When (not) to apply clinical risk prediction models to improve patient care

Lee, Anna; Moonesinghe, Ramani

doi:10.1111/anae.15990

Cited by 2 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Identifying high‐risk surgical patients may enable early detection and treatment of severe postoperative complications, which may in turn improve outcomes 2 . Risk prediction models for perioperative triage have been suggested to help physicians decide on the appropriate level of postoperative care and observation 3–5 . However, many risk prediction models were not designed for clinical decision‐making 6 …”

Section: Introductionmentioning

confidence: 99%

Risk prediction models in emergency surgery: Protocol for a scoping review

Hansted,

Møller,

Møller

et al. 2024

Acta Anaesthesiol Scand

View full text Add to dashboard Cite

BackgroundRisk prediction models are used for many purposes in emergency surgery, including critical care triage and benchmarking. Several risk prediction models have been developed, and some are used for purposes other than those for which they were developed. We aim to provide an overview of the existing literature on risk prediction models used in emergency surgery and highlight knowledge gaps.MethodsWe will conduct a scoping review on risk prediction models used for patients undergoing emergency surgery in accordance with the Preferred Reporting Items for Systematic Reviews and Meta‐Analyses extension for Scoping Reviews (PRISMA‐ScR). We will search Medline, EMBASE, and the Cochrane Library and include all study designs. We aim to answer the following questions: (1) What risk prediction models are used in emergency surgery? (2) Which variables are used in these models? (3) Which surgical specialties are the models used for? (4) Have the models been externally validated? (5) Where have the models been externally validated? (6) What purposes were the models developed for? (7) What are the strengths and limitations of the included models? We will summarize the results descriptively. The certainty of evidence will be evaluated using a modified Grading of Recommendations Assessment, Development and Evaluation (GRADE) approach.ConclusionThe outlined scoping review will summarize the existing literature on risk prediction models used in emergency surgery and highlight knowledge gaps.

show abstract

Section: Introductionmentioning

confidence: 99%

Risk prediction models in emergency surgery: Protocol for a scoping review

Hansted,

Møller,

Møller

et al. 2024

Acta Anaesthesiol Scand

View full text Add to dashboard Cite

show abstract

Development and prospective validation of postoperative pain prediction from preoperative EHR data using attention-based set embeddings

Liu,

Gutiérrez,

Mather

et al. 2023

npj Digit. Med.

View full text Add to dashboard Cite

Preoperative knowledge of expected postoperative pain can help guide perioperative pain management and focus interventions on patients with the greatest risk of acute pain. However, current methods for predicting postoperative pain require patient and clinician input or laborious manual chart review and often do not achieve sufficient performance. We use routinely collected electronic health record data from a multicenter dataset of 234,274 adult non-cardiac surgical patients to develop a machine learning method which predicts maximum pain scores on the day of surgery and four subsequent days and validate this method in a prospective cohort. Our method, POPS, is fully automated and relies only on data available prior to surgery, allowing application in all patients scheduled for or considering surgery. Here we report that POPS achieves state-of-the-art performance and outperforms clinician predictions on all postoperative days when predicting maximum pain on the 0–10 NRS in prospective validation, though with degraded calibration. POPS is interpretable, identifying comorbidities that significantly contribute to postoperative pain based on patient-specific context, which can assist clinicians in mitigating cases of acute pain.

show abstract

When (not) to apply clinical risk prediction models to improve patient care

Cited by 2 publications

References 19 publications

Risk prediction models in emergency surgery: Protocol for a scoping review

Risk prediction models in emergency surgery: Protocol for a scoping review

Development and prospective validation of postoperative pain prediction from preoperative EHR data using attention-based set embeddings

Contact Info

Product

Resources

About