Knowledge-based decision system for automatic sleep staging using symbolic fusion in a turing machine-like decision process formalizing the sleep medicine guidelines

Autor: Andrea Pinna, Jacques Bouaud, Brigitte Séroussi, Adrien Ugon, Amina Kotti, Patrick Garda, Carole Philippe, Karima Sedki, Jean-Gabriel Ganascia
Přispěvatelé: Laboratoire d'Informatique Médicale et Ingénierie des Connaissances en e-Santé (LIMICS), Université Paris 13 (UP13)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM), ESIEE Paris, Systèmes Electroniques (SYEL), LIP6, Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), UPMC - Département de santé publique, Université Pierre et Marie Curie - Paris 6 (UPMC)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-CHU Tenon [AP-HP], Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU), CHU Tenon [AP-HP], Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), Assistance Publique-Hôpitaux de Paris, Department of Clinical Research and Innovation (AP-HP), Agents Cognitifs et Apprentissage Symbolique Automatique (ACASA), CHU Pitié-Salpêtrière [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)
Rok vydání: 2018
Předmět:
medicine.medical_specialty
Computer science
Polysomnography
[SDV]Life Sciences [q-bio]
Context (language use)
02 engineering and technology
Sleep staging
Machine learning
computer.software_genre
Sleep medicine
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Turing machine
03 medical and health sciences
symbols.namesake
Knowledge-based systems
0302 clinical medicine
Symbolic fusion
Artificial Intelligence
0202 electrical engineering
electronic engineering
information engineering
medicine
Turing
computer.programming_language
Sleep Stages
medicine.diagnostic_test
business.industry
General Engineering
Cognition
Decision rule
3. Good health
Computer Science Applications
symbols
Knowledge based systems
020201 artificial intelligence & image processing
Artificial intelligence
[INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM]
business
computer
Automated decision support systems
030217 neurology & neurosurgery
Sleep stages
Zdroj: Expert Syst. Appl.
Expert Syst. Appl., 2018, 114, pp.414-427
Expert Systems with Applications
Expert Systems with Applications, Elsevier, 2018, 114, pp.414-427. ⟨10.1016/j.eswa.2018.07.023⟩
ISSN: 0957-4174
Popis: International audience; Automatic sleep staging is challenging since several issues need to be addressed. Traditional approaches from literature do not satisfy medical experts since they do not reflect the cognitive process they perform when scoring polysomnographic curves. We propose a new approach that is based on the implementation of medical knowledge by symbolic fusion. Medical knowledge coming from the international clinical practice guidelines for sleep medicine is formalized as a five-layer framework dedicated to data abstraction in order to deliver local and global propositions and support the interpretation of polysomnographic curves. Firstly, features are extracted from raw curves. Then these features are combined to recognize sleep events in accordance with guidelines. Sleep events are then fused into the criteria required to recognize the different sleep stages. Sleep is not homogeneous through the night. The physiological events observed during the night follow a dynamic that needs to be included into an automatic sleep staging system. In order to take this into account, decision rules are selected and applied to recognize a sleep stage according to the current context. Thereby, transitions are considered with interest. In this paper, we propose to use a Turing Machine-like decision process to handle transitions. To interpret the local observations and properly score a given state, the previous state which has been stored in a specific register is used as a context. One of the advantages of following the principles of symbolic fusion is to benefit from the full traceability of the decision. Hence, it makes possible to discuss each final — or intermediate — decision with an expert and check for relevance. The preliminary results are encouraging since agreement rates provided between decisions taken by our automatic approach and human experts are similar to those measured between human experts (average agreement rate = 54.60% / average Cohen's kappa = 0.40) on a dataset of 131 full polysomnographic recordings.
Databáze: OpenAIRE
Externí odkaz: