Characteristics and outcome of hospitalized patients with heart failure stratified for chronic kidney disease.

AIMS: Heart failure (HF) and chronic kidney disease (CKD) place significant challenges on the healthcare system, and their co-existence is associated with shared adverse outcomes. The multinational CaReMe project was initiated to provide contemporary, real-world epidemiological data on cardiovascular and reno-metabolic diseases. Utilizing data from the German CaReMe cohort, we characterize a multicentric HF population and describe in-hospital outcomes stratified for co-morbid CKD. METHODS AND RESULTS: This retrospective, observational study analysed administrative data from inpatient cases hospitalized in 87 German Helios hospitals between 1 January 2016 and 31 August 2022. The first hospitalization of patients aged ≥18 years with a primary discharge diagnosis of HF, based on ICD-10 codes, were considered the index cases, and subsequent hospitalizations were considered as readmissions. Baseline characteristics and outcomes were stratified for co-morbid CKD using ICD-10-encoding from the index cases. Cox regression was utilized for readmission endpoints and in-hospital mortality. In total, 174 829 index cases (mean age 79 ± 15 years, 49.9% female) were included; of these, 55.0% had coexisting CKD. Patients with CKD were older, suffered from worse HF-related symptoms, had a higher co-morbidity burden, and in-hospital mortality was increased at index and during follow-up. Prevalent CKD was associated with higher rehospitalization rates and was an independent predictor for in-hospital death. CONCLUSIONS: Within this HF inpatient cohort from a multicentric German database, CKD was diagnosed in more than half of the patients and was associated with increased in-hospital mortality at baseline and during follow-up. Rehospitalizations were observed earlier and more frequently in patients with HF and co-morbid CKD.

Artificial intelligence-based identification of left ventricular systolic dysfunction from 12-lead electrocardiograms: external validation and advanced application of an existing model.

Aims: The diagnostic application of artificial intelligence (AI)-based models to detect cardiovascular diseases from electrocardiograms (ECGs) evolves, and promising results were reported. However, external validation is not available for all published algorithms. The aim of this study was to validate an existing algorithm for the detection of left ventricular systolic dysfunction (LVSD) from 12-lead ECGs. Methods and results: Patients with digitalized data pairs of 12-lead ECGs and echocardiography (at intervals of ≤7 days) were retrospectively selected from the Heart Center Leipzig ECG and electronic medical records databases. A previously developed AI-based model was applied to ECGs and calculated probabilities for LVSD. The area under the receiver operating characteristic curve (AUROC) was computed overall and in cohorts stratified for baseline and ECG characteristics. Repeated echocardiography studies recorded ≥3 months after index diagnostics were used for follow-up (FU) analysis. At baseline, 42 291 ECG-echocardiography pairs were analysed, and AUROC for LVSD detection was 0.88. Sensitivity and specificity were 82% and 77% for the optimal LVSD probability cut-off based on Youden's J. AUROCs were lower in ECG subgroups with tachycardia, atrial fibrillation, and wide QRS complexes. In patients without LVSD at baseline and available FU, model-generated high probability for LVSD was associated with a four-fold increased risk of developing LVSD during FU. Conclusion: We provide the external validation of an existing AI-based ECG-analysing model for the detection of LVSD with robust performance metrics. The association of false positive LVSD screenings at baseline with a deterioration of ventricular function during FU deserves a further evaluation in prospective trials.

Patient perspectives on same-day discharge following catheter ablation for atrial fibrillation: results from a patient survey as part of the monocentric FAST AFA trial.

