medigraphic.com
ISSN 2007-1523 (Electronic)
Revista Mexicana de Trastornos Alimentarios

2024, Number 2

<< Back Next >>

Revista Mexicana de Trastornos Alimentarios 2024; 14 (2)

Analysis of drowsiness and health habits in patients with sleep apnea using Artificial Neural Network

Aguilera-Sosa V, Arias GL, Santa-Miranda R, Pérez VNM

Language: Spanish
References: 25
Page: 188-199
PDF size: 542.64 Kb.


ABSTRACT

Obesity is one of the main risk factors for Obstructive Sleep Apnea Syndrome (OSAS), which in turn causes daytime sleepiness. Habits and lifestyles, together with sociodemographic factors, can explain the levels of sleepiness in relation to OSAS. Objective: to generate an Artificial Neural Network to identify the difference in the synaptic weights of health habits, which includes over and under intake, BMI, and sociodemographic factors, in n=140 of patients between 18-65 years of age who attended to the Sleep Disorders Clinic, UNAM, BMI ≥25 kg/m2 and with severe to moderate OSAS, treated with CPAP (continuous positive airway pressure). Method: convenience, cross-sectional, exploratory, quantitative, and explanatory study. diagnosed with moderate to severe OSAS. Results: BMI, over-eating, cravings, under-eating, and expectations for weight loss each have synaptic weights by ›60%. Of the sociodemographic variables, schooling and suffering from some comorbidity, had synaptic weights of 46% each. Conclusions: the BMI, and health behaviors, with cut-off points at risk, explain sleepiness. These findings allow us to identify, with non-linear models, the separate importance of psychological and sociodemographic variables in sleepiness in subjects with OSAS.


REFERENCES

  1. Bonsignore M. R. (2022). Obesity and Obstructive SleepApnea. Handbook of experimental pharmacology, 274, 181–201. https://doi.org/10.1007/164_2021_558

  2. Castro, A. I., Gomez-Arbelaez, D., Crujeiras, A. B., Granero,R., Aguera, Z., Jimenez-Murcia, S., Sajoux, I., Lopez-Jaramillo,P., Fernandez-Aranda, F., & Casanueva, F. F.(2018). Effect of A Very Low-Calorie Ketogenic Diet onFood and Alcohol Cravings, Physical and Sexual Activity,Sleep Disturbances, and Quality of Life in ObesePatients. Nutrients, 10 (10), 1348. https://doi.org/10.3390/nu10101348

  3. Di, H., Guo, Y., Daghlas, I., Wang, L., Liu, G., Pan, A., Liu,L., & Shan, Z. (2022). Evaluation of Sleep Habits andDisturbances Among US Adults, 2017-2020. JAMAnetwork open, 5(11), e2240788. https://doi.org/10.1001/jamanetworkopen.2022.40788

  4. Dobbie, L.J., Coelho, C., Crane, J. et al. (2023). Clinical evaluationof patients living with obesity. Intern Emerg Med.,18, 1273–1285 https://doi.org/10.1007/s11739-023-03263-2

  5. Duong-Quy, S., Dang Thi Mai, K., Tran Van, N., NguyenXuan Bich, H., Hua-Huy, T., Chalumeau, F…Martin, F.(2018). Étude de la prévalence du syndrome d’apnéesobstructives du sommeil au Vietnam [Study about theprevalence of the obstructive sleep apnoea syndromein Vietnam]. Revue des maladies respiratoires, 35(1), 14–24.https://doi.org/10.1016/j.rmr.2017.10.006

  6. Eyvazlou, M., Hosseinpouri, M., Mokarami, H., Gharibi,V., Jahangiri, M., Cousins, R., Nikbakht, H. A., & Barkhordari,A. (2020). Prediction of metabolic syndromebased on sleep and work-related risk factors using anartificial neural network. BMC endocrine disorders, 20(1),169. https://doi.org/10.1186/s12902-020-00645-x

  7. Gagliano, A., Puligheddu, M., Ronzano, N., Congiu, P., Tanca,M. G., Cursio, I., Carucci, S., Sotgiu, S., Grossi, E., &Zuddas, A. (2021). Artificial Neural Networks Analysisof polysomnographic and clinical features in PediatricAcute-Onset Neuropsychiatric Syndrome (PANS):from sleep alteration to “Brain Fog”. Nature and scienceof sleep, 13, 1209–1224. https://doi.org/10.2147/NSS.S300818

  8. Gallego-Gómez, J. I., González-Moro, M. T. R.,González-Moro, J. M. R., Vera-Catalán, T., Balanza, S.,Simonelli-Muñoz, A. J., & Rivera-Caravaca, J. M. (2021).Relationship between sleep habits and academic performancein university Nursing students. BMC nursing,20(1), 100. https://doi.org/10.1186/s12912-021-00635-x.

