Background The focus on noncancer causes of death in patients with breast cancer (BC) remains superficial. The objective of the current study was to assess and quantify causes of death after BC diagnosis. Methods In total, 754,270 women with BC in the United States who were diagnosed during 2000 through 2015 and retrieved from the Surveillance, Epidemiology, and End Results (SEER) program were studied. Standardized mortality ratios (SMRs) for causes of death were calculated. Results Of the included patients, 183,002 (24.3%) died during the follow‐up period. The greatest proportion of deaths (46.2%) occurred within 1 to 5 years after diagnosis. Most deaths occurred from BC itself or from other cancers, and the number of BC deaths decreased as more years passed after diagnosis. The most common noncancer causes of death within <10 years after diagnosis were heart diseases followed by cerebrovascular diseases. However, >10 years after diagnosis, the most common noncancer causes of death were heart diseases followed by Alzheimer disease. Patients had a statistically significant higher risk of death from chronic liver diseases within 5 to 10 years after diagnosis compared with the general population (SMR, 1.23; 95% CI, 1.09‐1.38) and had statistically significant higher risks of death from Alzheimer disease (SMR, 1.21; 95% CI, 1.14‐1.29) and from diseases of the heart (SMR, 1.06; 95% CI, 1.02‐1.09) >10 years after diagnosis. Conclusions Although BC remains the most common cause of death after BC diagnosis, other non‐BC causes of death (mainly heart and cerebrovascular diseases) represent a significant number of deaths among patients with BC. These findings provide important insight into how BC survivors should be counselled regarding future health risks.

No abstract

No abstract

Background Artificial Intelligence (AI) may reduce miss rate of colorectal neoplasia at colonoscopy by improving lesion recognition (CADe), and cost of pathology by improving optical diagnosis (CADx). Methods To train a combined CADe and CADx (CAD-EYE,Fujifilm,Japan) based on deep learning, a multicenter library of >200,000 images from 1,572 polyps was used, while testing was performed on two independent image sets (CADe: 446 with polyps and 234 without; CADx: 267) from 234 polyps that was also evaluated by 6 endoscopists (3 experts, 3 non-experts). Results CADe showed a sensitivity, specificity and accuracy of 92.9%, 90.6% and 91.7%, respectively. Experts showed slightly higher accuracy and specificity and a similar sensitivity, while non-experts+CADe showed comparable sensitivity, but lower specificity and accuracy. CADx system showed a sensitivity, specificity and accuracy of 85%, 79.4% and 83.6% for polyp characterization, respectively. Experts comparable performances, while non-experts using CADx showed comparable accuracy, but lower specificity. Conclusions The high accuracy shown by CADe and CADx systems is similar to expert endoscopists, prompting its implementation in clinical practice. When using CAD, non-expert endoscopists achieve similar performances to those of expert endoscopists, with suboptimal specificity.

IMPORTANCE Owing to improved survival among US patients with prostate cancer (PC), patients tend to live long enough after a PC diagnosis for non-cancer-related comorbidities to be associated with their overall survival. Although studies have investigated causes of death among patients with localized PC, data are lacking regarding causes of death among patients with metastatic PC.