Skip to main content

Lundgren, Jens

Early Stimulated Immune Responses Predict Clinical Disease Severity in Hospitalized COVID-19 Patients

Svanberg, Rebecka
MacPherson, Cameron
Zucco, Adrian
Agius, Rudi
Faitova, Tereza
Andersen, Michael Asger
Da Cunha-Bang, Caspar
Gjærde, Lars Klingen
Møller, Maria Elizabeth Engel
Brooks, Patrick Terrence
Lindegaard, Birgitte
Sejdic, Adin
Gang, Anne Ortved
Hersby, Ditte Stampe
Brieghel, Christian
Nielsen, Susanne Dam
Podlekareva, Daria
Hald, Annemette
Bay, Jakob Thaning
Marquart, Hanne
Lundgren, Jens
Lebech, Anne-Mette
Helleberg, Marie
Niemann, Carsten Utoft
Ostrowski, Sisse Rye
Innate Immunity Viral Infection
The immune pathogenesis underlying the diverse clinical course of COVID-19 is poorly understood. Currently, there is an unmet need in daily clinical practice for early biomarkers and improved risk stratification tools to help identify and monitor COVID-19 patients at risk of severe disease.

Readmissions, Postdischarge Mortality, and Sustained Recovery Among Patients Admitted to Hospital With Coronavirus Disease 2019 (COVID-19)

Moestrup, Kasper S
Reekie, Joanne
Zucco, Adrian G
Jensen, Tomas Ø
Jensen, Jens Ulrik S
Wiese, Lothar
Ostrowski, Sisse R
Niemann, Carsten U
MacPherson, Cameron
Lundgren, Jens
Helleberg, Marie
Many interventional in-patient coronavirus disease 2019 (COVID-19) trials assess primary outcomes through day 28 post-randomization. Since a proportion of patients experience protracted disease or relapse, such follow-up period may not fully capture the course of the disease, even when randomization occurs a few days after hospitalization.Among adults hospitalized with COVID-19 in eastern Denmark from 18 March 2020–12 January 2021 we assessed all-cause mortality, recovery, and sustained recovery 90 days after admission, and readmission and all-cause mortality 90 days after discharge. Recovery was defined as hospital discharge and sustained recovery as recovery and alive without readmissions for 14 consecutive days.Among 3386 patients included in the study, 2796 (82.6%) reached recovery and 2600 (77.0%) achieved sustained recovery. Of those discharged from hospital, 556 (19.9%) were readmitted and 289 (10.3%) died. Overall, the median time to recovery was 6 days (interquartile range [IQR]: 3–10), and 19 days (IQR: 11–33) among patients in intensive care in the first 2 days of admission.Postdischarge readmission and mortality rates were substantial. Therefore, sustained recovery should be favored to recovery outcomes in clinical COVID-19 trials. A 28-day follow-up period may be too short for the critically ill.

Personalized Survival Probabilities for SARS-CoV-2 Positive Patients by Explainable Machine Learning

Zucco, Adrian G.
Agius, Rudi
Svanberg, Rebecka
Moestrup, Kasper S.
Marandi, Ramtin Z.
MacPherson, Cameron Ross
Lundgren, Jens
Ostrowski, Sisse R.
Niemann, Carsten U.
Machine Learning Prognosis Viral Infection
Interpretable risk assessment of SARS-CoV-2 positive patients can aid clinicians to implement precision medicine. Here we trained a machine learning model to predict mortality within 12~weeks of a first positive SARS-CoV-2 test. By leveraging data on 33,938 confirmed SARS-CoV-2 cases in eastern Denmark, we considered 2723 variables extracted from electronic health records (EHR) including demographics, diagnoses, medications, laboratory test results and vital parameters. A discrete-time framework for survival modelling enabled us to predict personalized survival curves and explain individual risk factors. Performance on the test set was measured with a weighted concordance index of 0.95 and an area under the curve for precision-recall of 0.71. Age, sex, number of medications, previous hospitalizations and lymphocyte counts were identified as top mortality risk factors. Our explainable survival model developed on EHR data also revealed temporal dynamics of the 22 selected risk factors. Upon further validation, this model may allow direct reporting of personalized survival probabilities in routine care.
Personalized Survival Probabilities for SARS-CoV-2 Positive Patients by Explainable Machine Learning