AIMS: Same-day discharge (SDD) following catheter ablation (CA) of atrial fibrillation (AF) was already introduced in selected facilities in Europe, but a widespread implementation has not yet succeeded. Data on patients' perspectives are lacking. Therefore, we conducted a survey to address patients' beliefs towards SDD and identify variables that are associated with their evaluation. METHODS AND RESULTS: As part of the prospective, monocentric FAST AFA trial, patients aged ≥20 years undergoing left atrial CA for AF were asked to participate in the survey consisting of a study-specific questionnaire, the AF knowledge scale, and pre-defined patient-reported outcome measures. The study cohort was stratified based on SDD willingness, and a logistic regression analysis was used to identify predictors for patients' valuation. Between 26 July 2021 and 01 July 2022, 256 of 376 screened patients consented to study participation of whom 248 (mean age 61.8 years, 33.9% female) completed the SDD survey. Of them, 50.0% were willing to have SDD concepts integrated into their clinical course with increased patient comfort (27.5%), shorter waiting times (14.6%), and a cost-efficient treatment (14.0%) being imaginable benefits. In contrast, expressed concerns included uncertainties with occurring complaints (50.6%), the insufficient recognition (47.8%), and treatment (48.9%) of complications. European Heart Rhythm Association class at baseline and inpatient treatments within the preceding year were predictors for SDD willingness whereas comorbidity burden or AF knowledge were not. CONCLUSION: We provide a detailed survey expressing patients' beliefs towards SDD following left atrial CA. Our findings may facilitate adequate patient selection to improve the future implementation of SDD programs in suitable cohorts.

Neurosurgical care for patients with high-grade gliomas during the coronavirus disease 2019 pandemic: Analysis of routine billing data of a German nationwide hospital network.

Background: Little is known about delivery of neurosurgical care, complication rate and outcome of patients with high-grade glioma (HGG) during the coronavirus disease 2019 (Covid-19) pandemic. Methods: This observational, retrospective cohort study analyzed routine administrative data of all patients admitted for neurosurgical treatment of an HGG within the Helios Hospital network in Germany. Data of the Covid-19 pandemic (March 1, 2020-May 31, 2022) were compared to the pre-pandemic period (January 1, 2016-February 29, 2020). Frequency of treatment and outcome (in-hospital mortality, length of hospital stay [LOHS], time in intensive care unit [TICU] and ventilation outside the operating room [OR]) were separately analyzed for patients with microsurgical resection (MR) or stereotactic biopsy (STBx). Results: A total of 1763 patients underwent MR of an HGG (648 patients during the Covid-19 pandemic; 1115 patients in the pre-pandemic period). 513 patients underwent STBx (182 [pandemic]; 331 patients [pre-pandemic]). No significant differences were found for treatment frequency (MR: 2.95 patients/week [Covid-19 pandemic] vs. 3.04 patients/week [pre-pandemic], IRR 0.98, 95% CI: 0.89-1.07; STBx (1.82 [Covid-19 pandemic] vs. 1.86 [pre-pandemic], IRR 0.96, 95% CI: 0.80-1.16, P > .05). Rates of in-hospital mortality, infection, postoperative hemorrhage, cerebral ischemia and ventilation outside the OR were similar in both periods. Overall LOHS was significantly shorter for patients with MR and STBx during the Covid-19 pandemic. Conclusions: The Covid-19 pandemic did not affect the frequency of neurosurgical treatment of patients with an HGG based on data of a large nationwide hospital network in Germany. LOHS was significantly shorter but quality of neurosurgical care and outcome was not altered during the Covid-19 pandemic.

COVID-19 and Severe Acute Respiratory Infections: Monitoring Trends in 421 German Hospitals During the First Four Pandemic Waves.

Introduction: Reliable surveillance systems to monitor trends of COVID-19 case numbers and the associated healthcare burden play a central role in efficient pandemic management. In Germany, the federal government agency Robert-Koch-Institute uses an ICD-code-based inpatient surveillance system, ICOSARI, to assess temporal trends of severe acute respiratory infection (SARI) and COVID-19 hospitalization numbers. In a similar approach, we present a large-scale analysis covering four pandemic waves derived from the Initiative of Quality Medicine (IQM), a German-wide network of acute care hospitals. Methods: Routine data from 421 hospitals for the years 2019-2021 with a "pre-pandemic" period (01-01-2019 to 03-03-2020) and a "pandemic" period (04-03-2020 to 31-12-2021) was analysed. SARI cases were defined by ICD-codes J09-J22 and COVID-19 by ICD-codes U07.1 and U07.2. The following outcomes were analysed: intensive care treatment, mechanical ventilation, in-hospital mortality. Results: Over 1.1 million cases of SARI and COVID-19 were identified. Patients with COVID-19 and additional codes for SARI were at higher risk for adverse outcomes when compared to non-COVID SARI and COVID-19 without any coding for SARI. During the pandemic period, non-COVID SARI cases were associated with 28%, 23% and 27% higher odds for intensive care treatment, mechanical ventilation and in-hospital mortality, respectively, compared to pre-pandemic SARI. Conclusion: The nationwide IQM network could serve as an excellent data source to enhance COVID-19 and SARI surveillance in view of the ongoing pandemic. Future developments of COVID-19/SARI case numbers and associated outcomes should be closely monitored to identify specific trends, especially considering novel virus variants.

