Una introducción a las aplicaciones de la inteligencia artificial en Medicina: Aspectos históricos

En un sentido amplio la inteligencia artificial y el aprendizaje automático se ha aplicado a los datos médicos desde los inicios de la informática dado el profundo arraigo de esta área en la innovación, pero los últimos años han sido testigo de una generación cada vez mayor de datos relacionados con...

Full description

Autores:
Arias Vanegas, Víctor Alfonso
Salazar Vílchez, Juan
Garicano Soto, Carlos Hernando
Contreras Velásquez, Julio César
Chacón Rangel, José Gerardo
Chacín González, Maricarmen
Añez, Roberto J.
Rojas Quintero, Joselyn Joanna
Bermúdez Pirela, Valmore José
Tipo de recurso:
Article of investigation
Fecha de publicación:
2019
Institución:
Tecnológico de Antioquia
Repositorio:
Repositorio Tdea
Idioma:
spa
OAI Identifier:
oai:dspace.tdea.edu.co:tdea/2821
Acceso en línea:
https://dspace.tdea.edu.co/handle/tdea/2821
Palabra clave:
Innovación
Innovation
Inovação
Inteligencia Artificial
Artificial Intelligence
Inteligência Artificial
Registros Médicos
Medical Records
Databases
Base de datos
Rights
openAccess
License
https://creativecommons.org/licenses/by-nd/4.0/
id RepoTdea2_14a48462a3829d174f83f934a09bf24f
oai_identifier_str oai:dspace.tdea.edu.co:tdea/2821
network_acronym_str RepoTdea2
network_name_str Repositorio Tdea
repository_id_str
dc.title.none.fl_str_mv Una introducción a las aplicaciones de la inteligencia artificial en Medicina: Aspectos históricos
dc.title.translated.none.fl_str_mv An introduction to artificial intelligence applications in medicine: Historical aspects
title Una introducción a las aplicaciones de la inteligencia artificial en Medicina: Aspectos históricos
spellingShingle Una introducción a las aplicaciones de la inteligencia artificial en Medicina: Aspectos históricos
Innovación
Innovation
Inovação
Inteligencia Artificial
Artificial Intelligence
Inteligência Artificial
Registros Médicos
Medical Records
Databases
Base de datos
title_short Una introducción a las aplicaciones de la inteligencia artificial en Medicina: Aspectos históricos
title_full Una introducción a las aplicaciones de la inteligencia artificial en Medicina: Aspectos históricos
title_fullStr Una introducción a las aplicaciones de la inteligencia artificial en Medicina: Aspectos históricos
title_full_unstemmed Una introducción a las aplicaciones de la inteligencia artificial en Medicina: Aspectos históricos
title_sort Una introducción a las aplicaciones de la inteligencia artificial en Medicina: Aspectos históricos
dc.creator.fl_str_mv Arias Vanegas, Víctor Alfonso
Salazar Vílchez, Juan
Garicano Soto, Carlos Hernando
Contreras Velásquez, Julio César
Chacón Rangel, José Gerardo
Chacín González, Maricarmen
Añez, Roberto J.
Rojas Quintero, Joselyn Joanna
Bermúdez Pirela, Valmore José
dc.contributor.author.none.fl_str_mv Arias Vanegas, Víctor Alfonso
Salazar Vílchez, Juan
Garicano Soto, Carlos Hernando
Contreras Velásquez, Julio César
Chacón Rangel, José Gerardo
Chacín González, Maricarmen
Añez, Roberto J.
Rojas Quintero, Joselyn Joanna
Bermúdez Pirela, Valmore José
dc.subject.agrovoc.none.fl_str_mv Innovación
Innovation
Inovação
topic Innovación
Innovation
Inovação
Inteligencia Artificial
Artificial Intelligence
Inteligência Artificial
Registros Médicos
Medical Records
Databases
Base de datos
dc.subject.decs.none.fl_str_mv Inteligencia Artificial
Artificial Intelligence
Inteligência Artificial
Registros Médicos
Medical Records
dc.subject.unesco.none.fl_str_mv Databases
Base de datos
description En un sentido amplio la inteligencia artificial y el aprendizaje automático se ha aplicado a los datos médicos desde los inicios de la informática dado el profundo arraigo de esta área en la innovación, pero los últimos años han sido testigo de una generación cada vez mayor de datos relacionados con las ciencias de la salud, cuestión que ha dado nacimiento a un nuevo campo de las ciencias de la computación llamado big data. Los datos médicos a gran escala (en forma de bases de datos estructuradas y no estructuradas) si son apropiadamente adquiridos e interpretados pueden generar grandes beneficios al reducir los costos y los tiempos del servicio de salud, pero también podrían servir para predecir epidemias, mejorar los esquemas terapéuticos, asesorar a médicos en lugares remotos y mejorar la calidad de vida. Los algoritmos de deep learning son especialmente útiles para manejar esta gran cantidad de datos complejos, poco documentados y generalmente no estructurados; todo esto debido a que el deep learning puede irrumpir al crear modelos que descubren de forma automática las características principales, así como las que mejor predicen el comportamiento de otras variables dentro de una gran cantidad de datos complejos. En el futuro, la relación hombre-máquina en biomedicina será más estrecha; mientras que la máquina se encargará de tareas de extracción, limpieza y búsquedas de correlaciones, el médico se concentraría en interpretar estas correlaciones y buscar nuevos tratamientos que mejoren la atención y en última instancia la calidad de vida del paciente. Palabras clave: Inteligencia artificial, innovación, registros médicos, bases de.
