Diabetes and other chronic diseases account for significant levels of morbidity and mortality in the United States, with an increasing proportion of patients living with multiple complex chronic conditions [1–3]. Multiple chronic conditions are associated with coordination challenges for both patients and health care providers, often across several clinicians and sites of care [1, 4–7]. This complexity can lead to less than optimal treatment, potentially redundant care, and preventable acute services [1, 7–24]. Patient portal tools that improve patient access to their own health information, support self-management, and help patients communicate asynchronously with providers offer an additional mechanism for delivering high-quality guideline-recommended care that can improve patient health [25, 26].

Electronic patient portals, linked to the patient’s clinical electronic health record (EHR), offer patients secure access to their own medical information and the ability to manage several aspects of their health care at any time of day or night through interactive tools, including lab result review, visit summaries, secure messages to providers, and medication refill orders. In some situations, this convenience may allow patients to communicate with health care providers while avoiding traveling to medical facilities and pharmacies, and without requiring time-off from work or care-giving[27–30]. Patient portal access can potentially improve patient engagement and shift the way that health care is delivered, but prior evidence is mixed about the overall portal-related impacts on in-person health care use [28, 31].Healthcare quality improvements have been associated with specific portal components such as patient-provider secure messages use or patient access to lab results [26, 28, 31–33]. However, to our knowledge, ours is the first study to specifically examine overall portal impacts in a population of patients with multiple complex conditions.

For patients with diabetes, many also with other complex chronic conditions, who are likely juggling multiple medications, lab tests, providers, and visits, using a portal to coordinate and manage these may be particularly effective [34]. Our study examines patient portal access in a population with diabetes, including patients with diabetes and additional comorbid conditions, within a large integrated delivery system that first implemented a comprehensive patient portal in late 2005. Our study design takes advantage of historical data from the first two years after the portal was implemented to compare patient health care utilization and events associated with precise timing of each patient’s own individual portal access, with particular attention to patients with multiple complex conditions. We hypothesized that the access to health information, health care self-management tools, and ability to communicate with providers directly through the portal could reduce disease exacerbations and clinical events for patients with multiple chronic conditions who use the portal as measured by emergency room visits and preventable hospitalizations.

Among all study patients with diabetes (N = 165,477), 77.4% had multiple chronic conditions (diabetes plus one or more other conditions, Table 1). During the study period 22.3% of all study patients started to use the patient portal (see supplement).

In examining the association between portal use and rates of office visits, ED visits and hospitalizations, we found two distinct patterns. After accounting for patient characteristics and time-varying clinical needs using IPW estimation, access to the portal was associated with significantly more office visits (170 per 1,000 patients per month, p<0.05, Fig 1). This difference was relatively consistent among patients with only diabetes (178 per 1,000 patients per month, p<0.05), and patients with multiple chronic conditions (167 more office visits per 1,000 patients per month, p<0.05).

In contrast, portal access was associated with significantly fewer ED visits (3.5 per 1,000 patients per month, p<0.05, Fig 2) and preventable hospital stays (0.8 per 1,000 patients per month, p<0.05) overall. In the population of patients with complex chronic conditions, portal access was associated with significantly fewer ED visits (3.9 per 1,000 patients per month, p<0.05) and preventable hospital stays (0.8 per 1,000 patients per month, p<0.05), as measured by ambulatory care sensitive hospitalizations (Fig 3).

In patients with only diabetes, the results were directionally consistent but not statistically significantly associated with ED visits and preventable hospitalizations (1.7 fewer ED visits per month with portal access, 95% CI -3.9–0.5; 0.5 fewer preventable hospitalizations per month with portal access, 95% CI -1.0–0.1; Figs 2 and 3).

Among patients with diabetes, particularly complex patients with multiple chronic conditions, we examined the association between portal access and office visits and health events as captured by ED visits and hospitalizations. We found that access to a patient portal was associated with engaging in significantly more outpatient office visits. When patients with multiple conditions had access to the portal, however, they were also less likely to have ED visits or preventable hospitalizations, suggesting a reduction in downstream clinical events associated with portal use.

Our study is unique in specifically examining portal impacts in patients with multiple complex chronic conditions. We anticipated that patients with this complexity in health care experience, likely managing multiple providers, visits, medications, and lab monitoring schedules, might have a particular opportunity to benefit from using the portal to facilitate self-management activities. We found that patients with diabetes had more office visits after gaining access to the patient portal. Consistent with prior evidence that higher outpatient healthcare access is associated with lower ED visits [44, 45], we found that the portal-associated increases in office visits were accompanied by a decrease in ED visits. Only patients with multiple conditions experienced statistically significantly fewer health events as measured by emergency department visits and ambulatory-care-sensitive hospital stays, although other patients with diabetes may well benefit as well [46].

