COVIDAL: A Machine Learning Classifier for Digital COVID-19 Diagnosis in German Hospitals

For the fight against the COVID-19 pandemic, it is particularly important to map the course of infection, in terms of patients who have currently tested SARS-CoV-2 positive, as accurately as possible. In hospitals, this is even more important because resources have become scarce. Although polymerase chain reaction (PCR) and point of care (POC) antigen testing capacities have been massively expanded, they are often very time-consuming and cost-intensive and, in some cases, lack appropriate performance. To meet these challenges, we propose the COVIDAL classifier for AI-based diagnosis of symptomatic COVID-19 subjects in hospitals based on laboratory parameters. We evaluate the algorithm's performance by unique multicenter data with approximately 4,000 patients and an extraordinary high ratio of SARS-CoV-2-positive patients. We analyze the influence of data preparation, flexibility in optimization targets, as well as the selection of the test set on the COVIDAL outcome. The algorithm is compared with standard AI, PCR, POC antigen testing and manual classifications of seven physicians by a decision theoretic scoring model including performance metrics, turnaround times and cost. Thereby, we define health care settings in which a certain classifier for COVID-19 diagnosis is to be applied. We find sensitivities, specificities, and accuracies of the COVIDAL algorithm of up to 90 percent. Our scoring model suggests using PCR testing for a focus on performance metrics. For turnaround times, POC antigen testing should be used. If balancing performance, turnaround times, and cost is of interest, as, for example, in the emergency department, COVIDAL is superior based on the scoring model. © 2023 Association for Computing Machinery.

A proof of concept study for the differentiation of SARS-CoV-2, hCoV-NL63, and IAV-H1N1 in vitro cultures using ion mobility spectrometry.

Rapid, high-throughput diagnostic tests are essential to decelerate the spread of the novel coronavirus disease 2019 (COVID-19) pandemic. While RT-PCR tests performed in centralized laboratories remain the gold standard, rapid point-of-care antigen tests might provide faster results. However, they are associated with markedly reduced sensitivity. Bedside breath gas analysis of volatile organic compounds detected by ion mobility spectrometry (IMS) may enable a quick and sensitive point-of-care testing alternative. In this proof-of-concept study, we investigated whether gas analysis by IMS can discriminate severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) from other respiratory viruses in an experimental set-up. Repeated gas analyses of air samples collected from the headspace of virus-infected in vitro cultures were performed for 5 days. A three-step decision tree using the intensities of four spectrometry peaks correlating to unidentified volatile organic compounds allowed the correct classification of SARS-CoV-2, human coronavirus-NL63, and influenza A virus H1N1 without misassignment when the calculation was performed with data 3 days post infection. The forward selection assignment model allowed the identification of SARS-CoV-2 with high sensitivity and specificity, with only one of 231 measurements (0.43%) being misclassified. Thus, volatile organic compound analysis by IMS allows highly accurate differentiation of SARS-CoV-2 from other respiratory viruses in an experimental set-up, supporting further research and evaluation in clinical studies.

[Role of university hospitals in Bavaria during the COVID-19 pandemic]. / Die Universitätsmedizin in Bayern im Rahmen der COVID-19-Pandemie.

BACKGROUND: In early 2020 the German healthcare system was put into a state of emergency due to the coronavirus disease 2019 (COVID-19) pandemic. Bavaria had to deal with more severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infections than any other German state during the first wave and currently has over 270,000 cases, accounting for about one fifth of all COVID-19 cases in Germany. The Bavarian Ministry of Interior together with the Bavarian Sate Ministry of Health and Care issued a general ruling at the beginning of the first wave that ordered the centralised organisation of hospital capacity, a redesign of the information technology (IT) management system and introduced reporting obligations for SARS-CoV-2/COVID-19. The goal of this analysis was to investigate the role that university hospitals played in the inpatient treatment of COVID-19 patients. METHODS: A retrospective evaluation of all inpatient COVID-19 cases that were reported through the "IVENA Sonderlage" (Ivena eHEALTH, [IVENA, interdisziplinärer Versorgungsnachweis, mainis IT-Service GmbH, Offenbach am Main, Germany]), a special module for the "Interdisciplinary Medical Care Capacity Management System" designed for extraordinary events and circumstances, was conducted by analysing the number of reported treatment days of all Bavarian hospitals that participated in the treatment of COVID-19 patients. RESULTS: During the first wave university hospitals provided relevant scientific contributions and played an important role in advising physicians, hospitals and politicians on the pandemic. In all, 20% of intensive care unit (ICU) and intermediate care (IMC) treatment days were provided by the university hospitals in particular for treatment of complex courses of COVID-19.

