Journal of healthcare engineering
-
Early detection and classification of pulmonary nodules using computer-aided diagnosis (CAD) systems is useful in reducing mortality rates of lung cancer. In this paper, we propose a new deep learning method to improve classification accuracy of pulmonary nodules in computed tomography (CT) scans. ⋯ We evaluated our method on the LIDC/IDRI dataset extracted by the LUNA16 challenge. The experiments showed that our deep learning method with focal loss is a high-quality classifier with an accuracy of 97.2%, sensitivity of 96.0%, and specificity of 97.3%.
-
For patients with cognitive disorders and dementia, accurate prognosis of cognitive worsening is critical to their ability to prepare for the future, in collaboration with health-care providers. Despite multiple efforts to apply computational brain magnetic resonance image (MRI) analysis in predicting cognitive worsening, with several successes, brain MRI is not routinely quantified in clinical settings to guide prognosis and clinical decision-making. To encourage the clinical use of a cutting-edge image segmentation method, we developed a prediction model as part of an established web-based cloud platform, MRICloud. ⋯ This MRICloud prediction model was then applied to a test dataset of clinically acquired MRIs from the Johns Hopkins Memory and Alzheimer's Treatment Center (MATC), a clinical care setting. In the latter setting, the model had both sensitivity and specificity of 1.0 in predicting substantial cognitive worsening. While the MRICloud prediction model demonstrated promise as a platform on which computational MRI findings can easily be extended to clinical use, further study with a larger number of patients is needed for validation.
-
Ontario has shown an increasing number of emergency department (ED) visits, particularly for mental health and addiction (MHA) complaints. Given the current opioid crises Canada is facing and the legalization of recreational cannabis in October 2018, the number of MHA visits to the ED is expected to grow even further. In face of these events, we examine capacity planning alternatives for the ED of an academic hospital in Toronto. ⋯ We then employ a discrete-event simulation model to analyze the impacts of the following scenarios: (a) increasing overall demand to the ED, (b) increasing or decreasing number of ED visits due to substance abuse, and (c) adjusting resource capacity to address the forecasted demand. Key performance indicators used in this analysis are the overall ED length of stay (LOS) and the total number of patients treated in the Psychiatric Emergency Services Unit (PESU) as a percentage of the total number of MHA visits. Our results showed that if resource capacity is not adjusted, ED LOS will deteriorate considerably given the expected growth in demand; programs that aim to reduce the number of alcohol and/or opioid visits can greatly aid in reducing ED wait times; the legalization of recreational use of cannabis will have minimal impact, and increasing the number of PESU beds can provide great aid in reducing ED pressure.
-
To meet the need for "standard" testing system for wearable blood pressure sensors, this study intends to develop a new radial pulsation simulator that can generate age-dependent reference radial artery pressure waveforms reflecting the physiological characteristics of human cardiovascular system. To closely duplicate a human cardiovascular system, the proposed simulator consists of a left ventricle simulation module, an aorta simulation module, a peripheral resistance simulation module, and a positive/negative pressure control reservoir module. Simulating physiologies of blood pressure, the compliance chamber in the simulator can control arterial stiffness to produce age-dependent pressure waveforms. ⋯ The proposed device can be effectively used as a "standard" radial artery pressure simulator to calibrate the wearable sensor's measurement characteristics and to develop more advanced sensors. The simulator is intended to serve as a platform for the development, performance verification, and calibration of wearable blood pressure sensors. It will contribute to the advancement of the wearable blood pressure sensor technology, which enables real-time monitoring of users' radial artery pressure waveforms and eventually predicting cardiovascular diseases.
-
Electrocardiogram (ECG) signal analysis has received special attention of the researchers in the recent past because of its ability to divulge crucial information about the electrophysiology of the heart and the autonomic nervous system activity in a noninvasive manner. Analysis of the ECG signals has been explored using both linear and nonlinear methods. However, the nonlinear methods of ECG signal analysis are gaining popularity because of their robustness in feature extraction and classification. The current study presents a review of the nonlinear signal analysis methods, namely, reconstructed phase space analysis, Lyapunov exponents, correlation dimension, detrended fluctuation analysis (DFA), recurrence plot, Poincaré plot, approximate entropy, and sample entropy along with their recent applications in the ECG signal analysis.