publishDate 2019
dc.date.issued.none.fl_str_mv 2019
dc.date.accessioned.none.fl_str_mv 2023-04-24T23:23:53Z
dc.date.available.none.fl_str_mv 2023-04-24T23:23:53Z
dc.type.spa.fl_str_mv Artículo de revista
dc.type.coar.spa.fl_str_mv http://purl.org/coar/resource_type/c_2df8fbb1
dc.type.content.spa.fl_str_mv Text
dc.type.driver.spa.fl_str_mv info:eu-repo/semantics/article
dc.type.redcol.spa.fl_str_mv http://purl.org/redcol/resource_type/ART
dc.type.version.spa.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.coarversion.spa.fl_str_mv http://purl.org/coar/version/c_970fb48d4fbd8a85
format http://purl.org/coar/resource_type/c_2df8fbb1
status_str publishedVersion
dc.identifier.issn.spa.fl_str_mv 1856-4550
dc.identifier.uri.none.fl_str_mv https://dspace.tdea.edu.co/handle/tdea/2821
dc.identifier.eissn.spa.fl_str_mv 2610-7996
identifier_str_mv 1856-4550
2610-7996
url https://dspace.tdea.edu.co/handle/tdea/2821
dc.language.iso.spa.fl_str_mv spa
language spa
dc.relation.citationendpage.spa.fl_str_mv 609
dc.relation.citationissue.spa.fl_str_mv 5
dc.relation.citationstartpage.spa.fl_str_mv 589
dc.relation.citationvolume.spa.fl_str_mv 14
dc.relation.ispartofjournal.spa.fl_str_mv Revista Latinoamericana de Hipertensión
dc.relation.references.spa.fl_str_mv DiCarlo JJ, Zoccolan D, Rust NC. How does the brain solve visual object recognition? Neuron. el 9 de febrero de 2012;73(3):415–34.
Wan J, Wang D, Hoi SCH, Wu P, Zhu J, Zhang Y, et al. Deep Learning for Content-Based Image Retrieval: A Comprehensive Study. En: Proceedings of the 22Nd ACM International Conference on Multimedia [Internet]. New York, NY, USA: ACM; 2014 [citado el 18 de octubre de 2017]. p. 157–166. (MM ’14). Disponible en: h ttp://doi.acm.org/10.1145/2647868.2654948
Nilsson F. Intelligent network video: understanding modern video surveillance systems. Boca Raton: CRC Press; 2009. 389 p.
Leuba G, Krasik R. Changes in volume, surface estimate, three-dimensional shape and total number of neurons of the human primary visual cortex from midgestation until old age. Anat Embryol (Berl). el 1 de octubre de 1994;190(4):351–66
Hof RD. Is Artificial Intelligence Finally Coming into Its Own? [Internet]. MIT Technology Review. [citado el 23 de octubre de 2017]. Disponible en: https://www.technologyreview.com/s/513696/deep-learning/
Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. el 2 de febrero de 2017;542(7639):115–8.
Brouillette M. AI diagnostics are coming [Internet]. MIT Technology Review. [citado el 23 de octubre de 2017]. Disponible en: https://www.technologyreview.com/s/604271/deep-learning-is-a-black-box-but-health-care-w ont-mind/
Eastwood G. How deep learning is transforming healthcare [Internet]. Network World. 2017 [citado el 23 de octubre de 2017]. Disponible en: https://www.networkworld.com/article/3183745/health/how-deep-learnin g-is-transforming-healthcare.html
Suk H-I. An Introduction to Neural Networks and Deep Learning. En: Deep Learning for Medical Image Analysis [Internet]. Elsevier; 2017 [citado el 13 de agosto de 2017]. p. 3–24. Disponible en: http://linkinghub.elsevier. com/retrieve/pii/B978012810408800002X
Rosenblatt F. e perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev. noviembre de 1958;65(6):386–408
McCulloch WS, Pitts W. A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys. el 1 de diciembre de 1943;5(4):115–33
Minsky M, Papert S. Perceptrons. Oxford, England: M.I.T. Press; 1969
Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Netw. 1989;2(5):359–66
Linnainmaa S. Taylor expansion of the accumulated rounding error. BIT Numer Math. el 1 de junio de 1976;16(2):146–60
Werbos PJ. Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences. Harvard University; 1975.906 p.
Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature. el 9 de octubre de 1986;323(6088):533–6.
Rumelhart DE, Hinton GE, Williams RJ. Learning Internal Representations by Error Propagation. 1985 sep.
Bengio Y. Learning Deep Architectures for AI. Found Trends® Mach Learn. 2009;2(1):1–127.
Bay H, Ess A, Tuytelaars T, Van Gool L. Speeded-Up Robust Features (SURF). Comput Vis Image Underst. el 1 de junio de 2008;110(3):346–59.
Zhou H, Yuan Y, Shi C. Object tracking using SIFT features and mean shi. Comput Vis Image Underst. el 1 de marzo de 2009;113(3):345–52
Dalal N, Triggs B. Histograms of oriented gradients for human detection. En: Computer Vision and Pattern Recognition, 2005 CVPR 2005 IEEE Computer Society Conference on [Internet]. IEEE; 2005 [citado el 11 de mayo de 2017]. p. 886–893. Disponible en: http://ieeexplore.ieee.org/abstract/document/1467360/
LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, et al. Backpropagation Applied to Handwritten Zip Code Recognition. Neural Comput. diciembre de 1989;1(4):541–51.
Hubel DH, Wiesel TN. Receptive fields and functional architecture in two nonstriate visual areas (18 and 19) of the cat. J Neurophysiol. 1965;28(2):229–289.
Lecun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE. noviembre de 1998;86(11):2278–324.
Waibel A, Hanazawa T, Hinton G, Shikano K, Lang KJ. Phoneme recognition using time-delay neural networks. IEEE Trans Acoust Speech Signal Process. marzo de 1989;37(3):328–39.
Werbos PJ. Backpropagation through time: what it does and how to do it. Proc IEEE. octubre de 1990;78(10):1550–60.
Bengio Y, Simard P, Frasconi P. Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw. marzo de 1994;5(2):157–66.
Schwarz G. Estimating the Dimension of a Model. Ann Stat. marzo de 1978;6(2):461–4.
Schmidhuber J. Deep Learning in Neural Networks: An Overview. Neural Netw. enero de 2015;61:85–117
Bengio Y. A connectionist approach to speech recognition. Int J Pattern Recognit Artif Intell. el 1 de agosto de 1993;07(04):647–67.
Hochreiter S. {Untersuchungen zu dynamischen neuronalen Netzen. Diploma thesis, Institut f\\"{u}r Informatik, Lehrstuhl Prof. Brauer, Technische Universit\\"{a}t M\\"{u}nchen}. 1991;
Hochreiter S, Schmidhuber J. Long Short-Term Memory. Neural Comput. el 1 de noviembre de 1997;9(8):1735– 80.
LeCun Y, Jackel LD, Bottou L, Brunot A, Cortes C, Denker JS, et al. Comparison of learning algorithms for handwritten digit recognition. En: International conference on artificial neural networks [Internet]. Perth, Australia; 1995 [citado el 2 de mayo de 2017]. p. 53–60. Disponible en: https://pdfs.semanticscholar.org/d50 d/ce749321301f0104689f2dc582303a83be65.pdf
Hinton GE, Osindero S, Teh Y-W. A Fast Learning Algorithm for Deep Belief Nets. Neural Comput. el 17 de mayo de 2006;18(7):1527–54.
DL4J. A Beginner’s Tutorial for Restricted Boltzmann Machines - Deeplearning4j: Open-source, Distributed Deep Learning for the JVM [Internet]. [citado el 14 de agosto de 2017]. Disponible en: https://deeplearning4 j.org/restrictedboltzmannmachine
Salakhutdinov R. Learning deep generative models [Internet]. University of Toronto; 2009 [citado el 14 de agosto de 2017]. Disponible en: http://www.cs.toronto.edu/~rsalakhu/papers/Russ_thesis.pdf
Kullback S, Leibler RA. On Information and Sufficiency. Ann Math Stat. 1951;22(1):79–86
Hinton GE. Training Products of Experts by Minimizing Contrastive Divergence. Neural Comput. el 1 de agosto de 2002;14(8):1771–800.
Bengio Y, Lamblin P, Popovici D, Larochelle H, others. Greedy layer-wise training of deep networks. Adv Neural Inf Process Syst. 2007;19:153
Raina R, Madhavan A, Ng AY. Large-scale Deep Unsupervised Learning Using Graphics Processors. En: Proceedings of the 26th Annual International Conference on Machine Learning [Internet]. New York, NY, USA: ACM; 2009 [citado el 2 de mayo de 2017]. p. 873–880. (ICML ’09). Disponible en: http://doi.acm.or g/10.1145/1553374.1553486
Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res. 2014;15(1):1929–1958.
Jarrett K, Kavukcuoglu K, LeCun Y, others. What is the best multi-stage architecture for object recognition? En: Computer Vision, 2009 IEEE 12th International Conference on [Internet]. IEEE; 2009 [citado el 13 de mayo de 2017]. p.2146–2153. Disponible en: http://ieeexplore.ieee.org/abstract/document/5459469/
Dahl GE, Sainath TN, Hinton GE. Improving deep neural networks for LVCSR using rectified linear units and dropout. En: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. 2013. p. 8609– 13
Nair V, Hinton GE. Rectified linear units improve restricted boltzmann machines. En: Proceedings of the 27th international conference on machine learning (ICML-10) [Internet]. 2010 [citado el 13 de mayo de 2017]. p. 807–814. Disponible en: http://machinelearning.wustl.edu/mlpapers/paper_files/icml2010_NairH10.pdf
Krizhevsky A, Sutskever I, Hinton GE. ImageNet Classification with Deep Convolutional Neural Networks. En: Pereira F, Burges CJC, Bottou L, Weinberger KQ, editores. Advances in Neural Information Processing Systems 25 [Internet]. Curran Associates, Inc.; 2012 [citado el 13 de mayo de 2017]. p. 1097–1105. Disponible en: htt p://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf
Channin D. Deep Learning in Healthcare: Challenges and Opportunities [Internet]. e Mission. 2016 [citado el 14 de mayo de 2017]. Disponible en: https://themission.co/deep-learning-in-healthcare-challenges-and-opp ortunities-d2eee7e2545
Leaper DJ, Horrocks JC, Staniland JR, de Dombal FT. Computer-Assisted Diagnosis of Abdominal Pain using “Estimates” Provided by Clinicians. Br Med J. el 11 de noviembre de 1972;4(5836):350–4.
Reaz MBI, Hussain MS, Mohd-Yasin F. Techniques of EMG signal analysis: detection, processing, classification and applications. Biol Proced Online. diciembre de 2006;8(1):11–35.
Ristevski B, Chen M. Big Data Analytics in Medicine and Healthcare. J Integr Bioinforma [Internet]. el 25 de septiembre de 2018 [citado el 2 de agosto de 2019];15(3). Disponible en: http://www.degruyter.com/view/j/j ib.2018.15.issue-3/jib-2017-0030/jib-2017-0030.xml
Salazar J, Espinoza C, Mindiola A, Bermudez V. Data Mining and Endocrine Diseases: A New Way to Classify? Arch Med Res. abril de 2018;49(3):213–5.
Gruber K. Is the future of medical diagnosis in computer algorithms? Lancet Digit Health. mayo de 2019;1(1):e15– 6.
Miotto R, Li L, Kidd BA, Dudley JT. Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records. Sci Rep. el 17 de mayo de 2016;6:26094
Xiong HY, Alipanahi B, Lee LJ, Bretschneider H, Merico D, Yuen RKC, et al. e human splicing code reveals new insights into the genetic determinants of disease. Science. el 9 de enero de 2015;347(6218):1254806
Gawehn E, Hiss JA, Schneider G. Deep Learning in Drug Discovery. Mol Inform. el 1 de enero de 2016;35(1):3– 14.
Cao C, Liu F, Tan H, Song D, Shu W, Li W, et al. Deep Learning and Its Applications in Biomedicine. Genomics Proteomics Bioinformatics. 2018; 16(1): 17–32
Shen D, Wu G, Suk HI. Deep Learning in Medical Image Analysis. Annu Rev Biomed Eng. 2017;19:221-248.
Klann JG, Szolovits P. An intelligent listening framework for capturing encounter notes from a doctor-patient dialog. BMC Med Inform Decis Mak. 2009; 9(Suppl 1): S3.
Pang S, Du A, Orgun MA, Yu Z. A novel fused convolutional neural network for biomedical image classification. Med Biol Eng Comput. 2019;57(1):107-121.
