Inteligencia artificial para asistir el diagnóstico clínico en medicina

Autores/as

  • Saúl Oswaldo Lugo-Reyes Secretaría de Salud, Instituto Nacional de Pediatría, Unidad de Investigación en Inmunodeficiencias, Ciudad de México
  • Guadalupe Maldonado-Colín Secretaría de Salud, Instituto Nacional de Pediatría, Ciudad de México
  • Chiharu Murata Secretaría de Salud, Instituto Nacional de Pediatría, Departamento de Metodología de la Investigación, Ciudad de México

DOI:

https://doi.org/10.29262/ram.v61i2.33

Palabras clave:

inteligencia artificial, diagnóstico clínico, aprendizaje automático, diagnóstico diferencial, minería de datos, regresión logística, apoyo en decisión clínica

Resumen

La medicina es uno de los campos del conocimiento que más podrían beneficiarse de una interacción cercana con la computación y las matemáticas, mediante la cual se optimizarían procesos complejos e imperfectos como el diagnóstico diferencial. De esto se ocupa el aprendizaje automático, rama de la inteligencia artificial que construye y estudia sistemas capaces de aprender a partir de un conjunto de datos de adiestramiento y de mejorar procesos de clasificación y predicción. En México, en los últimos años se ha avanzado en la implantación del expediente electrónico y los Institutos Nacionales de Salud cuentan con una riqueza de datos clínicos almacenada. Para que esos datos se conviertan en conocimiento, necesitan ser procesados y analizados a través de métodos estadísticos complejos, como ya se hace en otros países, usando: razonamiento basado en casos, redes neuronales artificiales, clasificadores bayesianos, regresión logística multivariante o máquinas de soporte vectorial, entre otros. Esto facilitará el diagnóstico clínico de padecimientos como: apendicitis aguda, cáncer de mama o hepatopatía crónica. En esta revisión se repasan conceptos, antecedentes, ejemplos y métodos de aprendizaje automático en diagnóstico clínico.

Citas

Siegel E. Predictive analytics: The power to predict who will click, buy, lie, or die. New York: John Wiley & Sons, Inc., 2013.

Cleophas TJ, Zwinderman AH. Machine Learning in Medicine part 2 [Internet]. Dordrecht Heidelberg New York, London: Springer, 2013. Disponible en: http://link.springer. com/10.1007/978-94-007-6886-4

Khattree R. Computational methods in biomedical research. Baton Rouge, LA: Chapman & Hall, 2007.

Reed K, May R, Nicholas C, Taylor H, Brown A. Health Grades Patient Safety in American Hospitals Study [Internet]. 2011 [cited 2014 Feb 14]. Disponible en: Healthgrades.com

Graber ML. The incidence of diagnostic error in medicine. BMJ Qual Saf [Internet]. 2013 Oct [cited 2014 Feb 9];22 Suppl 2:ii21-ii27. Disponible en: http://www.pubmedcentral. nih.gov/articlerender.fcgi?artid=3786666&tool=pmce ntrez&rendertype=abstract

Segal M. How doctors think, and how software can help avoid cognitive errors in diagnosis. Acta Paediatr [Internet]. 2007/09/14 ed. 2007;96:1720-1722. Disponible en: http:// www.ncbi.nlm.nih.gov/pubmed/17850393

Groves M, O’Rourke P, Alexander H. The clinical reasoning characteristics of diagnostic experts. Med Teach [Internet]. 2003/07/26 ed. 2003;25:308-313. Disponible en: http:// www.ncbi.nlm.nih.gov/pubmed/12881056

Sherbino J, Dore KL, Siu E, Norman GR. The effectiveness of cognitive forcing strategies to decrease diagnostic error: an exploratory study. Teach Learn Med [Internet]. 2011/01/18 ed. 2011;23:78-84. Disponible en: http://www.ncbi.nlm. nih.gov/pubmed/21240788

Gill CJ, Sabin L, Schmid CH. Why clinicians are natural bayesians. BMJ [Internet]. 2005/05/10 ed. 2005;330:1080- 1083. Disponible en: http://www.ncbi.nlm.nih.gov/ pubmed/15879401

Ebell MH, Smith MA, Barry HC, Ives K, Carey M. The rational clinical examination. Does this patient have strep throat? JAMA [Internet]. 2001/01/09 ed. 2000;284(22):2912- 2918. Disponible en: http://www.ncbi.nlm.nih.gov/ pubmed/11147989

Croskerry P. Cognitive forcing strategies in clinical decision making. Ann Emerg Med [Internet]. 2003/01/07 ed. 2003;41:110-120. Disponible en: http://www.ncbi.nlm.nih. gov/pubmed/12514691

Pines JM. Profiles in patient safety: confirmation bias in emergency medicine. Acad Emerg Med [Internet]. 2005/12/21 ed. 2006;13:90.94. Disponible en: http://www. ncbi.nlm.nih.gov/pubmed/1636532

Croskerry P. The importance of cognitive errors in diagnosis and strategies to minimize them. Acad Med [Internet]. 2003/08/14 ed. 2003;78:775-780. Disponible en: http:// www.ncbi.nlm.nih.gov/pubmed/12915363

Groves M, O’Rourke P, Alexander H. Clinical reasoning: the relative contribution of identification, interpretation and hypothesis errors to misdiagnosis. Med Teach [Internet]. 2004/09/17 ed. 2003;25:621-625. Disponible en: http:// www.ncbi.nlm.nih.gov/pubmed/15369910

Leblanc VR, Brooks LR, Norman GR. Believing is seeing: the influence of a diagnostic hypothesis on the interpretation of clinical features. Acad Med [Internet]. 2002/10/16 ed. 2002;77:S67-S69. Disponible en: http://www.ncbi.nlm.nih. gov/pubmed/12377709

Baxt WG, Shofer FS, Sites FD, Hollander JE. A neural network aid for the early diagnosis of cardiac ischemia in patients presenting to the emergency department with chest pain. Ann Emerg Med [Internet]. 2002/11/26 ed. 2002;40:575-583. Disponible en: http://www.ncbi.nlm. nih.gov/pubmed/12447333

Prabhudesai SG, Gould S, Rekhraj S, et al. Artificial neural networks: useful aid in diagnosing acute appendicitis. World J Surg [Internet]. 2007/11/29 ed. 2008;32:301- 305. Disponible en: http://www.ncbi.nlm.nih.gov/pubmed/ 18043966

Warner HR. A mathematical approach to medical diagnosis. JAMA [Internet]. American Medical Association; 1961 Jul 22 [cited 2014 Apr 8];177(3):177. Disponible en: http://jama. jamanetwork.com/article.aspx?articleid=331443

Yu VL, et al. Antimicrobial selection by a computer: a blinded evaluation by infectious disease experts. J Am Med Assoc 1979;242:1279-1282.

Siegel JD, Parrino TA. Computerized diagnosis: implications for clinical education. Med Educ [Internet]. 1988 Jan [cited 2014 Feb 6];22:47-54. Disponible en: http://www.ncbi.nlm. nih.gov/pubmed/3282154

(NSF) UNSF. National Science Foundation (NSF) News-NSF Leads Federal Efforts In Big Data [Internet]. Nsf.gov. 2012 [cited 2014 Apr 1]. Disponible en: http://www.nsf.gov/ news/news_summ.jsp?cntn_id=123607

(SIAM) S for I and applied M. SIAM International Conference on Data Mining (SDM12) [Internet]. 2012 [cited 2014 Apr 8]. Disponible en: http://www.siam.org/meetings/sdm12/

Cleophas TJ, Zwinderman AH. Machine Learning in Medicine [Internet]. Vasa. Springer; 2013 [cited 2014 Feb 14]. Disponible en: http://medcontent.metapress.com/index/ A65RM03P4874243N.pdf

Shapiro SC. Artificial Intelligence. In: Shapiro SC, editor. Encyclopedia of Artificial Intelligence. 2nd ed. New York: John Wiley & Sons, Inc., 1992.

Mitchell T. Machine learning. New York: McGraw Hill, 1997.

BBC News - Alan Turing: The experiment that shaped artificial intelligence [Internet]. Disponible en: http://www. bbc.co.uk/news/technology-18475646

Machine learning [Internet]. en.wikipedia.org: Wikipedia. Disponible en: http://en.wikipedia.org/wiki/Machine_ learning

Ramesh AN, Kambhampati C, Monson JR, Drew PJ. Artificial intelligence in medicine. Ann R Coll Surg Engl [Internet]. 2004/08/31 ed. 2004;86:334-338. Disponible en: http:// www.ncbi.nlm.nih.gov/pubmed/15333167

Patel VL, Shortliffe EH, Stefanelli M, Szolovits P, Berthold MR, Bellazzi R, et al. The coming of age of artificial intelligence in medicine. Artif Intell Med [Internet]. 2008/09/16 ed. 2009;46:5-17. Disponible en: http://www.ncbi.nlm.nih. gov/pubmed/18790621

Atkov OY, Gorokhova SG, Sboev AG, et al. Coronary heart disease diagnosis by artificial neural networks including genetic polymorphisms and clinical parameters. J Cardiol [Internet]. 2012/01/06 ed. 2012;59:190-194. Disponible en: http://www.ncbi.nlm.nih.gov/ pubmed/22218324

Yoldas O, Tez M, Karaca T. Artificial neural networks in the diagnosis of acute appendicitis. Am J Emerg Med [Internet]. 2011/09/13 ed. 2011. Disponible en: http://www.ncbi.nlm. nih.gov/pubmed/21908136

Dietzel M, Baltzer PA, Dietzel A, et al. Artificial Neural Networks for differential diagnosis of breast lesions in MR-Mammography: A systematic approach addressing the influence of network architecture on diagnostic performance using a large clinical database. Eur J Radiol [Internet]. 2011/04/05 ed. 2011. Disponible en: http://www.ncbi.nlm. nih.gov/pubmed/21459533

Chuang CL. Case-based reasoning support for liver disease diagnosis. Artif Intell Med [Internet]. 2011/07/16 ed. 2011;53:15-23. Disponible en: http://www.ncbi.nlm.nih. gov/pubmed/21757326

Park YJ, Chun SH, Kim BC. Cost-sensitive case-based reasoning using a genetic algorithm: application to medical diagnosis. Artif Intell Med [Internet]. 2011/01/11 ed. 2011;51:133-145. Disponible en: http://www.ncbi.nlm. nih.gov/pubmed/21216571

Huang ML, Hung YH, Lee WM, Li RK, Wang TH. Usage of case-based reasoning, neural network and adaptive neuro-fuzzy inference system classification techniques in breast cancer dataset classification diagnosis. J Med Syst [Internet]. 2010/08/13 ed. 2012;36:407-414. Disponible en: http://www.ncbi.nlm.nih.gov/pubmed/20703710

Tenorio JM, Hummel AD, Cohrs FM, Sdepanian VL, Pisa IT, et al. Artificial intelligence techniques applied to the development of a decision-support system for diagnosing celiac disease. Int J Med Inf [Internet]. 2011/09/16 ed. 2011;80(11):793-802. Disponible en: http://www.ncbi. nlm.nih.gov/pubmed/21917512

Perkins JN, Liang C, Gao D, Shultz L, Friedman NR. Risk of post-tonsillectomy hemorrhage by clinical diagnosis. Laryngoscope 2012;122:2311-2315.

Watson I. Case-based reasoning is a methodology not a technology. 1999;12:303-308.

Samarghitean C, Ortutay C, Vihinen M. Systematic classification of primary immunodeficiencies based on clinical, pathological, and laboratory parameters. J Immunol [Internet]. 2009 Dec 1 [cited 2013 Nov 8];183:7569-7575. Disponible en: http://www.ncbi.nlm.nih.gov/pubmed/19917694

Sajda P. Machine learning for detection and diagnosis of disease. Annu Rev Biomed Eng 2006;8:537-565.

