Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Cardiogenic shock (CS) is a severe complication of acute coronary syndrome (ACS) with mortality approaching 50% despite the use of percutaneous mechanical circulatory support devices (pMCS). Identifying high-risk patients prior to the development of CS could allow pre-emptive use of pMCS possibly preventing CS. For this purpose, we derived and externally validated a machine learning score to predict in-hospital CS in patients with ACS with c-statistics: 0.844 (95% confidence interval, 0.841-0.847). STOPSCHOCK score is available as a web or smartphone application.
The aim of this study is to prospectively validate the STOPSHOCK score on a large cohort of ACS patients in a real- world clinical environment.
Cardiogenic shock is a serious life-threatening condition affecting almost 10% of patients suffering from acute coronary syndrome (ACS). When untreated, it can rapidly progress to collapse of circulation and sudden death. Despite recent improvements in diagnostic and treatment options, mortality remains incredibly high, reaching nearly 50%. Currently available mechanical circulatory support devices can replace the function of the heart and/or lungs, thereby essentially eliminating the primary cause. However, cardiogenic shock is not only an isolated decrease in cardiac function but a rapidly progressing multiorgan dysfunction accompanied by severe cellular and metabolic abnormalities. The window for successful treatment is relatively narrow, and when missed, even the elimination of the underlying primary cause is not enough to reverse this vicious circle. The ability to identify high-risk patients prior to the development of shock would allow to take pre-emptive measures, such as the implantation of mechanical circulatory support, and thus prevent the development of shock leading to improved survival. For this purpose, Premedix Academy has developed and validated a predictive scoring system STOP SHOCK (Score TO Predict SHOCK). This scoring system showed better prediction compared to standard models and was accepted to the Late- Breaking Science section at the European Society of Cardiology (ESC) Congress 2024. STOP SHOCK was validated on an external cohort of 5123 ACS patients with area under the receiver operating characteristic curve (ROC AUC) of 0.844 (95% confidence interval: 0.841-0.8470) surpassing other externally validated cardiogenic shock (CS) models (e.g. ORBI score). Furthermore, our model is based on variables that are readily available at the first contact with patients and thus STOPSHOCK can be utilized in emergency room (ER) or ambulance even before catheterization. Novelty of our project is also in the concept of continuous training, improvement, and validation to ensure validity and clinical applicability in the future as well. Current medical models are developed, verified, and published. Once the model enters medical practice, research teams will either validate it or replace it with their own model based on a new cohort of patients. However, experience from other fields shows that as soon as machine learning models are deployed, their performance degrades. In order to preserve and even further improve the model, continuous performance monitoring and training/retraining are vital. A small prospective validation study on a cohort of 103 consecutive higher-risk ACS patients, enrolled in intensive cardiac care units in 8 centers from USA, Europe, and Asia demonstrated very good performance with ROC AUC of 0.97 and was presented at the 2023 American Heart Association Annual Meeting. The STOPSHOCK score is currently available as a smartphone application and as an online calculator: https://stopshock.org.
The primary objective of this study is to prospectively validate the STOPSHOCK score on a large cohort of ACS patients. The methods and results of this project follow the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement.
Not provided
Not provided
Not provided
Not provided
Not provided
| Label | Type | Description | Intervention Names |
|---|---|---|---|
| ACS Patients Admitted to CCU | This cohort includes adult patients (age >18 years) admitted to the coronary care unit (CCU) or intensive care unit (ICU) with a diagnosis of acute coronary syndrome (ACS), including STEMI, NSTEMI, and unstable angina. Patients are enrolled at the time of admission before the development of cardiogenic shock. The STOPSHOCK score is calculated using clinical variables available at first contact. Patients are followed during hospitalization to determine whether cardiogenic shock develops. No intervention is applied. |
Not provided
| Measure | Description | Time Frame |
|---|---|---|
| Discriminatory Power of the STOPSHOCK Score for Predicting Cardiogenic Shock | The primary outcome is the ability of the STOPSHOCK score to predict the development of cardiogenic shock in patients admitted with acute coronary syndrome. This will be assessed using the area under the receiver operating characteristic curve (ROC AUC), comparing the predicted risk score to the actual occurrence of cardiogenic shock during hospitalization. STOPSHOCK Score (0-100%): This score estimates the risk of developing cardiogenic shock during hospitalization. The higher the percentage, the higher the predicted risk. Higher scores indicate a worse outcome. | Up to hospital discharge (average of 14 days) |
| Measure | Description | Time Frame |
|---|---|---|
| Sensitivity (Recall) of the STOPSHOCK Score | The proportion of patients who develop cardiogenic shock during hospitalization and were correctly identified as high-risk by the STOPSHOCK score at admission. STOPSHOCK Score (0-100%): This score estimates the risk of developing cardiogenic shock during hospitalization. The higher the percentage, the higher the predicted risk. Higher scores indicate a worse outcome. |
Not provided
Inclusion Criteria:
Exclusion Criteria:
Not provided
Not provided
Not provided
Patients aged > 18 years, admitted for ACS.
Not provided
| Name | Affiliation | Role |
|---|---|---|
| Allan Böhm, MD, PhD, MSc, MBA, FESC, FJCS | Premedix Academy | Principal Investigator |
| Branislav Bezák, MD, PhD | Premedix Academy | Study Director |
| Facility | Status | City | State | ZIP | Country | Contacts |
|---|---|---|---|---|---|---|
| Premedix Academy | Bratislava | 81102 | Slovakia |
| PubMed Identifier | Type | Citation | Retractions |
|---|---|---|---|
| 25560730 | Background | Moons KG, Altman DG, Reitsma JB, Ioannidis JP, Macaskill P, Steyerberg EW, Vickers AJ, Ransohoff DF, Collins GS. Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): explanation and elaboration. Ann Intern Med. 2015 Jan 6;162(1):W1-73. doi: 10.7326/M14-0698. | |
| Background | Böhm A, Jajcay N, Spartalis M, et al. Abstract 14290: Prospective Clinical Validation of the STOPSHOCK Smartphone Application - Artificial Intelligence Model for Prediction of Cardiogenic Shock in Patients With Acute Coronary Syndrome. Circulation 2023; 148. | ||
| Background | Tran V, Pham H, Yang B-S, Nguyen T. Machine performance degradation assessment and remaining useful life prediction using proportional hazard model and support vector machine. Mechanical Systems and Signal Processing 2012; 32: 320-30. | ||
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| Up to hospital discharge (average of 14 days) |
| Specificity of the STOPSHOCK Score | The proportion of patients who do not develop cardiogenic shock and were correctly identified as low-risk by the STOPSHOCK score. STOPSHOCK Score (0-100%): This score estimates the risk of developing cardiogenic shock during hospitalization. The higher the percentage, the higher the predicted risk. Higher scores indicate a worse outcome. | Up to hospital discharge (average of 14 days) |
| Positive Predictive Value (Precision) | he proportion of patients identified as high-risk by the STOPSHOCK score who actually develop cardiogenic shock during hospitalization. STOPSHOCK Score (0-100%): This score estimates the risk of developing cardiogenic shock during hospitalization. The higher the percentage, the higher the predicted risk. Higher scores indicate a worse outcome. | Up to hospital discharge (average of 14 days) |
| Negative Predictive Value | The proportion of patients identified as low-risk by the STOPSHOCK score who do not develop cardiogenic shock. STOPSHOCK Score (0-100%): This score estimates the risk of developing cardiogenic shock during hospitalization. The higher the percentage, the higher the predicted risk. Higher scores indicate a worse outcome. | Up to hospital discharge (average of 14 days) |
| F1 Score of the STOPSHOCK Score | The harmonic mean of precision and sensitivity, providing a balanced metric that accounts for both false positives and false negatives. STOPSHOCK Score (0-100%): This score estimates the risk of developing cardiogenic shock during hospitalization. The higher the percentage, the higher the predicted risk. Higher scores indicate a worse outcome. | Up to hospital discharge (average of 14 days) |
| Accuracy of the STOPSHOCK Score | Proportion of all predictions (true positives and true negatives) that are correctly classified by the STOPSHOCK score. STOPSHOCK Score (0-100%): This score estimates the risk of developing cardiogenic shock during hospitalization. The higher the percentage, the higher the predicted risk. Higher scores indicate a worse outcome. | Up to hospital discharge (average of 14 days) |
| Area Under the Precision-Recall Curve (PR AUC) | Metric summarizing the trade-off between precision and recall for the STOPSHOCK score, especially relevant given the low incidence of cardiogenic shock. STOPSHOCK Score (0-100%): This score estimates the risk of developing cardiogenic shock during hospitalization. The higher the percentage, the higher the predicted risk. Higher scores indicate a worse outcome. | Up to hospital discharge (average of 14 days) |
