2024
Sousa, R.; Peixoto, H.; Guimarães, T.; Abelha, A.; Machado, J.
Towards a Standardized Real-Time Data Repository based on Laboratory Test Results Proceedings Article
Em: E., Shakshuki (Ed.): pp. 452-457, Elsevier B.V., 2024, ISSN: 18770509, (cited By 0; Conference of 14th International Conference on Emerging Ubiquitous Systems and Pervasive Networks / 13th International Conference on Current and Future Trends of Information and Communication Technologies in Healthcare, EUSPN/ICTH 2023 ; Conference Date: 7 November 2023 Through 9 November 2023; Conference Code:196395).
Resumo | Links | BibTeX | Etiquetas: API; Clinical test result; Clinical tests; Data repositories; Data standards; Health data; Health data standard; Patient care; Real-time data; Real-time information systems, Data warehouses, Decision making; Deep learning; Learning algorithms; Patient treatment; Real time systems
@inproceedings{Sousa2024452,
title = {Towards a Standardized Real-Time Data Repository based on Laboratory Test Results},
author = {R. Sousa and H. Peixoto and T. Guimarães and A. Abelha and J. Machado},
editor = {Shakshuki E.},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85183899245&doi=10.1016%2fj.procs.2023.12.233&partnerID=40&md5=92265b57dddfc7c279187e0735fa722b},
doi = {10.1016/j.procs.2023.12.233},
issn = {18770509},
year = {2024},
date = {2024-01-01},
journal = {Procedia Computer Science},
volume = {231},
pages = {452-457},
publisher = {Elsevier B.V.},
abstract = {Healthcare facilities use huge quantities of real-time and analytical data to discover meaningful information from patient clinical lab results. Advanced analytics and machine learning algorithms help doctors identify and treat patients more accurately. Accurate models must be trained, tested, and validated with enough data. New real-time data allows healthcare practitioners to quickly and accurately analyse patient demands. Healthcare organizations can improve patient care and outcomes through knowledge discovery. The goal of this effort is to develop a real-time data repository based on patient clinical exams. This collection feeds real-time monitoring panels and machine or deep learning algorithms that forecast patient progression from clinical lab results. Integrate HL7 messages from diverse sources, preprocess them, and add them to an API-accessible data warehouse. In conclusion, the proposed method creates an international-standard data warehouse. This data warehouse can increase healthcare decision-making accuracy and efficacy when utilised with machine learning models, improving patient care and outcomes through more personalised treatment options. © 2024 The Authors. Published by Elsevier B.V.},
note = {cited By 0; Conference of 14th International Conference on Emerging Ubiquitous Systems and Pervasive Networks / 13th International Conference on Current and Future Trends of Information and Communication Technologies in Healthcare, EUSPN/ICTH 2023 ; Conference Date: 7 November 2023 Through 9 November 2023; Conference Code:196395},
keywords = {API; Clinical test result; Clinical tests; Data repositories; Data standards; Health data; Health data standard; Patient care; Real-time data; Real-time information systems, Data warehouses, Decision making; Deep learning; Learning algorithms; Patient treatment; Real time systems},
pubstate = {published},
tppubtype = {inproceedings}
}
Healthcare facilities use huge quantities of real-time and analytical data to discover meaningful information from patient clinical lab results. Advanced analytics and machine learning algorithms help doctors identify and treat patients more accurately. Accurate models must be trained, tested, and validated with enough data. New real-time data allows healthcare practitioners to quickly and accurately analyse patient demands. Healthcare organizations can improve patient care and outcomes through knowledge discovery. The goal of this effort is to develop a real-time data repository based on patient clinical exams. This collection feeds real-time monitoring panels and machine or deep learning algorithms that forecast patient progression from clinical lab results. Integrate HL7 messages from diverse sources, preprocess them, and add them to an API-accessible data warehouse. In conclusion, the proposed method creates an international-standard data warehouse. This data warehouse can increase healthcare decision-making accuracy and efficacy when utilised with machine learning models, improving patient care and outcomes through more personalised treatment options. © 2024 The Authors. Published by Elsevier B.V.