A Modified PINN Approach for Identifiable Compartmental Models in Epidemiology with Applications to COVID-19 (preprint)

A variety of approaches using compartmental models have been used to study the COVID-19 pandemic and the usage of machine learning methods with these models has had particularly notable success. We present here an approach toward analyzing accessible data on Covid-19's U.S. development using a variation of the "Physics Informed Neural Networks" (PINN) which is capable of using the knowledge of the model to aid learning. We illustrate the challenges of using the standard PINN approach, then how with appropriate and novel modifications to the loss function the network can perform well even in our case of incomplete information. Aspects of identifiability of the model parameters are also assessed, as well as methods of denoising available data using a wavelet transform. Finally, we discuss the capability of the neural network methodology to work with models of varying parameter values, as well as a concrete application in estimating how effectively cases are being tested for in a population, providing a ranking of U.S. states by means of their respective testing.

Clinical characteristics of hospitalized patients in Binzhou, China during periods of the SARS-CoV-2 Omicron variant BA.2 predominance: a single-centered, retrospective, observational study (preprint)

Background: Since the first identification of the novel SARS-CoV-2 variant of concern Omicron in South Africa, it has rapidly spread around the world. This study aimed to evaluate the clinical and laboratory characteristics of patients infected with the SARS-CoV-2 Omicron variant BA.2. Methods: In this retrospective study, we extracted data for 422 patients in Binzhou COVID-19 treatment centerl from March 11 to April 28, 2022. Cases were analyzed on the basis of demographic, clinical, and laboratory data as well as radiological features. Results: Of 422 hospitalized patients with SARS-CoV-2 Omicron Variant BA.2, there were 311 (73.7%) asymptomatic, 102 (24.1%) mild cases and 9 (2.1%) moderate cases. The median age was 38 years (IQR, 14 to 58) for all the participants, and the cohort included 207 men and 215 women. Compared with asymptomatic patients, moderate patients were older and had more chronic comorbidities (P<0.001). For all patients, Only 23 (5.5%) of 422 patients had never received any COVID-19 vaccine dose. Nonvaccination rate was significant difference between asymptomatic group and moderte group (4.5% vs 33.3%, p=0.001), respectively. The most common symptoms at onset of illness were fever, fatigue. Moderate patients had more ground-glass opacity, and patchy shadowing. Lymphopenia was present in 6.6% of all patients, which was more common in moderate patients than asymptomatic patients (44.4% vs 4.8%, P<0.001). Conclusion: Unvaccinated and older patients (>65 years) with comorbidities are at increased risk of moderate infection. Lymphopenia, increased D-dimer, ground-glass opacity, and patchy shadowing are common in moderate patients.