|
 
 |
| EDITORIAL |
|
| Year : 2022 | Volume
: 11
| Issue : 1 | Page : 2-4 |
|
Glucometrics, hematometrics, and clinical metrics: Simple indices, scores, and models for risk stratification and prognostication in acute coronary syndromes
Satyanarayana Upadhyayula
Medanta - Mediclinic, New Delhi, India
| Date of Submission | 19-Jan-2022 |
| Date of Acceptance | 20-Jan-2022 |
| Date of Web Publication | 21-Apr-2022 |
Correspondence Address:
Dr. Satyanarayana Upadhyayula
MD, FEM, FIMSA, MIAE, Consultant Cardiology, Medanta - Mediclinic, Room No 5, E-18 Defence Colony, New Delhi - 110 024
India
 Source of Support: None, Conflict of Interest: None  | Check |
DOI: 10.4103/jcpc.jcpc_6_22
How to cite this article:
Upadhyayula S. Glucometrics, hematometrics, and clinical metrics: Simple indices, scores, and models for risk stratification and prognostication in acute coronary syndromes. J Clin Prev Cardiol 2022;11:2-4 |
How to cite this URL:
Upadhyayula S. Glucometrics, hematometrics, and clinical metrics: Simple indices, scores, and models for risk stratification and prognostication in acute coronary syndromes. J Clin Prev Cardiol [serial online] 2022 [cited 2023 Mar 29];11:2-4. Available from: https://www.jcpconline.org/text.asp?2022/11/1/2/343646 |
Despite numerous advances, cardiologists still face the challenge of controlling ischemia without increasing the risk of bleeding, a balancing act which forms the fulcrum of optimal acute coronary syndromes (ACS) management for improved patient outcomes.
Jadhav et al., in this issue of J Clin Prev Cardiol, have elegantly shown in a simple observational study (n = 400) how to risk stratify ST-segment elevation myocardial infarction patients. They have shown that the mean total leukocyte count, total neutrophil count, neutrophil–lymphocyte ratio, and plasma glucose levels were higher in patients with complications (13449.8/mm3, 10460.5/mm3, 5.20, and 180.8 mg%) than those without complications (11318.3/mm3, 8581.9/mm3, 4.15, and 151.1 mg%) (P < 0.05).
Over a period of time, numerous indices/scores/models have been developed for risk stratification/prognostication of ACS as shown in [Table 1]. Such indices/scores/models help to integrate thrombotic and bleeding risks in ACS. The outcomes will depend on how well we tailor antithrombotic therapy (precision medicine) according to risk in ACS patients.[1],[2] | Table 1: ACS - Risk stratification strategies - indices/scores/AI based models
Click here to view |
Some risk scores can help in secondary prevention. Thrombolysis in Myocardial Infarction Risk Score for Secondary Prevention (TRS2P), a risk score based on nine established clinical factors, was recently developed from the Thrombin Receptor Antagonist in Secondary Prevention of Atherothrombotic Ischemic Events trial (TRA2°P-TIMI50). The score is based on retrospective analysis of 13,593 patients who underwent coronary angiography (CAG) for the evaluation/or management of ACS. It helps in predicting long-term outcomes in real-world patients undergoing CAG in varying clinical settings.[3]
Fabrizio D'Ascenzo et al. used artificial intelligence (machine learning) techniques to develop the PRAISE model, a comprehensive and well-designed score based on 25 variables assessed at patient discharge, which elegantly shortlisted predictors of all-cause death (age, hemoglobin concentration, left ventricular ejection fraction [LVEF], and statin therapy) as well as predictors of both myocardial infarction recurrence and major bleeding (age, hemoglobin concentration, estimated glomerular filtration rate, and LVEF).[4]
As regards primary prevention, it is also essential not to waste valuable resources by subjecting low and intermediate pretest risk probability patients to hospitalization for ACS and extensive evaluation with noninvasive stress testing or an invasive CAG. Early recognition of patients at low risk for ACS can result in diminished patient burden, diagnostic testing, length of stay, frequency of hospitalization, and associated expense. Some risk scores have the ability to risk-stratify patients as low, intermediate, and high pretest risk probability for ACS.[5]
Several landmark trials have been conducted to compare the effectiveness of some of these risk scores. In a recent trial, “cost-effectiveness study of the history, electrocardiogram, age, risk factors, and initial troponin (HEART) score in the Management of Patients with Chest Pain Presenting in the Emergency Room (NCT01756846)” an attempt was made to quantify the impact of the use of the HEART risk score on outcomes and costs in patients presenting with chest pain. HEART score performance was compared with that of the thrombolysis in myocardial infarction (TIMI) and Global Registry of Acute Coronary Events (GRACE) scores. Head-to-head comparison of the GRACE, HEART, and TIMI score revealed that the HEART score performed best in discriminating between those with and without Major Adverse Cardiovascular Events (MACE). The HEART score identified the largest number of patients (40.5%) as low risk without compromising safety. The results justify the routine usage of HEART score in the risk stratification and prognostication of patients with low/intermediate-risk stable chest pain in the emergency department.[5]
What is intriguing is how, easy to use AI models like PRAISE and GESS are being developed. The general process flow chart for development of AI models like PRAISE and GESS for risk scoring and clinical decision making are shown in [Figure 1]. The types and components of AI are depicted schematically in [Figure 2]. How in future, AI positively impacts Cardiological Clinical decision-making depends on several laws (Moore's Law, Metcalfe's Law, Yule's Law, Hoff's Law, Evans's Law, and Digitiplication Law) as shown in [Table 2].[6],[7] | Table 2: Laws which positively influence the impact of AI on Cardiology Practice
Click here to view |
Finally, the proof of the pudding lies in the performance of the above mentioned indices/scores/models in improving patient outcomes in large high-quality prospective randomized controlled trials. Such a move would increase the generalizability of their utility in real-life populations, paving way to a personalized risk approach (precision medicine).
| References | |  |
| 1. | Ji Z, Liu G, Guo J, Zhang R, Su Y, Carvalho A, et al. The neutrophil-to-lymphocyte ratio is an important indicator predicting in-hospital death in ami patients. Front Cardiovasc Med 2021;8:706852.  |
| 2. | Bauer D, Toušek P. Risk stratification of patients with acute coronary syndrome. J Clin Med 2021;10:4574. |
| 3. | Zafrir B, Adawi S, Khalaily M, Jaffe R, Eitan A, Barnett-Griness O , et al. Long-Term risk stratification of patients undergoing coronary angiography according to the thrombolysis in myocardial infarction risk score for secondary prevention. J Am Heart Assoc 2019;8:e012433. |
| 4. | Templin C, Di Vece D. Risk scores in predicting adverse events following acute coronary syndrome. Lancet 2021;397:172-3. |
| 5. | Upadhyayula S, Kasliwal RR. The challenge of optimal evaluation of low and intermediate pre-test probability stable chest pain: Insights from recent randomized clinical trials. J Clin Prev Cardiol 2019;8:142-52. |
| 6. | Mittas N, Chatzopoulou F, Kyritsis KA, Papagiannopoulos CI, Theodoroula NF, Papazoglou AS, et al. A Risk-Stratification Machine Learning Framework for the Prediction of Coronary Artery Disease Severity: Insights from the GESS Trial. Front. Cardiovasc. Med., 2022;18:1-13. https://doi.org/10.3389/fcvm.2021.812182. |
| 7. | Dipti Itchhaporia. Artificial intelligence in cardiology. Trends in Cardiovascular Medicine 2022;32:34–1. |
[Figure 1], [Figure 2]
[Table 1], [Table 2]
|
Search Pubmed for