A Digital Infrastructure for Cardiovascular Patient Care Based on Mobile Health Data and Patient-Reported Outcomes: Concept Details of the Helios TeleWear Project Including Preliminary Experiences.

BACKGROUND: Mobile health (mHealth) approaches are already having a fundamental impact on clinical practice in cardiovascular medicine. A variety of different health apps and wearable devices for capturing health data such as electrocardiograms (ECGs) exist. However, most mHealth technologies focus on distinct variables without integrating patients' quality of life, and the impact on clinical outcome measures of implementing those digital solutions into cardiovascular health care is still to be determined. OBJECTIVE: Within this document, we describe the TeleWear project, which was recently initiated as an approach for contemporary patient management integrating mobile-collected health data and the standardized mHealth-guided measurement of patient-reported outcomes (PROs) in patients with cardiovascular disease. METHODS: The specifically designed mobile app and clinical frontend form the central elements of our TeleWear infrastructure. Because of its flexible framework, the platform allows far-reaching customization with the possibility to add different mHealth data sources and respective questionnaires (patient-reported outcome measures). RESULTS: With initial focus on patients with cardiac arrhythmias, a feasibility study is currently carried out to assess wearable-recorded ECG and PRO transmission and its evaluation by physicians using the TeleWear app and clinical frontend. First experiences made during the feasibility study yielded positive results and confirmed the platform's functionality and usability. CONCLUSIONS: TeleWear represents a unique mHealth approach comprising PRO and mHealth data capturing. With the currently running TeleWear feasibility study, we aim to test and further develop the platform in a real-world setting. A randomized controlled trial including patients with atrial fibrillation that investigates PRO- and ECG-based clinical management based on the established TeleWear infrastructure will evaluate its clinical benefits. Widening the spectrum of health data collection and interpretation beyond the ECG and use of the TeleWear infrastructure in different patient subcohorts with focus on cardiovascular diseases are further milestones of the project with the ultimate goal to establish a comprehensive telemedical center entrenched by mHealth.

Changing trends of patient characteristics and treatment pathways during the COVID-19 pandemic: A cross-sectional analysis of 72,459 inpatient cases from the German Helios database.

Background: This study compared patient profiles and clinical courses of SARS-CoV-2 infected inpatients over different pandemic periods. Methods: In a retrospective cross-sectional analysis, we examined administrative data of German Helios hospitals using ICD-10-codes at discharge. Inpatient cases with SARS-CoV-2 infection admitted between 03/04/2020 and 07/19/2022 were included irrespective of the reason for hospitalization. All endpoints were timely assigned to admission date for trend analysis. The first pandemic wave was defined by change points in time-series of incident daily infections and compared with different later pandemic phases according to virus type predominance. Results: We included 72,459 inpatient cases. Patients hospitalized during the first pandemic wave (03/04/2020-05/05/2020; n = 1,803) were older (68.5 ± 17.2 vs. 64.4 ± 22.6 years, p < 0.01) and severe acute respiratory infections were more prevalent (85.2 vs. 53.3%, p < 0.01). No differences were observed with respect to distribution of sex, but comorbidity burden was higher in the first pandemic wave. The risk of receiving intensive care therapy was reduced in all later pandemic phases as was in-hospital mortality when compared to the first pandemic wave. Trend analysis revealed declines of mean age and Elixhauser comorbidity index over time as well as a decline of the utilization of intensive care therapy, mechanical ventilation and in-hospital mortality. Conclusion: Characteristics and outcomes of inpatients with SARS-CoV-2 infection changed throughout the observational period. An ongoing evaluation of trends and care pathways will allow for the assessment of future demands.

Characteristics and outcomes of COVID-19 patients during B.1.1.529 (Omicron) dominance compared to B.1.617.2 (Delta) in 89 German hospitals.

BACKGROUND: The SARS-CoV-2 variant B.1.1.529 (Omicron) was first described in November 2021 and became the dominant variant worldwide. Existing data suggests a reduced disease severity with Omicron infections in comparison to B.1.617.2 (Delta). Differences in characteristics and in-hospital outcomes of COVID-19 patients in Germany during the Omicron period compared to Delta are not thoroughly studied. ICD-10-code-based severe acute respiratory infections (SARI) surveillance represents an integral part of infectious disease control in Germany. METHODS: Administrative data from 89 German Helios hospitals was retrospectively analysed. Laboratory-confirmed SARS-CoV-2 infections were identified by ICD-10-code U07.1 and SARI cases by ICD-10-codes J09-J22. COVID-19 cases were stratified by concomitant SARI. A nine-week observational period between December 6, 2021 and February 6, 2022 was defined and divided into three phases with respect to the dominating virus variant (Delta, Delta to Omicron transition, Omicron). Regression analyses adjusted for age, gender and Elixhauser comorbidities were applied to assess in-hospital patient outcomes. RESULTS: A total cohort of 4,494 inpatients was analysed. Patients in the Omicron dominance period were younger (mean age 47.8 vs. 61.6; p < 0.01), more likely to be female (54.7% vs. 47.5%; p < 0.01) and characterized by a lower comorbidity burden (mean Elixhauser comorbidity index 5.4 vs. 8.2; p < 0.01). Comparing Delta and Omicron periods, patients were at significantly lower risk for intensive care treatment (adjusted odds ratio 0.72 [0.57-0.91]; p = 0.005), mechanical ventilation (adjusted odds ratio 0.42 [0.31-0.57]; p < 0.001), and in-hospital mortality (adjusted odds ratio 0.42 [0.32-0.56]; p < 0.001). This also applied mostly to the separate COVID-SARI group. During the Delta to Omicron transition, case numbers of COVID-19 without SARI exceeded COVID-SARI for the first time in the pandemic's course. CONCLUSION: Patient characteristics and outcomes differ during the Omicron dominance period as compared to Delta suggesting a reduced disease severity with Omicron infections. SARI surveillance might play a crucial role in assessing disease severity of future SARS-CoV-2 variants.

Machine learning-derived prediction of in-hospital mortality in patients with severe acute respiratory infection: analysis of claims data from the German-wide Helios hospital network.

BACKGROUND: Severe acute respiratory infections (SARI) are the most common infectious causes of death. Previous work regarding mortality prediction models for SARI using machine learning (ML) algorithms that can be useful for both individual risk stratification and quality of care assessment is scarce. We aimed to develop reliable models for mortality prediction in SARI patients utilizing ML algorithms and compare its performances with a classic regression analysis approach. METHODS: Administrative data (dataset randomly split 75%/25% for model training/testing) from years 2016-2019 of 86 German Helios hospitals was retrospectively analyzed. Inpatient SARI cases were defined by ICD-codes J09-J22. Three ML algorithms were evaluated and its performance compared to generalized linear models (GLM) by computing receiver operating characteristic area under the curve (AUC) and area under the precision-recall curve (AUPRC). RESULTS: The dataset contained 241,988 inpatient SARI cases (75 years or older: 49%; male 56.2%). In-hospital mortality was 11.6%. AUC and AUPRC in the testing dataset were 0.83 and 0.372 for GLM, 0.831 and 0.384 for random forest (RF), 0.834 and 0.382 for single layer neural network (NNET) and 0.834 and 0.389 for extreme gradient boosting (XGBoost). Statistical comparison of ROC AUCs revealed a better performance of NNET and XGBoost as compared to GLM. CONCLUSION: ML algorithms for predicting in-hospital mortality were trained and tested on a large real-world administrative dataset of SARI patients and showed good discriminatory performances. Broad application of our models in clinical routine practice can contribute to patients' risk assessment and quality management.

A Comparative Analysis of In-Hospital Mortality per Disease Groups in Germany Before and During the COVID-19 Pandemic From 2016 to 2020.

Importance: Throughout the ongoing SARS-CoV-2 pandemic, it has been critical to understand not only the viral disease itself but also its implications for the overall health care system. Reports about excess mortality in this regard have mostly focused on overall death counts during specific pandemic phases. Objective: To investigate hospitalization rates and compare in-hospital mortality rates with absolute mortality incidences across a broad spectrum of diseases, comparing 2020 data with those of prepandemic years. Design, Setting, and Participants: Retrospective, cross-sectional, multicentric analysis of administrative data from 5 821 757 inpatients admitted from January 1, 2016, to December 31, 2020, to 87 German Helios primary to tertiary care hospitals. Exposures: Exposure to SARS-CoV-2. Main Outcomes and Measures: Administrative data were analyzed from January 1, 2016, to March 31, 2021, as a consecutive sample for all inpatients. Disease groups were defined according to International Statistical Classification of Diseases and Related Health Problems, 10th Revision (ICD-10; German modification) encoded main discharge diagnoses. Incidence rate ratios (IRRs) for hospital admissions and hospital mortality counts, as well as relative mortality risks (RMRs) comparing 2016-2019 with 2020 (exposure to the SARS-CoV-2 pandemic), were calculated with Poisson regression with log-link function. Results: Data were examined for 5 821 757 inpatients (mean [SD] age, 56.4 [25.3] years; 51.5% women), including 125 807 in-hospital deaths. Incidence rate ratios for hospital admissions were associated with a significant reduction for all investigated disease groups (IRR, 0.82; 95% CI, 0.79-0.86; P < .001). After adjusting for age, sex, the Elixhauser Comorbidity Index score, and SARS-CoV-2 infections, RMRs were associated with an increase in infectious diseases (RMR, 1.28; 95% CI, 1.21-1.34; P < .001), musculoskeletal diseases (RMR, 1.19; 95% CI, 1.04-1.36; P = .009), and respiratory diseases (RMR, 1.09; 95% CI, 1.05-1.14; P < .001) but not for the total cohort (RMR, 1.00; 95% CI, 0.99-1.02; P = .66). Regarding in-hospital mortality, IRR was associated with an increase within the ICD-10 chapter of respiratory diseases (IRR, 1.28; 95% CI, 1.13-1.46; P < .001) in comparing 2020 with 2016-2019, in contrast to being associated with a reduction in IRRs for the overall cohort and several other subgroups. After exclusion of patients with SARS-CoV-2 infections, IRRs were associated with a reduction in absolute in-hospital mortality for the overall cohort (IRR, 0.78; 95% CI, 0.72-0.84; P < .001) and the subgroup of respiratory diseases (IRR, 0.83; 95% CI, 0.74-0.92; P < .001). Conclusions and Relevance: This cross-sectional study of inpatients from a multicentric German database suggests that absolute in-hospital mortality for 2020 across disease groups was not higher compared with previous years. Higher IRRs of in-hospital deaths observed in patients with respiratory diseases were likely associated with individuals with SARS-CoV-2 infections.

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: 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.

From population- to patient-based prediction of in-hospital mortality in heart failure using machine learning.

Aims: Utilizing administrative data may facilitate risk prediction in heart failure inpatients. In this short report, we present different machine learning models that predict in-hospital mortality on an individual basis utilizing this widely available data source. Methods and results: Inpatient cases with a main discharge diagnosis of heart failure hospitalized between 1 January 2016 and 31 December 2018 in one of 86 German Helios hospitals were examined. Comorbidities were defined by ICD-10 codes from administrative data. The data set was randomly split into 75/25% portions for model development and testing. Five algorithms were evaluated: logistic regression [generalized linear models (GLMs)], random forest (RF), gradient boosting machine (GBM), single-layer neural network (NNET), and extreme gradient boosting (XGBoost). After model tuning, the receiver operating characteristics area under the curves (ROC AUCs) were calculated and compared with DeLong's test. A total of 59 074 inpatient cases (mean age 77.6 ± 11.1 years, 51.9% female, 89.4% NYHA Class III/IV) were included and in-hospital mortality was 6.2%. In the test data set, calculated ROC AUCs were 0.853 [95% confidence interval (CI) 0.842-0.863] for GLM, 0.851 (95% CI 0.840-0.862) for RF, 0.855 (95% CI 0.844-0.865) for GBM, 0.836 (95% CI 0.823-0.849) for NNET, and 0.856 (95% CI 9.846-0.867) for XGBoost. XGBoost outperformed all models except GBM. Conclusion: Machine learning-based processing of administrative data enables the creation of well-performing prediction models for in-hospital mortality in heart failure patients.

Hospitalisations for emergency-sensitive conditions in Germany during the COVID-19 pandemic: insights from the German-wide Helios hospital network.

BACKGROUND: While there are numerous reports that describe emergency care during the early COVID-19 pandemic, there is scarcity of data for later stages. This study analyses hospitalisation rates for 37 emergency-sensitive conditions in the largest German-wide hospital network during different pandemic phases. METHODS: Using claims data of 80 hospitals, consecutive cases between 1 January and 17 November 2020 were analysed and compared with a corresponding period in 2019. Incidence rate ratios (IRRs) comparing the two periods were calculated using Poisson regression to model the number of hospitalisations per day. RESULTS: There was a reduction in hospitalisations between 12 March and 13 June 2020 (coinciding with the first pandemic wave) with 32 807 hospitalisations (349.0/day) as opposed to 39 379 (419.0/day) in 2019 (IRR 0.83, 95% CI 0.82 to 0.85, p<0.01). During the following period (14 June-17 November 2020, including the start of second wave), hospitalisations were reduced from 63 799 (406.4/day) in 2019 to 59 910 (381.6/day) in 2020, but this reduction was not as pronounced (IRR 0.94, 95% CI 0.93 to 0.95, p<0.01). During the first wave hospitalisations for acute myocardial infarction, aortic aneurysm/dissection, pneumonitis, paralytic ileus/intestinal obstruction and pulmonary embolism declined but subsequently increased compared with the corresponding periods in 2019. In contrast, hospitalisations for sepsis, pneumonia, obstructive pulmonary disease and intracranial injuries were reduced during the entire observation period. CONCLUSIONS: There was an overall reduction of absolute hospitalisations for emergency-sensitive conditions in Germany during the first 10 months of the COVID-19 pandemic with heterogeneous effects on different disease categories. The increase in hospitalisations for acute myocardial infarction, aortic aneurysm/dissection and pulmonary embolism requires attention and further studies.

SARS-CoV-2 rapid antigen testing in the healthcare sector: A clinical prediction model for identifying false negative results.

OBJECTIVES: SARS-CoV-2 rapid antigen tests (RAT) provide fast identification of infectious patients when RT-PCR results are not immediately available. We aimed to develop a prediction model for identification of false negative (FN) RAT results. METHODS: In this multicenter trial, patients with documented paired results of RAT and RT-PCR between October 1st 2020 and January 31st 2021 were retrospectively analyzed regarding clinical findings. Variables included demographics, laboratory values and specific symptoms. Three different models were evaluated using Bayesian logistic regression. RESULTS: The initial dataset contained 4,076 patients. Overall sensitivity and specificity of RAT was 62.3% and 97.6%. 2,997 cases with negative RAT results (FN: 120; true negative: 2,877; reference: RT-PCR) underwent further evaluation after removal of cases with missing data. The best-performing model for predicting FN RAT results containing 10 variables yielded an area under the curve of 0.971. Sensitivity, specificity, PPV and NPV for 0.09 as cut-off value (probability for FN RAT) were 0.85, 0.99, 0.7 and 0.99. CONCLUSION: FN RAT results can be accurately identified through ten routinely available variables. Implementation of a prediction model in addition to RAT testing in clinical care can provide decision guidance for initiating appropriate hygiene measures and therefore helps avoiding nosocomial infections.

Potential Contributors to Increased Pulmonary Embolism Hospitalizations During the COVID-19 Pandemic: Insights From the German-Wide Helios Hospital Network.

Background: After the first COVID-19 infection wave, a constant increase of pulmonary embolism (PE) hospitalizations not linked with active PCR-confirmed COVID-19 was observed, but potential contributors to this observation are unclear. Therefore, we analyzed associations between changes in PE hospitalizations and (1) the incidence of non-COVID-19 pneumonia, (2) the use of computed tomography pulmonary angiography (CTPA), (3) volume depletion, and (4) preceding COVID-19 infection numbers in Germany. Methods: Claims data of Helios hospitals in Germany were used, and consecutive cases with a hospital admission between May 6 and December 15, 2020 (PE surplus period), were analyzed and compared to corresponding periods covering the same weeks in 2016-2019 (control period). We analyzed the number of PE cases in the target period with multivariable Poisson general linear mixed models (GLMM) including (a) cohorts of 2020 versus 2016-2019, (b) the number of cases with pneumonia, (c) CTPA, and (d) volume depletion and adjusted for age and sex. In order to associate the daily number of PE cases in 2020 with the number of preceding SARS-CoV-2 infections in Germany, we calculated the average number of daily infections (divided by 10,000) occurring between 14 up to 90 days with increasing window sizes before PE cases and modeled the data with Poisson regression. Results: There were 2,404 PE hospitalizations between May 6 and December 15, 2020, as opposed to 2,112-2,236 (total 8,717) in the corresponding 2016-2019 control periods (crude rate ratio [CRR] 1.10, 95% CI 1.05-1.15, P < 0.01). With the use of multivariable Poisson GLMM adjusted for age, sex, and volume depletion, PE cases were significantly associated with the number of cases with pneumonia (CRR 1.09, 95% CI 1.07-1.10, P < 0.01) and with CTPA (CRR 1.10, 95% CI 1.09-1.10, P < 0.01). The increase of PE cases in 2020 compared with the control period remained significant (CRR 1.07, 95% CI 1.02-1.12, P < 0.01) when controlling for those factors. In the 2020 cohort, the number of preceding average daily COVID-19 infections was associated with increased PE case incidence in all investigated windows, i.e., including preceding infections from 14 to 90 days. The best model (log likelihood -576) was with a window size of 4 days, i.e., average COVID-19 infections 14-17 days before PE hospitalization had a risk of 1.20 (95% CI 1.12-1.29, P < 0.01). Conclusions: There is an increase in PE cases since early May 2020 compared to corresponding periods in 2016-2019. This surplus was significant even when controlling for changes in potential modulators such as demographics, volume depletion, non-COVID-19 pneumonia, CTPA use, and preceding COVID-19 infections. Future studies are needed (1) to investigate a potential causal link for increased risk of delayed PE with preceding SARS-CoV-2 infection and (2) to define optimal screening for SARS-CoV-2 in patients presenting with pneumonia and PE.

Machine ​learning algorithms for claims data-based prediction of in-hospital mortality in patients with heart failure.