In this patient centered project, our patient research partners linked the study’s analytic findings to their own lived experiences in using the portal. For instance, while the statistical analysis found an overall increase in office visit rates associated with portal use, discussions with patients helped clarify that this should be interpreted as an averaged effect, and that individual patient experiences may differ. For example, patient partners related personal situations of directly avoiding an office visit by asking their doctor a question through the portal. In other instances, patient partners reported situations where using the portal to check a lab result led directly to follow-up engagement with their physician through an in-person visit. Similarly, patient partners linked the statistical findings of reductions in emergency visits to personal experiences, for example, in using the portal after regular medical hours to obtain a medication that helped to avoid an ED visit. While individual care-seeking experiences may vary, we found that on average patients experienced fewer ED visits and preventable hospital stays after starting to access the portal.

Our study examines the overall impact of patient portal access on patient health care activity and events. Several other studies have examined specific instances of portal use (a login transaction on a particular date), individual portal tools (such as secure messaging or open notes), or different target populations of patients (such as a general primary care patient population) [26, 28, 31, 33, 36, 37].Some studies, including across different settings within the same integrated delivery system, have reported an association with increases in office visits, and others with decreases, but few have examined downstream clinical events. Our study finds that portal use is associated with a statistically significant reduction in downstream clinical events among patients with higher complexity. These findings of differences in health care utilization and events are consistent with other patient-centered survey findings of portal use being associated with shifts toward greater communication, and patient-reported health improvements [27, 28, 47]. While some patient-reported findings have suggested that portal use may decrease office visits, we interpret our finding of an average increase in office visit activity as likely a combination of individual patient experiences that include both intentional substitution for office visits and increases in office visit engagement. Further research should examine the impact of targeted strategies to educate patients, providers, and health care delivery systems about the potential benefits of and barriers to portal use, including through dissemination of patient-reported experiences.

While prior observational studies have examined impacts of patient portal use on health care utilization, to the best of our knowledge, ours is the first to use a study design that accounts for time-changing clinical needs closely linked to the timing of portal use. Research designs that do not adequately account for time-changing factors close to the time of portal use may mistakenly attribute any increase in use of in-person health care services to using a patient portal, rather than to the new health need. In addition, our findings also incorporate adjustment for a relatively comprehensive list of potential statistical confounders. Thorough adjustment for time-changing covariates is critically important in designing observational studies to assess the impact of patient portal use on health outcomes [34].

There are several limitations to the generalizability of our study findings. Since the study was conducted in a single integrated health delivery system with a comprehensive patient portal, the results may not necessarily generalize directly to other settings. Still, this study setting includes both commercial and public insurance enrollees, represents approximately 33% of the underlying population in areas served, and is highly representative of the surrounding and statewide insured population in race/ethnicity and socio-economic status, with the exception of patients with extremely low income [48, 49]. We do not examine portal uses directly and our intent-to-treat approach examining general portal access may underestimate the impact of specific portal uses and actions. While the time period used in this study is historical, using this timeframe supported a stronger causal study design and analytic methods. Still, in examining a setting that is a technology leader within an integrated setting, the portal tools and functions studied are comparable to current portal implementations, including those used in the current federal Promoting Interoperability program criteria. Also, since the portal offered in this setting was available free of charge to patients, findings may vary when costs, such as for secure messages, are applied. Since our study was focused on patients with diabetes and other chronic conditions captured in available disease registries, the study is limited in its generalizability to other populations without chronic conditions. While our study accounts for many potential confounders and time-changing patient and clinical variables, there may be other patient characteristics associated with using or not using the portal that we could not measure or account for in our analyses. Since this is an observational study, we cannot rule out unmeasured confounding or establish causality.

Overall, we found that in patients with diabetes within an integrated delivery system offering a comprehensive patient portal, office visit rates were higher when patients had access to a patient portal compared to when they did not, and that portal access was associated with statistically significantly lower rates of ED visits and preventable hospitalizations in patients with complex chronic conditions. Together with patient partners in this patient-centered study, we interpret these findings as a signal that the portal may be helping to increase engagement in outpatient office visits, a preferable setting to potentially address otherwise unmet clinical needs, and thereby reducing downstream health events that lead to emergency and hospital care.