Development of an Ambient Intelligence Environment to improve Patient Safety in Critical Care

Abstract

In the late 1990's, when sophisticated personal computers and electronic devices with miniaturized sensors were being mass produced, the concept of ambient intelligence (AmI) emerged. An environment that has AmI is a space containing objects which includes technologies that are not visible to users, and which generates intelligent responses when appropriate. When people interact with an AmI environment, they intuitively use technologies according to their own needs and gain more awareness of their actions, thereby improving their quality of life, comfort, and empowerment.

Currently, healthcare professionals work inside a complex adaptive system in which the clinical environment and the health status of patients vary dynamically, and resources are limited. This can generate an increasing number of adverse events as well as medical errors and consequently patients are more exposed to potential harm during a hospital stay. Many researchers are creating new AmI tools to overcome these challenges. This is especially important in intensive care units (ICUs), where there are seriously ill patients who need advanced infrastructure and equipment to receive continuous clinical monitoring and treatment in as safe a way as possible. Three out of every ten patients in an ICU suffer some type of clinical safety issue, which puts their lives at risk.

In this context, the main aim of the work I present in this thesis is to develop an AmI environment for improving the efficiency of processes related to patient safety in ICUs. I have written this thesis with the collaboration of the clinical and engineering

team of the Smart ICU at the Hospital Cl(n

ic in Barcelona (HCB). That AmI

environment is equipped mainly with technologies related to the Internet of Things (IoT) that provide an adaptive and dynamic distribution of clinical information based on the role and location of each professional as well as the clinical health status of patients.

I divided the development of this thesis into three phases. Firstly, I designed, built, and tested a prototype to simulate the AmI environment in a laboratory setting, considering the main patient safety issues which arise in ICUs. I considered 5 patient safety issues: a code blue, a code red, a code pink, control of nosocomial infections and drug-related errors. Secondly, that prototype was adapted and implemented in a Smart ICU at HCB. Thirdly, I collected and analysed data generated by the AmI. It is important to highlight that part of the data collection and analysis related to the AmI environment took place during the SARS-CoV-2 epidemic (Covid- 19).

To summarize, my thesis evaluates the efficiency of the use of new technologies to improve patient safety processes in critical care. It improves clinical and educational standards in terms of patient safety processes at the unit concerned. Moreover, it enables quantification of events related to patient safety as well as heightening awareness of them.

A finales de la década de 1990, cuando las computadoras personales y los dispositivos electrónicos se producían en masa, el concepto de inteligencia en el entorno (AmI – Ambient Intelligence en inglés) surgió. Un entorno que contiene AmI es un espacio con objetos que incluyen tecnologías, invisibles para los usuarios, y que les generan respuestas inteligentes cuando sea necesario.

Actualmente, los profesionales sanitarios están trabajando dentro de un sistema complejo adaptativo en el que el entorno clínico y el estado de salud del paciente varían dinámicamente. Esto es especialmente importante en las Unidades de Cuidados Intensivos (UCIs), donde hay pacientes gravemente enfermos que necesitan infraestructuras y equipos avanzados para recibir monitorización de la forma más segura posible.

En este contexto, el objetivo principal del trabajo que presento en esta tesis es desarrollar un entorno AmI para mejorar la eficiencia en los procesos relacionados con la seguridad del paciente en las UCIs. He elaborado esta tesis con la colaboración del equipo de la UCI inteligente del Hospital Clínic de Barcelona (HCB). El desarrollo de esta tesis se ha dividido en tres fases. En primer lugar, he diseñado, construido y probado un prototipo para simular el entorno AmI en un escenario de laboratorio considerando los principales problemas de seguridad clínica que ocurren en las UCIs. En segundo lugar, este prototipo ha sido adaptado e implementado en una UCI inteligente del HCB. En tercer lugar, he recogido y analizado los datos generados por el entorno inteligente.

En conclusión, mi tesis evalúa la eficiencia del uso de nuevas tecnologías para mejorar los procesos de seguridad clínica en cuidados críticos, mejora los estándares clínicos y educativos sobre los procesos de seguridad del paciente en esta unidad y, finalmente, permite cuantificar los eventos relacionados con la seguridad clínica, así como ganar más conciencia sobre ellos.