dc.rights.uri.spa.fl_str_mv https://creativecommons.org/licenses/by-nd/4.0/
dc.rights.license.spa.fl_str_mv Atribución-SinDerivadas 4.0 Internacional (CC BY-ND 4.0)
dc.rights.accessrights.spa.fl_str_mv info:eu-repo/semantics/openAccess
dc.rights.coar.spa.fl_str_mv http://purl.org/coar/access_right/c_abf2
rights_invalid_str_mv https://creativecommons.org/licenses/by-nd/4.0/
Atribución-SinDerivadas 4.0 Internacional (CC BY-ND 4.0)
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.extent.spa.fl_str_mv 21 páginas
dc.format.mimetype.spa.fl_str_mv application/pdf
dc.publisher.spa.fl_str_mv Cooperativa Servicios y Suministros 212518
dc.publisher.place.spa.fl_str_mv Venezuela
dc.source.spa.fl_str_mv https://www.redalyc.org/journal/1702/170262877013/170262877013.pdf
institution Tecnológico de Antioquia
bitstream.url.fl_str_mv https://dspace.tdea.edu.co/bitstream/tdea/2821/1/An%20introduction%20to%20artificial%20intelligence%20applications%20in%20medicine-%20Historical%20aspects.pdf
https://dspace.tdea.edu.co/bitstream/tdea/2821/2/license.txt
https://dspace.tdea.edu.co/bitstream/tdea/2821/3/An%20introduction%20to%20artificial%20intelligence%20applications%20in%20medicine-%20Historical%20aspects.pdf.txt
https://dspace.tdea.edu.co/bitstream/tdea/2821/4/An%20introduction%20to%20artificial%20intelligence%20applications%20in%20medicine-%20Historical%20aspects.pdf.jpg
bitstream.checksum.fl_str_mv 0401ab76ef3a97feebd3d091ce4a7b36
2f9959eaf5b71fae44bbf9ec84150c7a
e1951d359c0c40b449265a546bd31460
92cd7cfd0139b2ecaac30787824a1991
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositorio Institucional Tecnologico de Antioquia
repository.mail.fl_str_mv bdigital@metabiblioteca.com
_version_ 1812189196035555328
spelling Arias Vanegas, Víctor Alfonsoc1a03f8e-4d7d-4f4f-b731-b6ec8c14a0f6Salazar Vílchez, Juan54353b36-16c1-42d2-97d6-f6c141bda13cGaricano Soto, Carlos Hernando4a855dee-ca91-4a62-9953-0b420fe8b83dContreras Velásquez, Julio César88e07ab2-7d2e-4b91-929d-b5df5c20bfeeChacón Rangel, José Gerardo9f4b2d85-080d-458d-af69-0eada98f13b5Chacín González, Maricarmenffc33296-c227-4524-9047-7172da02c195Añez, Roberto J.9eaf251a-1c35-4a06-978c-23413ef0f8e6Rojas Quintero, Joselyn Joanna6f45b296-2a73-4208-9808-1f4ccbbb0af3Bermúdez Pirela, Valmore José79e484db-2aa5-4704-8a1d-b40d817c2e5f2023-04-24T23:23:53Z2023-04-24T23:23:53Z20191856-4550https://dspace.tdea.edu.co/handle/tdea/28212610-7996En un sentido amplio la inteligencia artificial y el aprendizaje automático se ha aplicado a los datos médicos desde los inicios de la informática dado el profundo arraigo de esta área en la innovación, pero los últimos años han sido testigo de una generación cada vez mayor de datos relacionados con las ciencias de la salud, cuestión que ha dado nacimiento a un nuevo campo de las ciencias de la computación llamado big data. Los datos médicos a gran escala (en forma de bases de datos estructuradas y no estructuradas) si son apropiadamente adquiridos e interpretados pueden generar grandes beneficios al reducir los costos y los tiempos del servicio de salud, pero también podrían servir para predecir epidemias, mejorar los esquemas terapéuticos, asesorar a médicos en lugares remotos y mejorar la calidad de vida. Los algoritmos de deep learning son especialmente útiles para manejar esta gran cantidad de datos complejos, poco documentados y generalmente no estructurados; todo esto debido a que el deep learning puede irrumpir al crear modelos que descubren de forma automática las características principales, así como las que mejor predicen el comportamiento de otras variables dentro de una gran cantidad de datos complejos. En el futuro, la relación hombre-máquina en biomedicina será más estrecha; mientras que la máquina se encargará de tareas de extracción, limpieza y búsquedas de correlaciones, el médico se concentraría en interpretar estas correlaciones y buscar nuevos tratamientos que mejoren la atención y en última instancia la calidad de vida del paciente. Palabras clave: Inteligencia artificial, innovación, registros médicos, bases de.In a broad sense, artificial intelligence and machine learning have been applied to medical data since the beginning of computing given the deep roots of this area in innovation, but recent years have witnessed an increasing generation of data related to health sciences, an issue that has given birth to a new field of computer science called big data. Large-scale medical data (in the form of structured and unstructured databases) if properly acquired and interpreted can generate great benefits by reducing costs and times of health service, but could also serve to predict epidemics, improve therapeutic schemes, advise doctors in remote places and improve the quality of life. e deep learning algorithms are especially useful to deal with this large amount of complex, poorly documented and generally unstructured data, all this because deep learning can break when creating models that automatically discover the predictive characteristics of a large amount of complex data. In the future, the human-machine relationship in the medical evaluation will be narrower and complex; while the machine would be responsible for extraction, cleaning and assisted searches, the physician will be concentrate on both, data interpretation and the best treatment option, improving the patient´s attention and ultimately, quality of life. Keywords: Artificial intelligence, innovation, medical records, databases.21 páginasapplication/pdfspaCooperativa Servicios y Suministros 212518Venezuelahttps://creativecommons.org/licenses/by-nd/4.0/Atribución-SinDerivadas 4.0 Internacional (CC BY-ND 4.0)info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2https://www.redalyc.org/journal/1702/170262877013/170262877013.pdfUna introducción a las aplicaciones de la inteligencia artificial en Medicina: Aspectos históricosAn introduction to artificial intelligence applications in medicine: Historical aspectsArtículo de revistahttp://purl.org/coar/resource_type/c_2df8fbb1Textinfo:eu-repo/semantics/articlehttp://purl.org/redcol/resource_type/ARTinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/version/c_970fb48d4fbd8a85609558914Revista Latinoamericana de HipertensiónDiCarlo JJ, Zoccolan D, Rust NC. How does the brain solve visual object recognition? Neuron. el 9 de febrero de 2012;73(3):415–34.Wan J, Wang D, Hoi SCH, Wu P, Zhu J, Zhang Y, et al. Deep Learning for Content-Based Image Retrieval: A Comprehensive Study. En: Proceedings of the 22Nd ACM International Conference on Multimedia [Internet]. New York, NY, USA: ACM; 2014 [citado el 18 de octubre de 2017]. p. 157–166. (MM ’14). Disponible en: h ttp://doi.acm.org/10.1145/2647868.2654948Nilsson F. Intelligent network video: understanding modern video surveillance systems. Boca Raton: CRC Press; 2009. 389 p.Leuba G, Krasik R. Changes in volume, surface estimate, three-dimensional shape and total number of neurons of the human primary visual cortex from midgestation until old age. Anat Embryol (Berl). el 1 de octubre de 1994;190(4):351–66Hof RD. Is Artificial Intelligence Finally Coming into Its Own? [Internet]. MIT Technology Review. [citado el 23 de octubre de 2017]. Disponible en: https://www.technologyreview.com/s/513696/deep-learning/Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. el 2 de febrero de 2017;542(7639):115–8.Brouillette M. AI diagnostics are coming [Internet]. MIT Technology Review. [citado el 23 de octubre de 2017]. Disponible en: https://www.technologyreview.com/s/604271/deep-learning-is-a-black-box-but-health-care-w ont-mind/Eastwood G. How deep learning is transforming healthcare [Internet]. Network World. 2017 [citado el 23 de octubre de 2017]. Disponible en: https://www.networkworld.com/article/3183745/health/how-deep-learnin g-is-transforming-healthcare.htmlSuk H-I. An Introduction to Neural Networks and Deep Learning. En: Deep Learning for Medical Image Analysis [Internet]. Elsevier; 2017 [citado el 13 de agosto de 2017]. p. 3–24. Disponible en: http://linkinghub.elsevier. com/retrieve/pii/B978012810408800002XRosenblatt F. e perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev. noviembre de 1958;65(6):386–408McCulloch WS, Pitts W. A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys. el 1 de diciembre de 1943;5(4):115–33Minsky M, Papert S. Perceptrons. Oxford, England: M.I.T. Press; 1969Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Netw. 1989;2(5):359–66Linnainmaa S. Taylor expansion of the accumulated rounding error. BIT Numer Math. el 1 de junio de 1976;16(2):146–60Werbos PJ. Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences. Harvard University; 1975.906 p.Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature. el 9 de octubre de 1986;323(6088):533–6.Rumelhart DE, Hinton GE, Williams RJ. Learning Internal Representations by Error Propagation. 1985 sep.Bengio Y. Learning Deep Architectures for AI. Found Trends® Mach Learn. 