[S2k Guideline - Recommendations for Inpatient Therapy of Patients with COVID-19]. / S2k-Leitlinie ­ Empfehlungen zur stationären Therapie von Patienten mit COVID-19.

Since December 2019, the novel coronavirus SARS-CoV-2 (Severe Acute Respiratory Syndrome - Corona Virus-2) has been spreading rapidly in the sense of a global pandemic. This poses significant challenges for clinicians and hospitals and is placing unprecedented strain on the healthcare systems of many countries. The majority of patients with Coronavirus Disease 2019 (COVID-19) present with only mild symptoms such as cough and fever. However, about 6 % require hospitalization. Early clarification of whether inpatient and, if necessary, intensive care treatment is medically appropriate and desired by the patient is of particular importance in the pandemic. Acute hypoxemic respiratory insufficiency with dyspnea and high respiratory rate (> 30/min) usually leads to admission to the intensive care unit. Often, bilateral pulmonary infiltrates/consolidations or even pulmonary emboli are already found on imaging. As the disease progresses, some of these patients develop acute respiratory distress syndrome (ARDS). Mortality reduction of available drug therapy in severe COVID-19 disease has only been demonstrated for dexamethasone in randomized controlled trials. The main goal of supportive therapy is to ensure adequate oxygenation. In this regard, invasive ventilation and repeated prone positioning are important elements in the treatment of severely hypoxemic COVID-19 patients. Strict adherence to basic hygiene, including hand hygiene, and the correct wearing of adequate personal protective equipment are essential when handling patients. Medically necessary actions on patients that could result in aerosol formation should be performed with extreme care and preparation.

[Numbers of emergency room patients during the COVID-19 pandemic]. / Patientenzahlen im Rahmen der COVID-19-Pandemie in einer zentralen Notaufnahme.

BACKGROUND: Since end of March, the health care system in Germany has been placed into a state of emergency in order to gain resources for the spreading coronavirus disease 2019 (COVID-19) pandemic. The overall goal of this study is to evaluate the number of emergency room patients at the time of the pandemic in order to draw conclusions about the influence of the COVID 19 pandemic on the number of patients in an emergency department. MATERIALS AND METHODS: With this descriptive epidemiologic study we collected and analyzed anonymized patient-related data of 19,357 cases presenting to the emergency department of the Klinikum rechts der Isar (Munich) from 01 February 2019 to 30 April 2019 and from 01 February 2020 to 30 April 2020. RESULTS: Despite an increase in the number of patients from 2019 to 2020, there was a significant drop in the number of emergencies from February to March 2020 and proceeding in April to a level below that of 2019. This was particularly observed in the field of trauma surgery, with a 40% decrease in the number of patients. With regard to the individual complaint patterns in March 2020, it was found that an increased incidence of malaise (+47%) and breathing problems (+36%) was recorded, whereas back pain (-41%), wounds (-29%), thoracic (-24%) and abdominal pain (-23%) were significantly less common than in the previous year. In terms of the severity of the complaints, the decline was mainly due to complaints with a low degree of urgency. CONCLUSION: In the course of the COVID-19 pandemic we observed a significant decline in the number of patients in one of the largest emergency rooms in Munich. This has to be avoided with existing hospital capacities, in order to prevent potential damage to health caused by postponed or missing emergency presentations.