Aplicación de inteligencia artificial en el diagnóstico y monitoreo de enfermedades respiratorias asociadas al asbesto: una revisión de alcance

Gómez Ayarza, Víctor Aurelio

Aplicación de inteligencia artificial en el diagnóstico y monitoreo de enfermedades respiratorias asociadas al asbesto: una revisión de alcance

dc.contributor.advisor	Cetina Castillo, Lidy Yadira
dc.contributor.advisor	Giraldo Luna, Clara Margarita
dc.contributor.author	Gómez Ayarza, Víctor Aurelio
dc.contributor.orcid	Gómez Ayarza, Víctor Aurelio [0009-0000-8947-7208]
dc.date.accessioned	2025-02-12T18:22:14Z
dc.date.available	2025-02-12T18:22:14Z
dc.date.issued	2025-01
dc.description.abstract	Objetivo Analizar la aplicación de inteligencia artificial (IA) en el diagnóstico y monitoreo de enfermedades respiratorias relacionadas al asbesto (ERRA), evaluando modelos de aprendizaje automático (ML) para mejorar la precisión diagnóstica y la toma de decisiones clínicas en poblaciones expuestas. Metodología Se realizó una revisión de alcance con la metodología JBI y el protocolo PRISMA-ScR. La búsqueda en bases de datos científicas incluyó estudios entre 2019 y 2024 sobre IA aplicada al diagnóstico y monitoreo de ERRA. De 1095 estudios, se seleccionaron 40 relevantes tras aplicar filtros de inclusión, evaluando tecnologías, métricas y poblaciones. Resultados Los modelos de IA, incluyendo redes neuronales convolucionales (CNN, por sus siglas en inglés) y máquinas de soporte vectorial (SVM, por sus siglas en inglés), alcanzaron precisiones diagnósticas superiores al 90% en enfermedades como asbestosis y mesotelioma pleural. Herramientas como MesoNet y biomarcadores genéticos permitieron diagnósticos no invasivos y una mejor estratificación de riesgo en pacientes expuestos al asbesto. Conclusiones La IA ha demostrado su capacidad para optimizar el diagnóstico y monitoreo de ERRA. Sin embargo, persisten desafíos en la calidad de datos, generalización de modelos y equidad en el acceso. Para maximizar su impacto, es crucial el desarrollo de infraestructuras de datos accesibles, estándares de validación y colaboraciones interdisciplinarias que faciliten su integración en la práctica clínica.
dc.description.abstractenglish	Objective To analyze the application of artificial intelligence (AI) in the diagnosis and monitoring of asbestos-related respiratory diseases (ARRD), evaluating machine learning (ML) models to improve diagnostic accuracy and clinical decision-making in exposed populations. Methodology A scoping review was conducted using the JBI methodology and PRISMA-ScR protocol. The search in scientific databases included studies from 2019 to 2024 on AI applied to the diagnosis and monitoring of ARRD. Out of 1095 studies, 40 relevant ones were selected after applying inclusion filters, evaluating technologies, metrics, and populations. Results AI models, including convolutional neural networks (CNN) and support vector machines (SVM), achieved diagnostic accuracies above 90% for diseases such as asbestosis and pleural mesothelioma. Tools like MesoNet and genetic biomarkers enabled non-invasive diagnoses and improved risk stratification in asbestos-exposed patients. Conclusions AI has demonstrated its ability to optimize the diagnosis and monitoring of ARRD. However, challenges remain regarding data quality, model generalization, and equitable access. To maximize its impact, it is crucial to develop accessible data infrastructures, validation standards, and interdisciplinary collaborations to facilitate its integration into clinical practice.
dc.description.degreelevel	Especialización	spa
dc.description.degreename	Especialista en Higiene Industrial	spa
dc.format.mimetype	application/pdf
dc.identifier.instname	instname:Universidad El Bosque	spa
dc.identifier.reponame	reponame:Repositorio Institucional Universidad El Bosque	spa
dc.identifier.repourl	repourl:https://repositorio.unbosque.edu.co
dc.identifier.uri	https://hdl.handle.net/20.500.12495/13938
dc.language.iso	es
dc.publisher.faculty	Facultad de Medicina	spa
dc.publisher.grantor	Universidad El Bosque	spa
dc.publisher.program	Especialización en Higiene Industrial	spa
dc.relation.references	1. Lipman K, de Gooijer CJ, Boellaard TN, van der Heijden F, Beets-Tan RGH, Bodalal Z, et al. Artificial intelligence-based diagnosis of asbestosis: analysis of a database with applicants for asbestosis state aid. Eur Radiol. 2023;33(5):3557–65. https://doi.org/10.1007/s00330-022-09304-2
dc.relation.references	2. Lima LA de, Abe JM, Martinez AAG, Sakamoto LS, de Lima LP. Application of architecture using AI in the training of a set of pixels of the image at aid decision-making diagnostic cancer. Procedia Comput Sci [Internet]. 2021; 192:1740–9. https://doi.org/10.1016/j.procs.2021.08.179
dc.relation.references	3. Alam TM, Shaukat K, Hameed IA, Khan WA, Sarwar MU, Iqbal F, et al. A novel framework for prognostic factors identification of malignant mesothelioma through association rule mining. Biomed Signal Process Control [Internet]. 2021; 68:102726. https://doi.org/10.1016/j.bspc.2021.102726
dc.relation.references	4. Chicco D, Rovelli C. Computational prediction of diagnosis and feature selection on mesothelioma patient health records. PLoS One. 2019;14(1). https://doi.org/10.1371/journal.pone.0208737
dc.relation.references	5. Koul A, Bawa RK, Kumar Y. Artificial Intelligence Techniques to Predict the Airway Disorders Illness: A Systematic Review. Archives of Computational Methods in Engineering. 2023 Mar 1;30(2):831–64. https://doi.org/10.1007/s11831-022-09818-4
dc.relation.references	6. Min Kim H, Ko T, Young Choi I, Myong JP. Asbestosis diagnosis algorithm combining the lung segmentation method and deep learning model in computed tomography image. Int J Med Inform [Internet]. 2022; 158:104667. https://doi.org/10.1016/j.ijmedinf.2021.
dc.relation.references	7. Zadsafar F, Tabrizchi H, Parvizpour S, Razmara J, Lotfi S. A model for mesothelioma cancer diagnosis based on feature selection using Harris hawk optimization algorithm. Computer Methods and Programs in Biomedicine Update [Internet]. 2022; 2:100078. http://dx.doi.org/10.1016/j.cmpbup.2022.100078
dc.relation.references	8. Galateau Salle F, Le Stang N, Tirode F, Courtiol P, Nicholson AG, Tsao MS, et al. Comprehensive Molecular and Pathologic Evaluation of Transitional Mesothelioma Assisted by Deep Learning Approach: A Multi-Institutional Study of the International Mesothelioma Panel from the MESOPATH Reference Center. Journal of Thoracic Oncology [Internet]. 2020;15(6):1037–53. https://doi.org/10.1016/j.jtho.2020.01.025
dc.relation.references	9. Di Gilio A, Catino A, Lombardi A, Palmisani J, Facchini L, Mongelli T, et al. Breath Analysis for Early Detection of Malignant Pleural Mesothelioma: Volatile Organic Compounds (VOCs) Determination and Possible Biochemical Pathways. Cancers (Basel). 2020;12(5). https://doi.org/10.3390/cancers12051262
dc.relation.references	10. Yang F, Tang ZR, Chen J, Tang M, Wang S, Qi W, et al. Pneumoconiosis computer aided diagnosis system based on X-rays and deep learning. BMC Med Imaging. 2021 Dec 1;21(1). https://doi.org/10.1186/s12880-021-00723-z
