Imitating the respiratory activity of the brain stem by using artificial neural networks: exploratory study on an animal model of lactic acidosis and proof of concept.

Autor: Perchiazzi G; The Hedenstierna Laboratory, Department of Surgical Sciences, Uppsala University, Uppsala, Sweden. gaetano.perchiazzi@uu.se.; Department of Anesthesia, Operation and Intensive Care, Uppsala University Hospital, Uppsala, Sweden. gaetano.perchiazzi@uu.se.; Hedenstierna Laboratoriet, Akademiska sjukhuset ing 40 3 tr, Uppsala, 75185, Sweden. gaetano.perchiazzi@uu.se., Kawati R; Department of Anesthesia, Operation and Intensive Care, Uppsala University Hospital, Uppsala, Sweden., Pellegrini M; The Hedenstierna Laboratory, Department of Surgical Sciences, Uppsala University, Uppsala, Sweden.; Department of Anesthesia, Operation and Intensive Care, Uppsala University Hospital, Uppsala, Sweden., Liangpansakul J; The Hedenstierna Laboratory, Department of Surgical Sciences, Uppsala University, Uppsala, Sweden., Colella R; Ministry of Education and Merit, Rome, Italy., Bollella P; Department of Chemistry, University of Bari Aldo Moro, Bari, Italy., Rangaiah P; Department of Electrical Engineering, Solid-State Electronics, Uppsala University, Uppsala, Sweden., Cannone A; Department of Anaesthesia and Intensive Care, 'Madonna delle Grazie' Hospital, Matera, Italy., Venkataramana DH; Department of Information Technology, Uppsala University, Uppsala, Sweden., Perez M; Department of Electrical Engineering, Solid-State Electronics, Uppsala University, Uppsala, Sweden., Stramaglia S; Dipartimento Interateneo di Fisica, Università degli Studi di Bari, Rome, Italy.; Istituto Nazionale di Fisica Nucleare, Sezione di Bari, Italy., Torsi L; Department of Chemistry, University of Bari Aldo Moro, Bari, Italy., Bellotti R; Dipartimento Interateneo di Fisica, Università degli Studi di Bari, Rome, Italy.; Istituto Nazionale di Fisica Nucleare, Sezione di Bari, Italy., Augustine R; Department of Electrical Engineering, Solid-State Electronics, Uppsala University, Uppsala, Sweden.
Jazyk: angličtina
Zdroj: Journal of clinical monitoring and computing [J Clin Monit Comput] 2024 Dec; Vol. 38 (6), pp. 1269-1280. Date of Electronic Publication: 2024 Aug 20.
DOI: 10.1007/s10877-024-01208-4
Abstrakt: Artificial neural networks (ANNs) are versatile tools capable of learning without prior knowledge. This study aims to evaluate whether ANN can calculate minute volume during spontaneous breathing after being trained using data from an animal model of metabolic acidosis. Data was collected from ten anesthetized, spontaneously breathing pigs divided randomly into two groups, one without dead space and the other with dead space at the beginning of the experiment. Each group underwent two equal sequences of pH lowering with pre-defined targets by continuous infusion of lactic acid. The inputs to ANNs were pH, ΔPaCO 2 (variation of the arterial partial pressure of CO 2 ), PaO 2 , and blood temperature which were sampled from the animal model. The output was the delta minute volume (ΔV M ), (the change of minute volume as compared to the minute volume the animal had at the beginning of the experiment). The ANN performance was analyzed using mean squared error (MSE), linear regression, and the Bland-Altman (B-A) method. The animal experiment provided the necessary data to train the ANN. The best architecture of ANN had 17 intermediate neurons; the best performance of the finally trained ANN had a linear regression with R 2 of 0.99, an MSE of 0.001 [L/min], a B-A analysis with bias ± standard deviation of 0.006 ± 0.039 [L/min]. ANNs can accurately estimate ΔV M using the same information that arrives at the respiratory centers. This performance makes them a promising component for the future development of closed-loop artificial ventilators.
Competing Interests: Declarations. Compliance with ethical standards: The study received approval from the local institutional review board for the care of animal subjects. The animals were handled in accordance with the regulations of the Swedish Board for Laboratory Animals. The animal experiments were performed at the Hedenstierna Laboratory of Uppsala University, Sweden. Statement on artificial intelligence: No method of creative artificial intelligence was used to generate the text or the figures of the present report. Competing interests: The authors declare no competing interests.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz: