Background: The global burden of respiratory diseases such as influenza, tuberculosis, and viral pneumonia necessitates rapid, accurate diagnostic tools to improve healthcare responses. Current methods, including RT-PCR and chest radiography, face limitations in accuracy, speed, accessibility, and cost-effectiveness, especially in resource-constrained settings, often delaying treatment and increasing transmission. Methods: This study introduces an Enhanced Multi-Model Deep Learning (EMDL) approach to address these challenges. EMDL integrates an ensemble of five pre-trained deep learning models (VGG-16, VGG-19, ResNet, AlexNet, and GoogleNet) with advanced image preprocessing (histogram equalization and contrast enhancement) and a novel multi-stage feature selection and optimization pipeline (PCA, SelectKBest, Binary Particle Swarm Optimization (BPSO), and Binary Grey Wolf Optimization (BGWO)). Results: Evaluated on two independent chest X-ray datasets, EMDL achieved high accuracy in the multiclass classification of influenza, pneumonia, and tuberculosis. The combined image enhancement and feature optimization strategies significantly improved diagnostic precision and model robustness. Conclusions: The EMDL framework provides a scalable and efficient solution for accurate and accessible pulmonary disease diagnosis, potentially improving treatment efficacy and patient outcomes, particularly in resource-limited settings.

Background: The objective of this study was to assess sentinel event analysis and relative factors in different mental healthcare settings. In addition, the occurrence of sentinel events in different hospital settings was compared and potential risk factors contributing to sentinel events identified. Methods: A total of 75 consecutive adult subjects were enrolled from 2 psychiatric units, 1 within a general hospital and 1 at a psychiatric hospital in southern Taiwan. A retrospective chart review of the psychiatric inpatients was conducted for patients that met the criteria for a sentinel event between July 2004 and May 2011. A comparison of the hospital settings was made and differences between suicidal and non-suicidal sentinel events studied. Results: Psychiatric patients that received general hospital psychiatric services (1) appeared to experience a sentinel event soon after admission, (2) the time between the sentinel event occurrence and patient death was shorter, (3) there was a higher probability of potential medical illness than among inpatients treated at a specialized psychiatric hospital, (4) the sentinel event subjects that committed suicide were younger, had a shorter hospital stay, shorter time to occurrence of the sentinel event followed by an unexpected death than the non-suicidal group, and (5) a younger age, higher education level, previous suicide attempt and family psychiatric history were important predictors of suicide among psychiatric inpatients. Conclusions: The results of this study suggest that psychiatric inpatients treated at a general hospital require careful examination for potential physical illness and greater efforts to prevent suicide. A younger age, higher education level, history of a previous suicide attempt and family psychiatric history are additional risk factors for suicide among these patients.