Predicting in-hospital mortality after an in-hospital cardiac arrest: A multivariate analysis

Alnabelsi, Talal; Annabathula, Rahul; Shelton, Julie; Paranzino, Marc; Faulkner, S; Cook, Matthew D.; Dugan, Adam J.; Nerusu, Sethabhisha; Smyth, Susan S.; Gupta, Vedant

doi:10.1016/j.resplu.2020.100039

Cited by 5 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The risk factors were identi ed by order of importance. Surprisingly, the comorbidity of hypertension was found to have a protective effect on survival, which was reported by a recent study (Alnabelsi T. et. al.…”

mentioning

confidence: 66%

“…Patient characteristics were compared by mortality outcome. The statistical methods used in this work were the same as in (31). The analyses were done in R programming languages, version 3.6.1.…”

Section: Discussionmentioning

confidence: 99%

“…Recently, machine learning has emerged as an effective approach to integrate multiple quantitative variables to improve accuracy of incidence predictions in medicine, with the potential to dramatically improve health care delivery (22)(23)(24)(25)(26). Speci cally, in the research of anesthesiology and cardiac arrest, it has shown in very recent years ML is a promising method for a more comprehensive understanding of the risk factors and a supporting tool for care improvement (27)(28)(29)(30)(31).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Retrospective Study of Mortality for Perioperative Cardiac Arrests Towards Personalized Treatment

Shang

Chu

Zheng

et al. 2022

Preprint

View full text Add to dashboard Cite

Background Perioperative cardiac arrest (POCA) is associated with a high mortality rate. This work aims to study its prognostic factors for risk mitigation by means of care management and planning. Methods A database of 380,919 surgeries was reviewed and 150 POCAs were curated. The main outcome is the mortality prior to hospital discharge. Patient demographics, medical history, and clinical characteristics (anesthesia and surgery) were main features. Six ML algorithms were explored: LR, SVC, RF, GBM, AdaBoost, and VotingClassifier. The last one is an ensemble of the beginning five ones. k-fold cross-validation and bootstrapping minimized the prediction bias and variance, respectively. Explainers (SHAP and LIME) were used to interpret the predictions. Results The ensemble provided the most accurate and robust predictions (AUC=0.90 [95% CI, 0.78-0.98]) across various age groups. The risk factors were identified by order of importance. Surprisingly, the comorbidity of hypertension was found to have a protective effect on survival, which was reported by a recent study (Alnabelsi T. et. al. 2020) for the first time to our knowledge. Conclusions The validated ensemble classifier in aid of the explainers improved the predictive differentiation, deepening our understanding of POCA prognostication. It offers a holistic model-based approach for personalized anesthesia and surgical treatment.

show abstract

mentioning

confidence: 66%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Retrospective Study of Mortality for Perioperative Cardiac Arrests Towards Personalized Treatment

Shang

Chu

Zheng

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…17 In a recent singlecenter study of adult patients experiencing IHCA, lactic acidosis and RA were shown to be associated with increased mortality. 18 Severe acidosis and MODS in the peri-arrest period may reflect an acute state of inadequate oxygen delivery which is potentially reversible in which case, early initiation of ECLS may help to prevent early RA. Alternatively, acidosis and MODS may reflect the progression of an underlying disease process which is irreversible and, therefore, the use of ECLS would not be appropriate.…”

Section: Discussionmentioning

confidence: 99%

Factors Associated with Pediatric In-Hospital Recurrent Cardiac Arrest

Brown

Roberts

Killien

et al. 2022

J Pediatr Intensive Care

View full text Add to dashboard Cite

The objective of this article was to identify demographic and clinical factors associated with early recurrent arrest (RA) (<48 hours) and late RA (≥48 hours) among pediatric inpatients following an initial in-hospital cardiac arrest. A retrospective cohort study of inpatients was performed in a free-standing academic quaternary care children's hospital. All inpatients were <18 years old with a cardiac arrest event requiring ≥1 minute of cardiopulmonary resuscitation with the return of spontaneous circulation sustained for ≥20 minutes at Seattle Children's Hospital from February 1, 2012 to September 18, 2019. Of the 237 included patients, 20 (8%) patients had an early RA and 30 (13%) had a late RA. Older age and severe pre-arrest acidosis were associated with a higher risk of early RA, odds ratios (OR) 1.2 (95% confidence interval [CI] 1.1–1.3) per additional year and 4.6 (95% CI 1.2–18.1), respectively. Pre-arrest organ dysfunction was also associated with a higher risk of early RA with an OR of 3.3 (95% CI 1.1–9.4) for respiratory dysfunction, OR 1.4 (95% CI 1.1–1.9) for each additional dysfunctional organ system, and OR 1.1 (95% CI 1–1.2) for every one-point increase in PELOD2 score. The neonatal illness category was associated with a lower risk of late RA, OR 0.3 (95% CI 0.1–0.97), and severe post-arrest acidosis was associated with a higher risk of late RA, OR 4.2 (95% CI 1.1–15). Several demographic and clinical factors offer some ability to identify children who sustain a recurrent cardiac arrest, offering a potential opportunity for intervention to prevent early recurrent arrest.

show abstract

“…Recently, machine learning has emerged as an effective approach to integrate multiple quantitative variables to improve accuracy of incidence predictions in medicine, with the potential to dramatically improve healthcare delivery 22 – 26 . Specifically, in the fields of anesthesiology and cardiac arrest research, it has recently been shown that ML is a promising method for a more comprehensive understanding of the risk factors and a supporting tool for healthcare improvement 27 – 31 .…”

Section: Introductionmentioning

confidence: 99%

A retrospective study of mortality for perioperative cardiac arrests toward a personalized treatment

Shang

Chu

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Perioperative cardiac arrest (POCA) is associated with a high mortality rate. This work aimed to study its prognostic factors for risk mitigation by means of care management and planning. A database of 380,919 surgeries was reviewed, and 150 POCAs were curated. The main outcome was mortality prior to hospital discharge. Patient demographic, medical history, and clinical characteristics (anesthesia and surgery) were the main features. Six machine learning (ML) algorithms, including LR, SVC, RF, GBM, AdaBoost, and VotingClassifier, were explored. The last algorithm was an ensemble of the first five algorithms. k-fold cross-validation and bootstrapping minimized the prediction bias and variance, respectively. Explainers (SHAP and LIME) were used to interpret the predictions. The ensemble provided the most accurate and robust predictions (AUC = 0.90 [95% CI, 0.78–0.98]) across various age groups. The risk factors were identified by order of importance. Surprisingly, the comorbidity of hypertension was found to have a protective effect on survival, which was reported by a recent study for the first time to our knowledge. The validated ensemble classifier in aid of the explainers improved the predictive differentiation, thereby deepening our understanding of POCA prognostication. It offers a holistic model-based approach for personalized anesthesia and surgical treatment.

show abstract

Predicting in-hospital mortality after an in-hospital cardiac arrest: A multivariate analysis

Cited by 5 publications

References 29 publications

A Retrospective Study of Mortality for Perioperative Cardiac Arrests Towards Personalized Treatment

A Retrospective Study of Mortality for Perioperative Cardiac Arrests Towards Personalized Treatment

Factors Associated with Pediatric In-Hospital Recurrent Cardiac Arrest

A retrospective study of mortality for perioperative cardiac arrests toward a personalized treatment

Contact Info

Product

Resources

About