Dataset Information

Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients.

ABSTRACT: Patients with severe COVID-19 have overwhelmed healthcare systems worldwide. We hypothesized that machine learning (ML) models could be used to predict risks at different stages of management and thereby provide insights into drivers and prognostic markers of disease progression and death. From a cohort of approx. 2.6 million citizens in Denmark, SARS-CoV-2 PCR tests were performed on subjects suspected for COVID-19 disease; 3944 cases had at least one positive test and were subjected to further analysis. SARS-CoV-2 positive cases from the United Kingdom Biobank was used for external validation. The ML models predicted the risk of death (Receiver Operation Characteristics-Area Under the Curve, ROC-AUC) of 0.906 at diagnosis, 0.818, at hospital admission and 0.721 at Intensive Care Unit (ICU) admission. Similar metrics were achieved for predicted risks of hospital and ICU admission and use of mechanical ventilation. Common risk factors, included age, body mass index and hypertension, although the top risk features shifted towards markers of shock and organ dysfunction in ICU patients. The external validation indicated fair predictive performance for mortality prediction, but suboptimal performance for predicting ICU admission. ML may be used to identify drivers of progression to more severe disease and for prognostication patients in patients with COVID-19. We provide access to an online risk calculator based on these findings.

SUBMITTER: Jimenez-Solem E

PROVIDER: S-EPMC7864944 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients.

Jimenez-Solem Espen E Petersen Tonny S TS Hansen Casper C Hansen Christian C Lioma Christina C Igel Christian C Boomsma Wouter W Krause Oswin O Lorenzen Stephan S Selvan Raghavendra R Petersen Janne J Nyeland Martin Erik ME Ankarfeldt Mikkel Zöllner MZ Virenfeldt Gert Mehl GM Winther-Jensen Matilde M Linneberg Allan A Ghazi Mostafa Mehdipour MM Detlefsen Nicki N Lauritzen Andreas David AD Smith Abraham George AG de Bruijne Marleen M Ibragimov Bulat B Petersen Jens J Lillholm Martin M Middleton Jon J Mogensen Stine Hasling SH Thorsen-Meyer Hans-Christian HC Perner Anders A Helleberg Marie M Kaas-Hansen Benjamin Skov BS Bonde Mikkel M Bonde Alexander A Pai Akshay A Nielsen Mads M Sillesen Martin M

Scientific reports 20210205 1

Patients with severe COVID-19 have overwhelmed healthcare systems worldwide. We hypothesized that machine learning (ML) models could be used to predict risks at different stages of management and thereby provide insights into drivers and prognostic markers of disease progression and death. From a cohort of approx. 2.6 million citizens in Denmark, SARS-CoV-2 PCR tests were performed on subjects suspected for COVID-19 disease; 3944 cases had at least one positive test and were subjected to further ...[more]

PMID: 33547335

Similar Datasets

Project description:ObjectivesTo identify antenatal ultrasound markers that can differentiate between simple and complex gastroschisis and assess their predictive value.MethodsThis was a prospective nationwide study of pregnancies with isolated fetal gastroschisis that underwent serial longitudinal ultrasound examination at regular specified intervals between 20 and 37 weeks' gestation. The primary outcome was simple or complex (i.e. involving bowel atresia, volvulus, perforation or necrosis) gastroschisis at birth. Fetal biometry (abdominal circumference and estimated fetal weight), the occurrence of polyhydramnios, intra- and extra-abdominal bowel diameters and the pulsatility index (PI) of the superior mesenteric artery (SMA) were assessed. Linear mixed modeling was used to compare the individual trajectories of cases with simple and those with complex gastroschisis, and logistic regression analysis was used to estimate the strength of association between the ultrasound parameters and outcome.ResultsOf 104 pregnancies with isolated fetal gastroschisis included, four ended in intrauterine death. Eighty-one (81%) liveborn infants with simple and 19 (19%) with complex gastroschisis were included in the analysis. We found no relationship between fetal biometric variables and complex gastroschisis. The SMA-PI was significantly lower in fetuses with gastroschisis than in healthy controls, but did not differentiate between simple and complex gastroschisis. Both intra- and extra-abdominal bowel diameters were larger in cases with complex, compared to those with simple, gastroschisis (P < 0.001 and P < 0.005, respectively). The presence of intra-abdominal bowel diameter ≥ 97.7th percentile on at least three occasions, not necessarily on successive examinations, was associated with an increased risk of the fetus having complex gastroschisis (relative risk, 1.56 (95% CI, 1.02-2.10); P = 0.006; positive predictive value, 50.0%; negative predictive value, 81.4%).ConclusionsThis large prospective longitudinal study found that intra-abdominal bowel dilatation when present repeatedly during fetal development can differentiate between simple and complex gastroschisis; however, the positive predictive value is low, and therefore the clinical usefulness of this marker is limited. © 2019 Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Project description:To evaluate if oral fluoroquinolone use is associated with an increased risk of serious arrhythmia.Bi-national cohort study, linking register data on filled prescriptions, cases of serious arrhythmia, and patient characteristics.Denmark, 1997-2011; Sweden, 2006-13.The study cohort was derived from a source population of all Danish and Swedish adults, aged 40 to 79 years. 909,656 courses of fluoroquinolone use (ciprofloxacin 82.6%, norfloxacin 12.1%, ofloxacin 3.2%, moxifloxacin 1.2%, and other fluoroquinolones 0.9%) and 909,656 courses of penicillin V use, matched 1:1 on propensity score, were included.The main outcome was risk of serious arrhythmia (fatal and non-fatal), comparing courses of fluoroquinolone use with courses of penicillin V use (an antibiotic with no pro-arrhythmic effect). The risk period of interest was current use, defined as days 0-7 of treatment. Subgroup analyses were conducted according to country, sex, age, underlying cardiovascular disease, concomitant use of drugs known to increase the risk of torsades de pointes, fluoroquinolone type, and levels of arrhythmia risk score.144 cases of serious arrhythmia occurred during follow-up, 66 among current fluoroquinolone users (incidence rate 3.4 per 1000 person years) and 78 among current penicillin users (4.0 per 1000 person years); comparing oral fluoroquinolone treatment with penicillin V, the rate ratio was 0.85 (95% confidence interval 0.61 to 1.18). Compared with penicillin V, the absolute risk difference was -13 (95% confidence interval -35 to 16) cases of serious arrhythmia per 1,000,000 courses of fluoroquinolones. The risk of serious arrhythmia was not statistically significantly increased in any of the subgroups, including analyses by fluoroquinolone type.Contrary to previous reports, oral fluoroquinolone treatment was not associated with an increased risk of serious arrhythmia in the general adult populations of Denmark and Sweden. Given the statistical power of the study, even small increases in relative and absolute risk could be ruled out. Since ciprofloxacin was the most commonly used fluoroquinolone in our study, we cannot exclude that intraclass differences influence the risk of serious arrhythmia associated with other less frequently used fluoroquinolones.

