Dynamic of SOFA Score Predicts Functionality after ARDS Therapy (preprint)

Rationale: Health-related quality of life after surviving acute respiratory distress syndrome has come into focus in recent years, especially during the coronavirus disease 2019 pandemic. Objectives: A total of 143 patients with acute respiratory distress syndrome caused by COVID-19 or of other origin were recruited in a randomized multicenter trial. Methods: Clinical data during intensive care treatment and data up to 180 days after study inclusion were collected. Changes in the Sequential Organ Failure Assessment score were used to quantify disease severity. Disability was assessed using the Barthel index on days 1, 28, 90, and 180. Measurements: Mortality rate and morbidity after 180 days were compared between patients with and without COVID-19. Independent risk factors associated with high disability were identified using a binary logistic regression. Main Results: Mortality after 180 days and impairment measured by the Barthel index did not differ between patients with and without COVID-19. The SOFA score at day 5 was an independent risk factor for high disability in both groups, and score dynamic within the first 5 days significantly impacted disability in the non-COVID group. Conclusions: Acute respiratory distress syndrome caused by COVID-19 was not associated with increased mortality or morbidity. Resolution of organ dysfunction within the first 5 days significantly impacts long-term morbidity and emphasizes the importance of timely initiation of treatment in these critically ill patients.

Process Modeling and Conformance Checking in Healthcare: A COVID-19 Case Study (preprint)

The discipline of process mining has a solid track record of successful applications to the healthcare domain. Within such research space, we conducted a case study related to the Intensive Care Unit (ICU) ward of the Uniklinik Aachen hospital in Germany. The aim of this work is twofold: developing a normative model representing the clinical guidelines for the treatment of COVID-19 patients, and analyzing the adherence of the observed behavior (recorded in the information system of the hospital) to such guidelines. We show that, through conformance checking techniques, it is possible to analyze the care process for COVID-19 patients, highlighting the main deviations from the clinical guidelines. The results provide physicians with useful indications for improving the process and ensuring service quality and patient satisfaction. We share the resulting model as an open-source BPMN file.

Inhaled Prostacyclin Improves Oxygenation in Patients with COVID-19-induced Acute Respiratory Distress Syndrome – a randomized controlled multicenter trial (preprint)

Background. Acute Respiratory Distress Syndrome (ARDS) results in significant hypoxia, and ARDS is the central pathology of COVID-19. Inhaled prostacyclin has been proposed as a therapy for ARDS, but data regarding its role in this syndrome are unavailable. Therefore, we investigated whether inhaled prostacyclin would affect the oxygenation and survival of patients suffering from ARDS.Methods. We performed a prospective randomized controlled single-blind multicenter trial across Germany. The trial was conducted from March 2019 with final follow-up on 12th of August 2021. Patients with moderate to severe ARDS were included and randomized to receive either inhaled prostacyclin (3 times/day for 5 days) or sodium chloride. The primary outcome was the oxygenation index in the intervention and control groups on Day 5 of therapy. Secondary outcomes were mortality, secondary organ failure, disease severity and adverse events.Results. Of 707 patients approached 150 patients were randomized to receive inhaled prostacyclin (n = 73) or sodium chloride (n = 77). Data from 144 patients were analyzed. The baseline oxygenation index did not differ between groups. The primary analysis of the study was negative, and prostacyclin improved oxygenation by 20 mmHg more than NaCl (p = 0·17). Oxygenation was significantly improved in patients with ARDS who were COVID-19-positive (34 mmHg, p = 0·04). Mortality did not differ between groups. Secondary organ failure and adverse events were similar in the intervention and control groups.Conclusions. Although the primary result of our study was negative, our data suggest that inhaled prostacyclin might be a more beneficial treatment than standard care for patients with ARDS.Trial registration: The study was approved by the Institutional Review Board of the Research Ethics Committee of the University of Tübingen (899/2018AMG1) and the corresponding ethical review boards of all participating centers. The trial was also approved by the Federal Institute for Drugs and Medical Devices (BfArM, EudraCT No. 2016-003168-37) and registered at clinicaltrials.gov (NCT03111212) on April 6th 2017.

Analyzing Medical Data with Process Mining: a COVID-19 Case Study (preprint)

The recent increase in the availability of medical data, possible through automation and digitization of medical equipment, has enabled more accurate and complete analysis on patients' medical data through many branches of data science. In particular, medical records that include timestamps showing the history of a patient have enabled the representation of medical information as sequences of events, effectively allowing to perform process mining analyses. In this paper, we will present some preliminary findings obtained with established process mining techniques in regard of the medical data of patients of the Uniklinik Aachen hospital affected by the recent epidemic of COVID-19. We show that process mining techniques are able to reconstruct a model of the ICU treatments for COVID patients.