Seixas JM, Faria J, Souza Filho JBO, et al. Artificial neural network models to support the diagnosis of pleural tuberculosis in adult patients. Int J Tuberc Lung Dis [Internet]. International Union Against Tuberculosis and Lung Disease 2013 May [cited 2013 Nov 18];17:682-686. Disponible en: http://www.ingentaconnect.com/content/iuatld/ijtld/2013/00000017/00000005/art00021?token=00581a1cffd6a264d37e41225f40384d576b4628486b253e2c49576b3427656c3c6a333f2566e4ed81d7b599

Geenen PL, Gaag LC, Loeffen WLA, Elbers ARW. Constructing naive Bayesian classifiers for veterinary medicine : A case study in the clinical diagnosis of classical swine fever. Res Vet Sci [Internet]. Elsevier Ltd; 2011;91:64- 70. Disponible en: http://dx.doi.org /10.1016/j. rvsc.2010.08.006

Amaral JLM, Lopes AJ, Jansen JM, Faria ACD, Melo PL. Machine learning algorithms and forced oscillation measurements applied to the automatic identification of chronic obstructive pulmonary disease. Comput Methods Programs Biomed [Internet]. Elsevier Ireland Ltd; 2012 Mar [cited 2013 Nov 8];105:183-193. Disponible en: http:// www.ncbi.nlm.nih.gov/pubmed/22018532

Chen H, Yang B, Wang G. Support vector machine based diagnostic system for breast cancer using swarm intelligence. J Med Syst 2012;36:2505-2519.

Hart E, Timmis J. Application areas of AIS : The past, the present and the future. J Applied Soft Computer 2008;8:191-201

Zhao W, Davis CE. A modified artificial immune system based pattern recognition approach-an application to clinical diagnostics. Artif Intell Med [Internet]. Elsevier B.V.; 2011 May [cited 2013 Nov 8];52:1-9. Disponible en: http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3108456&tool=pmcentrez&rendertype=abstract

Kodaz H, Özşen S, Arslan A, Güneş S. Medical application of information gain based artificial immune recognition system (AIRS): Diagnosis of thyroid disease. Expert Syst Appl [Internet]. 2009 Mar [cited 2013 Nov 8];36:3086-3092. Disponible en: http://linkinghub.elsevier.com/retrieve/pii/S0957417408000171

Krawczyk B, Simić D, Simić S, Woźniak M. Automatic diagnosis of primary headaches by machine learning methods. Cent Eur J Med [Internet]. 2012 Nov 16 [cited 2014 Jan 29];8:157-165. Disponible en: http://www.springerlink. com/index/10.2478/s11536-012-0098-5.

Wu W, Bleecker E, Moore W, et al. Unsupervised phenotyping of Severe Asthma Research Program participants using expanded lung data. J Allergy Clin Immunol [Internet]. 2014 Feb 28 [cited 2014 Mar 24]. Disponible en: http://www. ncbi.nlm.nih.gov/pubmed/24589344

Lazic N, Roberts G, Custovic A, et al. Multiple atopy phenotypes and their associations with asthma: similar findings from two birth cohorts. Allergy [Internet]. 2013 Jun [cited 2014 Mar 26];68:764-770. Disponible en: http://www.ncbi. nlm.nih.gov/pubmed/23621120

Simpson A, Tan VYF, Winn J, et al. Beyond atopy: multiple patterns of sensitization in relation to asthma in a birth cohort study. Am J Respir Crit Care Med [Internet]. 2010 Jun 1 [cited 2014 Mar 21];181:1200-1206. Disponible en: http://www.ncbi.nlm.nih.gov/pubmed/20167852

Afzal Z, Engelkes M, Verhamme KMC, JA, et al. Automatic generation of case-detection algorithms to identify children with asthma from large electronic health record databases. Pharmacoepidemiol Drug Saf [Internet]. 2013 Aug [cited 2014 Apr 8];22:826-833. Disponible en: http://www.ncbi. nlm.nih.gov/pubmed/23592573

Dexheimer JW, Brown LE, Leegon J, Aronsky D. Comparing decision support methodologies for identifying asthma exacerbations. Stud Health Technol Inform [Internet]. 2007 Jan [cited 2014 Apr 8];129(Pt 2):880-884. Disponible en: http://www.ncbi.nlm.nih.gov/pubmed/17911842

Publicado

2014-03-31

Número

Sección

Artículos originales