Using Digital Crumbs from an Electronic Health Record to identify, study and improve health care teams

Abstract

We have developed a novel approach, the Digital Crumb Investigator, for using data collected as a byproduct of Electonic Health Record (EHR) use to help define care teams and care processes. We are developing tools and methods to utilize these routinely collected data to visualize and quantify care networks across acute care and ambulatory settings We have chosen a clinical care domain where clinicians use EHRs in their offices, on the maternity wards and in the neonatal intensive care units as a test paradigm for this technology. The tools and methods we deliver should readily translate to other health care settings that collect behind-the-scenes electronic metadata such as audit trails. We believe that by applying the methods of social networking to define clinical relationships around a patient's care we will enable new areas of research into the usage of EHRs to promote patient safety and other improvements in care.

Figure 1:

Visual representation of an affiliation network derived from NICU data. Squares represent patient rooms and circles represent patients cared for in those rooms. Darker red circles represent patients with episodes of bloody stools during this period.

Figure 2:

Digital Crumb Investigator Architecture

Figure 3:

Number of unique providers involved in maternal care during the perinatal through postnatal period. Whiskers represent the 10^th and 90^th percentile of the number of connected providers Boxes represent the interquartile range. + = mean.

Figure 4:

Cumulative Number of providers connected to individual obstetric patients. Series represent the mean number of connected providers. Delivery day is represented by Day 0 on the horizontal axis.

Figure 5:

In this patient centered NICU provider network the patient is represented by red sphere in center of figure. Providers are represented by other icons (see key). Providers with largest number of ties to patient in this progress note based network are closest to patient.

Figure 6:

In this nursing handoff network, each node represents a nurse involved in this particular patient’s care. Edges represent the handoffs that occurred between providers. Node size is proportional to that nodes betweenness centrality, a measure of the node’s importance to information flow.