Diaphragm Dysfunction as a Determinant of Persisting Dyspnoea in Patients One Year after Invasive Mechanical Ventilation Due to COVID-19 Related ARDS (preprint)

Background: Some patients with coronavirus disease 2019 (COVID-19) experience prolonged fatigue and dyspnoea without objective impairment of pulmonary or cardiac function. This study determined diaphragm function and its central voluntary activation as a possible pathophysiological correlate after severe COVID-19 acute respiratory distress syndrome (ARDS).Methods:Ten patients with severe COVID-19 ARDS treated with invasive mechanical ventilation (IMV) (6 female, age 56±14 years, 63±45 days of IMV) and ten matched healthy controls underwent pulmonary function tests (PFTs), 6-minute walk test, echocardiography, diaphragm ultrasound, and invasive recording of twitch transdiaphragmatic pressure (twPdi) following magnetic diaphragm stimulation. Twitch interpolation was used to determine the diaphragm voluntary activation index (DVAI); reflecting central diaphragm activation.Findings: One year post discharge, neither PFTs nor echocardiography were indicative of significant abnormalities in severe COVID-19 survivors. However, six patients reported persisting dyspnoea on exertion (severe in two, moderate in four). On ultrasound, the diaphragm thickening ratio was lower in patients versus controls (1.87±0.37 vs. 2.76±0.72; p<0.01), and diaphragm excursion velocity during a maximum sniff manoeuvre was associated with dyspnoea. TwPdi following cervical magnetic stimulation did not differ between patients and controls overall, but twPdi half relaxation time progressively increased in parallel with dyspnoea severity (ANOVA p=0.03), while sniff Pdi progressively decreased (ANOVA p=0.05). DVAI was lower in patients versus controls (30±27% vs 79±6%, p<0.01) and was associated with dyspnoea (ANOVA p=0.05).Interpretation: Inspiratory muscle dysfunction with impaired central voluntary activation of the diaphragm is present one year after severe COVID-19 ARDS treated with IMV, and relates to dyspnoea.Trial Registration: This prospective case-control study was registered with number, (NCT04854863)Funding: None to declare. Declaration of Interest: The authors have no conflicts of interest to disclose.Ethical Approval: This study was approved by the local ethics committee (Ethikkommission an der Medizinischen Fakultät der Rheinisch-Westfälischen Technischen Hochschule Aachen, CTCA-A-Nr. 20-515, AZ EK 443/20).

Machine Learning Identifies ICU Outcome Predictors in a Multicenter COVID-19 Cohort. (preprint)

Background. Intensive Care Resources are heavily utilized during the COVID-19 pandemic. However, risk stratification and prediction of SARS-CoV-2 patient clinical outcomes upon ICU admission remain inadequate. This study aimed to develop a machine learning model, based on retrospective & prospective clinical data, to stratify patient risk and predict ICU survival and outcomes.Methods. A Germany-wide electronic registry was established to pseudonymously collect admission, therapeutic and discharge information of SARS-CoV-2 ICU patients retrospectively and prospectively. Machine learning approaches were evaluated for the accuracy and interpretability of predictions. The Explainable Boosting Machine approach was selected as the most suitable method. Individual, non-linear shape functions for predictive parameters and parameter interactions are reported. Results. 1,039 patients were included in the Explainable Boosting Machine model, 596 patients retrospectively collected, and 443 patients prospectively collected. The model for prediction of general ICU outcome was shown to be more reliable to predict “survival”. Age, inflammatory and thrombotic activity, and severity of ARDS at ICU admission were shown to be predictive of ICU survival. Patients’ age, pulmonary dysfunction and transfer from an external institution were predictors for ECMO therapy. The interaction of patient age with D-dimer levels on admission and creatinine levels with SOFA score without GCS were predictors for renal replacement therapy. Conclusions. Using Explainable Boosting Machine analysis, we confirmed and weighed previously reported and identified novel predictors for outcome in critically ill COVID-19 patients. Using this strategy, predictive modeling of COVID-19 ICU patient outcomes can be performed overcoming the limitations of linear regression models.Trial registration. “ClinicalTrials” (clinicaltrials.gov) under NCT04455451

Biometric covariates and outcome in COVID-19 patients: Are we looking close enough? (preprint)

Background: The impact of biometric covariates on risk for adverse outcomes of COVID-19 disease was assessed by numerous observational studies on unstratified cohorts, which show great heterogeneity. However, multilevel evaluations to find possible complex, e. g. non-monotonic multi-variate patterns reflecting mutual interference of parameters are missing. We used a more detailed, computational analysis to investigate the influence of biometric differences on mortality and disease evolution among severely ill COVID-19 patients. Methods: We analyzed a group of COVID-19 patients requiring Intensive care unit (ICU) treatment. For further analysis, the study group was segmented into six subgroups according to BMI and age. To link the BMI/age derived subgroups with risk factors, we performed an enrichment analysis of diagnostic parameters and comorbidities. To suppress spurious patterns, multiple segmentations were analyzed and integrated into a consensus score for each analysis step. Results: We analyzed 81 COVID-19 patients, of whom 67 required MV. Mean mortality was 35.8 %. We found a complex, non-monotonic interaction between age, BMI and mortality. A subcohort of patients with younger age and intermediate BMI exhibited a strongly reduced mortality risk (p < 0.001), while differences in all other groups were not significant. Univariate impacts of BMI or age on mortality were missing. Comparing MV with non-MV patients, we found an enrichment of baseline CRP, PCT and D-Dimers within the MV-group, but not when comparing survivors vs. non-survivors within the MV patient group. Conclusions: The aim of this study was to get a more detailed insight into the influence of biometric covariates on the outcome of COVID-19 patients with high degree of severity. We found that survival in MV is affected by complex interactions of covariates differing to the reported covariates, which are hidden in generic, non-stratified studies on risk factors. Hence, our study suggests that a detailed, multivariate pattern analysis on larger patient cohorts reflecting the specific disease stages might reveal more specific patterns of risk factors supporting individually adapted treatment strategies.