935: Predicting Duration of Mechanical Ventilation With Medication Regimen Complexity Variables

Murray, Brian; Zhao, Bokai; Kong, Yanlei; Ye, Shen; Sikora, Andrea

doi:10.1097/01.ccm.0000909468.03569.76

Cited by 4 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Algorithms have been previously developed that include indicators of a broad class of medications, such as use of inotropes and vasopressors, without adjusting for the individual’s overall regimen. 37 , 50–56 While such broad strokes were often used due to limitations of the technology, large amounts of relevant detail were ignored, given the unique pharmacokinetic and pharmacodynamic profile of each drug and potential interactions with other drugs that go unaccounted for with that approach. Unsupervised machine learning using Restricted Boltzmann Machine has been applied to the medication administration records of ICU patients revealing unique pharmacophenotypes associated with patient outcomes.…”

Section: Discussionmentioning

confidence: 99%

“…Medication data have also been incorporated into supervised learning for prediction of prolonged duration of mechanical ventilation and mortality; however, neither of these analyses included the entire ICU medication regimen and focused just on generic name. 28 , 50–52 Overall, a common theme is the improvement of modeling performance with the inclusion of medication data (particularly drug name or class), though little has been done incorporating comprehensive medication data for the patient’s regimen (including both all medications they received and relevant information on those medications).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A common data model for the standardization of intensive care unit medication features

Sikora,

Keats,

Murphy

et al. 2024

JAMIA Open

Self Cite

View full text Add to dashboard Cite

Objective Common data models provide a standard means of describing data for artificial intelligence (AI) applications, but this process has never been undertaken for medications used in the intensive care unit (ICU). We sought to develop a common data model (CDM) for ICU medications to standardize the medication features needed to support future ICU AI efforts. Materials and Methods A 9-member, multi-professional team of ICU clinicians and AI experts conducted a 5-round modified Delphi process employing conference calls, web-based communication, and electronic surveys to define the most important medication features for AI efforts. Candidate ICU medication features were generated through group discussion and then independently scored by each team member based on relevance to ICU clinical decision-making and feasibility for collection and coding. A key consideration was to ensure the final ontology both distinguished unique medications and met Findable, Accessible, Interoperable, and Reusable (FAIR) guiding principles. Results Using a list of 889 ICU medications, the team initially generated 106 different medication features, and 71 were ranked as being core features for the CDM. Through this process, 106 medication features were assigned to 2 key feature domains: drug product-related (n = 43) and clinical practice-related (n = 63). Each feature included a standardized definition and suggested response values housed in the electronic data library. This CDM for ICU medications is available online. Conclusion The CDM for ICU medications represents an important first step for the research community focused on exploring how AI can improve patient outcomes and will require ongoing engagement and refinement.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

A common data model for the standardization of intensive care unit medication features

Sikora,

Keats,

Murphy

et al. 2024

JAMIA Open

Self Cite

View full text Add to dashboard Cite

show abstract

“…Medication data have also been incorporated into supervised learning for prediction of prolonged duration of mechanical ventilation and mortality; however, neither of these analyses included the entire ICU medication regimen and focused just on generic name. [28,41,43] Similarly, a large analysis of factors associated with hemodynamic compromise did incorporate some medication data, although it was not the complete regimen. [42] A common theme is the improvement of modeling performance with the inclusion of medication data (particularly drug name or class), though little has been done incorporating comprehensive medication data for the patient’s regimen (including both all medications they received and relevant information on those medications) to date.…”

Section: Discussionmentioning

confidence: 99%

A Common Data Model for the standardization of intensive care unit (ICU) medication features in artificial intelligence (AI) applications

Sikora,

Keats,

Murphy

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Objective: Common Data Models provide a standard means of describing data for artificial intelligence (AI) applications, but this process has never been undertaken for medications used in the intensive care unit (ICU). We sought to develop a Common Data Model (CDM) for ICU medications to standardize the medication features needed to support future ICU AI efforts. Materials and Methods: A 9-member, multi-professional team of ICU clinicians and AI experts conducted a 5-round modified Delphi process employing conference calls, web-based communication, and electronic surveys to define the most important medication features for AI efforts. Candidate ICU medication features were generated through group discussion and then independently scored by each team member based on relevance to ICU clinical decision-making and feasibility for collection and coding. A key consideration was to ensure the final ontology both distinguished unique medications and met Findable, Accessible, Interoperable, and Reusable (FAIR) guiding principles. Results: Using a list of 889 ICU medications, the team initially generated 106 different medication features, and 71 were ranked as being core features for the CDM. Through this process, 106 medication features were assigned to two key feature domains: drug product-related (n=43) and clinical practice-related (n=63). Each feature included a standardized definition and suggested response values housed in the electronic data library. This CDM for ICU medications is available online. Discussion: The CDM for ICU medications represents an important first step for the research community focused on exploring how AI can improve patient outcomes and will require ongoing engagement and refinement.

show abstract

“…(16)(17)(18)(19)(20)(21)(22)(23)(24) Moreover, use of machine learning techniques in combination with MRC-ICU appears to improve prediction and has shown utility in a variety of ICU prediction questions. (20,25) In this study, we aimed to employ both traditional and machine learning techniques to develop and validate PMV prediction models with the goal of identifying the most useful predictors at the bedside. We hypothesized that advanced machine learning techniques may be useful to identify the most important clinical factors that can differentiate between patients with high versus low risk of PMV.…”

Section: Introductionmentioning

confidence: 99%

“…(16–24) Moreover, use of machine learning techniques in combination with MRC-ICU appears to improve prediction and has shown utility in a variety of ICU prediction questions. (20,25)…”

Section: Introductionmentioning

confidence: 99%

Machine learning based prediction of prolonged duration of mechanical ventilation incorporating medication data

Sikora,

Zhao,

Kong

et al. 2023

Preprint

View full text Add to dashboard Cite

Rationale: Duration of mechanical ventilation is associated with adverse outcomes in critically ill patients and increased use of resources. The increasing complexity of medication regimens has been associated with increased mortality, length of stay, and fluid overload but has never been studied specifically in the setting of mechanical ventilation. Objective: The purpose of this analysis was to develop prediction models for mechanical ventilation duration to test the hypothesis that incorporating medication data may improve model performance. Methods: This was a retrospective cohort study of adults admitted to the ICU and undergoing mechanical ventilation for longer than 24 hours from October 2015 to October 2020. Patients were excluded if it was not their index ICU admission or if the patient was placed on comfort care in the first 24 hours of admission. Relevant patient characteristics including age, sex, body mass index, admission diagnosis, morbidities, vital signs measurements, severity of illness, medication regimen complexity as measured by the MRC-ICU, and medical treatments before intubation were collected. The primary outcome was area under the receiver operating characteristic (AUROC) of prediction models for prolonged mechanical ventilation (defined as greater than 5 days). Both logistic regression and supervised learning techniques including XGBoost, Random Forest, and Support Vector Machine were used to develop prediction models. Results: The 318 patients [age 59.9 (SD 16.9), female 39.3%, medical 28.6%] had mean 24-hour MRC-ICU score of 21.3 (10.5), mean APACHE II score of 21.0 (5.4), mean SOFA score of 9.9 (3.3), and ICU mortality rate of 22.6% (n=72). The strongest performing logistic model was the base model with MRC-ICU added, with AUROC of 0.72, positive predictive value (PPV) of 0.83, and negative prediction value (NPV) of 0.92. The strongest overall model was Random Forest with an AUROC of 0.78, a PPV of 0.53, and NPV of 0.90. Feature importance analysis using support vector machine and Random Forest revealed severity of illness scores and medication related data were the most important predictors. Conclusions: Medication regimen complexity is significantly associated with prolonged duration of mechanical ventilation in critically ill patients, and prediction models incorporating medication information showed modest improvement in this prediction.

show abstract

935: Predicting Duration of Mechanical Ventilation With Medication Regimen Complexity Variables

Cited by 4 publications

References 0 publications

A common data model for the standardization of intensive care unit medication features

A common data model for the standardization of intensive care unit medication features

A Common Data Model for the standardization of intensive care unit (ICU) medication features in artificial intelligence (AI) applications

Machine learning based prediction of prolonged duration of mechanical ventilation incorporating medication data

Contact Info

Product

Resources

About