Age shock index, shock index, and modified shock index for predicting postintubation hypotension in the emergency department

Lee, Kyoung-Mi; Jang, Jun Sung; Kim, Jihye; Suh, Young Ju

doi:10.1016/j.ajem.2019.07.011

Cited by 14 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our previous work adopted vital records and delayed the prediction time at intubation, to use vital records as long as possible. This achieved 80% accuracy, which improved the work of Lin et al [ 13 ]. Here, the accuracy refers to the ratio of data that is properly classified among all data, and AUC (area under the curve) refers to the area under the roc curve drawn with recall (sensitivity) and 1-specificity.…”

Section: Introductionsupporting

confidence: 71%

“…Ko et al [ 12 ] revealed that lactate levels, blood in the nasogastric tube, and systolic blood pressure values are risk factors for the occurrence of hypotension in patients with non-arrhythmic upper gastrointestinal bleeding. Lee et al [ 13 ] evaluated shock index (SI), modified shock index (MSI), and age shock index (SI) as predictors of hypotension after tracheal intubation, using a machine learning technique and logistic regression. Reich et al [ 14 ] tested the association of hypotension, gender, age, and height for 10 min after anesthesia induction, preoperative drug therapy, and anesthesia induction, using a Fisher’s exact test.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparative Analysis on Machine Learning and Deep Learning to Predict Post-Induction Hypotension

Lee

Woo

Kang

et al. 2020

Sensors

View full text Add to dashboard Cite

Hypotensive events in the initial stage of anesthesia can cause serious complications in the patients after surgery, which could be fatal. In this study, we intended to predict hypotension after tracheal intubation using machine learning and deep learning techniques after intubation one minute in advance. Meta learning models, such as random forest, extreme gradient boosting (Xgboost), and deep learning models, especially the convolutional neural network (CNN) model and the deep neural network (DNN), were trained to predict hypotension occurring between tracheal intubation and incision, using data from four minutes to one minute before tracheal intubation. Vital records and electronic health records (EHR) for 282 of 319 patients who underwent laparoscopic cholecystectomy from October 2018 to July 2019 were collected. Among the 282 patients, 151 developed post-induction hypotension. Our experiments had two scenarios: using raw vital records and feature engineering on vital records. The experiments on raw data showed that CNN had the best accuracy of 72.63%, followed by random forest (70.32%) and Xgboost (64.6%). The experiments on feature engineering showed that random forest combined with feature selection had the best accuracy of 74.89%, while CNN had a lower accuracy of 68.95% than that of the experiment on raw data. Our study is an extension of previous studies to detect hypotension before intubation with a one-minute advance. To improve accuracy, we built a model using state-of-art algorithms. We found that CNN had a good performance, but that random forest had a better performance when combined with feature selection. In addition, we found that the examination period (data period) is also important.

show abstract

Section: Introductionsupporting

confidence: 71%

Section: Introductionmentioning

confidence: 99%

Comparative Analysis on Machine Learning and Deep Learning to Predict Post-Induction Hypotension

Lee

Woo

Kang

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Endotracheal intubation is one of the most crucial tasks in an acutely unstable patient. Pre-intubation hemodynamics are one of the predictive factors for hypotension after intubation [ 18 ]. Post-intubation hypotension is associated with increased in-hospital mortality and length of stay [ 19 ].…”

Section: Discussionmentioning

confidence: 99%

Quality Evaluation of a Checklist for Intubation Preparation in Graduate Medical Education

