scholarly journals A Decision Support System is Needed for Rapid Triage of Chest Pain Patients Using High Sensitivity Troponin Testing-Based Algorithms

2019 ◽  
Vol 5 (1) ◽  
pp. e1-e2
Author(s):  
Chien-Chang Lee ◽  
◽  
Cheng-Heng Liu ◽  
Sih-Shiang Huang ◽  
Cho-Han Chiang ◽  
...  
Keyword(s):  
Decision Support ◽  
Chest Pain ◽  
Decision Support System ◽  
Support System ◽  
High Sensitivity ◽  
High Sensitivity Troponin ◽  
Pain Patients

Prediction of Postpartum Depression Using Multilayer Perceptrons and Pruning

2009 ◽  
Vol 48 (03) ◽  
pp. 291-298 ◽  
Author(s):  
J. M. García-Gómez ◽  
J. Vicente ◽  
J. Sanjuán ◽  
R. de Frutos ◽  
R. Martín-Santos ◽  
...  
Keyword(s):  
Decision Support ◽  
Postpartum Depression ◽  
Decision Support System ◽  
Sensitivity And Specificity ◽  
Support System ◽  
Geometric Mean ◽  
High Sensitivity ◽  
Classification Model ◽  
Multilayer Perceptrons ◽  
Future Work

Summary Objective: The main goal of this paper is to obtain a classification model based on feed-forward multilayer perceptrons in order to improve postpartum depression prediction during the 32 weeks after childbirth with a high sensitivity and specificity and to develop a tool to be integrated in a decision support system for clinicians. Materials and Methods: Multilayer perceptrons were trained on data from 1397 women who had just given birth, from seven Spanish general hospitals, including clinical, environmental and genetic variables. A prospective cohort study was made just after delivery, at 8 weeks and at 32 weeks after delivery. The models were evaluated with the geometric mean of accuracies using a hold-out strategy. Results: Multilayer perceptrons showed good performance (high sensitivity and specificity) as predictive models for postpartum depression. Conclusions: The use of these models in a decision support system can be clinically evaluated in future work. The analysis of the models by pruning leads to a qualitative interpretation of the influence of each variable in the interest of clinical protocols.

scholarly journals LO97: Validation of the HEART score in Canadian emergency department chest pain patients using a high-sensitivity troponin T assay

CJEM ◽  
2017 ◽  
Vol 19 (S1) ◽  
pp. S61-S62 ◽  
Author(s):  
J. Andruchow ◽  
A. McRae ◽  
T. Abedin ◽  
D. Wang ◽  
G. Innes ◽  
...  
Keyword(s):  
Emergency Department ◽  
Chest Pain ◽  
Troponin T ◽  
High Sensitivity ◽  
Low Risk ◽  
Moderate Risk ◽  
Heart Score ◽  
High Sensitivity Troponin ◽  
High Sensitivity Troponin T ◽  
Pain Patients

Introduction: The HEART score is a validated tool created to risk stratify emergency department (ED) chest pain patients using 5 simple criteria (History, ECG findings, Age, Risk factors, and Troponin). Several studies have demonstrated the superiority of HEART over other well known risk stratification tools in identifying low risk chest pain patients suitable for early discharge. All but one of these studies used conventional troponin assays, and most were conducted in European populations. This study aims to validate the HEART score using a high-sensitivity troponin T assay in a Canadian population. Methods: This prospective cohort study was conducted at a single urban tertiary centre and regional percutaneous coronary intervention site in Calgary, Alberta. Patients were eligible for enrolment if they presented to the ED with chest pain, were age 25-years or older and required biomarker testing to rule out AMI at the discretion of the attending emergency physician. Patients were excluded if they had clear acute ischemic ECG changes, new arrhythmia or renal failure requiring hemodialysis. Clinical data were recorded by the emergency physician at the time of enrolment and outcomes were obtained from administrative data. High-sensitivity troponin-T (Roche Elecsys hs-cTnT) results were obtained in all patients at presentation. The primary outcome was AMI within 30-days of ED visit, the secondary outcome was 30-day major adverse cardiac events (MACE). Results: A total of 984 ED patients with complete HEART scores were enrolled from August 2014 to September 2016. The 30-day incidence of AMI and MACE in the overall population was 3.3% and 20.6%, respectively. HEART scores were predictive of 30-day AMI incidence: low risk (0-3): 0.77% (95%CI 0.0-1.5%), moderate risk (4-6): 4.3% (95%CI 2.3-6.2%) and high risk (7-10): 12.2% (95%CI 5.5-19.0%). HEART scores also predicted 30-day MACE: low risk (0-3): 5.0% (95%CI 3.1-6.9%), moderate risk (4-6): 31.8% (95%CI 27.2-36.4%) and high-risk (7-10): 61.4% (95%CI 51.2-71.5%). More than half of patients, 522 (53.0%) could be identified as low risk based on the HEART score using a single troponin result. Conclusion: Using a single high-sensitivity troponin result collected at ED presentation, the HEART score can rapidly and effectively identify more than half of ED chest pain patients as low risk for 30-day AMI, but is less sensitive for 30-day MACE.

