SurvMaximin: Robust federated approach to transporting survival risk prediction models

OBJECTIVE

For multi-center heterogeneous Real-World Data (RWD) with time-to-event outcomes and high-dimensional features, we propose the SurvMaximin algorithm to estimate Cox model feature coefficients for a target population by borrowing summary information from a set of health care centers without sharing patient-level information.

MATERIALS AND METHODS

For each of the centers from which we want to borrow information to improve the prediction performance for the target population, a penalized Cox model is fitted to estimate feature coefficients for the center. Using estimated feature coefficients and the covariance matrix of the target population, we then obtain a SurvMaximin estimated set of feature coefficients for the target population. The target population can be an entire cohort comprised of all centers, corresponding to federated learning, or a single center, corresponding to transfer learning.

RESULTS

Simulation studies and a real-world international electronic health records application study, with 15 participating health care centers across three countries (France, Germany, and the U.S.), show that the proposed SurvMaximin algorithm achieves comparable or higher accuracy compared with the estimator using only the information of the target site and other existing methods. The SurvMaximin estimator is robust to variations in sample sizes and estimated feature coefficients between centers, which amounts to significantly improved estimates for target sites with fewer observations.

CONCLUSIONS

The SurvMaximin method is well suited for both federated and transfer learning in the high-dimensional survival analysis setting. SurvMaximin only requires a one-time summary information exchange from participating centers. Estimated regression vectors can be very heterogeneous. SurvMaximin provides robust Cox feature coefficient estimates without outcome information in the target population and is privacy-preserving.

International electronic health record-derived post-acute sequelae profiles of COVID-19 patients

The risk profiles of post-acute sequelae of COVID-19 (PASC) have not been well characterized in multi-national settings with appropriate controls. We leveraged electronic health record (EHR) data from 277 international hospitals representing 414,602 patients with COVID-19, 2.3 million control patients without COVID-19 in the inpatient and outpatient settings, and over 221 million diagnosis codes to systematically identify new-onset conditions enriched among patients with COVID-19 during the post-acute period. Compared to inpatient controls, inpatient COVID-19 cases were at significant risk for angina pectoris (RR 1.30, 95% CI 1.09–1.55), heart failure (RR 1.22, 95% CI 1.10–1.35), cognitive dysfunctions (RR 1.18, 95% CI 1.07–1.31), and fatigue (RR 1.18, 95% CI 1.07–1.30). Relative to outpatient controls, outpatient COVID-19 cases were at risk for pulmonary embolism (RR 2.10, 95% CI 1.58–2.76), venous embolism (RR 1.34, 95% CI 1.17–1.54), atrial fibrillation (RR 1.30, 95% CI 1.13–1.50), type 2 diabetes (RR 1.26, 95% CI 1.16–1.36) and vitamin D deficiency (RR 1.19, 95% CI 1.09–1.30). Outpatient COVID-19 cases were also at risk for loss of smell and taste (RR 2.42, 95% CI 1.90–3.06), inflammatory neuropathy (RR 1.66, 95% CI 1.21–2.27), and cognitive dysfunction (RR 1.18, 95% CI 1.04–1.33). The incidence of post-acute cardiovascular and pulmonary conditions decreased across time among inpatient cases while the incidence of cardiovascular, digestive, and metabolic conditions increased among outpatient cases. Our study, based on a federated international network, systematically identified robust conditions associated with PASC compared to control groups, underscoring the multifaceted cardiovascular and neurological phenotype profiles of PASC.

Changes in laboratory value improvement and mortality rates over the course of the pandemic: an international retrospective cohort study of hospitalised patients infected with SARS-CoV-2

OBJECTIVE

To assess changes in international mortality rates and laboratory recovery rates during hospitalisation for patients hospitalised with SARS-CoV-2 between the first wave (1 March to 30 June 2020) and the second wave (1 July 2020 to 31 January 2021) of the COVID-19 pandemic.

DESIGN, SETTING AND PARTICIPANTS

This is a retrospective cohort study of 83 178 hospitalised patients admitted between 7 days before or 14 days after PCR-confirmed SARS-CoV-2 infection within the Consortium for Clinical Characterization of COVID-19 by Electronic Health Record, an international multihealthcare system collaborative of 288 hospitals in the USA and Europe. The laboratory recovery rates and mortality rates over time were compared between the two waves of the pandemic.