Pazderka¹,

Mastenbrook²,

Billian³

et al. 2022

Cureus

View full text Add to dashboard Cite

Background Rapid sequence intubation (RSI) is a multistep process that emergency physicians commonly perform. Unfortunately, there is little published in the graduate medical education literature regarding the use of checklists for RSI education. Methods We developed a pre-intubation checklist for RSI preparation and evaluated emergency medicine residents’ use of it. We developed the checklist using a three-round modified Delphi process among a group of emergency medicine faculty physicians within our institution. Over a three-year period, residents were randomized into two groups: a “checklist group” and a “without-checklist group.” Residents were then evaluated for RSI critical step completion in a simulated critically ill patient by two independent study investigators. Inter-rater reliability kappa scores were calculated. Following completion of the scenario, residents in both groups were asked to complete an anonymous survey. Both groups had access to the checklist at the time of the survey. The survey was used to determine if they found the checklist helpful. Odds ratios with p-values, at an alpha of 0.05 for significance, were computed for checklist items comparing the checklist and without-checklist groups. Data analysis was performed using SAS software (SAS, Cary, NC v 9.4). This study was approved by the authors’ Institutional Review Board. Results Each assessment was completed by two investigators. Inter-rater reliability was substantial (κ=0.79). Residents having access to the checklist were more likely to verbalize a critical step with a p-value of < 0.0001 and an odds ratio of 2.17 (95% CI: 1.48, 3.19). The checklist group normalized vital signs prior to intubation in 25/28 (89%, 95% CI: 72.81, 96.29) versus only 6/29 (21%, 95% CI: 9.85, 38.39) with a p-value of <0.0001 in the without-checklist group. The checklist group evaluated for difficult laryngoscopy 26/28 (93%, 95% CI: 77.36, 98.02) versus only 21/29 (72%, CI 95% 54.28, 85.30) with p=0.0223 in the without-checklist group. All of the surveyed residents indicated that the checklist would be helpful for future use in the ED. Conclusion This RSI checklist improved adherence to preparatory steps of RSI. Utilizing a checklist increased evaluation for a difficult airway and normalizing vital signs. Residents found the checklist helpful for ED use.

show abstract

“…Measurement of vital signs by calculating the Shock Index (SI) before intubation is a simple bedside and effective tool for predicting early shock than using a single parameter. SI can be defined as the ratio of Heart Rate (HR) to Systolic Blood Pressure (SBP), with a normal range of 0.5-0.7 (7)(8)(9). The prevalence of PIH in the SI of <0.7 group (23%) was lower than those in the SI of ≥0.7 (37.5%) group of patients who underwent intubation in the emergency department (8).…”

Section: Introductionmentioning

confidence: 99%

Association Between Shock Index and Post-Emergency Intubation Hypotension in Patients Who Called the Rapid Response Team at Dr. Cipto Mangunkusumo Hospital

Rahmah

Adisasmita²,

Manggala³

et al. 2023

IJAR

View full text Add to dashboard Cite

Introduction: Hypotension is an acute complication following Emergency Endotracheal Intubation (ETI) in populations who called the Rapid Response Team (RRT). Thus, a fast and simple tool is needed to identify the risk of Post-emergency Intubation Hypotension (PIH). Shock Index (SI) pre-intubation is one of the potential factors to predict PIH. Objective: To measure the association between shock index with post-emergency intubation hypotension after calling for the RRT. Materials and Methods: This research is a cohort retrospective study that analyzed 171 patients aged ≥18 years who have called RRT and underwent an emergency ETI. The cut-off point for SI was determined using the ROC curve to predict PIH. The modification effect was evaluated using stratification analysis. Data were analyzed using cox regression to determine the likelihood of SI in the cause of hypotension. Result: A total of 92 patients (53.8%) underwent post-emergency intubation hypotension. The SI cut-off point of 0.9 had a sensitivity of 82.6% and a specificity of 67.1% for predicting PIH (Area Under Curve (AUC) 0.81; 95% CI 0.754–0.882, p <0.05). The increased risk of PIH associated with high SI score was an aRR of 1.9; 95% CI 1.03–3.57, a p-value of 0.040 among those with sepsis, and an aRR of 7.9, 95% CI 2.36–26.38, a p-value of 0.001 among those without sepsis. Conclusion: This study showed that a high SI score was associated with PIH after being controlled with other PIH risk variables. The risk of PIH associated with SI score modestly increased (2-fold increase) in those with sepsis and significantly increased (8-fold increase) in those without sepsis.

show abstract

Age shock index, shock index, and modified shock index for predicting postintubation hypotension in the emergency department

Cited by 14 publications

References 25 publications

Comparative Analysis on Machine Learning and Deep Learning to Predict Post-Induction Hypotension

Comparative Analysis on Machine Learning and Deep Learning to Predict Post-Induction Hypotension

Quality Evaluation of a Checklist for Intubation Preparation in Graduate Medical Education

Association Between Shock Index and Post-Emergency Intubation Hypotension in Patients Who Called the Rapid Response Team at Dr. Cipto Mangunkusumo Hospital

Contact Info

Product

Resources

About