A belief rule-based decision support system for clinical risk assessment of cardiac chest pain

2012 ◽  
Vol 219 (3) ◽  
pp. 564-573 ◽  
Author(s):  
Guilan Kong ◽  
Dong-Ling Xu ◽  
Richard Body ◽  
Jian-Bo Yang ◽  
Kevin Mackway-Jones ◽  
...  
Keyword(s):  
Risk Assessment ◽  
Decision Support ◽  
Chest Pain ◽  
Decision Support System ◽  
Support System ◽  
Rule Based ◽  
Clinical Risk ◽  
Clinical Risk Assessment

LO57: Very low concentrations of high-sensitivity troponin T at presentation can rapidly exclude acute myocardial infarction in a significant proportion of ED chest pain patients

CJEM ◽  
2018 ◽  
Vol 20 (S1) ◽  
pp. S26-S27
Author(s):  
J. E. Andruchow ◽  
T. S. Boyne ◽  
S. Vatanpour ◽  
D. Wang ◽  
A. D. McRae
Keyword(s):  
Myocardial Infarction ◽  
Acute Myocardial Infarction ◽  
Chest Pain ◽  
Emergency Physician ◽  
Troponin T ◽  
High Sensitivity ◽  
High Sensitivity Troponin ◽  
Low Concentrations ◽  
High Sensitivity Troponin T ◽  
Pain Patients

Introduction: Chest pain is one of the most common presenting complaints to emergency departments (EDs) across the world, and the exclusion of acute myocardial infarction (AMI) using troponin testing is central to the care of many of these patients. While testing strategies using conventional troponin assays require repeat testing over many hours to avoid missed diagnoses, high-sensitivity troponin (hs-cTn) assays may be able to exclude AMI in a large proportion of patients with a single result at presentation. This objective of this study is to validate the ability of very low concentrations of hs-cTn at presentation to exclude AMI in ED chest pain patients. Methods: This prospective cohort study was conducted at a single urban tertiary center and regional percutaneous coronary intervention site in Calgary, Alberta. Patients were eligible for enrolment if they presented to the ED with chest pain, were 25-years or older and required biomarker testing to rule out AMI at the discretion of the attending emergency physician. Patients were excluded if they had clear acute ischemic ECG changes, new arrhythmia or renal failure requiring hemodialysis. A high-sensitivity troponin result (Roche Elecsys hs-cTnT) was obtained in all patients at presentation. The primary outcome was AMI on the index visit. Secondary outcomes included 30-day AMI and major adverse cardiac events (MACE - including AMI, revascularization or cardiac death). Electronic medical records were reviewed and telephone follow-up was obtained for all patients at 30-days to ensure relevant events were captured. Two physician adjudication (board-certified emergency physician and cardiologist) was obtained for all outcomes. This study was REB approved. Results: A total of 1,167 patients were enrolled from August 2014 September 2016, of which 191 (16.3%) patients had an initial troponin below the limit of blank (LoB, <3 ng/L) and 416 (32.8%) were below the limit of detection (LoD, <5 ng/L). The sensitivity of a single troponin below the LoB (<3 ng/L) for index AMI was 100% (95% CI 96.2%-100%) and for 30-day AMI was 100% (95% CI 96.4-100%). The sensitivity of a troponin below the LoD (<5 ng/L) for index AMI was 97.9% (95% CI 92.7%-99.8%) and for 30-day AMI was 98.0% (95% CI 93.0-99.8%). Sensitivity for 30-day MACE at both cutoffs was lower: 98.4% (95% CI 94.3-99.8%) for <3 ng/L, and 94.4% (95% CI 88.8-97.7%) for <5 ng/L, respectively; however, negative predictive values remained high at both cutoffs: <3 ng/L, 99.0% (95% CI 96.3-99.9%) and <5 ng/L, 98.3% (95% CI 96.6-99.3%). Conclusion: A high sensitivity troponin T result below the LoB (<3 ng/L) is highly sensitive for excluding AMI and identifies patients at low risk of 30-day MACE. A result below the LoB (<5 ng/L) will identify a larger population of patients as low risk but has a greater risk of missed AMI and MACE.

Sign in / Sign up

Export Citation Format

Share Document