Elucidating the causal relationship of mechanical power and lung injury: a dynamic approach to ventilator management
Abstract Background Mechanical power (MP) serves as a crucial predictive indicator for ventilator-induced lung injury and plays a pivotal role in tailoring the management of mechanical ventilation. However, its application across different diseases and stages remains nuanced. Methods Using Amsterdam...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-02-01
|
| Series: | Intensive Care Medicine Experimental |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40635-025-00736-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850132963407167488 |
|---|---|
| author | ChaoPing Wu Arif Canakoglu Jacob Vine Anya Mathur Ronit Nath Markos Kashiouris Piyush Mathur Ari Ercole Paul Elbers Abhijit Duggal Ken Koon Wong Anirban Bhattacharyya |
| author_facet | ChaoPing Wu Arif Canakoglu Jacob Vine Anya Mathur Ronit Nath Markos Kashiouris Piyush Mathur Ari Ercole Paul Elbers Abhijit Duggal Ken Koon Wong Anirban Bhattacharyya |
| author_sort | ChaoPing Wu |
| collection | DOAJ |
| description | Abstract Background Mechanical power (MP) serves as a crucial predictive indicator for ventilator-induced lung injury and plays a pivotal role in tailoring the management of mechanical ventilation. However, its application across different diseases and stages remains nuanced. Methods Using AmsterdamUMCdb, we conducted a retrospective study to analyze the causal relationship between MP and outcomes of invasive mechanical ventilation, specifically SpO2/FiO2 ratio (P/F) and ventilator-free days at day 28 (VFD28). We employed causal inferential analysis with backdoor linear regression and double machine learning, guided by directed acyclic graphs, to estimate the average treatment effect (ATE) in the whole population and conditional average treatment effect (CATE) in the individual cohort. Additionally, to enhance interpretability and identify MP thresholds, we conducted a simulation analysis. Results In the study, we included 11,110 unique admissions into analysis, of which 58.3% (6391) were surgical admissions. We revealed a negative and significant causal effect of median MP on VFD28, with estimated ATEs of −0.135 (95% confidence interval [CI]: −0.15 to −0.121). The similar effect was not observed in Maximal MP and minimal MP. The effect of MP was more pronounced in the medical subgroup, with a CATE of −0.173 (95% CI: −0.197 to −0.143) determined through backdoor linear regression. Patients with cardio, respiratory, and infection diagnoses, who required long-term intubation, sustained higher impact on CATEs across various admission diagnoses. Our simulations showed that there is no single MP threshold that can be applied to all patients, as the optimal threshold varies depending on the patient’s condition. Conclusion Our study underscores the importance of tailoring MP adjustments on an individualized basis in ventilator management. This approach opens up new avenues for personalized treatment strategies and provides fresh insights into the real-time impact of MP in diverse clinical scenarios. It highlights the significance of median MP while acknowledging the absence of universally applicable thresholds. |
| format | Article |
| id | doaj-art-fdbfa640159c4b2c8bbf0d88c1b8230e |
| institution | OA Journals |
| issn | 2197-425X |
| language | English |
| publishDate | 2025-02-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Intensive Care Medicine Experimental |
| spelling | doaj-art-fdbfa640159c4b2c8bbf0d88c1b8230e2025-08-20T02:32:05ZengSpringerOpenIntensive Care Medicine Experimental2197-425X2025-02-0113111110.1186/s40635-025-00736-wElucidating the causal relationship of mechanical power and lung injury: a dynamic approach to ventilator managementChaoPing Wu0Arif Canakoglu1Jacob Vine2Anya Mathur3Ronit Nath4Markos Kashiouris5Piyush Mathur6Ari Ercole7Paul Elbers8Abhijit Duggal9Ken Koon Wong10Anirban Bhattacharyya11Critical Care, Integrated Hospital Care Institute, Cleveland ClinicDepartment of Anestesia, Intensive Care and Emergency, Fondazione IRCCS Ca’ Granda Ospedale Maggiore PoliclinicoCenter for Resuscitation Science, Beth Israel Deaconess Medical CenterWestern Reserve AcademyComputer Science, University of California, BerkeleyCritical Care, INOVA Fairfax HospitalAnesthesiology, Integrated Hospital Care Institute, Cleveland ClinicCambridge Center for Artificial Intelligence in Medicine.Intensive Care Medicine, Amsterdam UMCCritical Care, Integrated Hospital Care Institute, Cleveland ClinicInfectious Diseases, Integrated Hospital Care Institute, Cleveland ClinicCritical Care, Mayo ClinicAbstract Background Mechanical power (MP) serves as a crucial predictive indicator for ventilator-induced lung injury and plays a pivotal role in tailoring the management of mechanical ventilation. However, its application across different diseases