Simulation in Neurocritical Care: Past, Present, and Future

Morris, Nicholas; Czeisler, Barry; Sarwal, Aarti

doi:10.1007/s12028-018-0629-2

Cited by 15 publications

(17 citation statements)

References 112 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, neurosurgical insults could affect hypothalamic-pituitary-adrenal axis and hormonal generation, resulting in intractable immunosuppression ( 38 ). Therefore, well-performed neurocritical care is warranted for neurosurgical patients, especially for those with postoperative sepsis ( 39 ).…”

Section: Discussionmentioning

confidence: 99%

A Machine Learning-Based Prediction of Hospital Mortality in Patients With Postoperative Sepsis

et al. 2020

View full text Add to dashboard Cite

Introduction: The incidence of postoperative sepsis is continually increased, while few studies have specifically focused on the risk factors and clinical outcomes associated with the development of sepsis after surgical procedures. The present study aimed to develop a mathematical model for predicting the in-hospital mortality among patients with postoperative sepsis. Materials and Methods: Surgical patients in Medical Information Mart for Intensive Care (MIMIC-III) database who simultaneously fulfilled Sepsis 3.0 and Agency for Healthcare Research and Quality (AHRQ) criteria at ICU admission were incorporated. We employed both extreme gradient boosting (XGBoost) and stepwise logistic regression model to predict the in-hospital mortality among patients with postoperative sepsis. Consequently, the model performance was assessed from the angles of discrimination and calibration. Results: We included 3,713 patients who fulfilled our inclusion criteria, in which 397 (10.7%) patients died during hospitalization, and 3,316 (89.3%) patients survived through discharge. Fluid-electrolyte disturbance, coagulopathy, renal replacement therapy (RRT), urine output, and cardiovascular surgery were important features related to the in-hospital mortality. The XGBoost model had a better performance in both discriminatory ability (c-statistics, 0.835 vs. 0.737 and 0.621, respectively; AUPRC, 0.418 vs. 0.280 and 0.237, respectively) and goodness of fit (visualized by calibration curve) compared to the stepwise logistic regression model and baseline model. Conclusion: XGBoost model has a better performance in predicting hospital mortality among patients with postoperative sepsis in comparison to the stepwise logistic regression model. Machine learning-based algorithm might have significant application in the development of early warning system for septic patients following major operations.

show abstract

Section: Discussionmentioning

confidence: 99%

A Machine Learning-Based Prediction of Hospital Mortality in Patients With Postoperative Sepsis

et al. 2020

View full text Add to dashboard Cite

show abstract

“…2 The authors modified a cognitive aid that was developed previously for patient assessment of clinician communications to use as an assessment rubric for the VOP. 16 Ten skills considered important to ICDs were assessed on a 5-point global rating scoring system Objectives Develop a curriculum and assessment program with the intent to standardize the training process for informed consent discussions.…”

Section: Discussionmentioning

confidence: 99%

“…(Poor, Fair, Good, Very Good, Excellent), with a maximum potential sum score of 50 points (provided as online supplementary data). 2,10,16,17 Through faculty consensus, a cut score of 31 was chosen as a ''pass'' score.…”

Section: Bottom Linementioning

confidence: 99%

A Novel Blended Curriculum for Communication of Informed Consent With Surgical Interns

Anderson

Kaba

Gros

et al. 2021

Journal of Graduate Medical Education

View full text Add to dashboard Cite

Background Interns often conduct procedural informed consent discussions (ICDs), identified as a core entrustable professional activity. Deficiencies in the training process for ICDs span across specialties. Objective We provide evidence for a curriculum and assessment designed to standardize the training process and ensure ICD competency in surgical interns. Methods In March 2019, PowerPoint educational materials were emailed to one academic institution's new surgical interns, who in June participated in an onsite 1-hour role-play “hot seat” group activity (GA) with an untrained simulated patient, and in October completed a single trained simulated patient (real-time raters) verification of proficiency (VOP) assessment. Curriculum evaluation was measured through intern pre-/post-confidence (5-point scale), and the VOP's Cronbach's alpha and test-retest were examined. Data were analyzed with descriptive statistics, paired t tests, and 2-way random effects models. Results Of 44 new interns, 40 (91%) participated in the remote teaching and live GA and were assessed by the VOP. Pre-/post-GA confidence increased a mean difference of 1.3 (SD = 0.63, P < .001). The VOP's Cronbach's alpha was 0.88 and test-retest was 0.84 (95% CI 0.67–0.93, P < .001), with a 95% pass rate. The 2 first-time fail students required remediation. Time commitment included 1 hour maximum for individual training and implementation and 30 minutes for assessment. The use of volunteers and donated space mitigated additional costs. Conclusions Remote asynchronous and group skills teaching for new general surgical interns improved their confidence in conducting procedural ICDs. A patient-simulation verification process appeared feasible with preliminary evidence of retest and internal consistency.

show abstract

“…Furthermore, neurosurgical insults could affect hypothalamic-pituitary-adrenal axis and consequent hormonal generation, contributing to the development of postoperative immunosuppression (37). Therefore, well-performed neurocritical care is warranted for neurosurgical patients complicated with postoperative sepsis (38).…”

Section: Discussionmentioning

confidence: 99%

A machine learning-based prediction of hospital mortality in patients with postoperative sepsis

Yao

Jin²,

Wang

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: The incidence of postoperative sepsis is continually increased, while few studies have specifically focused on the risk factors and clinical outcomes associated with the development of sepsis after surgical procedures. The present study aimed to develop a mathematical model for predicting the in-hospital mortality among patients with postoperative sepsis.Methods: Surgical patients in Medical Information Mart for Intensive Care (MIMIC-III) database who simultaneously fulfilled Sepsis 3.0 as well as Agency for Healthcare Research and Quality (AHRQ) criteria during ICU admission were incorporated. We employed both extreme gradient boosting (XGBoost) and stepwise logistic regression model to predict in-hospital mortality among included patients with postoperative sepsis. Consequently, model performance was assessed from the angles of discrimination and calibration.Results: We included 3713 patients who fulfilled our inclusion criteria, in which 397 (10.7%) patients died during hospitalization, while 3316 (89.3%) of them survived through discharge. Fluid-electrolyte disturbance, coagulopathy, renal replacement therapy (RRT), urine output, and cardiovascular surgery were important features related to the in-hospital mortality. The XGBoost model had a better performance in both discriminatory ability (c-statistics, 0.835 [95% CI, 0.786 to 0.877] vs. c-statistics, 0.737 [95% CI, 0.688 to 0.786]) and goodness of fit (visualized by calibration curve) compared to the stepwise logistic regression model. Conclusion: XGBoost model appears to be a better performance in predicting hospital mortality among postoperative septic patients compared to the conventional stepwise logistic regression model. Machine learning-based algorithm might have significant application in the development of early warning system for septic patients following major operations.

show abstract

Simulation in Neurocritical Care: Past, Present, and Future

Cited by 15 publications

References 112 publications

A Machine Learning-Based Prediction of Hospital Mortality in Patients With Postoperative Sepsis

A Machine Learning-Based Prediction of Hospital Mortality in Patients With Postoperative Sepsis

A Novel Blended Curriculum for Communication of Informed Consent With Surgical Interns

A machine learning-based prediction of hospital mortality in patients with postoperative sepsis

Contact Info

Product

Resources

About