Prospective validation of artificial neural network trained to identify acute myocardial infarction

Baxt, William G.; Skóra, Jan

doi:10.1016/s0140-6736(96)91555-x

Cited by 195 publications

(93 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…been applied to different aspects of automated interpretation of ECGs, for example, in the diagnosis of myocardial infarction. [6][7][8] These studies have demonstrated a significantly improved performance over both conventional ECG criteria and experienced ECG readers. Neural networks have also been used for ACS prediction in patients with acute chest pain [9][10][11] and have been compared to standard statistical methods such as multiple logistic regression.…”

Section: Introductionmentioning

confidence: 99%

Best leads in the standard electrocardiogram for the emergency detection of acute coronary syndrome

Green

Ohlsson

Forberg

et al. 2007

Journal of Electrocardiology

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Best leads in the standard electrocardiogram for the emergency detection of acute coronary syndrome

Green

Ohlsson

Forberg

et al. 2007

Journal of Electrocardiology

View full text Add to dashboard Cite

“…There have been a large number of reports on the use of ANN for clinical diagnosis (18), staging and prognosis (19), and management of cancers (20). In a previous study, an ANN-based composite diagnostic index derived using a panel of four serum markers, CA 125II, CA 72-4, CA 15-3, and lipid-associated sialic acid (LASA), was evaluated for it ability to discriminate malignant from benign pelvic masses (21).…”

Section: Introductionmentioning

confidence: 99%

Combining multiple serum tumor markers improves detection of stage I epithelial ovarian cancer

Zhang¹,

Yu²,

Xu³

et al. 2007

Gynecologic Oncology

View full text Add to dashboard Cite

Objective-Currently available tumor markers for ovarian cancer are still inadequate in both sensitivity and specificity to be used for population-based screening. Artificial neural network (ANN) as a modeling tool has demonstrated its ability to assimilate information from multiple sources and to detect subtle and complex patterns. In this paper, an ANN model was evaluated for its performance in detecting early stage epithelial ovarian cancer using multiple serum markers.Methods-Serum specimens collected at four institutions in the US, the Netherlands, and the United Kingdom were analyzed for CA125II, CA72-4, CA15-3, and macrophage colony stimulating factor (M-CSF). The four tumor marker values were then used as inputs to an ANN derived using a training set from 100 apparently healthy women, 45 women with benign conditions arising from the ovary, and 55 invasive epithelial ovarian cancer patients (including 27 stage I/II cases). A separate validation set from 27 apparently healthy women, 56 women with benign conditions, and 35 women with various types of malignant pelvic masses was used to monitor the ANN's performance during training. An independent test dataset from 98 apparently healthy women and 52 early stage epithelial ovarian cancer patients (38 stage I and 4 stage II invasive cases and 10 stage I borderline ovarian tumor cases) was used to evaluate the ANN.Results-ROC analysis confirmed the overall superiority of the ANN-derived composite index over CA125II alone (p=0.0333). At a fixed specificity of 98%, the sensitivities for ANN and CA125II alone were 71% (37/52) and 46% (24/52) (p=0.047), respectively, for detecting early stage epithelial ovarian cancer, and 71% (30/42) and 43% (18/42) (p=0.040), respectively, for detecting invasive early stage epithelial ovarian cancer.Conclusions-The combined use of multiple tumor markers through an ANN improves the overall accuracy to discern healthy women from patients with early stage ovarian cancer. Analysis of multiple markers with an ANN may be a better choice than the use of CA125II alone in a two-step

show abstract

“…In spite of previous studies 1, [8][9][10][11][12][13][14] that proposed computer protocols for emergency department physicians to diagnose patients with chest pain, this study is the first study proposing a computer protocol for diagnosing patients with chest pain at home. Because of the high incidence today of coronary cardiac disease, there is an increase in the number of people who visit an emergency department with complaints of noncardiac chest pain.…”

Section: Discussionmentioning

confidence: 83%

“…[5][6][7] Some algorithms and computer programs have been developed to make the diagnosis of patients with chest pain easier. 1,[8][9][10][11][12][13][14] All of the protocols have been developed to guide the physician in the emergency department. In all of these studies, there is no protocol that has been prepared that takes into account patients with chest pain at home.…”

mentioning

confidence: 99%

A Computer Based Telemedicine Protocol to Predict Acute Coronary Syndrome in Patients With Chest Pain at Home

Coşkun

Eren

2006

Int. Heart J.

View full text Add to dashboard Cite

SUMMARYThe decision to admit a patient to a coronary care unit for acute coronary syndrome (ACS) has serious medical and financial consequences. In this study, we aimed to develop a computer program to predict the existence of ACS in patients with chest pain at home; it is intended that patients will be able to access the program via the website to test its validity.This study proceeded in two phases. In the first phase, a computer-based decision protocol was developed using recursive-partitioning analysis to predict ACS in 250 patients with chest pain on the basis of their historical data. In the second phase, this protocol was tested in 115 patients for diagnosis of ACS prospectively. Thirty-two of the patients answered the algorithm questions on the website. All of the patients who visited the website of this study were advised to go to the emergency department.Although the algorithm showed the presence of ACS in 82 of 115 patients, 60 of 115 patients were diagnosed as having ACS in the emergency department (n = 55) or at follow-up. The agreement between the diagnosis of the algorithm and the true diagnosis was moderate and statistically significant (Kappa coefficient 0.61, P < 0.001). The sensitivity of the algorithm was 100%, although its specificity was 60%. The accuracy of the algorithm in diagnosing ACS was 81%.The algorithm diagnoses patients with ACS at a high ratio and decreases the number of patients being unnecessarily admitted to the emergency with non-ACS. (Int Heart J 2006; 47: 491-500)

show abstract

Prospective validation of artificial neural network trained to identify acute myocardial infarction

Cited by 195 publications

References 20 publications

Best leads in the standard electrocardiogram for the emergency detection of acute coronary syndrome

Best leads in the standard electrocardiogram for the emergency detection of acute coronary syndrome

Combining multiple serum tumor markers improves detection of stage I epithelial ovarian cancer

A Computer Based Telemedicine Protocol to Predict Acute Coronary Syndrome in Patients With Chest Pain at Home

Contact Info

Product

Resources

About