Researchers Develop Web-Based Calculator to Predict Health Risks for Postmenopausal Women

Researchers developed a web-based calculator that assists postmenopausal women in determining risk toward conditions like heart attack, stroke, and various cancers, according to a September study published in the journal Menopause.

Lead study author John Robbins, MD, physician at UC Davis Health, described how often some conditions are focused on more than others, but this health-risk prediction tool has the potential to give women and their physicians a sense of what conditions shoudl receive their attention. Thus, it will help with prioritizing attributable preventative measures. “Most are concerned about breast cancer and, of course, they absolutely should be. But if your history and lifestyle indicate that your greatest risk is heart disease, that should be your number one concern,” said Robbins.

Researchers partnered with medical and computer science experts from throughout the United States and Saudi Arabia to develop an interactive, web-based calculator that predicts the likelihood of experiencing multiple, competing morbidity and mortality outcomes prospectively over 5, 10, and 15 years. To determine a woman’s personalized risk, participants would answer 35 to 50 questions related to current and past health and family history.

The calculator’s data was derived from the Women’s Health Initiative (WHI), a long-term study containing lifestyle, medical history, and health outcomes information, for 161,808 diverse postmenopausal women aged 50 to 79 enrolled across 4 regions of the United States:

• A calculator predicts all-cause mortality, adjudicated outcomes of health events (myocardial infarction [MI], stroke, and hip fracture), and disease (lung, breast, and colorectal cancer)
• A proportional subdistribution hazards regression model was used to develop the calculator in a training dataset using data from 3 regions
• The calculator was evaluated using the C-statistic in a test dataset with data from the fourth region

The predictive validity of the calculator for a first event at 5 and 15 years was shown by the C-statistic in the test dataset for MI (0.77, 0.61), stroke (0.77, 0.72), lung cancer (0.82, 0.79), breast cancer (0.60, 0.59), colorectal cancer (0.67, 0.60), hip fracture (0.79, 0.76), and death (0.74, 0.72).

Study results of the risk prediction calculator represent the first step toward enabling women to prioritize interventions that may decrease health risks, noted the authors. The potential of the calculator to account for multiple health conditions at once, as opposed to solely 1 at a time, was additionally highlighted by Robbins. “The risk of 1 disease is always relative to the risks of another, and our tool accounts for those competing risk,” said Robbins. By delineating which risks are and are not associated with their current health status, women and physicians can initiate preventative measures sooner.

Reference

Hedlin H, Weitlauf J, Crandall C, et al. Development of a comprehensive health-risk prediction tool for postmenopausal women. [published online September 16, 2019]. Menopause. doi: 10.1097/GME.0000000000001411.