Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

Design and Development of an Intelligent Clinical Decision Support System Applied towards the Diagnosis of Suspected Obstructive Sleep Apnea Patients from the Patient’s Health Profile and Symptomatology

Version 1 : Received: 27 March 2023 / Approved: 28 March 2023 / Online: 28 March 2023 (03:18:38 CEST)

A peer-reviewed article of this Preprint also exists.

Casal-Guisande, M.; Ceide-Sandoval, L.; Mosteiro-Añón, M.; Torres-Durán, M.; Cerqueiro-Pequeño, J.; Bouza-Rodríguez, J.-B.; Fernández-Villar, A.; Comesaña-Campos, A. Design of an Intelligent Decision Support System Applied to the Diagnosis of Obstructive Sleep Apnea. Diagnostics 2023, 13, 1854. Casal-Guisande, M.; Ceide-Sandoval, L.; Mosteiro-Añón, M.; Torres-Durán, M.; Cerqueiro-Pequeño, J.; Bouza-Rodríguez, J.-B.; Fernández-Villar, A.; Comesaña-Campos, A. Design of an Intelligent Decision Support System Applied to the Diagnosis of Obstructive Sleep Apnea. Diagnostics 2023, 13, 1854.

Abstract

Obstructive Sleep Apnea (OSA) is nowadays one of the respiratory pathologies with a higher in-cidence globally in developed countries. This situation led to an increase in the demand for medical appointments and diagnostic studies related to that condition, especially those based on poly-somnographies and cardiorespiratory polygraphies. These studies are limited in resources, causing long waiting lists with the subsequent impact on the patients’ health. Furthermore, it is necessary to mention that OSA’s symptomatology is not very specific, and it is typically present in the general population (excessive sleepiness, snore, etc.). In this regard, this paper proposes a novel intelligent clinical decision support system for the diagnosis of OSA which could be used to help medical teams, both in primary care settings and in units specialized in respiratory pathologies. The aim of the proposed system is to help discriminate the patients suspected of suffering from the pathology from those who are not. To this end, two types of information sets of heterogeneous nature are consid-ered. The first one encompasses objective data, related to the patient's health profile with infor-mation usually available in electronic health records. The second type comprises subjective data, referred to the symptomatology reported by the patient in a previous interview. To process the first group of information, a Machine Learning classification algorithm is used, Bagged Trees in this case. For processing the second information set, related with the symptomatology of the patient, a col-lection of expert systems based on fuzzy inferential systems arranged in cascade are employed. As a result, the system is able to determine two risk indicators related to the patient's risk of suffering from OSA: the Statistical Risk and the Symbolic Risk respectively. Subsequently, by interpreting both risk indicators mentioned it will be possible to determine the severity of the patients’ health, proposing a preliminary evaluation on their condition. For the initial tests of the system, a software artifact has been built using a dataset with 4,978 selected patients, suspected of suffering from OSA, from the Álvaro Cunqueiro Hospital in Vigo. The results obtained are promising, demonstrating the potential usefulness of this type of tools in medical diagnosis. Once the system has been validated with new data from clinical environments, it is considered as possible to obtain a relevant improvement in the quality of the healthcare services, and a reduction in the associated costs.

Keywords

design; clinical decision support systems; intelligent systems; expert systems; Machine Learning; decision-making; medical algorithm; design science research.; obstructive sleep apnea

Subject

Medicine and Pharmacology, Other

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.

Leave a public comment
Send a private comment to the author(s)
* All users must log in before leaving a comment
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.