Cargando…
Machine Learning Identification of Obstructive Sleep Apnea Severity through the Patient Clinical Features: A Retrospective Study
Objectives: To evaluate the role of clinical scores assessing the risk of disease severity in patients with clinical suspicion of obstructive sleep apnea syndrome (OSA). The hypothesis was tested by applying artificial intelligence (AI) to demonstrate its effectiveness in distinguishing between mild...
Autores principales: | , , , , , , , , , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10056063/ https://www.ncbi.nlm.nih.gov/pubmed/36983857 http://dx.doi.org/10.3390/life13030702 |
_version_ | 1785016034180202496 |
---|---|
author | Maniaci, Antonino Riela, Paolo Marco Iannella, Giannicola Lechien, Jerome Rene La Mantia, Ignazio De Vincentiis, Marco Cammaroto, Giovanni Calvo-Henriquez, Christian Di Luca, Milena Chiesa Estomba, Carlos Saibene, Alberto Maria Pollicina, Isabella Stilo, Giovanna Di Mauro, Paola Cannavicci, Angelo Lugo, Rodolfo Magliulo, Giuseppe Greco, Antonio Pace, Annalisa Meccariello, Giuseppe Cocuzza, Salvatore Vicini, Claudio |
author_facet | Maniaci, Antonino Riela, Paolo Marco Iannella, Giannicola Lechien, Jerome Rene La Mantia, Ignazio De Vincentiis, Marco Cammaroto, Giovanni Calvo-Henriquez, Christian Di Luca, Milena Chiesa Estomba, Carlos Saibene, Alberto Maria Pollicina, Isabella Stilo, Giovanna Di Mauro, Paola Cannavicci, Angelo Lugo, Rodolfo Magliulo, Giuseppe Greco, Antonio Pace, Annalisa Meccariello, Giuseppe Cocuzza, Salvatore Vicini, Claudio |
author_sort | Maniaci, Antonino |
collection | PubMed |
description | Objectives: To evaluate the role of clinical scores assessing the risk of disease severity in patients with clinical suspicion of obstructive sleep apnea syndrome (OSA). The hypothesis was tested by applying artificial intelligence (AI) to demonstrate its effectiveness in distinguishing between mild–moderate OSA and severe OSA risk. Methods: A support vector machine model (SVM) was developed from the samples included in the analysis (N = 498), and they were split into 75% for training (N = 373) with the remaining for testing (N = 125). Two diagnostic thresholds were selected for OSA severity: mild to moderate (apnea–hypopnea index (AHI) ≥ 5 events/h and AHI < 30 events/h) and severe (AHI ≥ 30 events/h). The algorithms were trained and tested to predict OSA patient severity. Results: The sensitivity and specificity for the SVM model were 0.93 and 0.80 with an accuracy of 0.86; instead, the logistic regression full mode reported a value of 0.74 and 0.63, respectively, with an accuracy of 0.68. After backward stepwise elimination for features selection, the reduced logistic regression model demonstrated a sensitivity and specificity of 0.79 and 0.56, respectively, and an accuracy of 0.67. Conclusion: Artificial intelligence could be applied to patients with symptoms related to OSA to identify individuals with a severe OSA risk with clinical-based algorithms in the OSA framework. |
format | Online Article Text |
id | pubmed-10056063 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-100560632023-03-30 Machine Learning Identification of Obstructive Sleep Apnea Severity through the Patient Clinical Features: A Retrospective Study Maniaci, Antonino Riela, Paolo Marco Iannella, Giannicola Lechien, Jerome Rene La Mantia, Ignazio De Vincentiis, Marco Cammaroto, Giovanni Calvo-Henriquez, Christian Di Luca, Milena Chiesa Estomba, Carlos Saibene, Alberto Maria Pollicina, Isabella Stilo, Giovanna Di Mauro, Paola Cannavicci, Angelo Lugo, Rodolfo Magliulo, Giuseppe Greco, Antonio Pace, Annalisa Meccariello, Giuseppe Cocuzza, Salvatore Vicini, Claudio Life (Basel) Article Objectives: To evaluate the role of clinical scores assessing the risk of disease severity in patients with clinical suspicion of obstructive sleep apnea syndrome (OSA). The hypothesis was tested by applying artificial intelligence (AI) to demonstrate its effectiveness in distinguishing between mild–moderate OSA and severe OSA risk. Methods: A support vector machine model (SVM) was developed from the samples included in the analysis (N = 498), and they were split into 75% for training (N = 373) with the remaining for testing (N = 125). Two diagnostic thresholds were selected for OSA severity: mild to moderate (apnea–hypopnea index (AHI) ≥ 5 events/h and AHI < 30 events/h) and severe (AHI ≥ 30 events/h). The algorithms were trained and tested to predict OSA patient severity. Results: The sensitivity and specificity for the SVM model were 0.93 and 0.80 with an accuracy of 0.86; instead, the logistic regression full mode reported a value of 0.74 and 0.63, respectively, with an accuracy of 0.68. After backward stepwise elimination for features selection, the reduced logistic regression model demonstrated a sensitivity and specificity of 0.79 and 0.56, respectively, and an accuracy of 0.67. Conclusion: Artificial intelligence could be applied to patients with symptoms related to OSA to identify individuals with a severe OSA risk with clinical-based algorithms in the OSA framework. MDPI 2023-03-05 /pmc/articles/PMC10056063/ /pubmed/36983857 http://dx.doi.org/10.3390/life13030702 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Maniaci, Antonino Riela, Paolo Marco Iannella, Giannicola Lechien, Jerome Rene La Mantia, Ignazio De Vincentiis, Marco Cammaroto, Giovanni Calvo-Henriquez, Christian Di Luca, Milena Chiesa Estomba, Carlos Saibene, Alberto Maria Pollicina, Isabella Stilo, Giovanna Di Mauro, Paola Cannavicci, Angelo Lugo, Rodolfo Magliulo, Giuseppe Greco, Antonio Pace, Annalisa Meccariello, Giuseppe Cocuzza, Salvatore Vicini, Claudio Machine Learning Identification of Obstructive Sleep Apnea Severity through the Patient Clinical Features: A Retrospective Study |
title | Machine Learning Identification of Obstructive Sleep Apnea Severity through the Patient Clinical Features: A Retrospective Study |
title_full | Machine Learning Identification of Obstructive Sleep Apnea Severity through the Patient Clinical Features: A Retrospective Study |
title_fullStr | Machine Learning Identification of Obstructive Sleep Apnea Severity through the Patient Clinical Features: A Retrospective Study |
title_full_unstemmed | Machine Learning Identification of Obstructive Sleep Apnea Severity through the Patient Clinical Features: A Retrospective Study |
title_short | Machine Learning Identification of Obstructive Sleep Apnea Severity through the Patient Clinical Features: A Retrospective Study |
title_sort | machine learning identification of obstructive sleep apnea severity through the patient clinical features: a retrospective study |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10056063/ https://www.ncbi.nlm.nih.gov/pubmed/36983857 http://dx.doi.org/10.3390/life13030702 |
work_keys_str_mv | AT maniaciantonino machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT rielapaolomarco machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT iannellagiannicola machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT lechienjeromerene machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT lamantiaignazio machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT devincentiismarco machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT cammarotogiovanni machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT calvohenriquezchristian machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT dilucamilena machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT chiesaestombacarlos machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT saibenealbertomaria machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT pollicinaisabella machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT stilogiovanna machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT dimauropaola machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT cannavicciangelo machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT lugorodolfo machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT magliulogiuseppe machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT grecoantonio machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT paceannalisa machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT meccariellogiuseppe machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT cocuzzasalvatore machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy AT viciniclaudio machinelearningidentificationofobstructivesleepapneaseveritythroughthepatientclinicalfeaturesaretrospectivestudy |