and stages remains nuanced. Methods Using AmsterdamUMCdb, we conducted a retrospective study to analyze the causal relationship between MP and outcomes of invasive mechanical ventilation, specifically SpO2/FiO2 ratio (P/F) and ventilator-free days at day 28 (VFD28). We employed causal inferential analysis with backdoor linear regression and double machine learning, guided by directed acyclic graphs, to estimate the average treatment effect (ATE) in the whole population and conditional average treatment effect (CATE) in the individual cohort. Additionally, to enhance interpretability and identify MP thresholds, we conducted a simulation analysis. Results In the study, we included 11,110 unique admissions into analysis, of which 58.3% (6391) were surgical admissions. We revealed a negative and significant causal effect of median MP on VFD28, with estimated ATEs of −0.135 (95% confidence interval [CI]: −0.15 to −0.121). The similar effect was not observed in Maximal MP and minimal MP. The effect of MP was more pronounced in the medical subgroup, with a CATE of −0.173 (95% CI: −0.197 to −0.143) determined through backdoor linear regression. Patients with cardio, respiratory, and infection diagnoses, who required long-term intubation, sustained higher impact on CATEs across various admission diagnoses. Our simulations showed that there is no single MP threshold that can be applied to all patients, as the optimal threshold varies depending on the patient’s condition. Conclusion Our study underscores the importance of tailoring MP adjustments on an individualized basis in ventilator management. This approach opens up new avenues for personalized treatment strategies and provides fresh insights into the real-time impact of MP in diverse clinical scenarios. It highlights the significance of median MP while acknowledging the absence of universally applicable thresholds.https://doi.org/10.1186/s40635-025-00736-wMechanical powerMechanical ventilationCausal inferenceCounterfactual testingMachine learningDirect acyclic graph |
| spellingShingle | ChaoPing Wu Arif Canakoglu Jacob Vine Anya Mathur Ronit Nath Markos Kashiouris Piyush Mathur Ari Ercole Paul Elbers Abhijit Duggal Ken Koon Wong Anirban Bhattacharyya Elucidating the causal relationship of mechanical power and lung injury: a dynamic approach to ventilator management Intensive Care Medicine Experimental Mechanical power Mechanical ventilation Causal inference Counterfactual testing Machine learning Direct acyclic graph |
| title | Elucidating the causal relationship of mechanical power and lung injury: a dynamic approach to ventilator management |
| title_full | Elucidating the causal relationship of mechanical power and lung injury: a dynamic approach to ventilator management |
| title_fullStr | Elucidating the causal relationship of mechanical power and lung injury: a dynamic approach to ventilator management |
| title_full_unstemmed | Elucidating the causal relationship of mechanical power and lung injury: a dynamic approach to ventilator management |
| title_short | Elucidating the causal relationship of mechanical power and lung injury: a dynamic approach to ventilator management |
| title_sort | elucidating the causal relationship of mechanical power and lung injury a dynamic approach to ventilator management |
| topic | Mechanical power Mechanical ventilation Causal inference Counterfactual testing Machine learning Direct acyclic graph |
| url | https://doi.org/10.1186/s40635-025-00736-w |
| work_keys_str_mv | AT chaopingwu elucidatingthecausalrelationshipofmechanicalpowerandlunginjuryadynamicapproachtoventilatormanagement AT arifcanakoglu elucidatingthecausalrelationshipofmechanicalpowerandlunginjuryadynamicapproachtoventilatormanagement AT jacobvine elucidatingthecausalrelationshipofmechanicalpowerandlunginjuryadynamicapproachtoventilatormanagement AT anyamathur elucidatingthecausalrelationshipofmechanicalpowerandlunginjuryadynamicapproachtoventilatormanagement AT ronitnath elucidatingthecausalrelationshipofmechanicalpowerandlunginjuryadynamicapproachtoventilatormanagement AT markoskashiouris elucidatingthecausalrelationshipofmechanicalpowerandlunginjuryadynamicapproachtoventilatormanagement AT piyushmathur elucidatingthecausalrelationshipofmechanicalpowerandlunginjuryadynamicapproachtoventilatormanagement AT ariercole elucidatingthecausalrelationshipofmechanicalpowerandlunginjuryadynamicapproachtoventilatormanagement AT paulelbers elucidatingthecausalrelationshipofmechanicalpowerandlunginjuryadynamicapproachtoventilatormanagement AT abhijitduggal elucidatingthecausalrelationshipofmechanicalpowerandlunginjuryadynamicapproachtoventilatormanagement AT kenkoonwong elucidatingthecausalrelationshipofmechanicalpowerandlunginjuryadynamicapproachtoventilatormanagement AT anirbanbhattacharyya elucidatingthecausalrelationshipofmechanicalpowerandlunginjuryadynamicapproachtoventilatormanagement |