- author = "Leonardo Lucio Custode and Federico Mento and Sajjad Afrakhteh and Francesco Tursi and Andrea Smargiassi and Riccardo Inchingolo and Tiziano Perrone and Libertario Demi and Giovanni Iacca",
- title = "Neuro-symbolic interpretable {AI} for automatic {COVID-19} patient-stratification based on standardised lung ultrasound data",
- booktitle = "182nd Meeting of the Acoustical Society of America",
- year = "2022",
- volume = "46",
- pages = "Paper 2pBAb6",
- address = "Denver, Colorado, USA",
- month = "23-27 " # may # " 2022",
- publisher = "Acoustical Society of America",
- keywords = "genetic algorithms, genetic programming, grammatical evolution, NSGA-II",
-
URL = "
https://human-competitive.org/sites/default/files/custodeentryform.txt",
-
URL = "
https://human-competitive.org/sites/default/files/custodepapera.pdf",
-
DOI = "
doi:10.1121/2.0001600",
- size = "12 pages",
- abstract = "In the current pandemic, being able to efficiently stratify patients depending on their probability to develop a severe form of COVID-19 can improve the outcome of treatments and optimize the use of the available resources. To this end, recent studies proposed to use deep-networks to perform automatic stratification of COVID-19 patients based on lung ultrasound (LUS) data. In this work, we present a novel neuro-symbolic approach able to provide video-level predictions by aggregating results from frame-level analysis made by deep-networks. Specifically, a decision tree was trained, which provides direct access to the decision process and a high-level explainability. This approach was tested on 1808 LUS videos acquired from 100 patients diagnosed as COVID-19 positive by a RT-PCR swab test. Each video was scored by LUS experts according to a 4-level scoring system specifically developed for COVID-19. This information was used for both the training and testing of the algorithms. A five-folds cross-validation process was used to assess the performance of the presented approach and compare it with results achieved by deep-learning models alone. Results show that this novel approach achieves better performance (82percent of mean prognostic agreement) than a threshold-based ensemble of deep-learning models (78percent of mean prognostic agreement).",
-
notes = "Entered 2023 HUMIES http://acousticalsociety.org/
See also Journal of the Acoustical Society of America 2022 151 A112--A113 https://pubs.aip.org/asa/jasa/article/151/4_Supplement/A112/2838489/Neuro-symbolic-interpretable-AI-for-automatic doi:10.1121/10.0010820",
