Domain Shifts in Machine Learning Based Covid-19 Diagnosis From Blood Tests.

Many previous studies claim to have developed machine learning models that diagnose COVID-19 from blood tests. However, we hypothesize that changes in the underlying distribution of the data, so called domain shifts, affect the predictive performance and reliability and are a reason for the failure of such machine learning models in clinical application. Domain shifts can be caused, e.g., by changes in the disease prevalence (spreading or tested population), by refined RT-PCR testing procedures (way of taking samples, laboratory procedures), or by virus mutations. Therefore, machine learning models for diagnosing COVID-19 or other diseases may not be reliable and degrade in performance over time. We investigate whether domain shifts are present in COVID-19 datasets and how they affect machine learning methods. We further set out to estimate the mortality risk based on routinely acquired blood tests in a hospital setting throughout pandemics and under domain shifts. We reveal domain shifts by evaluating the models on a large-scale dataset with different assessment strategies, such as temporal validation. We present the novel finding that domain shifts strongly affect machine learning models for COVID-19 diagnosis and deteriorate their predictive performance and credibility. Therefore, frequent re-training and re-assessment are indispensable for robust models enabling clinical utility.

qSOFA score poorly predicts critical progression in COVID-19 patients.

BACKGROUND: In December 2019, the new virus infection coronavirus disease 2019 (COVID-19) caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) emerged. Simple clinical risk scores may improve the management of COVID-19 patients. Therefore, the aim of this pilot study was to evaluate the quick Sequential Organ Failure Assessment (qSOFA) score, which is well established for other diseases, as an early risk assessment tool predicting a severe course of COVID-19. METHODS: We retrospectively analyzed data from adult COVID-19 patients hospitalized between March and July 2020. A critical disease progress was defined as admission to intensive care unit (ICU) or death. RESULTS: Of 64 COVID-19 patients, 33% (21/64) had a critical disease progression from which 13 patients had to be transferred to ICU. The COVID-19-associated mortality rate was 20%, increasing to 39% after ICU admission. All patients without a critical progress had a qSOFA score ≤ 1 at admission. Patients with a critical progress had in only 14% (3/21) and in 20% (3/15) of cases a qSOFA score ≥ 2 at admission (p = 0.023) or when measured directly before critical progression, respectively, while 95% (20/21) of patients with critical progress had an impairment oxygen saturation (SO2) at admission time requiring oxygen supplementation. CONCLUSION: A low qSOFA score cannot be used to assume short-term stable or noncritical disease status in COVID-19.

Implications of early respiratory support strategies on disease progression in critical COVID-19: a matched subanalysis of the prospective RISC-19-ICU cohort.

BACKGROUND: Uncertainty about the optimal respiratory support strategies in critically ill COVID-19 patients is widespread. While the risks and benefits of noninvasive techniques versus early invasive mechanical ventilation (IMV) are intensely debated, actual evidence is lacking. We sought to assess the risks and benefits of different respiratory support strategies, employed in intensive care units during the first months of the COVID-19 pandemic on intubation and intensive care unit (ICU) mortality rates. METHODS: Subanalysis of a prospective, multinational registry of critically ill COVID-19 patients. Patients were subclassified into standard oxygen therapy ≥10 L/min (SOT), high-flow oxygen therapy (HFNC), noninvasive positive-pressure ventilation (NIV), and early IMV, according to the respiratory support strategy employed at the day of admission to ICU. Propensity score matching was performed to ensure comparability between groups. RESULTS: Initially, 1421 patients were assessed for possible study inclusion. Of these, 351 patients (85 SOT, 87 HFNC, 87 NIV, and 92 IMV) remained eligible for full analysis after propensity score matching. 55% of patients initially receiving noninvasive respiratory support required IMV. The intubation rate was lower in patients initially ventilated with HFNC and NIV compared to those who received SOT (SOT: 64%, HFNC: 52%, NIV: 49%, p = 0.025). Compared to the other respiratory support strategies, NIV was associated with a higher overall ICU mortality (SOT: 18%, HFNC: 20%, NIV: 37%, IMV: 25%, p = 0.016). CONCLUSION: In this cohort of critically ill patients with COVID-19, a trial of HFNC appeared to be the most balanced initial respiratory support strategy, given the reduced intubation rate and comparable ICU mortality rate. Nonetheless, considering the uncertainty and stress associated with the COVID-19 pandemic, SOT and early IMV represented safe initial respiratory support strategies. The presented findings, in agreement with classic ARDS literature, suggest that NIV should be avoided whenever possible due to the elevated ICU mortality risk.

Myocardial injury in severe COVID-19 is similar to pneumonias of other origin: results from a multicentre study.

AIMS: COVID-19, a respiratory viral disease causing severe pneumonia, also affects the heart and other organs. Whether its cardiac involvement is a specific feature consisting of myocarditis, or simply due to microvascular injury and systemic inflammation, is yet unclear and presently debated. Because myocardial injury is also common in other kinds of pneumonias, we investigated and compared such occurrence in severe pneumonias due to COVID-19 and other causes. METHODS AND RESULTS: We analysed data from 156 critically ill patients requiring mechanical ventilation in four European tertiary hospitals, including all n = 76 COVID-19 patients with severe disease course requiring at least ventilatory support, matched to n = 76 from a retrospective consecutive patient cohort of severe pneumonias of other origin (matched for age, gender, and type of ventilator therapy). When compared to the non-COVID-19, mortality (COVID-19 = 38.2% vs. non-COVID-19 = 51.3%, P = 0.142) and impairment of systolic function were not significantly different. Surprisingly, myocardial injury was even more frequent in non-COVID-19 (96.4% vs. 78.1% P = 0.004). Although inflammatory activity [C-reactive protein (CRP) and interleukin-6] was indifferent, d-dimer and thromboembolic incidence (COVID-19 = 23.7% vs. non-COVID-19 = 5.3%, P = 0.002) driven by pulmonary embolism rates (COVID-19 = 17.1% vs. non-COVID-19 = 2.6%, P = 0.005) were higher. CONCLUSIONS: Myocardial injury was frequent in severe COVID-19 requiring mechanical ventilation, but still less frequent than in similarly severe pneumonias of other origin, indicating that cardiac involvement may not be a specific feature of COVID-19. While mortality was also similar, COVID-19 is characterized with increased thrombogenicity and high pulmonary embolism rates.

Machine Learning Prediction of SARS-CoV-2 Polymerase Chain Reaction Results with Routine Blood Tests.

OBJECTIVE: The diagnosis of COVID-19 is based on the detection of SARS-CoV-2 in respiratory secretions, blood, or stool. Currently, reverse transcription polymerase chain reaction (RT-PCR) is the most commonly used method to test for SARS-CoV-2. METHODS: In this retrospective cohort analysis, we evaluated whether machine learning could exclude SARS-CoV-2 infection using routinely available laboratory values. A Random Forests algorithm with 28 unique features was trained to predict the RT-PCR results. RESULTS: Out of 12,848 patients undergoing SARS-CoV-2 testing, routine blood tests were simultaneously performed in 1357 patients. The machine learning model could predict SARS-CoV-2 test results with an accuracy of 86% and an area under the receiver operating characteristic curve of 0.74. CONCLUSION: Machine learning methods can reliably predict a negative SARS-CoV-2 RT-PCR test result using standard blood tests.