Two-Stage Chance-Constrained Telemedicine Assignment Model with No-Show Behavior and Uncertain Service Duration

The current global pandemic of COVID-19 has caused significant strain on the medical resources of the healthcare providers, so more and more hospitals use telemedicine and virtual care for remote treatment (i.e. consulting, remote diagnosis, treatment, monitoring and follow-ups and so on) in response to COVID-19 pandemic, which is expected to deliver timely care while minimizing exposure to protect medical practitioners and patients. In this study, we study the telemedicine assignment between the patients and telemedical specialists by considering different sources of uncertainty, i.e. uncertain service duration and the no-show behavior of the doctors that is caused by the unexpected situations (i.e. emergency events). We propose a two-stage chance-constrained model with the assignment decisions in the recourse problem and employ an uncertainty set to capture the behavior of telemedical doctors, which finally gives rise to a two-stage binary integer program with binary variables in the recourse problem. We propose an enumeration-based column-and-constraint generation solution method to solve the resulting problem. A simple numerical study is done to illustrate our proposed framework. To the best of our knowledge, this is the first attempt to incorporate the behavior of doctors and uncertain service duration for the telemedicine assignment problem in the literature. We expect that this work could open an avenue for the research of telemedicine by incorporating different sources of uncertainty from an operations management viewpoint, especially in the context of a data-driven optimization framework. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Early Identification of COVID-19 Progression to Its Severe Form Using Artificial Intelligence

Background: Early prediction of disease progression in COVID-19 patients can be helpful for personalized therapy, as well as the optimal allocation of public health resources. Objectives: This study aimed to present predictive models for identifying potential high-risk COVID-19 patients upon hospital ad-mission, based on the examination of clinical and radiological features by radiologists and artificial intelligence (AI). Patients and Methods: A total of 786 initially non-severe COVID-19 patients were retrospectively enrolled in this study between January 2 and May 28, 2020. The patients were randomly divided into training (n = 628, 80%) and test (n = 158, 20%) groups. Clinical factors, laboratory indicators, and radiologist-and AI-extracted radiological features of pneumonia lesions were determined using a convolution neural network. The features were selected based on the Boruta algorithm with five-fold cross-validation. Four mod-els, including a model based on clinical findings (model C), a model based on the physician’s examination of radiological features (R-Doc model), a model based on AI-derived radiological features (R-AI model), and an AI-based model mimicking the physician’s examinations (AI-Mimic-Doc model), were constructed for predicting COVID-19 progression upon admission, using a logistic regres-sion analysis. The predictive performance of the four models was evaluated by calculating the area under the receiver operating characteristic (AUC) curve with a 95% confidence interval (95% CI) and then compared using the DeLong test. Results: Overall, 238 out of 786 patients (30.3%) progressed into severe or critical pneumonia during the 14-day follow-up. Nine clinical findings, 17 laboratory indicators, 48 physician-extracted radiological features of pneumonia lesions, and 126 AI-driven radiological features were collected. The urea, albumin level, and lesion size in the basal segment of the right lower lobe of the lung or the proportion of CT values in the range of-200-60 in the left lung were the representative features for constructing the R-Doc and R-AI models, respectively. Comparison of the R-Doc model (AUC: 0.840, 95% CI: 0.747-0.933 for the training set and 0.731, 95% CI: 0.606-0.857 for the test set) with the R-AI model (AUC: 0.803, 95% CI: 0.701-0.906 for the training set and AUC: 0.731, 95% CI: 0.606-0.857 for the validation set) indicated a marginal difference in identifying patients at risk of progression to pneumonia upon admission (P < 0.1). The R-AI model was superior to model C, with an AUC of 0.770 for the training set (95% CI: 0.657-0.882) and 0.666 for the validation set to identify high-risk non-severe cases upon admission. Conclusion: By using radiological features along with blood tests, early identification of COVID-19 patients, who are at risk of disease progression, can be achieved on admission (rapidly by using AI);therefore, the use of these features can contribute to the clinical management of COVID-19. © 2022, Author(s).

LuMiRa: An Integrated Lung Deformation Atlas and 3D-CNN Model of Infiltrates for COVID-19 Prognosis

Although, recently convolutional neural networks (CNNs) based prognostic models have been developed for COVID-19 severity prediction, most of these studies have analyzed characteristics of lung infiltrates (ground-glass opacities and consolidations) on chest radiographs or CT. However, none of the studies have explored the possible lung deformations due to the disease. Our hypothesis is that more severe disease results in more pronounced deformation. The key contributions of this work are three-fold: (1) A new lung deformation based biomarker analyzing regions of differential distensions between COVID-19 patients with mild and severe disease. (2) Integrating 3D-CNN characterization of lung deformation regions and lung infiltrates on lung CT into a novel framework (LuMiRa) for prognosticating COVID-19 severity. (3) Validating LuMiRa on one of the largest multi-institutional cohort till date (N = 948 patients). We found that majority of the shape deformations were observed in the mediastinal surface of both the lungs and in left interior lobe. On a testing cohort based on two institutions, Av (N = 419) and Bv (N = 113), LuMiRa yielded an area under the receiver operating characteristic curve (AUC) of 0.89 and 0.77 respectively showing significant improvement over a 3D-CNN trained over just lung infiltrates (AUC = 0.85 (p < 0.001), AUC = 0.75 (p = 0.01)). Additionally, LuMiRa performed significantly better than machine learning models trained on clinical and radiomic features (0.82, 0.78 and 0.72, 0.72 on Av and Bv respectively). © 2021, Springer Nature Switzerland AG.

Investigation of the discomforts of the medical staff in COVID-19 isolation room

Objective: To investigate the occurrence of medical staff leaving the COVID-19 isolation room due to discomforts and to provide reference for clinical prevention and treatment. Methods: Stratified sampling method was used to investigate the occurrence of medical staff from Shanghai medical team leaving isolation room earlier due to discomforts, as well as the main symptoms and signs of theirs. Logistic regression was used for risk factor analysis. Results: Among the 227 medical staff working in Leishenshan Hospital in Wuhan, Hubei Province, who were assisted by Shanghai, 69 (30.4%) staff left earlier due to discomforts while working in the isolation room. Two of them had syncope, and sixty-seven of them had symptoms and signs related to presyncope. Symptoms of presyncope include headache, nausea, sweating, dyspnea, and palpitations, etc. Univariate analysis revealed statistically significant differences in occupation (P=0.002), gender (P=0.006), and standing time (P=0.002). Logistic regression analysis showed that occupation (P=0.000), standing time (P=0.025), and hunger (P=0.029) were statistically significant. Conclusion: Different occupation, gender and standing time have different effects on the situation of medical staff leaving the isolation room due to discomforts. Occupation, standing time and feeling of hunger are the influencial factors for medical staff leaving the isolation room earlier.