| Matthews Correlation Coefficient | Balanced performance metric accounting for true and false positives and negatives, especially useful in imbalanced datasets such as cardiogenic shock prediction. STOPSHOCK Score (0-100%): This score estimates the risk of developing cardiogenic shock during hospitalization. The higher the percentage, the higher the predicted risk. Higher scores indicate a worse outcome. | Up to hospital discharge (average of 14 days) |
| Youden's J Statistic | Metric calculated as Sensitivity + Specificity - 1, representing the optimal threshold for distinguishing between high- and low-risk patients. STOPSHOCK Score (0-100%): This score estimates the risk of developing cardiogenic shock during hospitalization. The higher the percentage, the higher the predicted risk. Higher scores indicate a worse outcome. | Up to hospital discharge (average of 14 days) |
| Brier Score | Mean squared difference between predicted probabilities and actual outcomes of cardiogenic shock, assessing the calibration and accuracy of the STOPSHOCK score. STOPSHOCK Score (0-100%): This score estimates the risk of developing cardiogenic shock during hospitalization. The higher the percentage, the higher the predicted risk. Higher scores indicate a worse outcome. | Up to hospital discharge (average of 14 days) |
| Calibration Slope and Intercept | Metrics used to assess how well the STOPSHOCK score's predicted probabilities align with observed cardiogenic shock outcomes; slope = 1 and intercept = 0 indicate perfect calibration. STOPSHOCK Score (0-100%): This score estimates the risk of developing cardiogenic shock during hospitalization. The higher the percentage, the higher the predicted risk. Higher scores indicate a worse outcome. | Up to hospital discharge (average of 14 days) |
| Grohmann J, Nicholson P, Iglesias J, Kounev S, Lugones D. Monitorless: Predicting Performance Degradation in Cloud Applications with Machine Learning; 2019. |
| 40110217 | Background | Bohm A, Segev A, Jajcay N, Krychtiuk KA, Tavazzi G, Spartalis M, Kollarova M, Berta I, Jankova J, Guerra F, Pogran E, Remak A, Jarakovic M, Sebenova Jerigova V, Petrikova K, Matetzky S, Skurk C, Huber K, Bezak B. Machine learning-based scoring system to predict cardiogenic shock in acute coronary syndrome. Eur Heart J Digit Health. 2025 Jan 6;6(2):240-251. doi: 10.1093/ehjdh/ztaf002. eCollection 2025 Mar. |
| 30828750 | Background | Bagai J, Brilakis ES. Update in the Management of Acute Coronary Syndrome Patients with Cardiogenic Shock. Curr Cardiol Rep. 2019 Mar 4;21(4):17. doi: 10.1007/s11886-019-1102-3. |
| 26339723 | Background | De Luca L, Olivari Z, Farina A, Gonzini L, Lucci D, Di Chiara A, Casella G, Chiarella F, Boccanelli A, Di Pasquale G, De Servi S, Bovenzi FM, Gulizia MM, Savonitto S. Temporal trends in the epidemiology, management, and outcome of patients with cardiogenic shock complicating acute coronary syndromes. Eur J Heart Fail. 2015 Nov;17(11):1124-32. doi: 10.1002/ejhf.339. Epub 2015 Sep 4. |
| Background | Thiele H, Zeymer U. Cardiogenic shock in patients with acute coronary syndromes. In: Tubaro M, Vranckx P, Price S, Vrints C, eds. The ESC Textbook of Intensive and Acute Cardiovascular Care: Oxford University Press; 2015: 0. |
| ID | Term |
|---|---|
| D012770 | Shock, Cardiogenic |
| D054058 | Acute Coronary Syndrome |
| D002318 | Cardiovascular Diseases |
| ID | Term |
|---|---|
| D009203 | Myocardial Infarction |
| D017202 | Myocardial Ischemia |
| D006331 | Heart Diseases |
| D014652 | Vascular Diseases |
| D007238 | Infarction |
| D007511 | Ischemia |
| D010335 | Pathologic Processes |
| D013568 | Pathological Conditions, Signs and Symptoms |
| D009336 | Necrosis |
| D012769 | Shock |
Not provided
Not provided