PRIMARY AND SECONDARY OUTCOME MEASURES

The primary outcome was all-cause mortality rate within 28 days after hospitalisation stratified by predicted low, medium and high mortality risk at baseline. The secondary outcome was the average rate of change in laboratory values during the first week of hospitalisation.

RESULTS

Baseline Charlson Comorbidity Index and laboratory values at admission were not significantly different between the first and second waves. The improvement in laboratory values over time was faster in the second wave compared with the first. The average C reactive protein rate of change was -4.72 mg/dL vs -4.14 mg/dL per day (p=0.05). The mortality rates within each risk category significantly decreased over time, with the most substantial decrease in the high-risk group (42.3% in March-April 2020 vs 30.8% in November 2020 to January 2021, p<0.001) and a moderate decrease in the intermediate-risk group (21.5% in March-April 2020 vs 14.3% in November 2020 to January 2021, p<0.001).

CONCLUSIONS

Admission profiles of patients hospitalised with SARS-CoV-2 infection did not differ greatly between the first and second waves of the pandemic, but there were notable differences in laboratory improvement rates during hospitalisation. Mortality risks among patients with similar risk profiles decreased over the course of the pandemic. The improvement in laboratory values and mortality risk was consistent across multiple countries.

Biosensor-Enabled Multiplexed On-Site Therapeutic Drug Monitoring of Antibiotics

Personalized antibiotherapy ensures that the antibiotic concentration remains in the optimal therapeutic window to maximize efficacy, minimize side effects, and avoid the emergence of drug resistance due to insufficient dosing. However, such individualized schemes need frequent sampling to tailor the blood antibiotic concentrations. To optimally integrate therapeutic drug monitoring (TDM) into the clinical workflow, antibiotic levels can either be measured in blood using point-of-care testing (POCT), or can rely on noninvasive sampling. Here, a versatile biosensor with an antibody-free assay for on-site TDM is presented. The platform is evaluated with an animal study, where antibiotic concentrations are quantified in different matrices including whole blood, plasma, urine, saliva, and exhaled breath condensate (EBC). The clearance and the temporal evaluation of antibiotic levels in EBC and plasma are demonstrated. Influence of matrix effects on measured drug concentrations is determined by comparing the plasma levels with those in noninvasive samples. The system's potential for blood-based POCT is further illustrated by tracking ß-lactam concentrations in untreated blood samples. Finally, multiplexing capabilities are explored successfully for multianalyte/sample analysis. By enabling a rapid, low-cost, sample-independent, and multiplexed on-site TDM, this system can shift the paradigm of "one-size-fits-all" strategy.

International Changes in COVID-19 Clinical Trajectories Across 315 Hospitals and 6 Countries: Retrospective Cohort Study

Background

Many countries have experienced 2 predominant waves of COVID-19–related hospitalizations. Comparing the clinical trajectories of patients hospitalized in separate waves of the pandemic enables further understanding of the evolving epidemiology, pathophysiology, and health care dynamics of the COVID-19 pandemic.

Objective

In this retrospective cohort study, we analyzed electronic health record (EHR) data from patients with SARS-CoV-2 infections hospitalized in participating health care systems representing 315 hospitals across 6 countries. We compared hospitalization rates, severe COVID-19 risk, and mean laboratory values between patients hospitalized during the first and second waves of the pandemic.

Methods

Using a federated approach, each participating health care system extracted patient-level clinical data on their first and second wave cohorts and submitted aggregated data to the central site. Data quality control steps were adopted at the central site to correct for implausible values and harmonize units. Statistical analyses were performed by computing individual health care system effect sizes and synthesizing these using random effect meta-analyses to account for heterogeneity. We focused the laboratory analysis on C-reactive protein (CRP), ferritin, fibrinogen, procalcitonin, D-dimer, and creatinine based on their reported associations with severe COVID-19.