dc.relation.references	11. Agarwal S, Yadav AS, Dinesh V, Vatsav KSS, Prakash KSS, Jaiswal S. By artificial intelligence algorithms and machine learning models to diagnosis cancer. Mater Today Proc [Internet]. 2023;80:2969–75. http://dx.doi.org/10.1016/j.matpr.2021.07.088
dc.relation.references	12. Adams SJ, Stone E, Baldwin DR, Vliegenthart R, Lee P, Fintelmann FJ. Lung cancer screening. The Lancet [Internet]. 2023;401(10374):390–408. https://doi.org/10.1016/s0140-6736(22)01694-4
dc.relation.references	13. Huang Y, Si Y, Hu B, Zhang Y, Wu S, Wu D, et al. Transformer-based factorized encoder for classification of pneumoconiosis on 3D CT images. Comput Biol Med [Internet]. 2022; 150:106137. https://doi.org/10.1016/j.compbiomed.2022.106137
dc.relation.references	14. Yin Y, Cui Q, Zhao J, Wu Q, Sun Q, Wang H qiang, et al. Integrated Bioinformatics and Machine Learning Analysis Identify ACADL as a Potent Biomarker of Reactive Mesothelial Cells. Am J Pathol [Internet]. 2024;194(7):1294–305. https://doi.org/10.1016/j.ajpath.2024.03.013
dc.relation.references	15. Alam MS, Wang D, Sowmya A. DLA-Net: dual lesion attention network for classification of pneumoconiosis using chest X-ray images. Sci Rep. 2024 Dec 1;14(1). https://doi.org/10.1038/s41598-024-61024-3
dc.relation.references	16. Eastwood M, Marc ST, Gao X, Sailem H, Offman J, Karteris E, et al. Malignant Mesothelioma subtyping via sampling driven multiple instance prediction on tissue image and cell morphology data. Artif Intell Med [Internet]. 2023; 143:102628. https://doi.org/10.1016/j.artmed.2023.102628
dc.relation.references	17. Thakral G, Gambhir S. Early Detection of Lung Cancer with Low-Dose CT Scan Using Artificial Intelligence: A Comprehensive Survey. SN Comput Sci. 2024 Jun 1;5(5). http://dx.doi.org/10.1007/s42979-024-02811-7
dc.relation.references	18. Shenouda M, Gudmundsson E, Li F, Straus CM, Kindler HL, Dudek AZ, et al. Convolutional Neural Networks for Segmentation of Pleural Mesothelioma: Analysis of Probability Map Thresholds (CALGB 30901, Alliance). Journal of Imaging Informatics in Medicine [Internet]. 2024 Sep 12 [cited 2024 Nov 19]. https://doi.org/10.1007/s10278-024-01092-z
dc.relation.references	19. Moirangthem A, Lepcha OS, Panigrahi R, Brahma B, Bhoi AK. Early Malignant Mesothelioma Detection Using Ensemble of Naive Bayes Under Decorate Ensemble Framework. Journal of The Institution of Engineers (India): Series B. 2024 Apr 1;105(2):251–64. http://dx.doi.org/10.1007/s40031-023-00988-8
dc.relation.references	20. Hakkarainen AJ, Randen-Brady R, Wolff H, Mäyränpää MI, Sajantila A. Deep Learning Neural Network-Guided Detection of Asbestos Bodies in Bronchoalveolar Lavage Samples. Acta Cytol. 2023. https://doi.org/10.1159/000534149
dc.relation.references	21. Courtiol P, Maussion C, Moarii M, Pronier E, Pilcer S, Sefta M, et al. Deep learning-based classification of mesothelioma improves prediction of patient outcome. Nat Med. 2019 Oct 1;25(10):1519–25. https://doi.org/10.1038/s41591-019-0583-3
dc.relation.references	22. Zauderer MG, Martin A, Egger J, Rizvi H, Offin M, Rimner A, et al. The use of a next-generation sequencing-derived machine-learning risk-prediction model (OncoCast-MPM) for malignant pleural mesothelioma: a retrospective study. Lancet Digit Health [Internet]. 2021;3(9): e565–76. https://doi.org/10.1016/s2589-7500(21)00104-7
