Analysis of Chest X-ray for COVID-19 Diagnosis as a Use Case for an HPC-Enabled Data Analysis and Machine Learning Platform for Medical Diagnosis Support.

The COVID-19 pandemic shed light on the need for quick diagnosis tools in healthcare, leading to the development of several algorithmic models for disease detection. Though these models are relatively easy to build, their training requires a lot of data, storage, and resources, which may not be available for use by medical institutions or could be beyond the skillset of the people who most need these tools. This paper describes a data analysis and machine learning platform that takes advantage of high-performance computing infrastructure for medical diagnosis support applications. This platform is validated by re-training a previously published deep learning model (COVID-Net) on new data, where it is shown that the performance of the model is improved through large-scale hyperparameter optimisation that uncovered optimal training parameter combinations. The per-class accuracy of the model, especially for COVID-19 and pneumonia, is higher when using the tuned hyperparameters (healthy: 96.5%; pneumonia: 61.5%; COVID-19: 78.9%) as opposed to parameters chosen through traditional methods (healthy: 93.6%; pneumonia: 46.1%; COVID-19: 76.3%). Furthermore, training speed-up analysis shows a major decrease in training time as resources increase, from 207 min using 1 node to 54 min when distributed over 32 nodes, but highlights the presence of a cut-off point where the communication overhead begins to affect performance. The developed platform is intended to provide the medical field with a technical environment for developing novel portable artificial-intelligence-based tools for diagnosis support.

A training strategy for hybrid models to break the curse of dimensionality.

Mechanistic/data-driven hybrid modeling is a key approach when the mechanistic details of the processes at hand are not sufficiently well understood, but also inferring a model purely from data is too complex. By the integration of first principles into a data-driven approach, hybrid modeling promises a feasible data demand alongside extrapolation. In this work, we introduce a learning strategy for tree-structured hybrid models to perform a binary classification task. Given a set of binary labeled data, the challenge is to use them to develop a model that accurately assesses labels of new unlabeled data. Our strategy employs graph-theoretic methods to analyze the data and deduce a function that maps input features to output labels. Our focus here is on data sets represented by binary features in which the label assessment of unlabeled data points is always extrapolation. Our strategy shows the existence of small sets of data points within given binary data for which knowing the labels allows for extrapolation to the entire valid input space. An implementation of our strategy yields a notable reduction of training-data demand in a binary classification task compared with different supervised machine learning algorithms. As an application, we have fitted a tree-structured hybrid model to the vital status of a cohort of COVID-19 patients requiring intensive-care unit treatment and mechanical ventilation. Our learning strategy yields the existence of patient cohorts for whom knowing the vital status enables extrapolation to the entire valid input space of the developed hybrid model.

HybridML: Open Source Platform for Hybrid Modeling

Hybrid modelling, i.e., the combination of data-driven modelling with mechanistic model components, reduces the data demand and enables extrapolation of data-driven models. However, building, training and evaluation of hybrid models is cumbersome with current frameworks. We developed HybridML, an open-source modeling platform, in which hybrid models can be trained, i.e., combinations of artificial neural networks, arithmetic expressions, and differential equations. We employ TensorFlow for artificial neural network training and Casadi to integrate ordinary differential equations and provide gradients of differential model equations enabling continuous time representations. HybridML provides also a JSON interface for the model development. We apply HybridML to an industrial case study, in which the trained model is used to predict drug concentrations over time, based on physiological information about the patients. To demonstrate its versatility, we also present a nonlinear application, where HybridML is used to model the spread of the COVID-19 pandemic in German federal states based on the state’s socio-economic attributes.

Biometric covariates and outcome in COVID-19 patients: are we looking close enough?

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 Body mass index (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 mechanical ventilation (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.

Effectiveness of extended shutdown measures during the ´Bundesnotbremse´ introduced in the third SARS-CoV-2 wave in Germany.

A third SARS-CoV-2 infection wave has affected Germany from March 2021 until April 24th, until the ´Bundesnotbremse´ introduced nationwide shutdown measures. The ´Bundesnotbremse´ is the technical term which was used by the German government to describe nationwide shutdown measures to control the rising infection numbers. These measures included mainly contact restrictions on several level. This study investigates which effects locally dispersed pre- and post-´Bundesnotbremse´ measures had on the infection dynamics. We analyzed the variability and strength of the rates of the changes of weekly case numbers considering different regions, age groups, and contact restrictions. Regionally diverse measures slowed the rate of weekly increase by about 50% and about 75% in regions with stronger contact restrictions. The 'Bundesnotbremse' induced a coherent reduction of infection numbers across all German federal states and age groups throughout May 2021. The coherence of the infection dynamics after the 'Bundesnotbremse' indicates that these stronger measures induced the decrease of infection numbers. The regionally diverse non-pharmaceutical interventions before could only decelerate further spreading, but not prevent it alone.

[Intensive care bed requirements for COVID-19 in the fall/winter of 2021 : Simulation of different scenarios under consideration of incidences and vaccination rates]. / Intensivbettenbedarf für COVID­19 im Herbst/Winter 2021 : Simulation unterschiedlicher Szenarien unter Berücksichtigung von Inzidenzen und Impfquoten.

