Network-medicine framework for studying disease trajectories in U.S. veterans

Abstract

A better understanding of the sequential and temporal aspects in which diseases occur in patient's lives is essential for developing improved intervention strategies that reduce burden and increase the quality of health services. Here we present a network-based framework to study disease relationships using Electronic Health Records from > 9 million patients in the United States Veterans Health Administration (VHA) system. We create the Temporal Disease Network, which maps the sequential aspects of disease co-occurrence among patients and demonstrate that network properties reflect clinical aspects of the respective diseases. We use the Temporal Disease Network to identify disease groups that reflect patterns of disease co-occurrence and the flow of patients among diagnoses. Finally, we define a strategy for the identification of trajectories that lead from one disease to another. The framework presented here has the potential to offer new insights for disease treatment and prevention in large health care systems.

Figure 1

Temporal Disease Network. (a) Example of the disease records for a single patient and its representation into disease paths. The Disease Network connects diseases that occur consecutively in patients' records. Edge weights w_ij, p-values, and $\varphi$ values are shown for raw data and represent the number of patients, the correlation coefficient, and the significance, respectively, for each progression step. (b) Nodes represent diagnoses (ICD9 at the 3-digit level) and links represent the number of patients with disease A before diseases B. For visualization purposes, the edge directions were merged as single undirected edges, edges with $\varphi$ < 0.001 were filtered, and disconnected nodes resulting from this filtering were omitted. The full network contains 718 nodes and 60,425 edges, while the visualization shows 638 nodes and 4,582 edges. The labels highlight diseases mentioned throughout the text and their corresponding nodes in the network.

Figure 2

Network centrality and fatality. Comparison of network centrality and fatality values across nodes of the Disease Network. Inset numbers represent the Spearman correlation coefficient (all with p < 0.05).

Figure 3

Communities. (a) Visualization of TDN with colors representing the different communities detected using InfoMap. (b) The community assignments for diagnoses in the ICD-9 chapter “Diseases of The Circulatory System”. (c) Alluvial diagrams representing the re-assignment of diseases from different ICD-9 chapters into the detected communities. (d) Distribution of % of deceased patients after 8 years of first diagnosis for diseases assigned in the different communities.

Figure 4

Disease Trajectories. Trajectories connecting diabetes mellitus to all diseases in the ICD-9 chapter “Diseases Of The Circulatory System”.