Trends in Incidence and Case Fatality Rates of Heart Disease and Its Subtypes in Korea, 2006-2015

Mammography-based deep learning model for coronary artery calcification

AIMS

Mammography, commonly used for breast cancer screening in women, can also predict cardiovascular disease. We developed mammography-based deep learning models for predicting coronary artery calcium (CAC) scores, an established predictor of coronary events.

METHODS AND RESULTS

We evaluated a subset of Korean adults who underwent image mammography and CAC computed tomography and randomly selected approximately 80% of the participants as the training dataset, used to develop a convolutional neural network (CNN) to predict detectable CAC. The sensitivity, specificity, area under the receiver operating characteristic curve (AUROC), and overall accuracy of the model's performance were evaluated. The training and validation datasets included 5235 and 1208 women, respectively [mean age, 52.6 (±10.2) years], including non-zero cases (46.8%). The CNN-based deep learning prediction model based on the Resnet18 model showed the best performance. The model was further improved using contrastive learning strategies based on positive and negative samples: sensitivity, 0.764 (95% CI, 0.667-0.830); specificity, 0.652 (95% CI, 0.614-0.710); AUROC, 0.761 (95% CI, 0.742-0.780); and accuracy, 70.8% (95% CI, 68.8-72.4). Moreover, including age and menopausal status in the model further improved its performance (AUROC, 0.776; 95% CI, 0.762-0.790). The Framingham risk score yielded an AUROC of 0.736 (95% CI, 0.712-0.761).

CONCLUSION

Mammography-based deep learning models showed promising results for predicting CAC, performing comparably to conventional risk models. This indicates mammography's potential for dual-risk assessment in breast cancer and cardiovascular disease. Further research is necessary to validate these findings in diverse populations, with a particular focus on representation from national breast screening programmes.

Risk factors profile of young and older patients with myocardial infarction

Myocardial infarction (MI) among young adults (<45 years) represents a considerable proportion of the total heart attack incidents. The underlying pathophysiologic characteristics, atherosclerotic plaque features, and risk factors profile differ between young and older patients with MI. This review article discusses the main differences between the younger and elderly MI patients as well as the different pathogenic mechanisms underlying the development of MI in the younger. Young patients with MI often have eccentric atherosclerotic plaques with inflammatory features but fewer lesions, and are more likely to be smokers, obese, and have poor lifestyle, such as inactivity and alcohol intake. Compared to older MI patients, younger are more likely to be men, have familial-combined hyperlipidaemia and increased levels of lipoprotein-a. In addition, MI in younger patients may be related to use of cannabis, cocaine use, and androgenic anabolic steroids. Genomic differences especially in the pathways of coagulation and lipid metabolism have also been identified between young and older patients with MI. Better understanding of the risk factors and the anatomic and pathophysiologic processes in young adults can improve MI prevention and treatment strategies in this patient group. Awareness could help identify young subjects at increased risk and guide primary prevention strategies. Additional studies focusing on gene pathways related to lipid metabolism, inflammation, and coagulation are needed.

Non-Alcoholic Fatty Liver Disease Defined by Fatty Liver Index and Incidence of Heart Failure in the Korean Population: A Nationwide Cohort Study

Fatty liver index (FLI) is a simple and useful index that evaluates non-alcoholic fatty liver disease (NAFLD), particularly in large epidemiologic studies. Heart failure (HF) is becoming a burden to public health as the global trend toward an aging society continues. Thus, we investigated the effect of FLI on the incidence of HF using large cohort data from the Korean National Health Insurance health database. Methods and Results: A total of 7,958,538 subjects aged over 19 years without baseline HF (men = 4,142,264 and women = 3,816,274) were included. Anthropometric and biochemical measurements were evaluated. FLI scores were calculated and FLI ≥ 60 was considered as having NAFLD. Hazard ratios (HRs) and 95% confidence intervals (CIs) for HF incidence were analysed using multivariable time-dependent Cox proportional hazard models. During a mean follow up of 8.26 years, 17,104 participants developed HF. The FLI components associated with the incidence of HF and FLI showed a causal relationship with HF; the FLI ≥ 60 group had a higher HR for HF (HR 1.493; 95% CIs 1.41−1.581) than the FLI < 30 group. Subgroup analysis showed that fatty liver (FLI ≥ 60) with age ≥ 65 years or women displayed higher HR for HF than fatty liver with age < 65 or men, respectively. An increase in FLI score significantly increased the HR for HF except for those with a FLI score change from <30 to 30−60. Conclusion: NAFLD defined by FLI and increase in FLI score were associated with the incidence of HF. Further detailed prospective studies are needed.