Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Study flowchart.

KorAHF denotes Korean Acute Heart Failure registry.

More »

Fig 1 Expand

Fig 2.

Train and validation of deep-learning prediction model.

DAHF denotes deep-learning-based artificial intelligence algorithm for predicting mortality of patients with acute heart failure. Abbreviations: DBP, diastolic blood pressure; DNN, deep neural network; ECHO, echocardiography; ECG, electrocardiography; Hb, hemoglobin; LAD, left atrium dimension; LVDd, left ventricle end-diastolic dimension; QRS, QRS duration; QTc, corrected QT duration.

More »

Fig 2 Expand

Table 1.

Baseline characteristics.

More »

Table 1 Expand

Fig 3.

Receiver operating characteristic curve for predicting in-hospital mortality.

AUC, area under the receiver operating characteristic curve; CI, confidence interval; GWTG-HF, Get with the Guideline–Heart Failure.

More »

Fig 3 Expand

Fig 4.

Receiver operating characteristic curves for predicting long-term mortalities.

AUC, area under the receiver operating characteristic curve; CI, confidence interval; MAGGIC, Meta-Analysis Global Group in Chronic Heart Failure.

More »

Fig 4 Expand

Fig 5.

Cumulative hazard of 36-month mortality by deep-learning-based algorithm risk group.

More »

Fig 5 Expand