Risk factors for long-term invasive mechanical ventilation: a retrospective longitudinal study using German health claims data

Abstract Purpose Long-term invasive mechanical ventilation (IMV) is a major burden for those affected and causes high costs for the health care system. Early risk assessment is a prerequisite for the best possible support of high-risk patients during the weaning process. We aimed to identify risk factors for long-term IMV within 96 hours after the onset of IMV. Methods The analysis was based on data from the AOK Baden-Württemberg; patients who received IMV ≥ 96h and were discharged between 2015 and 2017 were analysed. Health claims data were considered for the previous year and 30 days after hospitalisation. Long-term IMV was defined as evidence of invasive home mechanical ventilation (HMV), IMV≥ 500h, or readmission with (re)prolonged ventilation. The performance of the model was evaluated on a 2018 data-set. Results 7.584 hospitalisations were analysed. Criteria for long-term IMV were met in 38.3% of cases, of which 13.9% had evidence of HMV, 73.1% were ventilated >500 hours and/or 40.3% were rehospitalised with IMV. Several risk factors could be identified, including pre-existing conditions, admission diagnosis, prescribed aids and procedures. By combining all these factors into a final model, the risk for long-term IMV could be estimated with a sensitivity and specificity of respectively 49 and 80% on the test data set (when classifiying patients based on their predicted probability with a cut-off of 41.15%). Conclusion Based on health claims data alone, the risk for long-term IMV could be estimated with an acceptable predictive quality as early as 96 hours after the start of IMV.