BACKGROUND: Despite the increasing vaccination rates against SARS-CoV­2, there is a risk of a renewed wave of infections in autumn 2021 due to the high seasonality of the pathogen, with the associated renewed possible heavy burden on intensive care. In the following manuscript we simulated different scenarios using defined mathematical models to estimate the burden of intensive care treatment by COVID-19 patients within certain limits during the coming autumn. METHODS: The simulation of the scenarios uses a stationary model supplemented by the effect of vaccinations. The age group-specific risk profile for intensive care unit (ICU)-associated disease progression is calculated using third wave ICU admission data from sentinel hospitals, local DIVI registry occupancy data and the corresponding local incidence rates by linear regression with time lag. We simulated vaccination rates of 15% for the over 18-year-old cohort, 70% for the 15-34 year cohort, 75%/80%/85% for the 35-59 year cohort and 85%/90%/95% for the over 60-year-old cohort. The simulations take into account that vaccination provides 100% protection against disease progression requiring intensive care. Regarding protection against infection in vaccinated persons the simulations are depicted for the scenario of 70% protection against infection in vaccinated persons and for the scenario of 85% protection against infection in vaccinated persons. RESULTS: The incidence is proportional to ICU bed occupancy. The proportionality factor is higher than in the second and third waves, so that comparable ICU bed occupancy is only achieved at a higher incidence. A 10% increase in vaccination rates of the over 35-year-olds to 85% and of the over 60-year-olds to 95% leads to a significant reduction in ICU bed occupancy. DISCUSSION: There will continue to be a close and linear relationship between SARS-CoV­2 incidence and ICU bed occupancy in the coming months. Even above incidences of 200/100,000 a considerable burden of ICUs with more than 3000 COVID-19 patients can be expected again, unless the vaccination rate is significantly increased. A few percentage points in the vaccination rate have a significant impact on potential ICU occupancy in the autumn, so efforts to increase vaccination acceptance should be a priority in the coming weeks. For intensive care medicine, the vaccination rate of those over 35 years of age is crucial.

6-month mortality and readmissions of hospitalized COVID-19 patients: A nationwide cohort study of 8,679 patients in Germany.

BACKGROUND: COVID-19 frequently necessitates in-patient treatment and in-patient mortality is high. Less is known about the long-term outcomes in terms of mortality and readmissions following in-patient treatment. AIM: The aim of this paper is to provide a detailed account of hospitalized COVID-19 patients up to 180 days after their initial hospital admission. METHODS: An observational study with claims data from the German Local Health Care Funds of adult patients hospitalized in Germany between February 1 and April 30, 2020, with PCR-confirmed COVID-19 and a related principal diagnosis, for whom 6-month all-cause mortality and readmission rates for 180 days after admission or until death were available. A multivariable logistic regression model identified independent risk factors for 180-day all-cause mortality in this cohort. RESULTS: Of the 8,679 patients with a median age of 72 years, 2,161 (24.9%) died during the index hospitalization. The 30-day all-cause mortality rate was 23.9% (2,073/8,679), the 90-day rate was 27.9% (2,425/8,679), and the 180-day rate, 29.6% (2,566/8,679). The latter was 52.3% (1,472/2,817) for patients aged ≥80 years 23.6% (1,621/6,865) if not ventilated during index hospitalization, but 53.0% in case of those ventilated invasively (853/1,608). Risk factors for the 180-day all-cause mortality included coagulopathy, BMI ≥ 40, and age, while the female sex was a protective factor beyond a fewer prevalence of comorbidities. Of the 6,235 patients discharged alive, 1,668 were readmitted a total of 2,551 times within 180 days, resulting in an overall readmission rate of 26.8%. CONCLUSIONS: The 180-day follow-up data of hospitalized COVID-19 patients in a nationwide cohort representing almost one-third of the German population show significant long-term, all-cause mortality and readmission rates, especially among patients with coagulopathy, whereas women have a profoundly better and long-lasting clinical outcome compared to men.

Different spreading dynamics throughout Germany during the second wave of the COVID-19 pandemic: a time series study based on national surveillance data.

BACKGROUND: The second wave of the COVID-19 pandemic led to substantial differences in incidence rates across Germany. METHODS: Assumption-free k-nearest neighbour clustering from the principal component analysis of weekly incidence rates of German counties groups similar spreading behaviour. Different spreading dynamics was analysed by the derivative plots of the temporal evolution of tuples [x(t),x'(t)] of weekly incidence rates and their derivatives. The effectiveness of the different shutdown measures in Germany during the second wave is assessed by the difference of weekly incidences before and after the respective time periods. FINDINGS: The implementation of non-pharmaceutical interventions of different extents resulted in four distinct time periods of complex, spatially diverse, and age-related spreading patterns during the second wave of the COVID-19 pandemic in Germany. Clustering gave three regions of coincident spreading characteristics. October 2020 showed a nationwide exponential growth of weekly incidence rates with a doubling time of 10 days. A partial shutdown during November 2020 decreased the overall infection rates by 20-40% with a plateau-like behaviour in northern and southwestern Germany. The eastern parts exhibited a further near-linear growth by 30-80%. Allover the incidence rates among people above 60 years still increased by 15-35% during partial shutdown measures. Only an extended shutdown led to a substantial decrease in incidence rates. These measures decreased the numbers among all age groups and in all regions by 15-45%. This decline until January 2021 was about -1•25 times the October 2020 growth rates with a strong correlation of -0•96. INTERPRETATION: Three regional groups with different dynamics and different degrees of effectiveness of the applied measures were identified. The partial shutdown was moderately effective and at most stopped the exponential growth, but the spread remained partly plateau-like and regionally continued to grow in a nearly linear fashion. Only the extended shutdown reversed the linear growth. FUNDING: Institutional support and physical resources were provided by the University Witten/ Herdecke and Kliniken der Stadt Köln, German ministry of education and research 'Netzwerk Universitätsmedizin' (NUM), egePan Unimed (01KX2021).