Poster: Privacy-Preserving Epidemiological Modeling on Mobile Graphs

Over the last two years, governments all over the world have used a variety of containment measures to control the spread of covid, such as contact tracing, social distance regulations, and curfews. Epidemiological simulations are commonly used to assess the impact of those policies before they are implemented in actuality. Unfortunately, their predictive accuracy is hampered by the scarcity of relevant empirical data, concretely detailed social contact graphs. As this data is inherently privacy-critical, there is an urgent need for a method to perform powerful epidemiological simulations on real-world contact graphs without disclosing sensitive information. In this work, we present RIPPLE, a privacy-preserving epidemiological modeling framework that enables the execution of a wide range of standard epidemiological models for any infectious disease on a population's most recent real contact graph while keeping all contact information private locally on the participants' devices. Our theoretical constructs are supported by a proof-of-concept implementation in which we show that a 2-week simulation over a population of half a million can be finished in 7 minutes with each participant consuming less than 50 KB of data. © 2022 Owner/Author.

Data-driven development of digital health applications on the example of dementia screening

Following the paradigm of precision medicine, the combination of health data and Machine Learning (ML) is promising to improve the quality of healthcare services e.g. by making diagnoses and therapeutic interventions as early and precise as possible. The implementation of this approach requires sufficient amounts of data with a high quality along the data life cycle. This goal seems recently achievable through the implementation of several national digital health strategies and the hope of a growing societal acceptance of digital health applications due to the implications of the COVID-19 pandemic. But, a collection of tools and methods is missing, which supports developers to use data as driving force of the development process. Due to the iterative nature of software application development, it allows the continuous improvement through the integration of collected digital data. We refer to this as a data-driven approach and identify steps to take and tools for its implementation. Associated challenges and opportunities of this translational approach are outlined on the example of a self-developed dementia screening application. Using our methodology, we compared multiple ML algorithms based on the data of an observational study (n=55) and achieved models with sensitivity up to 89% for unhealthy participants within this use case. © 2021 IEEE.

Successful treatment of severe COVID-19 pneumonia and cytokine release with simultaneous tocilizumab and anakinra with one-month follow-up

Background: Severe and life threating COVID-19 pneumonia is often characterized by local and systemic immune-mediated hyperinflammation At the early disease stage activated monocytes are migrating to the lung and cause the typical opac infiltrates, which lead to an reduction of oxygen uptake. These pathophysiological observations and the fact that corticosteroids are so far the only drug, which has shown significant improvement, was the rationale use this combination anti-inflammatory drugs in severe COVID-19 disease. Interleukin (IL)-6 and IL-1 blockade alone, respectively showed contradictory results in severe COVID-19 pneumonia that might be related to the differences is patient populations (early vs. late stage) and to the fact that blockade of just one cytokine might be not sufficient against the cytokine storm. Objectives: Here we report results of an open-label treatment with a combination of an IL-6 receptor blocker tocilizumab and an IL-1 receptor antagonist anakinra in patients with early (up to 10 days since symptom onset) severe COVID-19 pneumonia with evidence of cytokine release. Methods: Adult patients with, according to World Health Organisation criteria, severe to critical COVID-19 infection associated pneumonia and cytokine release, requiring oxygen supplementation and evidence of rapid deterioration and decrease of oxygen saturation to ≤ 95% hospitalized between May 2020 and December 2020 were treated with tocilizumab 8 mg/ kg up to 800 mg intravenously and anakinra 100 to 300 mg for 3 to 5 days, starting at the same day. We excluded patients with a symptom duration of ≥ 10 days, patients with evidence of bacterial infection, indicated by an elevated procalcitonin serum level, patients with severe pre-existing lung disease such as severe COPD or heart failure of ≥ II according to the NYHA classification and patients ≥ 80 years. Laboratory parameters and chest CT were performed on initial presentation and one month after treatment. A semi-quantitative CT score was calculated based on the extent of lobar pneumonia involvement (0:0%;1, < 5%;2:5-25%;3:26-50%;4:51-75%;5, ≥ 75%;range 0-5;global score 0-25) for each time point. Results: 15 patients with severe to critical COVID-19 pneumonia and signs of cytokine release, mean age 55 (range 31-79) years, all male, with a mean symptom duration of 6 (range 4-10) days were treated. Mean oxygen saturation was 86% (range 76-95%) before initiating therapy. Mean ferritin was 1297 μg/l (range 347 -2734), mean IL-6 112 ng/L (range 2.2 -607.4) and CRP 82.4 mg/L (range 36.4 -125). In all patients we were able to prevent them from intubation and mechanic ventilation, none of our patients died. Fife patients did not need to be referred to the intensive care unit at all, while 9 patients received noninvasive ventilation and high-flow nasal oxygen support. All patients showed typical imaging features of COVID-19 pneumonia at baseline (BL) according to the Radiological Society of North America (RSNA) chest CT classification system. The mean of the global chest CT severity score at BL was 13 (range 7-20) and decreased to 6 (range 0-16) within 1 month which corresponded to a mean reduction of 58%. Chronic fibrotic pulmonary changes were not seen in any patient at BL and after 1 month mild changes were observed in 6 patients. One patient experienced lower abdominal pain, urinary tract infection, gastrointestinal bleeding due to antrum ulcers Forrest III, in another patient atrial fibrillation, urinary tract infection and apoplexy were observed. Conclusion: In our case series, all patients treated with the combination tocilizumab and anakinra recovered fast and sustained without major infectious side effects, indicating that early interruption of cytocine release might be very effective and safe in preventing patients from mechanical ventilation, death and longterm damage.