For accountable care to truly take off, access to constantly updated health information of patients will be vital. As Aetna President of Strategic Diversification Dr. Charles Saunders said during a panel discussion at the World Healthcare Innovation & Technology Congress earlier this month, everything with regard to patient care, thus far, has been retrospective.

"What you need is to make a difference in real time," Saunders said. A combination of health information exchange (HIE) capability, "married" clinical and claims data, and platform care coordination would help to make that possible.

Saunders added, "It's going to be a long journey to get [to the point where ACOs are successful]. It's a complete change. It's not enough just to have an EHR."

Hospitals like Vineland, N.J.-based South Jersey Healthcare have jumped ahead of the game on that front, building a data warehouse and implementing various business intelligence tools that enable monitoring and review of performance for both clinicians and administrators. What's more, South Jersey's HIE connects it with six ambulatory-care EHRs and 13 outpatient practices with expanded connectivity on the horizon.

"Everybody has to have access to everybody else's encounters and expertise," Battani told FierceHealthIT. "And then, because there's so much information, decision-support tools are required to help filter that information for what's relevant, important, impactful, insightful at that moment of care."

Director of the Johns Hopkins Center for Population Health IT Jonathan Weiner made similar points while talking with FierceHealthcare just prior to CMS's publishing of the final rule.

"Accountable care organizations are virtually integrated delivery systems," Weiner said. "It will be impossible for them to achieve...integration unless key participants are able to actively share patient information."

Weiner also advocated that the use of predictive modeling could help ACOs achieve success.

"Predictive models will be essential as a means of identifying persons at risk for high-impact events, such as hospitalization and/or doctor shopping," he said. "To be most useful to ACOs, predictive modeling tools will need to be available on close to a real-time basis to influence care, which means they ideally should be integrated into EHR systems as automated 'population-health-decision-support' systems."