2009;2(1):1–127.Bay H, Ess A, Tuytelaars T, Van Gool L. Speeded-Up Robust Features (SURF). Comput Vis Image Underst. el 1 de junio de 2008;110(3):346–59.Zhou H, Yuan Y, Shi C. Object tracking using SIFT features and mean shi. Comput Vis Image Underst. el 1 de marzo de 2009;113(3):345–52Dalal N, Triggs B. Histograms of oriented gradients for human detection. En: Computer Vision and Pattern Recognition, 2005 CVPR 2005 IEEE Computer Society Conference on [Internet]. IEEE; 2005 [citado el 11 de mayo de 2017]. p. 886–893. Disponible en: http://ieeexplore.ieee.org/abstract/document/1467360/LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, et al. Backpropagation Applied to Handwritten Zip Code Recognition. Neural Comput. diciembre de 1989;1(4):541–51.Hubel DH, Wiesel TN. Receptive fields and functional architecture in two nonstriate visual areas (18 and 19) of the cat. J Neurophysiol. 1965;28(2):229–289.Lecun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE. noviembre de 1998;86(11):2278–324.Waibel A, Hanazawa T, Hinton G, Shikano K, Lang KJ. Phoneme recognition using time-delay neural networks. IEEE Trans Acoust Speech Signal Process. marzo de 1989;37(3):328–39.Werbos PJ. Backpropagation through time: what it does and how to do it. Proc IEEE. octubre de 1990;78(10):1550–60.Bengio Y, Simard P, Frasconi P. Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw. marzo de 1994;5(2):157–66.Schwarz G. Estimating the Dimension of a Model. Ann Stat. marzo de 1978;6(2):461–4.Schmidhuber J. Deep Learning in Neural Networks: An Overview. Neural Netw. enero de 2015;61:85–117Bengio Y. A connectionist approach to speech recognition. Int J Pattern Recognit Artif Intell. el 1 de agosto de 1993;07(04):647–67.Hochreiter S. {Untersuchungen zu dynamischen neuronalen Netzen. Diploma thesis, Institut f\\"{u}r Informatik, Lehrstuhl Prof. Brauer, Technische Universit\\"{a}t M\\"{u}nchen}. 1991;Hochreiter S, Schmidhuber J. Long Short-Term Memory. Neural Comput. el 1 de noviembre de 1997;9(8):1735– 80.LeCun Y, Jackel LD, Bottou L, Brunot A, Cortes C, Denker JS, et al. Comparison of learning algorithms for handwritten digit recognition. En: International conference on artificial neural networks [Internet]. Perth, Australia; 1995 [citado el 2 de mayo de 2017]. p. 53–60. Disponible en: https://pdfs.semanticscholar.org/d50 d/ce749321301f0104689f2dc582303a83be65.pdfHinton GE, Osindero S, Teh Y-W. A Fast Learning Algorithm for Deep Belief Nets. Neural Comput. el 17 de mayo de 2006;18(7):1527–54.DL4J. A Beginner’s Tutorial for Restricted Boltzmann Machines - Deeplearning4j: Open-source, Distributed Deep Learning for the JVM [Internet]. [citado el 14 de agosto de 2017]. Disponible en: https://deeplearning4 j.org/restrictedboltzmannmachineSalakhutdinov R. Learning deep generative models [Internet]. University of Toronto; 2009 [citado el 14 de agosto de 2017]. Disponible en: http://www.cs.toronto.edu/~rsalakhu/papers/Russ_thesis.pdfKullback S, Leibler RA. On Information and Sufficiency. Ann Math Stat. 1951;22(1):79–86Hinton GE. Training Products of Experts by Minimizing Contrastive Divergence. Neural Comput. el 1 de agosto de 2002;14(8):1771–800.Bengio Y, Lamblin P, Popovici D, Larochelle H, others. Greedy layer-wise training of deep networks. Adv Neural Inf Process Syst. 2007;19:153Raina R, Madhavan A, Ng AY. Large-scale Deep Unsupervised Learning Using Graphics Processors. En: Proceedings of the 26th Annual International Conference on Machine Learning [Internet]. New York, NY, USA: ACM; 2009 [citado el 2 de mayo de 2017]. p. 873–880. (ICML ’09). Disponible en: http://doi.acm.or g/10.1145/1553374.1553486Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res. 2014;15(1):1929–1958.Jarrett K, Kavukcuoglu K, LeCun Y, others. What is the best multi-stage architecture for object recognition? En: Computer Vision, 2009 IEEE 12th International Conference on [Internet]. IEEE; 2009 [citado el 13 de mayo de 2017]. p.2146–2153. Disponible en: http://ieeexplore.ieee.org/abstract/document/5459469/Dahl GE, Sainath TN, Hinton GE. Improving deep neural networks for LVCSR using rectified linear units and dropout. En: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. 2013. p. 8609– 13Nair V, Hinton GE. Rectified linear units improve restricted boltzmann machines. En: Proceedings of the 27th international conference on machine learning (ICML-10) [Internet]. 