Dataset Information

Expected and observed in-hospital mortality in heart failure patients before and during the COVID-19 pandemic: Introduction of the machine learning-based standardized mortality ratio at Helios hospitals.

ABSTRACT:

Background

Reduced hospital admission rates for heart failure (HF) and evidence of increased in-hospital mortality were reported during the COVID-19 pandemic. The aim of this study was to apply a machine learning (ML)-based mortality prediction model to examine whether the latter is attributable to differing case mixes and exceeds expected mortality rates.

Methods and results

Inpatient cases with a primary discharge diagnosis of HF non-electively admitted to 86 German Helios hospitals between 01/01/2016 and 08/31/2020 were identified. Patients with proven or suspected SARS-CoV-2 infection were excluded. ML-based models were developed, tuned, and tested using cases of 2016-2018 (n = 64,440; randomly split 75%/25%). Extreme gradient boosting showed the best model performance indicated by a receiver operating characteristic area under the curve of 0.882 (95% confidence interval [CI]: 0.872-0.893). The model was applied on data sets of 2019 and 2020 (n = 28,556 cases) and the hospital standardized mortality ratio (HSMR) was computed as the observed to expected death ratio. Observed mortality rates were 5.84% (2019) and 6.21% (2020), HSMRs based on an individual case-based mortality probability were 100.0 (95% CI: 93.3-107.2; p = 1.000) for 2019 and 99.3 (95% CI: 92.5-106.4; p = .850) for 2020. Within subgroups of age or hospital volume, there were no significant differences between observed and expected deaths. When stratified for pandemic phases, no excess death during the COVID-19 pandemic was observed.

Conclusion

Applying an ML algorithm to calculate expected inpatient mortality based on administrative data, there was no excess death above expected event rates in HF patients during the COVID-19 pandemic.

SUBMITTER: Konig S

PROVIDER: S-EPMC8799043 | biostudies-literature | 2022 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Expected and observed in-hospital mortality in heart failure patients before and during the COVID-19 pandemic: Introduction of the machine learning-based standardized mortality ratio at Helios hospitals.

König Sebastian S Pellissier Vincent V Leiner Johannes J Hohenstein Sven S Ueberham Laura L Meier-Hellmann Andreas A Kuhlen Ralf R Hindricks Gerhard G Bollmann Andreas A

Clinical cardiology 20211223 1

<h4>Background</h4>Reduced hospital admission rates for heart failure (HF) and evidence of increased in-hospital mortality were reported during the COVID-19 pandemic. The aim of this study was to apply a machine learning (ML)-based mortality prediction model to examine whether the latter is attributable to differing case mixes and exceeds expected mortality rates.<h4>Methods and results</h4>Inpatient cases with a primary discharge diagnosis of HF non-electively admitted to 86 German Helios hospi ...[more]

PMID: 34951030

Similar Datasets

Project description:IntroductionA common quality indicator for monitoring and comparing hospitals is based on death within 30 days of admission. An important use is to determine whether a hospital has higher or lower mortality than other hospitals. Thus, the ability to identify such outliers correctly is essential. Two approaches for detection are: 1) calculating the ratio of observed to expected number of deaths (OE) per hospital and 2) including all hospitals in a logistic regression (LR) comparing each hospital to a form of average over all hospitals. The aim of this study was to compare OE and LR with respect to correctly identifying 30-day mortality outliers. Modifications of the methods, i.e., variance corrected approach of OE (OE-Faris), bias corrected LR (LR-Firth), and trimmed mean variants of LR and LR-Firth were also studied.Materials and methodsTo study the properties of OE and LR and their variants, we performed a simulation study by generating patient data from hospitals with known outlier status (low mortality, high mortality, non-outlier). Data from simulated scenarios with varying number of hospitals, hospital volume, and mortality outlier status, were analysed by the different methods and compared by level of significance (ability to falsely claim an outlier) and power (ability to reveal an outlier). Moreover, administrative data for patients with acute myocardial infarction (AMI), stroke, and hip fracture from Norwegian hospitals for 2012-2014 were analysed.ResultsNone of the methods achieved the nominal (test) level of significance for both low and high mortality outliers. For low mortality outliers, the levels of significance were increased four- to fivefold for OE and OE-Faris. For high mortality outliers, OE and OE-Faris, LR 25% trimmed and LR-Firth 10% and 25% trimmed maintained approximately the nominal level. The methods agreed with respect to outlier status for 94.1% of the AMI hospitals, 98.0% of the stroke, and 97.8% of the hip fracture hospitals.ConclusionWe recommend, on the balance, LR-Firth 10% or 25% trimmed for detection of both low and high mortality outliers.

Project description:IntroductionA health care system is a complex adaptive system. The effect of a single intervention, incorporated into a complex clinical environment, may be different from that expected. A national database such as the Intensive Care National Audit & Research Centre (ICNARC) Case Mix Programme in the UK represents a centralised monitoring, surveillance and reporting system for retrospective quality and comparative audit. This can be supplemented with real-time process monitoring at a local level for continuous process improvement, allowing early detection of the impact of both unplanned and deliberately imposed changes in the clinical environment.MethodsDemographic and UK Acute Physiology and Chronic Health Evaluation II (APACHE II) data were prospectively collected on all patients admitted to a UK regional hospital between 1 January 2003 and 30 June 2004 in accordance with the ICNARC Case Mix Programme. We present a cumulative expected minus observed (E-O) plot and the risk-adjusted p chart as methods of continuous process monitoring. We describe the construction and interpretation of these charts and show how they can be used to detect planned or unplanned organisational process changes affecting mortality outcomes.ResultsFive hundred and eighty-nine adult patients were included. The overall death rate was 0.78 of predicted. Calibration showed excess survival in ranges above 30% risk of death. The E-O plot confirmed a survival above that predicted. Small transient variations were seen in the slope that could represent random effects, or real but transient changes in the quality of care. The risk-adjusted p chart showed several observations below the 2 SD control limits of the expected mortality rate. These plots provide rapid analysis of risk-adjusted performance suitable for local application and interpretation. The E-O chart provided rapid easily visible feedback of changes in risk-adjusted mortality, while the risk-adjusted p chart allowed statistical evaluation.ConclusionLocal analysis of risk-adjusted mortality data with an E-O plot and a risk-adjusted p chart is feasible and allows the rapid detection of changes in risk-adjusted outcome of intensive care patients. This complements the centralised national database, which is more archival and comparative in nature.

Dataset Information

Expected and observed in-hospital mortality in heart failure patients before and during the COVID-19 pandemic: Introduction of the machine learning-based standardized mortality ratio at Helios hospitals.

Background

Methods and results

Conclusion

Publications

Expected and observed in-hospital mortality in heart failure patients before and during the COVID-19 pandemic: Introduction of the machine learning-based standardized mortality ratio at Helios hospitals.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets