Using Machine Learning for Early Prediction of Cardiogenic Shock in Patients With Acute Heart Failure

Rahman, Faisal; Finkelstein, Noam; Alyakin, Anton; Gilotra, Nisha A.; Trost, Jeff; Schulman, Steven P.; Saria, Suchi

doi:10.1016/j.jscai.2022.100308

Cited by 7 publications

(14 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been other recent efforts to predict cardiogenic shock with machine learning [18,19]. However, they only considered patients who required inotropes/mechanical circulatory support as developing cardiogenic shock and used the time to initiate supportive measures as shock onset, which are not in alignment with the clinical criteria used in previous landmark trials [9,37]; the early presentation of cardiogenic shock with low blood pressure and end-organ hypoperfusion would be missed by their algorithms.…”

Section: Discussionmentioning

confidence: 99%

“…In addition, both studies lacked external validation to demonstrate generalizability in other populations. 1% of the study cohort developed cardiogenic shock in the study by Rahman et al [19], which resulted in the best positive predictive value being only 11% (with recall/sensitivity 27%) and would lead to the algorithm sounding many false alarms secondary to extreme class imbalance [38] and missing the majority of cardiogenic shock patients. The study by Chang et al [18] relied on icd codes to determine outcomes, which would be inaccurate as discussed above; they excluded mixed cardiogenic/noncardiogenic shock patients from the study cohort, which could limit the algorithm's applicability.…”

Section: Discussionmentioning

confidence: 99%

“…Well-established scores such as CardShock [15], IABP-shock II [16] and Acute Physiology and Chronic Health Evaluation (apache) II [17] were developed to predict outcomes such as in-hospital or 30-day mortality rather than the development of cardiogenic shock. Recent machine learning algorithms only classified patients who were initiated on inotropes and/or mechanical circulatory support as developing cardiogenic shock, but omitted those with low blood pressure and end-organ hypoperfusion [18,19]. The best positive predictive value was 11% (with recall/sensitivity 27%) due to the low prevalence (1%) of cardiogenic shock patients in the study cohort [19], which would result in the algorithm having a high rate of false alarms, while also missing the majority of cardiogenic shock patients.…”

Section: Introductionmentioning

confidence: 99%

“…Recent machine learning algorithms only classified patients who were initiated on inotropes and/or mechanical circulatory support as developing cardiogenic shock, but omitted those with low blood pressure and end-organ hypoperfusion [18,19]. The best positive predictive value was 11% (with recall/sensitivity 27%) due to the low prevalence (1%) of cardiogenic shock patients in the study cohort [19], which would result in the algorithm having a high rate of false alarms, while also missing the majority of cardiogenic shock patients.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A dynamic risk score for early prediction of cardiogenic shock using machine learning

Hu¹,

Lui²,

Goldstein³

et al. 2023

Preprint

View full text Add to dashboard Cite

Myocardial infarction and heart failure are major cardiovascular diseases that affect millions of people in the US. The morbidity and mortality are highest among patients who develop cardiogenic shock. Early recognition of cardiogenic shock is critical. Prompt implementation of treatment measures can prevent the deleterious spiral of ischemia, low blood pressure, and reduced cardiac output due to cardiogenic shock. However, early identification of cardiogenic shock has been challenging due to human providers' inability to process the enormous amount of data in the cardiac intensive care unit (icu) and lack of an effective risk stratification tool. We developed a deep learning-based risk stratification tool, called CShock, for patients admitted into the cardiac icu with acute decompensated heart failure and/or myocardial infarction to predict onset of cardiogenic shock. To develop and validate CShock, we annotated cardiac icu datasets with physician adjudicated outcomes. CShock achieved an area under the receiver operator characteristic curve (auroc) of 0.820, which substantially outperformed CardShock (auroc 0.519), a well-established risk score for cardiogenic shock prognosis. CShock was externally validated in an independent patient cohort and achieved an auroc of 0.800, demonstrating its generalizability in other cardiac icus.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A dynamic risk score for early prediction of cardiogenic shock using machine learning

Hu¹,

Lui²,

Goldstein³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The specific timing of CS development was not evaluated. Rahman et al ( 32 ) utilized machine learning methods in an attempt to identify a cohort of patients at higher risk of developing CS from a population of patients admitted to three hospitals with acute decompensated heart failure. A novel feature of this study is continuous monitoring of EHR data.…”

Section: Discussionmentioning

confidence: 99%

Early Prediction of Cardiogenic Shock Using Machine Learning

Chang

Antonescu

Ravindranath

et al. 2022

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

Cardiogenic shock (CS) is a severe condition with in-hospital mortality of up to 50%. Patients who develop CS may have previous cardiac history, but that may not always be the case, adding to the challenges in optimally identifying and managing these patients. Patients may present to a medical facility with CS or develop CS while in the emergency department (ED), in a general inpatient ward (WARD) or in the critical care unit (CC). While different clinical pathways for management exist once CS is recognized, there are challenges in identifying the patients in a timely manner, in all settings, in a timeframe that will allow proper management. We therefore developed and evaluated retrospectively a machine learning model based on the XGBoost (XGB) algorithm which runs automatically on patient data from the electronic health record (EHR). The algorithm was trained on 8 years of de-identified data (from 2010 to 2017) collected from a large regional healthcare system. The input variables include demographics, vital signs, laboratory values, some orders, and specific pre-existing diagnoses. The model was designed to make predictions 2 h prior to the need of first CS intervention (inotrope, vasopressor, or mechanical circulatory support). The algorithm achieves an overall area under curve (AUC) of 0.87 (0.81 in CC, 0.84 in ED, 0.97 in WARD), which is considered useful for clinical use. The algorithm can be refined based on specific elements defining patient subpopulations, for example presence of acute myocardial infarction (AMI) or congestive heart failure (CHF), further increasing its precision when a patient has these conditions. The top-contributing risk factors learned by the model are consistent with existing clinical findings. Our conclusion is that a useful machine learning model can be used to predict the development of CS. This manuscript describes the main steps of the development process and our results.

show abstract

Heart failure disease prediction and stratification with temporal electronic health records data using patient representation

Liang

Guo

2023

Biocybernetics and Biomedical Engineering

View full text Add to dashboard Cite

Using Machine Learning for Early Prediction of Cardiogenic Shock in Patients With Acute Heart Failure

Cited by 7 publications

References 35 publications

A dynamic risk score for early prediction of cardiogenic shock using machine learning

A dynamic risk score for early prediction of cardiogenic shock using machine learning

Early Prediction of Cardiogenic Shock Using Machine Learning

Heart failure disease prediction and stratification with temporal electronic health records data using patient representation

Contact Info

Product

Resources

About