Currently in hospitals, several information systems manage, very often autonomously, the patient’s personal, clinical and diagnostic data. This originates a clinical information management system consisting of a myriad of independent subsystems which, although efficient in their specific purpose, make the integration of the whole system very difficult and limit the use of clinical data, especially as regards the reuse of these data for research purposes. Mainly for these reasons, the management of the Genoese ASL3 decided to commission the University of Genoa to set up a medical record system that could be easily integrated with the rest of the information system already present, but which offered solid interoperability features, and which could support the research skills of hospital health workers. My PhD work aimed to develop an electronic health record system for a cardiology ward, obtaining a prototype which is functional and usable in a hospital ward. The choice of cardiology was due to the wide availability of the staff of the cardiology department to support me in the development and in the test phase. The resulting medical record system has been designed “ab initio” to be fully integrated into the hospital information system and to exchange data with the regional health information infrastructure. In order to achieve interoperability the system is based on the Health Level Seven standards for exchanging information between medical information systems. These standards are widely deployed and allow for the exchange of information in several functional domains. Specific decision support sections for particular aspects of the clinical life were also included. The data collected by this system were the basis for examples of secondary use for the development of two models based on machine learning algorithms. The first model allows to predict mortality in patients with heart failure within 6 months from their admission, and the second is focused on the discrimination between heart failure versus chronic ischemic heart disease in the elderly population, which is the widest population section served by the cardiological ward.
An Interoperable Clinical Cardiology Electronic Health Record System - a standards based approach for Clinical Practice and Research with Data Reuse
LAZAROVA, ELENA
2022
Abstract
Currently in hospitals, several information systems manage, very often autonomously, the patient’s personal, clinical and diagnostic data. This originates a clinical information management system consisting of a myriad of independent subsystems which, although efficient in their specific purpose, make the integration of the whole system very difficult and limit the use of clinical data, especially as regards the reuse of these data for research purposes. Mainly for these reasons, the management of the Genoese ASL3 decided to commission the University of Genoa to set up a medical record system that could be easily integrated with the rest of the information system already present, but which offered solid interoperability features, and which could support the research skills of hospital health workers. My PhD work aimed to develop an electronic health record system for a cardiology ward, obtaining a prototype which is functional and usable in a hospital ward. The choice of cardiology was due to the wide availability of the staff of the cardiology department to support me in the development and in the test phase. The resulting medical record system has been designed “ab initio” to be fully integrated into the hospital information system and to exchange data with the regional health information infrastructure. In order to achieve interoperability the system is based on the Health Level Seven standards for exchanging information between medical information systems. These standards are widely deployed and allow for the exchange of information in several functional domains. Specific decision support sections for particular aspects of the clinical life were also included. The data collected by this system were the basis for examples of secondary use for the development of two models based on machine learning algorithms. The first model allows to predict mortality in patients with heart failure within 6 months from their admission, and the second is focused on the discrimination between heart failure versus chronic ischemic heart disease in the elderly population, which is the widest population section served by the cardiological ward.File | Dimensione | Formato | |
---|---|---|---|
phdunige_3803594.pdf
accesso aperto
Dimensione
10.98 MB
Formato
Adobe PDF
|
10.98 MB | Adobe PDF | Visualizza/Apri |
I documenti in UNITESI sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/20.500.14242/105824
URN:NBN:IT:UNIGE-105824