dc.relation.references	23. Li N, Yang CX, Zhou SC, Song SY, Jin YY, Wang D, et al. Combination of Plasma-Based Metabolomics and Machine Learning Algorithm Provides a Novel Diagnostic Strategy for Malignant Mesothelioma. DIAGNOSTICS. 2021;11(7). https://doi.org/10.3390/diagnostics11071281
dc.relation.references	24. Xie XJ, Liu SY, Chen JY, Zhao Y, Jiang J, Wu L, et al. Development of unenhanced CT-based imaging signature for BAP1 mutation status prediction in malignant pleural mesothelioma: Consideration of 2D and 3D segmentation. Lung Cancer [Internet]. 2021; 157:30–9. https://doi.org/10.1016/j.lungcan.2021.04.023
dc.relation.references	25. W GLKB, Boellaard TN, J de GC, Bogveradze N, Hong EK, Landolfi F, et al. Artificial Intelligence-based Quantification of Pleural Plaque Volume and Association With Lung Function in Asbestos-exposed Patients. J Thorac Imaging. 2024. https://doi.org/10.1097/rti.0000000000000759
dc.relation.references	26. Benlala I, D DSB, Dournes G, Menant M, Gramond C, Thaon I, et al. Deep Learning for the Automatic Quantification of Pleural Plaques in Asbestos-Exposed Subjects. Int J Environ Res Public Health. 2022. https://doi.org/10.3390/ijerph19031417
dc.relation.references	27. Li Y, Cai B, Wang B, Lv Y, He W, Xie X, et al. Differentiating malignant pleural mesothelioma and metastatic pleural disease based on a machine learning model with primary CT signs: A multicentre study. Heliyon [Internet]. 2022;8(11): e11383. https://doi.org/10.1016/j.heliyon.2022.e11383
dc.relation.references	28. Peters MDJ, Marnie C, Tricco AC, Pollock D, Munn Z, Alexander L, et al. Updated methodological guidance for the conduct of scoping reviews. JBI Evid Synth. 2020 Oct 1;18(10):2119–26. https://doi.org/10.11124/jbies-20-00167
dc.relation.references	29. Tricco AC, Lillie E, Zarin W, O’Brien KK, Colquhoun H, Levac D, et al. PRISMA extension for scoping reviews (PRISMA-ScR): Checklist and explanation. Ann Intern Med [Internet]. 2018 Oct 2 [cited 2025 Jan 22];169(7):467–73. https://doi.org/10.7326/m18-0850
dc.relation.references	30. Zhang Q, Wang H, Yoon SW, Won D, Srihari K. Lung Nodule Diagnosis on 3D Computed Tomography Images Using Deep Convolutional Neural Networks. Procedia Manuf [Internet]. 2019; 39:363–70. http://dx.doi.org/10.1016/j.promfg.2020.01.375
dc.relation.references	31. Sousa AM, Castelo-Fernandez C, Osaku D, Bagatin E, Reis F, Falcao AX. An Approach for Asbestos-related Pleural Plaque Detection. Annu Int Conf IEEE Eng Med Biol Soc. 2020. https://doi.org/10.1109/embc44109.2020.9176605
dc.relation.references	32. Huang ML, Chou YC. Combining a gravitational search algorithm, particle swarm optimization, and fuzzy rules to improve the classification performance of a feed-forward neural network. Comput Methods Programs Biomed [Internet]. 2019; 180:105016. https://doi.org/10.1016/j.cmpb.2019.105016
dc.relation.references	33. Alam TM, Shaukat K, Mahboob H, Sarwar MU, Iqbal F, Nasir A, et al. A Machine Learning Approach for Identification of Malignant Mesothelioma Etiological Factors in an Imbalanced Dataset. COMPUTER JOURNAL. 2022;65(7):1740–51. https://doi.org/10.1093/comjnl/bxab015
dc.relation.references	34. Gupta S, Gupta MK. Computational Model for Prediction of Malignant Mesothelioma Diagnosis. COMPUTER JOURNAL. 2023;66(1):86–100. http://dx.doi.org/10.1093/comjnl/bxab146
dc.relation.references	35. Eastwood M, Sailem H, Marc ST, Gao X, Offman J, Karteris E, et al. MesoGraph: Automatic profiling of mesothelioma subtypes from histological images. Cell Rep Med [Internet]. 2023;4(10):101226. https://doi.org/10.1016/j.xcrm.2023.101226