Results

Data were available for 79,613 patients, of which 32,467 were hospitalized in the first wave and 47,146 in the second wave. The prevalence of male patients and patients aged 50 to 69 years decreased significantly between the first and second waves. Patients hospitalized in the second wave had a 9.9% reduction in the risk of severe COVID-19 compared to patients hospitalized in the first wave (95% CI 8.5%-11.3%). Demographic subgroup analyses indicated that patients aged 26 to 49 years and 50 to 69 years; male and female patients; and black patients had significantly lower risk for severe disease in the second wave than in the first wave. At admission, the mean values of CRP were significantly lower in the second wave than in the first wave. On the seventh hospital day, the mean values of CRP, ferritin, fibrinogen, and procalcitonin were significantly lower in the second wave than in the first wave. In general, countries exhibited variable changes in laboratory testing rates from the first to the second wave. At admission, there was a significantly higher testing rate for D-dimer in France, Germany, and Spain.

Conclusions

Patients hospitalized in the second wave were at significantly lower risk for severe COVID-19. This corresponded to mean laboratory values in the second wave that were more likely to be in typical physiological ranges on the seventh hospital day compared to the first wave. Our federated approach demonstrated the feasibility and power of harmonizing heterogeneous EHR data from multiple international health care systems to rapidly conduct large-scale studies to characterize how COVID-19 clinical trajectories evolve.

Effect of individualized PEEP titration guided by intratidal compliance profile analysis on regional ventilation assessed by electrical impedance tomography - a randomized controlled trial

Background

The application of positive end-expiratory pressure (PEEP) may reduce dynamic strain during mechanical ventilation. Although numerous approaches for PEEP titration have been proposed, there is no accepted strategy for titrating optimal PEEP. By analyzing intratidal compliance profiles, PEEP may be individually titrated for patients.

Methods

After obtaining informed consent, 60 consecutive patients undergoing general anesthesia were randomly allocated to mechanical ventilation with PEEP 5 cmH₂O (control group) or PEEP individually titrated, guided by an analysis of the intratidal compliance profile (intervention group). The primary endpoint was the frequency of each nonlinear intratidal compliance (C_RS) profile of the respiratory system (horizontal, increasing, decreasing, and mixed). The secondary endpoints measured were respiratory mechanics, hemodynamic variables, and regional ventilation, which was assessed via electrical impedance tomography.

Results

The frequencies of the C_RS profiles were comparable between the groups. Besides PEEP [control: 5.0 (0.0), intervention: 5.8 (1.1) cmH₂O, p < 0.001], the respiratory and hemodynamic variables were comparable between the two groups. The compliance profile analysis showed no significant differences between the two groups. The loss of ventral and dorsal regional ventilation was higher in the control [ventral: 41.0 (16.3)%; dorsal: 25.9 (13.8)%] than in the intervention group [ventral: 29.3 (17.6)%; dorsal: 16.4 (12.7)%; p (ventral) = 0.039, p (dorsal) = 0.028].

Conclusions

Unfavorable compliance profiles indicating tidal derecruitment were found less often than in earlier studies. Individualized PEEP titration resulted in slightly higher PEEP. A slight global increase in aeration associated with this was indicated by regional gain and loss analysis. Differences in dorsal to ventral ventilation distribution were not found.

Trial registration

This clinical trial was registered at the German Register for Clinical Trials (DRKS00008924) on August 10, 2015.

A novel mechanical ventilator providing flow-controlled expiration for small animals

For investigating the effects of mechanical ventilation on the respiratory system, experiments in small mammal models are used. However, conventional ventilators for small animals are usually limited to a specific ventilation mode, and in particular to passive expiration. Here, we present a computer-controlled research ventilator for small animals which provides conventional mechanical ventilation as well as new type ventilation profiles. Typical profiles of conventional mechanical ventilation, as well as flow-controlled expiration and sinusoidal ventilation profiles can be generated with our new ventilator. Flow control during expiration reduced the expiratory peak flow rate by 73% and increased the mean airway pressure by up to 1 mbar compared with conventional ventilation without increasing peak pressure and end-expiratory pressure. Our new ventilator for small animals allows for the application of various ventilation profiles. We could analyse the effects of applying conventional ventilation profiles, pressure-controlled ventilation and volume-controlled ventilation, as well as the novel flow-controlled ventilation profile. This new approach enables studying the mechanical properties of the respiratory system with an increased freedom for choosing independent ventilation parameters.

