The Potential Cost-Effectiveness of a Machine Learning Tool That Can Prevent Untimely Intensive Care Unit Discharge.

OBJECTIVES: The machine learning prediction model Pacmed Critical (PC), currently under development, may guide intensivists in their decision-making process on the most appropriate time to discharge a patient from the intensive care unit (ICU). Given the financial pressure on healthcare budgets, this study assessed whether PC has the potential to be cost-effective compared with standard care, without the use of PC, for Dutch patients in the ICU from a societal perspective. METHODS: A 1-year, 7-state Markov model reflecting the ICU care pathway and incorporating the PC decision tool was developed. A hypothetical cohort of 1000 adult Dutch patients admitted in the ICU was entered in the model. We used the literature, expert opinion, and data from Amsterdam University Medical Center for model parameters. The uncertainty surrounding the incremental cost-effectiveness ratio was assessed using deterministic and probabilistic sensitivity analyses and scenario analyses. RESULTS: PC was a cost-effective strategy with an incremental cost-effectiveness ratio of €18 507 per quality-adjusted life-year. PC remained cost-effective over standard care in multiple scenarios and sensitivity analyses. The likelihood that PC will be cost-effective was 71% at a willingness-to-pay threshold of €30 000 per quality-adjusted life-year. The key driver of the results was the parameter "reduction in ICU length of stay." CONCLUSIONS: We showed that PC has the potential to be cost-effective for Dutch ICUs in a time horizon of 1 year. This study is one of the first cost-effectiveness analyses of a machine learning device. Further research is needed to validate the effectiveness of PC, thereby focusing on the key parameter "reduction in ICU length of stay" and potential spill-over effects.

Comparison of Linear and Sector Array Probe for Handheld Lung Ultrasound in Invasively Ventilated ICU Patients.

International guidelines do not recommend a specific probe for assessment of lung aeration using lung ultrasound (LUS). The aim of this study was to assess the concordance between linear and sector array probes of a handheld ultrasound device in assessment of lung aeration in invasively ventilated intensive care unit patients. This study included intensive care unit patients who were expected to be ventilated for longer than 24 h. A 12-region LUS exam was performed with a linear and a sector array probe. In each image, the LUS aeration score and number of B-lines were determined. Adding the LUS aeration scores of all regions resulted in a global LUS aeration score. Agreement between the two probes was calculated using intra-class correlation coefficients (ICCs). A total of 30 LUS exams were performed in 19 patients, resulting in a total of 328 pairs of images. Twenty-nine pairs of images were excluded from analysis because the images from the linear probe could not be scored. ICCs calculated for the remaining images revealed good concordance the LUS aeration scores for individual images (ICC = 0.73, 95% confidence interval 0.67-0.78), number of B-lines (ICC = 0.79, 95% confidence interval 0.72-0.83) and global LUS aeration score (ICC = 0.74, 95% confidence interval 0.52-0.87). In conclusion, there is good concordance between linear and sector array probes of a handheld ultrasound device in assessment of lung aeration patterns in mechanically ventilated intensive care unit patients. However, in roughly 10% of the images acquired using the linear probe, the aeration pattern could not be scored.