Chest X-ray (CXR) is one of the most commonly performed medical imaging tests. Although aging, sex and disease status have been known to cause changes in CXR findings, the extent of these effects has not been fully characterized. Here, we present a deep neural network (DNN) model trained using more than 100,000 CXRs to estimate the patient's age and sex solely from CXRs. Our DNN exhibited high performance in terms of estimating age and sex, with Pearson's correlation coefficient between the actual and estimated age of above 0.9 and an area under the ROC curve of 0.98 for sex estimation. The difference between the actual and estimated age is large in CXRs with abnormal findings, suggesting that the estimated age ("CXR age") can be a biomarker for disease status. Furthermore, by applying our DNN to CXRs of consecutive 1,562 hospitalized heart failure patients, we demonstrated that an elevated CXR age is not only associated with aging-related diseases, such as hypertension and atrial fibrillation, but also a worse outcome of heart failure. Given these results, our new concept "CXR age" serves as a novel biomarker for cardiovascular aging and can help clinicians to predict, prevent, and manage cardiovascular diseases.

No abstract

Aims The long‐term outcome in patients with heart failure (HF) after hospitalization may vary substantially depending on their age and left ventricular ejection fraction (LVEF). We aimed to assess the relative rates of cardiovascular death (CVD) and non‐CVD based on the age and how the rates differ under the updated LVEF classification system. Methods and results Consecutively registered hospitalized patients with HF ( N = 3558; 39.7% women with a mean age of 73.9 ± 13.3 years) were followed for a median of 2 (interquartile range, 0.8–3.1) years. The CVDs and non‐CVDs were evaluated based on age [young (<65 years), older (65–84 years), and very old (≥85 years)] and LVEF classification [HF with preserved EF (HFpEF; LVEF ≥50%) and non‐HFpEF (LVEF <50%)]. The adverse clinical events were adjudicated independently by a central committee. Overall, 1505 (42.3%) had HFpEF [young: n = 182 (12.1%), older: n = 894 (59.4%), very old: n = 429 (28.5%)], and 2053 (57.7%) had non‐HFpEF [young: n = 575 (28.0%), older: n = 1159 (56.5%), very old: n = 319 (15.5%)]. During the follow‐up, the crude incidence of all‐cause death was higher in non‐HFpEF than in HFpEF across all age groups (non‐HFpEF vs. HFpEF, young: 10.4% vs. 5.5%, log‐rank P = 0.10; older: 26.6% vs. 20.9%, log‐rank P = 0.002; very old: 36.7% vs. 31.7%, log‐rank P = 0.043). CVDs accounted for more than half of all deaths in non‐HFpEF (young 65.0%, older 64.2%, and very old 55.6%), whereas the proportion of CVDs remained less than half in HFpEF (young 50.0%, older 41.2%, very old 38.2%). HF readmission was associated with subsequent all‐cause death in non‐HFpEF [hazard ratio (HR): 1.72, 95% confidence interval (CI): 1.41–2.09, P < 0.001], but not in HFpEF (HR: 1.12, 95% CI: 0.87–1.43, P = 0.39). Conclusions The probability of a non‐CVD increases in both LVEF categories with advancing age, but that it is greater in the HFpEF category. The findings indicate that mitigating CV‐related outcomes alone may be insufficient for treating HF in older population, particularly in the HFpEF category.

Background: The concept of Clinical Scenario (CS) classification has been widely utilized to aid in choosing appropriate management strategies for acute decompensated heart failure (ADHF). Methods and Results: The West Tokyo-Heart Failure (WET-HF) Registry is a multicenter, prospective cohort registry enrolling consecutive hospitalized ADHF patients. Based on systolic blood pressure (SBP) at admission, 4,000 patients enrolled between 2006 and 2017 were classified into 3 groups: CS1, SBP ≥140 mmHg; CS2, 100≤SBP<140 mmHg; and CS3, SBP <100 mmHg. The CS1 group had a high rate of fluid retention such as leg edema, and the largest reduction in body weight at discharge. In-hospital diuretics use was the most frequent in CS1. Although the primary endpoint of long-term all-cause death and/or ADHF re-hospitalization was more common in more advanced CS, there was no significant difference between the 3 CS groups in patients with HF with preserved ejection fraction (HFpEF; P=0.10). Although more advanced CS was associated with larger left ventricular (LV) chamber size in HF with reduced EF (HFrEF), it was associated with smaller LV size in HFpEF. Conclusions: The long-term prognostic value of CS classification was limited in HFpEF. Whereas CS was closely associated with degree of LV remodeling in HFrEF, a smaller LV chamber might be associated with a lower cardiovascular functional reserve in HFpEF.