Severity prediction of pulmonary diseases using chest CT scans via cost-sensitive label multi-kernel distribution learning.

BACKGROUND AND OBJECTIVES: The progression of pulmonary diseases is a complex progress. Timely predicting whether the patients will progress to the severe stage or not in its early stage is critical to take appropriate hospital treatment. However, this task suffers from the "insufficient and incomplete" data issue since it is clinically impossible to have adequate training samples for one patient at each day. Besides, the training samples are extremely imbalanced since the patients who will progress to the severe stage is far less than those who will not progress to the non-severe stage. METHOD: We consider the severity prediction of pulmonary diseases as a time estimation problem based on CT scans. To handle the issue of "insufficient and incomplete" training samples, we introduced label distribution learning (LDL). Specifically, we generate a label distribution for each patient, making a CT image contribute to not only the learning of its chronological day, but also the learning of its neighboring days. In addition, a cost-sensitive mechanism is introduced to explore the imbalance data issue. To identify the importance of pulmonary segments in pulmonary disease severity prediction, multi-kernel learning in composite kernel space is further incorporated and particle swarm optimization (PSO) is used to find the optimal kernel weights. RESULTS: We compare the performance of the proposed CS-LD-MKSVR algorithm with several classical machine learning algorithms and deep learning (DL) algorithms. The proposed method has obtained the best classification results on the in-house data, fully indicating its effectiveness in pulmonary disease severity prediction. CONTRIBUTIONS: The severity prediction of pulmonary diseases is considered as a time estimation problem, and label distribution is introduced to describe the conversion time from non-severe stage to severe stage. The cost-sensitive mechanism is also introduced to handle the data imbalance issue to further improve the classification performance.

Caps-3WD: A three-way diagnostic CapsNet for COVID-19

Pulmonary medical image processing is an effective diagnostic method for COVID-19, and CapsNet-based methods have achieved good performance. However, as cost-blind methods, these diagnostic methods only consider immediate and deterministic decisions, which easily lead to misdiagnosis and high costs. Therefore, based on a revised CapsNet, we propose a cost-sensitive three-way decision (3WD) method for COVID-19 diagnosis, named as Caps-3WD. To enhance the feature extraction ability for pneumonia areas, we introduce a Restage module to improve convolution layer of the original CapsNet. Further, to lighten the model, we introduce depth wise separable convolution to reconstruct decoder. Additionally, three options are considered in the decision set: infected, normal, and suspected, which are given different costs, respectively. The lowest-cost decision is chosen for each input. In the experimental analysis, we compare Caps-3WD with CNN-based and CapsNet-based methods on COVID-CXR dataset, which proves the effectiveness of 3WD and the superiority of Caps-3WD in COVID-19 diagnosis. © 2022 SPIE. Downloading of the is permitted for personal use only.

Derivation of a Cost-Sensitive COVID-19 Mortality Risk Indicator Using a Multistart Framework

The overall global death rate for COVID-19 patients has escalated to 2.13% after more than a year of worldwide spread. Despite strong research on the infection pathogenesis, the molecular mechanisms involved in a fatal course are still poorly understood. Machine learning constitutes a perfect tool to develop algorithms for predicting a patient's hospitalization outcome at triage. This paper presents a probabilistic model, referred to as a mortality risk indicator, able to assess the risk of a fatal outcome for new patients. The derivation of the model was done over a database of 2,547 patients from the first COVID-19 wave in Spain. Model learning was tackled through a five multistart configuration that guaranteed good generalization power and low variance error estimators. The training algorithm made use of a class weighting correction to account for the mortality class imbalance and two regularization learners, logistic and lasso regressors. Outcome probabilities were adjusted to obtain cost-sensitive predictions by minimizing the type II error. Our mortality indicator returns both a binary outcome and a three-stage mortality risk level. The estimated AUC across multistarts reaches an average of 0.907. At the optimal cutoff for the binary outcome, the model attains an average sensitivity of 0.898, with a 0.745 specificity. An independent set of 121 patients later released from the same consortium attained perfect sensitivity (1), with a 0.759 specificity when predicted by our model. Best performance for the indicator is achieved when the prediction's time horizon is within two weeks since admission to hospital. In addition to a strong predictive performance, the set of selected features highlights the relevance of several underrated molecules in COVID-19 research, such as blood eosinophils, bilirubin, and urea levels. © 2021 IEEE.