Developing a Data-Driven Approach in Order to Improve the Safety and Quality of Patient Care

Abstract

Objective: To improve the safety and quality of patient care in hospitals by shaping clinical pathways throughout the patient journey. Study Setting: A risk model designed for healthcare organizations in the context of the challenges arising from comorbidity and other treatment-related complexities. Study Design: The core of the model is the patient and his intra-hospital journey, which is analyzed using a data-driven approach. The structure of a predictive model to support organizational and clinical decision-making activities is explained. Data relating to each step of the intra-hospital journey (from hospital admission to discharge) are extracted from clinical records. Principal Findings: The proposed approach is feasible and can be used effectively to improve safety and quality. It enables the evaluation of clinical risks at each step of the patient journey. Conclusion: Based on data from real cases, the model can record and calculate, over time, variables and behaviors that affect the safety and quality of healthcare organizations. This provides a greater understanding of healthcare processes and their complexity which can, in turn, advance research relating to clinical pathways and improve strategies adopted by organizations.

Keywords: best practices; clinical governance; guidelines; patient safety; quality of care.

Figure 1

The patient journeys. Examples of journeys with possible variations: In (A), journey P1 varies from the initial expectations after step S1. It consequently then becomes the real journey, P1* and passes through new stages that had not been anticipated and finally arrives at the expected result, O. In contrast, journey P2, as shown in (B), is varied by means of an additional stage between Steps S1 and S2. In the journey P3, shown in (C), we see a substantial variation from the expected journey, producing an unintended final condition, O* ≠ O. By analyzing the journeys of patients, it is possible to see how these are subject to changes, even when based on CPs. It is also possible to notice steps that patients have to pass through, interpret them, and consider the features of the variables depending on the healthcare facility and the health conditions of the particular patient.

Figure 2

Oriented graph of possible patient journeys. Example of a graph that models the data collected for a cluster of journeys, according to their specific initial features (condition on admission), I. The expected (or positive) result of this path is O, which can be reached with probability pO. The patient's risk is defined by the probability of reaching different final conditions given the same starting condition upon admission. The risk of obtaining a final condition different from O, starting from condition I on admission, is given by the list of probabilities [p (O1), p (O2), p (O3), p (O4)]. Each node of the graph represents a possible step (initial, intermediate, or final) of the journey (and thus a stage of the patient's condition between admission and discharge), and each edge (or line between nodes) represents a possible succession of steps/stages according to the probability of encountering each of them. Such journeys make up our knowledge base. In particular, we can calculate the probability of arriving at the final step/stage, given any initial node of the graph, be it initial or intermediate.