AIMS: Models predicting mortality in heart failure (HF) patients are often limited with regard to performance and applicability. The aim of this study was to develop a reliable algorithm to compute expected in-hospital mortality rates in HF cohorts on a population level based on administrative data comparing regression analysis with different machine learning (ML) models. METHODS AND RESULTS: Inpatient cases with primary International Statistical Classification of Diseases and Related Health Problems (ICD-10) encoded discharge diagnosis of HF non-electively admitted to 86 German Helios hospitals between 1 January 2016 and 31 December 2018 were identified. The dataset was randomly split 75%/25% for model development and testing. Highly unbalanced variables were removed. Four ML algorithms were applied, and all algorithms were tuned using a grid search with multiple repetitions. Model performance was evaluated by computing receiver operating characteristic areas under the curve. In total, 59 125 cases (69.8% aged 75 years or older, 51.9% female) were investigated, and in-hospital mortality was 6.20%. Areas under the curve of all ML algorithms outperformed regression analysis in the testing dataset with values of 0.829 [95% confidence interval (CI) 0.814-0.843] for logistic regression, 0.875 (95% CI 0.863-0.886) for random forest, 0.882 (95% CI 0.871-0.893) for gradient boosting machine, 0.866 (95% CI 0.854-0.878) for single-layer neural networks, and 0.882 (95% CI 0.872-0.893) for extreme gradient boosting. Brier scores demonstrated a good calibration especially of the latter three models. CONCLUSIONS: We introduced reliable models to calculate expected in-hospital mortality based only on administrative routine data using ML algorithms. A broad application could supplement quality measurement programs and therefore improve future HF patient care.

Utilization of in- and outpatient hospital care in Germany during the Covid-19 pandemic insights from the German-wide Helios hospital network.

BACKGROUND: During the early phase of the Covid-19 pandemic, reductions of hospital admissions with a focus on emergencies have been observed for several medical and surgical conditions, while trend data during later stages of the pandemic are scarce. Consequently, this study aims to provide up-to-date hospitalization trends for several conditions including cardiovascular, psychiatry, oncology and surgery cases in both the in- and outpatient setting. METHODS AND FINDINGS: Using claims data of 86 Helios hospitals in Germany, consecutive cases with an in- or outpatient hospital admission between March 13, 2020 (the begin of the "protection" stage of the German pandemic plan) and December 10, 2020 (end of study period) were analyzed and compared to a corresponding period covering the same weeks in 2019. Cause-specific hospitalizations were defined based on the primary discharge diagnosis according to International Statistical Classification of Diseases and Related Health Problems (ICD-10) or German procedure classification codes for cardiovascular, oncology, psychiatry and surgery cases. Cumulative hospitalization deficit was computed as the difference between the expected and observed cumulative admission number for every week in the study period, expressed as a percentage of the cumulative expected number. The expected admission number was defined as the weekly average during the control period. A total of 1,493,915 hospital admissions (723,364 during the study and 770,551 during the control period) were included. At the end of the study period, total cumulative hospitalization deficit was -10% [95% confidence interval -10; -10] for cardiovascular and -9% [-10; -9] for surgical cases, higher than -4% [-4; -3] in psychiatry and 4% [4; 4] in oncology cases. The utilization of inpatient care and subsequent hospitalization deficit was similar in trend with some variation in magnitude between cardiovascular (-12% [-13; -12]), psychiatry (-18% [-19; -17]), oncology (-7% [-8; -7]) and surgery cases (-11% [-11; -11]). Similarly, cardiovascular and surgical outpatient cases had a deficit of -5% [-6; -5] and -3% [-4; -3], respectively. This was in contrast to psychiatry (2% [1; 2]) and oncology cases (21% [20; 21]) that had a surplus in the outpatient sector. While in-hospital mortality, was higher during the Covid-19 pandemic in cardiovascular (3.9 vs. 3.5%, OR 1.10 [95% CI 1.06-1.15], P<0.01) and in oncology cases (4.5 vs. 4.3%, OR 1.06 [95% CI 1.01-1.11], P<0.01), it was similar in surgical (0.9 vs. 0.8%, OR 1.06 [95% CI 1.00-1.13], P = 0.07) and in psychiatry cases (0.4 vs. 0.5%, OR 1.01 [95% CI 0.78-1.31], P<0.95). CONCLUSIONS: There have been varying changes in care pathways and in-hospital mortality in different disciplines during the Covid-19 pandemic in Germany. Despite all the inherent and well-known limitations of claims data use, this data may be used for health care surveillance as the pandemic continues worldwide. While this study provides an up-to-date analysis of utilization of hospital care in the largest German hospital network, short- and long-term consequences are unknown and deserve further studies.