2010 [citado el 13 de mayo de 2017]. p. 807–814. Disponible en: http://machinelearning.wustl.edu/mlpapers/paper_files/icml2010_NairH10.pdfKrizhevsky A, Sutskever I, Hinton GE. ImageNet Classification with Deep Convolutional Neural Networks. En: Pereira F, Burges CJC, Bottou L, Weinberger KQ, editores. Advances in Neural Information Processing Systems 25 [Internet]. Curran Associates, Inc.; 2012 [citado el 13 de mayo de 2017]. p. 1097–1105. Disponible en: htt p://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdfChannin D. Deep Learning in Healthcare: Challenges and Opportunities [Internet]. e Mission. 2016 [citado el 14 de mayo de 2017]. Disponible en: https://themission.co/deep-learning-in-healthcare-challenges-and-opp ortunities-d2eee7e2545Leaper DJ, Horrocks JC, Staniland JR, de Dombal FT. Computer-Assisted Diagnosis of Abdominal Pain using “Estimates” Provided by Clinicians. Br Med J. el 11 de noviembre de 1972;4(5836):350–4.Reaz MBI, Hussain MS, Mohd-Yasin F. Techniques of EMG signal analysis: detection, processing, classification and applications. Biol Proced Online. diciembre de 2006;8(1):11–35.Ristevski B, Chen M. Big Data Analytics in Medicine and Healthcare. J Integr Bioinforma [Internet]. el 25 de septiembre de 2018 [citado el 2 de agosto de 2019];15(3). Disponible en: http://www.degruyter.com/view/j/j ib.2018.15.issue-3/jib-2017-0030/jib-2017-0030.xmlSalazar J, Espinoza C, Mindiola A, Bermudez V. Data Mining and Endocrine Diseases: A New Way to Classify? Arch Med Res. abril de 2018;49(3):213–5.Gruber K. Is the future of medical diagnosis in computer algorithms? Lancet Digit Health. mayo de 2019;1(1):e15– 6.Miotto R, Li L, Kidd BA, Dudley JT. Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records. Sci Rep. el 17 de mayo de 2016;6:26094Xiong HY, Alipanahi B, Lee LJ, Bretschneider H, Merico D, Yuen RKC, et al. e human splicing code reveals new insights into the genetic determinants of disease. Science. el 9 de enero de 2015;347(6218):1254806Gawehn E, Hiss JA, Schneider G. Deep Learning in Drug Discovery. Mol Inform. el 1 de enero de 2016;35(1):3– 14.Cao C, Liu F, Tan H, Song D, Shu W, Li W, et al. Deep Learning and Its Applications in Biomedicine. Genomics Proteomics Bioinformatics. 2018; 16(1): 17–32Shen D, Wu G, Suk HI. Deep Learning in Medical Image Analysis. Annu Rev Biomed Eng. 2017;19:221-248.Klann JG, Szolovits P. An intelligent listening framework for capturing encounter notes from a doctor-patient dialog. BMC Med Inform Decis Mak. 2009; 9(Suppl 1): S3.Pang S, Du A, Orgun MA, Yu Z. A novel fused convolutional neural network for biomedical image classification. Med Biol Eng Comput. 2019;57(1):107-121.InnovaciónInnovationInovaçãoInteligencia ArtificialArtificial IntelligenceInteligência ArtificialRegistros MédicosMedical RecordsDatabasesBase de datosORIGINALAn introduction to artificial intelligence applications in medicine- Historical aspects.pdfAn introduction to artificial intelligence applications in medicine- Historical aspects.pdfapplication/pdf1659443https://dspace.tdea.edu.co/bitstream/tdea/2821/1/An%20introduction%20to%20artificial%20intelligence%20applications%20in%20medicine-%20Historical%20aspects.pdf0401ab76ef3a97feebd3d091ce4a7b36MD51open accessLICENSElicense.txtlicense.txttext/plain; charset=utf-814828https://dspace.tdea.edu.co/bitstream/tdea/2821/2/license.txt2f9959eaf5b71fae44bbf9ec84150c7aMD52open accessTEXTAn introduction to artificial intelligence applications in medicine- Historical aspects.pdf.txtAn introduction to artificial intelligence applications in medicine- Historical aspects.pdf.txtExtracted texttext/plain61628https://dspace.tdea.edu.co/bitstream/tdea/2821/3/An%20introduction%20to%20artificial%20intelligence%20applications%20in%20medicine-%20Historical%20aspects.pdf.txte1951d359c0c40b449265a546bd31460MD53open accessTHUMBNAILAn introduction to artificial intelligence applications in medicine- Historical aspects.pdf.jpgAn introduction to artificial intelligence applications in medicine- Historical aspects.pdf.jpgGenerated Thumbnailimage/jpeg7988https://dspace.tdea.edu.co/bitstream/tdea/2821/4/An%20introduction%20to%20artificial%20intelligence%20applications%20in%20medicine-%20Historical%20aspects.pdf.jpg92cd7cfd0139b2ecaac30787824a1991MD54open accesstdea/2821oai:dspace.tdea.edu.co:tdea/28212023-04-25 03:01:04.679An error occurred on the license name.|||https://creativecommons.org/licenses/by-nd/4.0/open accessRepositorio Institucional Tecnologico de Antioquiabdigital@metabiblioteca.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

Publicaciones similares