An interpretable multi-task system for clinically applicable COVID-19 diagnosis using CXR.

BACKGROUND: With the emergence of continuously mutating variants of coronavirus, it is urgent to develop a deep learning model for automatic COVID-19 diagnosis at early stages from chest X-ray images. Since laboratory testing is time-consuming and requires trained laboratory personal, diagnosis using chest X-ray (CXR) is a befitting option. OBJECTIVE: In this study, we proposed an interpretable multi-task system for automatic lung detection and COVID-19 screening in chest X-rays to find an alternate method of testing which are reliable, fast and easily accessible, and able to generate interpretable predictions that are strongly correlated with radiological findings. METHODS: The proposed system consists of image preprocessing and an unsupervised machine learning (UML) algorithm for lung region detection, as well as a truncated CNN model based on deep transfer learning (DTL) to classify chest X-rays into three classes of COVID-19, pneumonia, and normal. The Grad-CAM technique was applied to create class-specific heatmap images in order to establish trust in the medical AI system. RESULTS: Experiments were performed with 15,884 frontal CXR images to show that the proposed system achieves an accuracy of 91.94% in a test dataset with 2,680 images including a sensitivity of 94.48% on COVID-19 cases, a specificity of 88.46% on normal cases, and a precision of 88.01% on pneumonia cases. Our system also produced state-of-the-art outcomes with a sensitivity of 97.40% on public test data and 88.23% on a previously unseen clinical data (1,000 cases) for binary classification of COVID-19-positive and COVID-19-negative films. CONCLUSION: Our automatic computerized evaluation for grading lung infections exhibited sensitivity comparable to that of radiologist interpretation in clinical applicability. Therefore, the proposed solution can be used as one element of patient evaluation along with gold-standard clinical and laboratory testing.

A Hybrid Method for Density Power Divergence Minimization with Application to Robust Univariate Location and Scale Estimation.

We develop a new globally convergent optimization method for solving a constrained minimization problem underlying the minimum density power divergence estimator for univariate Gaussian data in the presence of outliers. Our hybrid procedure combines classical Newton's method with a gradient descent iteration equipped with a step control mechanism based on Armijo's rule to ensure global convergence. Extensive simulations comparing the resulting estimation procedure with the more prominent robust competitor, Minimum Covariance Determinant (MCD) estimator, across a wide range of breakdown point values suggest improved efficiency of our method. Application to estimation and inference for a real-world dataset is also given.

Multi-modal learning for inpatient length of stay prediction.

Predicting inpatient length of stay (LoS) is important for hospitals aiming to improve service efficiency and enhance management capabilities. Patient medical records are strongly associated with LoS. However, due to diverse modalities, heterogeneity, and complexity of data, it becomes challenging to effectively leverage these heterogeneous data to put forth a predictive model that can accurately predict LoS. To address the challenge, this study aims to establish a novel data-fusion model, termed as DF-Mdl, to integrate heterogeneous clinical data for predicting the LoS of inpatients between hospital discharge and admission. Multi-modal data such as demographic data, clinical notes, laboratory test results, and medical images are utilized in our proposed methodology with individual "basic" sub-models separately applied to each different data modality. Specifically, a convolutional neural network (CNN) model, which we termed CRXMDL, is designed for chest X-ray (CXR) image data, two long short-term memory networks are used to extract features from long text data, and a novel attention-embedded 1D convolutional neural network is developed to extract useful information from numerical data. Finally, these basic models are integrated to form a new data-fusion model (DF-Mdl) for inpatient LoS prediction. The proposed method attains the best R2 and EVAR values of 0.6039 and 0.6042 among competitors for the LoS prediction on the Medical Information Mart for Intensive Care (MIMIC)-IV test dataset. Empirical evidence suggests better performance compared with other state-of-the-art (SOTA) methods, which demonstrates the effectiveness and feasibility of the proposed approach.

Investigating the effects of storage conditions on urinary volatilomes for their reliability in disease diagnosis.

BACKGROUND: Cancer detection presents challenges regarding invasiveness, cost, and reliability. As a result, exploring alternative diagnostic methods holds significant clinical importance. Urinary metabolomic profiling has emerged as a promising avenue; however, its application for cancer diagnosis may be influenced by sample preparation or storage conditions. OBJECTIVE: This study aimed to assess the impact of sample storage and processing conditions on urinary volatile organic compounds (VOCs) profiles and establish a robust standard operating procedure (SOP) for such diagnostic applications. METHODS: Five key variables were investigated: storage temperatures, durations, freeze-thaw cycles, sample collection conditions, and sample amounts. The analysis of VOCs involved stir bar sorptive extraction coupled with thermal desorption-gas chromatography/mass spectrometry (SBSE-TD-GC-MS), with compound identification facilitated by the National Institute of Standards and Technology Library (NIST). Extensive statistical analysis, including combined scatterplot and response surface (CSRS) plots, partial least squares-discriminant analysis (PLS-DA), and probability density function plots (PDFs), were employed to study the effects of the factors. RESULTS: Our findings revealed that urine storage duration, sample amount, temperature, and fasting/non-fasting sample collection did not significantly impact urinary metabolite profiles. This suggests flexibility in urine sample collection conditions, enabling individuals to contribute samples under varying circumstances. However, the influence of freeze-thaw cycles was evident, as VOC profiles exhibited distinct clustering patterns based on the number of cycles. This emphasizes the effect of freeze-thaw cycles on the integrity of urinary profiles. CONCLUSIONS: The developed SOP integrating SBSE-TD-GC-MS and statistical analyses can serve as a valuable tool for analyzing urinary organic compounds with minimal preparation and sensitive detection. The findings also support that urinary VOCs for cancer screening and diagnosis could be a feasible alternative offering a robust, non-invasive, and sensitive approach for cancer screening.

Univariate fast initial response statistical process control with taut strings.

We present a novel real-time univariate monitoring scheme for detecting a sustained departure of a process mean from some given standard assuming a constant variance. Our proposed stopping rule is based on the total variation of a nonparametric taut string estimator of the process mean and is designed to provide a desired average run length for an in-control situation. Compared to the more prominent CUSUM fast initial response (FIR) methodology and allowing for a restart following a false alarm, the proposed two-sided taut string (TS) scheme produces a significant reduction in average run length for a wide range of changes in the mean that occur at or immediately after process monitoring begins. A decision rule for when to choose our proposed TS chart compared to the CUSUM FIR chart that takes into account both false alarm rate and average run length to detect a shift in the mean is proposed and implemented. Supplementary materials are available online.

Time-to-event modeling for hospital length of stay prediction for COVID-19 patients.

Providing timely patient care while maintaining optimal resource utilization is one of the central operational challenges hospitals have been facing throughout the pandemic. Hospital length of stay (LOS) is an important indicator of hospital efficiency, quality of patient care, and operational resilience. Numerous researchers have developed regression or classification models to predict LOS. However, conventional models suffer from the lack of capability to make use of typically censored clinical data. We propose to use time-to-event modeling techniques, also known as survival analysis, to predict the LOS for patients based on individualized information collected from multiple sources. The performance of six proposed survival models is evaluated and compared based on clinical data from COVID-19 patients.