Intratidal recruitment/derecruitment persists at low and moderate positive end-expiratory pressure in paediatric patients

In paediatric patients positive end-expiratory pressure (PEEP) is traditionally set lower than in adults. We investigated whether moderately higher PEEP improves respiratory mechanics and regional ventilation. Therefore, 40 children were mechanically ventilated with PEEP 2 and 5cmH₂O. Volume-dependent compliance profiles were analysed as a measure of intratidal recruitment/derecruitment. Regional ventilation was assessed using electrical impedance tomography. Mean compliance was 17.9±9.9mLcmH₂O^-1 (PEEP 2cmH₂O), and 19.0±10.9mLcmH₂O^-1 (PEEP 5 cmH₂O, p<0.001). Strong intratidal recruitment/derecruitment occurred in 40% of children at PEEP 2 cmH₂O, and 36% at PEEP 5 cmH₂O. Children showing strong recruitment/derecruitment were 33 (PEEP 2 cmH₂0) and 20 (PEEP 5 cmH₂0) months younger than children showing moderate recruitment/derecruitment. A higher PEEP improved peripheral ventilation. In conclusion, mechanically ventilated paediatric patients undergo intratidal recruitment/derecruitment which occurs more prominently in younger than in older children. A PEEP of 5cmH₂O does not fully prevent intratidal recruitment/derecruitment but homogenizes regional ventilation in comparison to 2cmH₂O.

Breathing-phase selective filtering of respiratory data improves analysis of dynamic respiratory mechanics

BACKGROUND

The analysis of non-linear respiratory system mechanics under the dynamic conditions of controlled mechanical ventilation is affected by systemic disturbances of the respiratory signals. Cardio-pulmonary coupling induces cardiogenic oscillations to the respiratory signals, which appear prominently in the second half of expiration.

OBJECTIVE

We hypothesized that breathing phase-selective filtering of expiratory data improves the analysis of respiratory system mechanics.

METHODS

We retrospectively analyzed data from a multicenter-study (28 patients with injured lungs, under volume-controlled ventilation) and from two additional studies (3 lung healthy patients and 3 with injured lungs, under pressure-controlled ventilation). Data streams were recorded at different levels of positive end-expiratory pressure. Using the gliding-SLICE method, intratidal dynamic respiratory mechanics were analyzed with and without low-pass filtering of expiratory or inspiratory data separately. The quality of data analysis was derived from the coefficient of determination R^2.

RESULTS

Without filtering, R^2 lay below 0.995 for 87 of 280 investigated data streams. In 68 cases expiration-selective low-pass filtering improved the quality of analysis to R^2 ⩾ 0.995. In contrast, inspiration-selective filtering did not improve R^2.

CONCLUSIONS

The selective filtering of expiration data eliminates negative side-effects of cardiogenic oscillations thus leading to a significant improvement of the analysis of dynamic respiratory system mechanics.

Automated mechanical ventilation: adapting decision making to different disease states

The purpose of the present study is to introduce a novel methodology for adapting and upgrading decision-making strategies concerning mechanical ventilation with respect to different disease states into our fuzzy-based expert system, AUTOPILOT-BT. The special features are: (1) Extraction of clinical knowledge in analogy to the daily routine. (2) An automated process to obtain the required information and to create fuzzy sets. (3) The controller employs the derived fuzzy rules to achieve the desired ventilation status. For demonstration this study focuses exclusively on the control of arterial CO(2) partial pressure (p(a)CO(2)). Clinical knowledge from 61 anesthesiologists was acquired using a questionnaire from which different disease-specific fuzzy sets were generated to control p(a)CO(2). For both, patients with healthy lung and with acute respiratory distress syndrome (ARDS) the fuzzy sets show different shapes. The fuzzy set "normal", i.e., "target p(a)CO(2) area", ranges from 35 to 39 mmHg for healthy lungs and from 39 to 43 mmHg for ARDS lungs. With the new fuzzy sets our AUTOPILOT-BT reaches the target p(a)CO(2) within maximal three consecutive changes of ventilator settings. Thus, clinical knowledge can be extended, updated, and the resulting mechanical ventilation therapies can be individually adapted, analyzed, and evaluated.