  9. Tlatoa-Ramírez, H.L. Ocaña-Servín, M.L. Márquez-López, J.Bermeo-Méndez, A.F. Gallo-Avalos (2015). El género, unfactor determinante en el riesgo de somnolencia. Medicinae Investigación, 3(1):17-21. http://dx.doi.org/10.1016/j.mei.2014.06.003

  10. Kalmbach, D. A., Cheng, P., Sangha, R., O’Brien, L. M.,Swanson, L. M., Palagini, L., Bazan, L. F., Roth, T., &Drake, C. L. (2019). Insomnia, Short Sleep, And SnoringIn Mid-To-Late Pregnancy: Disparities Related ToPoverty, Race, And Obesity. Nature and science of sleep, 11,301–315. https://doi.org/10.2147/NSS.S226291

  11. Kuvat, N., Tanriverdi, H., & Armutcu, F. (2020). The relationshipbetween obstructive sleep apnea syndromeand obesity: A new perspective on the pathogenesis interms of organ crosstalk. The clinical respiratory journal,14(7), 595–604. https://doi.org/10.1111/crj.13175

  12. Li, A., Quan, S. F., Silva, G. E., Perfect, M. M., & Roveda,J. M. (2018). A Novel Artificial Neural Network BasedSleep-Disordered Breathing Screening Tool. Journalof clinical sleep medicine: JCSM: official publication ofthe American Academy of Sleep Medicine, 14(6), 1063–1069.https://doi.org/10.5664/jcsm.7182

  13. López-Meza, Elmer, Olmos-Muñoz, Adriana, Vargas-Cañas,Steven, Ramírez-Bermúdez, Jesús, López-Gómez,Mario, Corona, Teresa, & Volkers, Georgina. (2006).Somnolencia en la ciudad de México. Gaceta médicade México, 142(3), 201-203. http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S0016-38132006000300004&lng=es&tlng=e

  14. Malafeev, A., Laptev, D., Bauer, S., Omlin, X., Wierzbicka,A., Wichniak, A., Jernajczyk, W., Riener, R., Buhmann,J., & Achermann, P. (2018). Automatic Human SleepStage Scoring Using Deep Neural Networks. Frontiersin neuroscience, 12, 781. https://doi.org/10.3389/fnins.2018.00781

  15. Mena Frau, Carlos, & Montecinos Guajardo, Rodrigo. (2006).Comparación de redes neuronales y regresión lineal paraestimar productividad de sitio en plantaciones forestales,utilizando geomática. Bosque (Valdivia), 27(1), 35-43.https://dx.doi.org/10.4067/S0717-92002006000100004

  16. Méndez-Peña, B. I., Murillo-Tovar, M. M., Leija-Alva, G.,Montufar Burgos, I. I., Serena-Alvarado, A., Durán-Arciniega,R. S., Pérez-Vielma, N. M., & Aguilera-Sosa, V.R. (2022). Artificial neural networks model: Neuropsychologicalvariables and their relationship with body fatpercentage in adults: Variables neuropsicológicas y surelación con el porcentaje de grasa corporal en adultos.Revista Mexicana de Trastornos Alimentarios, 12(1), 61-70.https://doi.org/10.22201/fesi.20071523e.2022.1.718

  17. Morales, Y., Zamora, Y., Vásquez, P., Porras, M., Bárzaga, J.,López, R. (2018). Comparación entre redes neuronalesartificiales y regresión múltiple para la predicción de larugosidad superficial en el torneado en seco. Ingenius,19, 79-88. doi: https://doi.org/10.17163/ings.n19.2018.08.

  18. O’Donnell W. E. y Warren W. L. (2007). Cuestionario de SobreingestaAlimentaria (OQ) (trad. de Olivare y Mancilla).México: Manual Moderno.

  19. Rodrigues, G. D., Fiorelli, E. M., Furlan, L., Montano, N.,& Tobaldini, E. (2021). Obesity and sleep disturbances:The “chicken or the egg” question. European journalof internal medicine, 92, 11–16. https://doi.org/10.1016/j.ejim.2021.04.017

  20. Sáenz Bajo, N., & Alvaro Ballesteros, M. (2002). Redes neuronales:concepto, aplicaciones y utilidad en medicina[Neural networks: concept, applications and usefulnessin medicine]. Atencion primaria, 30(2), 119–120. https://doi.org/10.1016/s0212-6567(02)78981-6

  21. Sandoval-Sandoval R., Alcalá-Lozano R., Herrera-JiménezI. & Jiménez-Genchi A. (2013). Validación de la escalade somnolencia de Epworth en población mexicana.Gaceta medica de México, 149(4), 409–416. PMID: 23999632

  22. Sierra JC., Sánchez AI., BuelaCasalG., Ambrosio I. &ViruésOrtegaJ. (2007). Predictores del nivel de somnolenciaen pacientes con Apnea Obstructiva del Sueño.Rev. Ecuat. Neurol, 15 (23):1-8. https://revecuatneurol.com/wp-content/uploads/2015/06/Predictor.pdf)

  23. Teferra, R. A., Grant, B. J., Mindel, J. W., Siddiqi, T. A.,Iftikhar, I. H., Ajaz, F., Aliling, J. P., Khan, M. S.,Hoffmann, S. P., & Magalang, U. J. (2014). Cost minimizationusing an artificial neural network sleep apneaprediction tool for sleep studies. Annals of the AmericanThoracic Society, 11(7), 1064–1074. https://doi.org/10.1513/AnnalsATS.201404-161OC

  24. Thorn, C. E., Knight, B., Pastel, E., McCulloch, L. J., Patel,B., Shore, A. C., & Kos, K. (2017). Adipose tissue is influencedby hypoxia of obstructive sleep apnea syndromeindependent of obesity. Diabetes & metabolism, 43(3),240–247. https://doi.org/10.1016/j.diabet.2016.12.002

  25. Yeckle, J., & Manian, V. (2023). Automated Sleep StageClassification in Home Environments: An Evaluationof Seven Deep Neural Network Architectures. Sensors(Basel, Switzerland), 23(21), 8942. https://doi.org/10.3390/s23218942




2020     |     www.medigraphic.com