Definition and Classification of Postoperative Complications After Cardiac Surgery: Pilot Delphi Study

Lapp, Linda; Bouamrane, Matt-Mouley; Roper, Marc; Kavanagh, Kimberley; Schraag, Stefan

doi:10.2196/39907

Cited by 2 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, as ICU mortality rates are decreasing 78 other care quality benchmarks are becoming more important, such as complications. 79 With an ageing population, morbidity, on the other hand, is becoming more prevalent and is the reason why healthcare systems around the world are struggling to sustain their current “reactive” models of care. 80 , 81 …”

Section: Discussionmentioning

confidence: 99%

“…77 However, as ICU mortality rates are decreasing 78 other care quality benchmarks are becoming more important, such as complications. 79 With an ageing population, morbidity, on the other hand, is becoming more prevalent and is the reason why healthcare systems around the world are struggling to sustain their current "reactive" models of care. 80,81 The definition of the predicted outcome can be what makes or breaks a prediction model: Because the definition of mortality is clear, there is no bias in the recorded outcome.…”

Section: Predicted Outcomesmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Prediction of Patient Outcomes in the Intensive Care Unit: A Scoping Review of the State-of-the-Art

Lapp

Roper

Kavanagh

et al. 2023

J Intensive Care Med

Self Cite

View full text Add to dashboard Cite

Introduction Intensive care units (ICUs) are high-pressure, complex, technology-intensive medical environments where patient physiological data are generated continuously. Due to the complexity of interpreting multiple signals at speed, there are substantial opportunities and significant potential benefits in providing ICU staff with additional decision support and predictive modeling tools that can support and aid decision-making in real-time. This scoping review aims to synthesize the state-of-the-art dynamic prediction models of patient outcomes developed for use in the ICU. We define “dynamic” models as those where predictions are regularly computed and updated over time in response to updated physiological signals. Methods Studies describing the development of predictive models for use in the ICU were searched, using PubMed. The studies were screened as per Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines, and the data regarding predicted outcomes, methods used to develop the predictive models, preprocessing the data and dealing with missing values, and performance measures were extracted and analyzed. Results A total of n = 36 studies were included for synthesis in our review. The included studies focused on the prediction of various outcomes, including mortality (n = 17), sepsis-related complications (n = 12), cardiovascular complications (n = 5), and other complications (respiratory, renal complications, and bleeding, n = 5). The most common classification methods include logistic regression, random forest, support vector machine, and neural networks. Conclusion The included studies demonstrated that there is a strong interest in developing dynamic prediction models for various ICU patient outcomes. Most models reported focus on mortality. As such, the development of further models focusing on a range of other serious and well-defined complications—such as acute kidney injury—would be beneficial. Furthermore, studies should improve the reporting of key aspects of model development challenges.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Predicted Outcomesmentioning

confidence: 99%

Dynamic Prediction of Patient Outcomes in the Intensive Care Unit: A Scoping Review of the State-of-the-Art

Lapp

Roper

Kavanagh

et al. 2023

J Intensive Care Med

Self Cite

View full text Add to dashboard Cite

show abstract

Predictive Modelling and Decision Support in Cardiac Surgery: Requirements Analysis with Cardiac Surgeons and Anesthetists (Preprint)

Lapp¹,

Bouamrane²,

Roper³

et al. 2023

Preprint

View full text Add to dashboard Cite

BACKGROUND The use of predictive models and decision support systems can potentially make a substantial difference in clinical management and patient care in cardiac surgery. However, in order to develop decision support systems that are fit for purpose, working with clinical domain experts and stakeholders from the start is essential to gather key requirements early on in the system design process, prototyping, testing, and evaluation. OBJECTIVE This study aimed to capture the current challenges in cardiac surgery, clinical processes to avoid these challenges, and cardiac surgeons’ and anesthetists’ priorities when developing new prediction models and decision support tools in cardiac surgery. METHODS In total, n=12 in-depth semi-structured interviews were conducted across 3 Scottish cardiac centers with cardiac surgeons and cardiac anesthetists. The interview transcripts were analyzed, following a thematic analysis framework and using three a priori themes: “challenges in cardiac surgery”, “current processes to avoid adverse outcomes in cardiac surgery”, and “clinicians’ priorities for new clinical risk prediction models”. RESULTS A thematic analysis identified challenges regarding adverse postoperative outcomes connected to the changing cardiac patient population and surgical procedures, challenges in communication between health professionals and patients, and data collection. It was found that preoperative assessment clinics play the most important role when reducing the risk of patients developing adverse postoperative outcomes. Risk prediction tools were largely not used to avoid adverse outcomes, but rather for auditing and documentation purposes. CONCLUSIONS The findings of this study suggest that there is a need to increase research efforts on more personalized risk prediction tools and expand the remit of predictions to postoperative complications rather than the more traditional focus on mortality. While there are numerous prediction models in cardiac surgery, the involvement of potential users of such models in the development process is rare. Hence, this study provides a contribution by presenting the cardiac surgeons’ and anesthetists’ priorities for a clinical prediction model.

show abstract

Definition and Classification of Postoperative Complications After Cardiac Surgery: Pilot Delphi Study

Cited by 2 publications

References 35 publications

Dynamic Prediction of Patient Outcomes in the Intensive Care Unit: A Scoping Review of the State-of-the-Art

Dynamic Prediction of Patient Outcomes in the Intensive Care Unit: A Scoping Review of the State-of-the-Art

Predictive Modelling and Decision Support in Cardiac Surgery: Requirements Analysis with Cardiac Surgeons and Anesthetists (Preprint)

Contact Info

Product

Resources

About