Introduction: Digital health applications have gained popularity in the healthcare industry. Clinicians are inundated with new types of data to promptly synthesize to make a qualified clinical decision about patient care. This study presents an overview of the architectural specifications to construct an innovative service-oriented software suite, which can be used to support evidence-based healthcare decisions in a variety of clinical settings and procedures. Methods: The designed system will use data from repositories and clinical systems to produce a multidimensional view of a patient, infer possible outcomes, and propose actions. Predefined pathways, as well as paths developed by artificial intelligence, machine learning, and process mining algorithms, will be used to construct inferential models, and use them to suggest further actions, which adapt to changing patient circumstances. Results: The intended system's adoption depends on numerous requirements, including the need for cooperation, the development of protocols for legal purposes, and clinical decision-making and procedure assistance. As a basis, electronic clinical information is used to evaluate human decisions against predefined protocols or statistically known evolution patterns. Conclusion: The system will enhance strategic decision-making in the diagnosis of heart disease using the large quantity of accessible data in the healthcare system and providing full and transparent assistance for patient treatment and clinician workflows.

Composition of a Service-Oriented Clinical Decision Support System using Machine Learning / Walter-Tscharf, F. F. W. V.. - In: PUBLIC HEALTH MEDICINE. - ISSN 1465-1505. - ELETTRONICO. - 18:4(2022), pp. 62-67. [10.47836//mjmhs18.4.9]

Composition of a Service-Oriented Clinical Decision Support System using Machine Learning

Walter-Tscharf F. F. W. V.
2022-01-01

Abstract

Introduction: Digital health applications have gained popularity in the healthcare industry. Clinicians are inundated with new types of data to promptly synthesize to make a qualified clinical decision about patient care. This study presents an overview of the architectural specifications to construct an innovative service-oriented software suite, which can be used to support evidence-based healthcare decisions in a variety of clinical settings and procedures. Methods: The designed system will use data from repositories and clinical systems to produce a multidimensional view of a patient, infer possible outcomes, and propose actions. Predefined pathways, as well as paths developed by artificial intelligence, machine learning, and process mining algorithms, will be used to construct inferential models, and use them to suggest further actions, which adapt to changing patient circumstances. Results: The intended system's adoption depends on numerous requirements, including the need for cooperation, the development of protocols for legal purposes, and clinical decision-making and procedure assistance. As a basis, electronic clinical information is used to evaluate human decisions against predefined protocols or statistically known evolution patterns. Conclusion: The system will enhance strategic decision-making in the diagnosis of heart disease using the large quantity of accessible data in the healthcare system and providing full and transparent assistance for patient treatment and clinician workflows.
2022
4
Walter-Tscharf, F. F. W. V.
Composition of a Service-Oriented Clinical Decision Support System using Machine Learning / Walter-Tscharf, F. F. W. V.. - In: PUBLIC HEALTH MEDICINE. - ISSN 1465-1505. - ELETTRONICO. - 18:4(2022), pp. 62-67. [10.47836//mjmhs18.4.9]
File in questo prodotto:
File Dimensione Formato  
2022093009254711_MJMHS_1604.pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 208.62 kB
Formato Adobe PDF
208.62 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/362842
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact