Recently, considerable progress has been made in interpreting perceptual information through artificial intelligence, allowing better interpretation of highly complex data by machines. Furthermore, the applications of artificial intelligence, represented by deep learning technology, to the fields of medical and biomedical research are increasing exponentially. In this article, we will explain the stages of deep learning algorithm development in the field of medical imaging, namely topic selection, data collection, data exploration and refinement, algorithm development, algorithm evaluation, and clinical application; we will also discuss the latest trends for each stage.

Background The benefit of statin use after acute ST-segment elevation myocardial infarction (STEMI) has been well established, however, the influence of the timing of statin administration has not been elucidated. The objective of this study focused on early clinical outcomes after percutaneous coronary intervention (PCI). Methods This analysis of the Korea Working Group on Myocardial Infarction registry (KorMI) study included 3,584 STEMI patients (mean age, 63 ±13 years;male, 2,684, 74.9%) undergoing PCI from January 2008 to June 2009. Rates of major adverse cardiac events (MACE:all-cause death, recurrent MI, and target lesion revascularization) were compared among patients grouped according to statin therapy timing:I, both during and after hospitalization (n=2,653, 74%);II, only during hospita-lization (n=309, 8.6%);III, only after discharge (n=157, 4.4%);and IV, no statin therapy (n=465, 13%). Mean follow-up duration was 234 ± 113 days. Results Multivariate factors of statin use during hospitalization included prior statin use, multiple diseased vessels, final thrombolysis in myocardial infarction flow grade III, and low-density lipoprotein cholesterol level. At 6-month follow-up, groups III and IV had the highest MACE rates (2.3%, 3.9%, 5.1%, and 4.9%for groups I-IV, respectively, P=0.004). After adjusting for confounders, groups II-IV had a higher MACE risk than group I [hazard ratio (HR):3.20, 95%confidence interval (95%CI):1.31-7.86, P=0.011;HR:3.84, 95%CI:1.47-10.02, P=0.006;and HR:3.17, 95%CI:1.59-6.40, P=0.001;respectively]. Conclusions This study, based on the national registry database, shows early and continuous statin therapy improvs early outcomes of STEMI patients after PCI in real-world clinical prac-tice.

BACKGROUND AND OBJECTIVES: No-reflow is an important phenomenon for limiting the prognosis of patients following primary percutaneous coronary intervention (PCI) for acute myocardial infarction (AMI). Coronary stenting is the current standard procedure for primary PCI in AMI. However, stenting is suspected to cause more microembolization, and no-reflow phenomenon. This study was performed to elucidate the risk factors for the no-reflow phenomenon following primary PCI with stenting, in patients with AMI. SUBJCETS AND METHODS: The clinical, angiographic and procedure related parameters were reviewed in patients with AMI that had undergone primary PCI, with stent implantation, within 12 h of the onset of chest pain, at Seoul National University Hospital, Yonsei University Hospital Cardiovascular Center and Chungbuk National University Hospital (n=183). RESULTS: 29 patients (16%) showed no-reflow phenomenon (final TIMI flow grade less than 3). Conventional risk factors for coronary artery disease were not significant risk factors for the no-reflow phenomenon. In a univariate analysis, a high initial CK-MB level (>50 IU) (8.45% vs. 21.9%, p=0.04), low left ventricular ejection fraction (LV EF) (<50%) (19% vs. 5%, p=0.03) and long pre-dilatation balloon inflation time (>30 sec) (31% vs. 15%, p=0.04) were significant risk factors of the no-reflow phenomenon. A low LV EF and long pre-dilatation balloon inflation time were significant risk factors in a multivariate analysis. CONCLUSION: LV dysfunction at presentation and a long pre-dilatation balloon inflation time were independent risk factors for the no-reflow phenomenon following primary PCI with stenting for AMI. Preventive measures against the no-reflow phenomenon should be considered in patients with these risk factors.
Chest Pain ; Chungcheongbuk-do ; Coronary Artery Disease ; Humans ; Inflation, Economic ; Multivariate Analysis ; Myocardial Infarction ; No-Reflow Phenomenon* ; Percutaneous Coronary Intervention* ; Prognosis ; Risk Factors* ; Seoul ; Stents* ; Stroke Volume

BACKGROUND AND OBJECTIVES: No-reflow is an important phenomenon for limiting the prognosis of patients following primary percutaneous coronary intervention (PCI) for acute myocardial infarction (AMI). Coronary stenting is the current standard procedure for primary PCI in AMI. However, stenting is suspected to cause more microembolization, and no-reflow phenomenon. This study was performed to elucidate the risk factors for the no-reflow phenomenon following primary PCI with stenting, in patients with AMI. SUBJCETS AND METHODS: The clinical, angiographic and procedure related parameters were reviewed in patients with AMI that had undergone primary PCI, with stent implantation, within 12 h of the onset of chest pain, at Seoul National University Hospital, Yonsei University Hospital Cardiovascular Center and Chungbuk National University Hospital (n=183). RESULTS: 29 patients (16%) showed no-reflow phenomenon (final TIMI flow grade less than 3). Conventional risk factors for coronary artery disease were not significant risk factors for the no-reflow phenomenon. In a univariate analysis, a high initial CK-MB level (>50 IU) (8.45% vs. 21.9%, p=0.04), low left ventricular ejection fraction (LV EF) (<50%) (19% vs. 5%, p=0.03) and long pre-dilatation balloon inflation time (>30 sec) (31% vs. 15%, p=0.04) were significant risk factors of the no-reflow phenomenon. A low LV EF and long pre-dilatation balloon inflation time were significant risk factors in a multivariate analysis. CONCLUSION: LV dysfunction at presentation and a long pre-dilatation balloon inflation time were independent risk factors for the no-reflow phenomenon following primary PCI with stenting for AMI. Preventive measures against the no-reflow phenomenon should be considered in patients with these risk factors.
Chest Pain ; Chungcheongbuk-do ; Coronary Artery Disease ; Humans ; Inflation, Economic ; Multivariate Analysis ; Myocardial Infarction ; No-Reflow Phenomenon* ; Percutaneous Coronary Intervention* ; Prognosis ; Risk Factors* ; Seoul ; Stents* ; Stroke Volume