Geoeconomic variations in epidemiology, ventilation management, and outcomes in invasively ventilated intensive care unit patients without acute respiratory distress syndrome: a pooled analysis of four observational studies

Abstract

Background: Geoeconomic variations in epidemiology, the practice of ventilation, and outcome in invasively ventilated intensive care unit (ICU) patients without acute respiratory distress syndrome (ARDS) remain unexplored. In this analysis we aim to address these gaps using individual patient data of four large observational studies.

Methods: In this pooled analysis we harmonised individual patient data from the ERICC, LUNG SAFE, PRoVENT, and PRoVENT-iMiC prospective observational studies, which were conducted from June, 2011, to December, 2018, in 534 ICUs in 54 countries. We used the 2016 World Bank classification to define two geoeconomic regions: middle-income countries (MICs) and high-income countries (HICs). ARDS was defined according to the Berlin criteria. Descriptive statistics were used to compare patients in MICs versus HICs. The primary outcome was the use of low tidal volume ventilation (LTVV) for the first 3 days of mechanical ventilation. Secondary outcomes were key ventilation parameters (tidal volume size, positive end-expiratory pressure, fraction of inspired oxygen, peak pressure, plateau pressure, driving pressure, and respiratory rate), patient characteristics, the risk for and actual development of acute respiratory distress syndrome after the first day of ventilation, duration of ventilation, ICU length of stay, and ICU mortality.

Findings: Of the 7608 patients included in the original studies, this analysis included 3852 patients without ARDS, of whom 2345 were from MICs and 1507 were from HICs. Patients in MICs were younger, shorter and with a slightly lower body-mass index, more often had diabetes and active cancer, but less often chronic obstructive pulmonary disease and heart failure than patients from HICs. Sequential organ failure assessment scores were similar in MICs and HICs. Use of LTVV in MICs and HICs was comparable (42·4% vs 44·2%; absolute difference -1·69 [-9·58 to 6·11] p=0·67; data available in 3174 [82%] of 3852 patients). The median applied positive end expiratory pressure was lower in MICs than in HICs (5 [IQR 5-8] vs 6 [5-8] cm H₂O; p=0·0011). ICU mortality was higher in MICs than in HICs (30·5% vs 19·9%; p=0·0004; adjusted effect 16·41% [95% CI 9·52-23·52]; p<0·0001) and was inversely associated with gross domestic product (adjusted odds ratio for a US$10 000 increase per capita 0·80 [95% CI 0·75-0·86]; p<0·0001).

Interpretation: Despite similar disease severity and ventilation management, ICU mortality in patients without ARDS is higher in MICs than in HICs, with a strong association with country-level economic status.

Funding: No funding.

Figure 1

Ventilation parameters on the first day of mechanical ventilation in patients stratified by economic group Cumulative frequency distribution of tidal volume (A), positive end-expiratory pressure (B), plateau pressure (C), and driving pressure (D). Vertical dotted lines represent the cutoff for each variable and horizontal dotted lines represent the respective proportion of patients reaching each cutoff.

Figure 2

Marginal effect plot (A) showing the predicted mortality according to the SOFA score at day 1 and variable life-adjusted display (B) to assess cumulative excess survival according to income groups ICU=intensive care unit. SOFA=sequential organ failure assessment.

Figure 3

Scatter plot exploring the association between crude intensive care unit mortality and gross domestic product per capita Each circle represents a country. The size of the circle reflects the number of enrolled patients in the country (appendix pp 8–9). Middle-income countries were further divided into lower-middle-income (red) and upper-middle-income countries (green). Countries that recruited fewer than 50 patients were excluded.