The impact of big data on health care: Health Affairs' July issue

Big data can yield big savings, if they are used in the right ways. David W. Bates of the Brigham and Women's Hospital and coauthors analyzed six use cases with strong opportunities for cost savings—high-cost patients; readmissions; triage; decompensation (when a patient's condition worsens); adverse events; and treatment optimization when a disease affects multiple organ systems. They suspect that cost-savings benefits will vary widely, though the current costs associated with all six scenarios will be significant. The authors suggest that using analytics for multiple conditions is likely to yield even stronger cost savings. They highlight key areas for policy makers to emphasize in this environment, including: federal investment in research into analytics and big data; a clearer regulatory stance at the Food and Drug Administration regarding the use of these tools; a strengthening of incentives for providers to control costs; and more defined privacy parameters regarding the use of big data at the federal level.

Don't get sick over the weekend, or go to a hospital with a lot of sick people already in beds. Flemming Madsen of the Allergy and Lung Clinic in Helsingoer, Denmark, and coauthors examined the effects of hospital bed shortages on patient outcomes using 2.65 million admissions to Danish hospitals from 1995–2012. They found that while high rates of bed occupancy (above 85 percent) can be a sign of more efficient care, they were also associated with a 9 percent increase in rates of both inhospital mortality and thirty-day mortality. In addition, they found that patients who were admitted outside of normal working hours had higher inpatient and thirty-day mortality rates, especially among the elderly. The authors further suggest that chronic bed shortages are likely a product of a self-regulating mechanism and deliberate planning to keep occupancy rates high. They recommend approaching high-occupancy rates as a public health issue as opposed to a purely economic one. They point out that the rapidly aging US population will put further strain on hospitals both with and without emergency departments.

A series of papers focus on comparative effectiveness and predictive analysis:

Implementing Electronic Health Care Predictive Analytics: Considerations And Challenges by Ruben Amarasingham of the Parkland Center for Clinical Innovation and coauthors
Patient-Powered Research Networks Aim To Improve Patient Care And Health Research by Rachael L. Fleurence of the Patient-Centered Outcomes Research Institute and colleagues
Assessing The Value Of Patient-Generated Data To Comparative Effectiveness Research by Lynn Howie of Duke University and colleagues
Optum Labs: Building A Novel Node In The Learning Health Care System by Paul J. Wallace of Optum Labs and colleagues

Provided by Health Affairs