dc.relation.references	36. Devnath L, Luo S, Summons P, Wang D. Automated detection of pneumoconiosis with multilevel deep features learned from chest X-Ray radiographs. Comput Biol Med [Internet]. 2021; 129:104125. https://doi.org/10.1016/j.compbiomed.2020.104125
dc.relation.references	37. Jurmeister P, Leitheiser M, Wolkenstein P, Klauschen F, Capper D, Brcic L. DNA methylation-based machine learning classification distinguishes pleural mesothelioma from chronic pleuritis, pleural carcinosis, and pleomorphic lung carcinomas. Lung Cancer [Internet]. 2022; 170:105–13. https://doi.org/10.1016/j.lungcan.2022.06.008
dc.relation.references	38. Cohen MW, Ghidotti A, Regazzoni D. Bi-level Analysis of Computed Tomography Images of Malignant Pleural Mesothelioma: Deep Learning-Based Classification and Subsequent Three-Dimensional Reconstruction. J Comput Inf Sci Eng. 2024;24(6). https://doi.org/10.1115/1.4064410
dc.relation.references	39. Yang HY. Prediction of pneumoconiosis by serum and urinary biomarkers in workers exposed to asbestos-contaminated minerals. PLoS One. 2019;14(4). https://doi.org/10.1371/journal.pone.0214808
dc.relation.references	40. Zhang L, Rong R, Li Q, Yang DM, Yao B, Luo D, et al. A deep learning-based model for screening and staging pneumoconiosis. Sci Rep. 2021 Dec 1;11(1). https://doi.org/10.1038/s41598-020-77924-z
dc.relation.references	41. Alam MdS, Wang D, Sowmya A. AMFP-net: Adaptive multi-scale feature pyramid network for diagnosis of pneumoconiosis from chest X-ray images. Artif Intell Med [Internet]. 2024; 154:102917. https://doi.org/10.1016/j.artmed.2024.102917
dc.relation.references	42. Zhang Y, Qian F, Teng J, Wang H, Yu H, Chen Q, et al. China lung cancer screening (CLUS) version 2.0 with new techniques implemented: Artificial intelligence, circulating molecular biomarkers and autofluorescence bronchoscopy. Lung Cancer [Internet]. 2023; 181:107262. https://doi.org/10.1016/j.lungcan.2023.107262
dc.rights	Attribution-NonCommercial-ShareAlike 4.0 International	en
dc.rights.accessrights	https://purl.org/coar/access_right/c_abf2
dc.rights.accessrights	info:eu-repo/semantics/openAccess
dc.rights.local	Acceso abierto	spa
dc.rights.uri	http://creativecommons.org/licenses/by-nc-sa/4.0/
dc.subject	Inteligencia artificial
dc.subject	Aprendizaje automático
dc.subject	Asbestosis
dc.subject	Mesotelioma maligno
dc.subject	Neoplasia pulmonar
dc.subject	Redes neurales de la computación
dc.subject	Biomarcadores de tumor
dc.subject	Radiografía torácica
dc.subject	Tomografía computarizada por rayos X
dc.subject	Minería de datos
dc.subject.keywords	Artificial intelligence
dc.subject.keywords	Machine learning
dc.subject.keywords	Asbestosis
dc.subject.keywords	Malignant mesothelioma
dc.subject.keywords	Lung neoplasm
dc.subject.keywords	Convolutional neural network
dc.subject.keywords	Tumor biomarkers
dc.subject.keywords	Thoracic radiography
dc.subject.keywords	X-ray computed tomography
dc.subject.keywords	Data mining
dc.subject.nlm	WA450
dc.title	Aplicación de inteligencia artificial en el diagnóstico y monitoreo de enfermedades respiratorias asociadas al asbesto: una revisión de alcance
dc.title.translated	Application of Artificial Intelligence in the diagnosis and monitoring of asbestos-related respiratory diseases: A scoping review
dc.type.coar	https://purl.org/coar/resource_type/c_7a1f
dc.type.coarversion	https://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.driver	info:eu-repo/semantics/bachelorThesis
dc.type.hasversion	info:eu-repo/semantics/acceptedVersion
dc.type.local	Tesis/Trabajo de grado - Monografía - Especialización	spa