowed us to generate suggestions for developing the next generation of DAISY players for people, especially for Chinese audience.