Project description:Rationale & objectiveRisk factors for acute kidney injury (AKI) in the hospital have been well studied. Yet, risk factors for identifying high-risk patients for AKI occurring and managed in the outpatient setting are unknown and may differ.Study designPredictive model development and external validation using observational electronic health record data.Setting & participantsPatients aged 18-90 years with recurrent primary care encounters, known baseline serum creatinine, and creatinine measured during an 18-month outcome period without established advanced kidney disease.New predictors & established predictorsEstablished predictors for inpatient AKI were considered. Potential new predictors were hospitalization history, smoking, serum potassium levels, and prior outpatient AKI.OutcomesA ≥50% increase in the creatinine level above a moving baseline of the recent measurement(s) without a hospital admission within 7 days defined outpatient AKI.Analytical approachLogistic regression with bootstrap sampling for backward stepwise covariate elimination was used. The model was then transformed into 2 binary tests: one identifying high-risk patients for research and another identifying patients for additional clinical monitoring or intervention.ResultsOutpatient AKI was observed in 4,611 (3.0%) and 115,744 (2.4%) patients in the development and validation cohorts, respectively. The model, with 18 variables and 3 interaction terms, produced C statistics of 0.717 (95% CI, 0.710-0.725) and 0.722 (95% CI, 0.720-0.723) in the development and validation cohorts, respectively. The research test, identifying the 5.2% most at-risk patients in the validation cohort, had a sensitivity of 0.210 (95% CI, 0.208-0.213) and specificity of 0.952 (95% CI, 0.951-0.952). The clinical test, identifying the 20% most at-risk patients, had a sensitivity of 0.494 (95% CI, 0.491-0.497) and specificity of 0.806 (95% CI, 0.806-0.807).LimitationsOnly surviving patients with measured creatinine levels during a baseline period and outcome period were included.ConclusionsThe outpatient AKI risk prediction model performed well in both the development and validation cohorts in both continuous and binary forms.

Project description:PurposeTools for survival prediction for non-small cell lung cancer (NSCLC) patients treated with chemoradiation or radiation therapy are of limited quality. In this work, we developed a predictive model of survival at 2 years. The model is based on a large volume of historical patient data and serves as a proof of concept to demonstrate the distributed learning approach.Methods and materialsClinical data from 698 lung cancer patients, treated with curative intent with chemoradiation or radiation therapy alone, were collected and stored at 2 different cancer institutes (559 patients at Maastro clinic (Netherlands) and 139 at Michigan university [United States]). The model was further validated on 196 patients originating from The Christie (United Kingdon). A Bayesian network model was adapted for distributed learning (the animation can be viewed at https://www.youtube.com/watch?v=ZDJFOxpwqEA). Two-year posttreatment survival was chosen as the endpoint. The Maastro clinic cohort data are publicly available at https://www.cancerdata.org/publication/developing-and-validating-survival-prediction-model-nsclc-patients-through-distributed, and the developed models can be found at www.predictcancer.org.ResultsVariables included in the final model were T and N category, age, performance status, and total tumor dose. The model has an area under the curve (AUC) of 0.66 on the external validation set and an AUC of 0.62 on a 5-fold cross validation. A model based on the T and N category performed with an AUC of 0.47 on the validation set, significantly worse than our model (P<.001). Learning the model in a centralized or distributed fashion yields a minor difference on the probabilities of the conditional probability tables (0.6%); the discriminative performance of the models on the validation set is similar (P=.26).ConclusionsDistributed learning from federated databases allows learning of predictive models on data originating from multiple institutions while avoiding many of the data-sharing barriers. We believe that distributed learning is the future of sharing data in health care.

Dataset Information

Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients.

Publications

Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets