Uso de la inteligencia artificial para el tratamiento del trauma craneoencefálico en niños: revisión de alcance
DOI:
https://doi.org/10.20453/rnp.v88i4.6389Palabras clave:
machine learning, inteligencia artificial, trauma craneoencefálico, niños, revisión de alcanceResumen
La inteligencia artificial (IA) constituye una herramienta significativa en la práctica clínica. El trauma craneoencefálico (TCE) representa una de las principales causas de morbimortalidad infantil, por lo que se espera que la IA mejore los resultados clínicos en esta población. El objetivo de esta revisión fue analizar la literatura existente sobre el uso de IA en el manejo del TCE pediátrico. Se realizó una búsqueda en bases de datos (PubMed/MEDLINE, PMC, Cochrane, Embase, Web of Science, IEEE Xplore, Scopus, SciELO y LILACS). Se incluyeron estudios publicados entre enero de 2015 y junio de 2024 que aplicaron modelos de machine learning (ML) para predecir diagnóstico, tratamiento y pronóstico. Se identificaron 1727 artículos, de los cuales se seleccionaron 31, la mayoría publicados entre 2021 y 2024, predominando la procedencia de Estados Unidos (51,6 %) y países asiáticos (29,0 %). Los modelos de aprendizaje supervisado, como bosque aleatorio (RF) y máquina de soporte vectorial (SVM), fueron los más utilizados (51,6 %), seguidos del aprendizaje profundo (32,2 %), donde destacaron las redes neuronales artificiales (ANN). Los modelos de ML se aplicaron principalmente en diagnóstico (64,5 %) y pronóstico (38,7 %). En diagnóstico, se reportó un área bajo la curva (AUC) entre 0,78 y 0,99, destacando las ANN (exactitud de 99 %; precisión de 100 %); mientras que, en pronóstico, se reportó un AUC entre 0,71 y 0,99, sobresaliendo la SVM (exactitud 94 %; precisión 99 %). Se concluye que existe un interés creciente en el uso de la IA para el diagnóstico y pronóstico del TCE pediátrico, con énfasis en modelos de aprendizaje profundo que muestran un rendimiento superior a las herramientas clínicas tradicionales.
Descargas
Citas
Dewan MC, Mummareddy N, Wellons JC, Bonfield CM. Epidemiology of global pediatric traumatic brain injury: qualitative review. World Neurosurg [Internet]. 2016; 91: 497-509.e1. Disponible en: https://doi.org/10.1016/j.wneu.2016.03.045
Maas AI, Menon DK, Manley GT, Abrams M, Åkerlund C, Andelic N, et al. Traumatic brain injury: progress and challenges in prevention, clinical care, and research. Lancet Neurol [Internet]. 2022; 21(11): 1004-1060. Disponible en: https://doi.org/10.1016/S1474-4422(22)00309-X
Lumba-Brown A, Yeates KO, Sarmiento K, Breiding MJ, Haegerich TM, Gioia GA, et al. Centers for disease control and prevention guideline on the diagnosis and management of mild traumatic brain injury among children. JAMA Pediatr [Internet]. 2018; 172(11): e182853. Disponible en: https://doi.org/10.1001/jamapediatrics.2018.2853
Goh MS, Looi DS, Goh JL, Sultana R, Goh SS, Lee JH, et al. The impact of traumatic brain injury on neurocognitive outcomes in children: a systematic review and meta-analysis. J Neurol Neurosurg Psychiatry [Internet]. 2021; 92(8): 847-853. Disponible en: https://doi.org/10.1136/jnnp-2020-325066
Blackwell LS, Grell R. Pediatric traumatic brain injury: impact on the developing brain. Pediatr Neurol [Internet]. 2023; 148: 215-222. Disponible en: https://doi.org/10.1016/j.pediatrneurol.2023.06.019
Fulkerson DH, White IK, Rees JM, Baumanis MM, Smith JL, Ackerman LL, et al. Analysis of long-term (median 10.5 years) outcomes in children presenting with traumatic brain injury and an initial Glasgow Coma Scale score of 3 or 4. J Neurosurg Pediatr [Internet]. 2015; 16(4): 410-419. Disponible en: https://thejns.org/pediatrics/view/journals/j-neurosurg-pediatr/16/4/article-p410.pdf
Agramonte JS. Aspectos epidemiológicos en pacientes que sufrieron trauma pediátrico [tesis de título profesional en Internet]. Lima: Universidad Nacional Mayor de San Marcos; 2002. Disponible en: https://hdl.handle.net/20.500.12672/1994
Guillén-Pinto D, Zea-Vera A, Guillén-Mendoza D, Situ-Kcomt M, Reynoso-Osnayo C, Milla-Vera LM, et al. Traumatismo encefalocraneano en niños atendidos en un hospital nacional de Lima, Perú 2004-2011. Rev Peru Med Exp Salud Pública [Internet]. 2013; 30(4): 630-634. Disponible en: http://www.scielo.org.pe/scielo.php?script=sci_arttext&pid=S1726-46342013000400015
Uparela-Reyes MJ, Villegas-Trujillo LM, Cespedes J, Velásquez-Vera M, Rubiano AM. Usefulness of Artificial Intelligence in traumatic brain injury: a bibliometric analysis and mini-review. World Neurosurg [Internet]. 2024; 188: 83-92. Disponible en: https://doi.org/10.1016/j.wneu.2024.05.065
Folweiler KA, Sandsmark DK, Diaz-Arrastia R, Cohen AS, Masino AJ. Unsupervised machine learning reveals novel traumatic brain injury patient phenotypes with distinct acute injury profiles and long-term outcomes. J Neurotrauma [Internet]. 2020; 37(12): 1431-1444. Disponible en: https://doi.org/10.1089/neu.2019.6705
Hibi A, Jaberipour M, Cusimano MD, Bilbily A, Krishnan RG, Aviv RI, et al. Automated identification and quantification of traumatic brain injury from CT scans: Are we there yet? Medicine [Internet]. 2022; 101(47): e31848. Disponible en: https://doi.org/10.1097/MD.0000000000031848
Kang D. Evaluating the accuracy and reliability of blowout fracture area measurement methods: a review and the potential role of Artificial Intelligence. J Craniofac Surg [Internet]. 2023; 34(6): 1834-1836. Disponible en: https://doi.org/10.1097/SCS.0000000000009486
Bao XL, Zhan X, Wang L, Zhu Q, Fan B, Li GY. Automatic identification and segmentation of orbital blowout fractures based on Artificial Intelligence. Transl Vis Sci Technol [Internet]. 2023; 12(4): 7. Disponible en: https://doi.org/10.1167/tvst.12.4.7
Wang J, Yin MJ, Wen HC. Prediction performance of the machine learning model in predicting mortality risk in patients with traumatic brain injuries: a systematic review and meta-analysis. BMC Med Inform Decis Mak [Internet]. 2023; 23(1): 142. Disponible en: https://doi.org/10.1186/s12911-023-02247-8
Fleck DE, Ernest N, Asch R, Adler CM, Cohen K, Yuan W, et al. Predicting post-concussion symptom recovery in adolescents using a novel Artificial Intelligence. J Neurotrauma [Internet]. 2021; 38(7): 830-836. Disponible en: https://doi.org/10.1089/neu.2020.7018
Choo YJ, Chang MC. Use of machine learning in stroke rehabilitation: a narrative review. Brain Neurorehabil [Internet]. 2022; 15(3): e26. Disponible en: https://doi.org/10.12786/bn.2022.15.e26
Moore L, Abdeljelil AB, Tardif PA, Zemek R, Reed N, Yeates KO, et al. Clinical practice guideline recommendations in pediatric mild traumatic brain injury: a systematic review. Ann Emerg Med [Internet]. 2024; 83(4): 327–339. Disponible en: https://doi.org/10.1016/j.annemergmed.2023.11.012
Peters MD, Godfrey C, McInerney P, Munn Z, Tricco AC, Khalil H. Scoping Reviews (2020). En: Aromataris E, Lockwood C, Porritt K, Pilla B, Jordan Z, editors. JBI Manual for Evidence Synthesis. JBI; 2024. Cap. 10. Disponible en: https://doi.org/10.46658/JBIMES-24-09
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; 169(7): 467-473. Disponible en: https://doi.org/10.7326/M18-0850
Xie Y, Zhai Y, Lu G. Evolution of Artificial Intelligence in healthcare: a 30-year bibliometric study. Front Med [Internet]. 2025; 11: 1505692. Disponible en: https://doi.org/10.3389/fmed.2024.1505692
Ouzzani M, Hammady, H, Fedorowicz Z, Elmagarmid A. Rayyan-a web and mobile app for systematic reviews. Syst Rev [Internet]. 2016; 5(1): 210. Disponible en: https://doi.org/10.1186/s13643-016-0384-4
Tunthanathip T, Duangsuwan J, Wattanakitrungroj N, Tongman S, Phuenpathom N. Comparison of intracranial injury predictability between machine learning algorithms and the nomogram in pediatric traumatic brain injury. Neurosurg Focus [Internet]. 2021; 51(5): E7. Disponible en: https://doi.org/10.3171/2021.8.FOCUS2155
Tunthanathip T, Oearsakul T. Application of machine learning to predict the outcome of pediatric traumatic brain injury. Chin J Traumatol [Internet]. 2021; 24(6): 350-355. Disponible en: https://doi.org/10.1016/j.cjtee.2021.06.003
Ellethy H, Chandra SS, Nasrallah FA. The detection of mild traumatic brain injury in paediatrics using artificial neural networks. Comput Biol Med [Internet]. 2021; 135: 104614. Disponible en: https://doi.org/10.1016/j.compbiomed.2021.104614
Daley M, Cameron S, Ganesan SL, Patel MA, Stewart TC, Miller MR, et al. Pediatric severe traumatic brain injury mortality prediction determined with machine learning-based modeling. Injury [Internet]. 2022; 53(3): 992-998. Disponible en: https://doi.org/10.1016/j.injury.2022.01.008
Shahi N, Shahi AK, Phillips R, Shirek G, Bensard D, Moulton SL. Decision-making in pediatric blunt solid organ injury: a deep learning approach to predict massive transfusion, need for operative management, and mortality risk. J Pediatr Surg [Internet]. 2021; 56(2): 379-384. Disponible en: https://doi.org/10.1016/j.jpedsurg.2020.10.021
Farzaneh CA, Schomberg J, Sullivan BG, Guner YS, Nance ML, Gibbs D, et al. Development and validation of machine learning models for the prediction of blunt cerebrovascular injury in children. J Pediatr Surg [Internet]. 2022; 57(4): 732-738. Disponible en: https://doi.org/10.1016/j.jpedsurg.2021.11.008
Rowe C, Wiesendanger K, Polet C, Kuppermann N, Aronoff S. Derivation and validation of a simplified clinical prediction rule for identifying children at increased risk for clinically important traumatic brain injuries following minor blunt head trauma. J Pediatr X [Internet]. 2020; 3: 100026. Disponible en: https://doi.org/10.1016/j.ympdx.2020.100026
Bahado-Singh RO, Vishweswaraiah S, Er A, Aydas B, Turkoglu O, Taskin BD, et al. Artificial Intelligence and the detection of pediatric concussion using epigenomic analysis. Brain Res [Internet]. 2020; 1726: 146510. Disponible: https://doi.org/10.1016/j.brainres.2019.146510
Fedorchak G, Rangnekar A, Onks C, Loeffert AC, Loeffert J, Olympia RP, et al. Saliva RNA biomarkers predict concussion duration and detect symptom recovery: a comparison with balance and cognitive testing. J Neurol [Internet]. 2021; 268(11): 4349-4361. Disponible en: https://doi.org/10.1007/s00415-021-10566-x
Chong SL, Liu N, Barbier S, Ong ME. Predictive modeling in pediatric traumatic brain injury using machine learning. BMC Med Res Methodol [Internet]. 2015; 15: 22. Disponible en: https://doi.org/10.1186/s12874-015-0015-0
Heo S, Ha J, Jung W, Yoo S, Song Y, Kim T, et al. Decision effect of a deep-learning model to assist a head computed tomography order for pediatric traumatic brain injury. Sci Rep [Internet]. 2022; 12: 12454. Diponible en: https://doi.org/10.1038/s41598-022-16313-0
Zou B, Mi X, Stone E, Zou F. A deep neural network framework to derive interpretable decision rules for accurate traumatic brain injury identification of infants. BMC Med Inform Decis Mak [Internet]. 2023; 23(1): 58. Disponible en: https://doi.org/10.1186/s12911-023-02155-x
Iyer KK, Zalesky A, Barlow KM, Cocchi L. Default mode network anatomy and function is linked to pediatric concussion recovery. Ann Clin Transl Neurol [Internet]. 2019; 6(12): 2544-2554. Disponible en: https://doi.org/10.1002/acn3.50951
Zahid A, Hubbard ME, Lockyer J, Podolak O, Dammavalam VM, Grady M, et al. Eye Tracking as a biomarker for concussion in children. Clin J Sport Med [Internet]. 2020; 30(5): 433-443. Disponible en: https://doi.org/10.1097/JSM.0000000000000639
Bertsimas D, Dunn J, Steele DW, Trikalinos TA, Wang Y. Comparison of machine learning optimal classification trees with the pediatric emergency care applied research network head trauma decision rules. JAMA Pediatr [Internet]. 2019; 173(7): 648-656. Disponible en: https://doi.org/10.1001/jamapediatrics.2019.1068
Guberman GI, Stojanovski S, Nishat E, Ptito A, Bzdok D, Wheeler AL, et al. Multi-tract multi-symptom relationships in pediatric concussion. eLife [Internet]. 2022; 11: e70450. Disponible en: https://doi.org/10.7554/eLife.70450
Kim YT, Kim H, Lee CH, Yoon BC, Kim JB, Choi YH, et al. Intracranial densitometry-augmented machine learning enhances the prognostic value of brain ct in pediatric patients with traumatic brain injury: a retrospective pilot study. Front Pediatr [Internet]. 2021; 9: 750272. Disponible en: https://doi.org/10.3389/fped.2021.750272
Ren Y, Osborne N, Peterson CB, DeMaster DM, Ewing-Cobbs L, Vannucci M. Bayesian varying-effects vector autoregressive models for inference of brain connectivity networks and covariate effects in pediatric traumatic brain injury. Hum Brain Mapp [Internet]. 2024; 45(10): e26763. Disponible en: https://doi.org/10.1002/hbm.26763
Greenan K, Taylor SL, Fulkerson D, Shahlaie K, Gerndt C, Krueger EM, et al. Selection of children with ultra-severe traumatic brain injury for neurosurgical intervention. J Neurosurg Pediatr [Internet]. 2019; 23(6): 670-679. Disponible en: https://doi.org/10.3171/2019.1.PEDS18293
Choi JW, Cho YJ, Ha JY, Lee YY, Koh SY, Seo JY, et al. Deep learning-assisted diagnosis of pediatric skull fractures on plain radiographs. Korean J Radiol [Internet]. 2022; 23(3): 343-354. Disponible en: https://doi.org/10.3348/kjr.2021.0449
Jeong TS, Yee GT, Kim KG, Kim YJ, Lee SG, Kim WK. Automatically diagnosing skull fractures using an object detection method and deep learning algorithm in plain radiography images. J Korean Neurosurg Soc [Internet]. 2023; 66(1): 53-62. Disponible en: https://doi.org/10.3340/jkns.2022.0062
Huang MX, Angeles-Quinto A, Robb-Swan A, De-la-Garza BG, Huang CW, Cheng CK, et al. Assessing pediatric mild traumatic brain injury and its recovery using resting-state magnetoencephalography source magnitude imaging and machine learning. J Neurotrauma [Internet]. 2023; 40(11-12): 1112-1129. Disponible en: https://doi.org/10.1089/neu.2022.0220
Hale AT, Stonko DP, Brown A, Lim J, Voce DJ, Gannon SR, et al. Machine-learning analysis outperforms conventional statistical models and CT classification systems in predicting 6-month outcomes in pediatric patients sustaining traumatic brain injury. Neurosurg Focus [Internet]. 2018; 45(5): E2. Disponible en: https://doi.org/10.3171/2018.8.FOCUS17773
Raji CA, Wang MB, Nguyen N, Owen JP, Palacios EM, Yuh EL, et al. Connectome mapping with edge density imaging differentiates pediatric mild traumatic brain injury from typically developing controls: proof of concept. Pediatr Radiol [Internet]. 2020; 50(11): 1594-1601. Disponible en: https://doi.org/10.1007/s00247-020-04743-9
Maddux AB, Sevick C, Cox-Martin M, Bennett TD. Novel claims-based outcome phenotypes in survivors of pediatric traumatic brain injury. J Head Trauma Rehabil [Internet]. 2021; 36(4): 242-252. Disponible en: https://doi.org/10.1097/HTR.0000000000000646
Hale AT, Stonko DP, Lim J, Guillamondegui OD, Shannon CN, Patel MB. Using an artificial neural network to predict traumatic brain injury. J Neurosurg Pediatr [Internet]. 2019; 23(2): 219-226. Disponible en: https://doi.org/10.3171/2018.8.PEDS18370
Yadav K, Sarioglu E, Choi HA, Cartwright WB, Hinds PS, Chamberlain JM. Automated outcome classification of computed tomography imaging reports for pediatric traumatic brain injury. Acad Emerg Med [Internet]. 2016; 23(2): 171-178. Disponible en: https://doi.org/10.1111/acem.12859
Miyagawa T, Saga M, Sasaki M, Shimizu M, Yamaura A. Statistical and machine learning approaches to predict the necessity for computed tomography in children with mild traumatic brain injury. PloS One [Internet]. 2023; 18(1): e0278562. Disponible en: https://doi.org/10.1371/journal.pone.0278562
Kayhanian S, Young AM, Mangla C, Jalloh I, Fernandes HM, Garnett MR, et al. Modelling outcomes after paediatric brain injury with admission laboratory values: a machine-learning approach. Pediatr Res [Internet]. 2019; 86(5): 641-645. Disponible en: https://doi.org/10.1038/s41390-019-0510-9
Yang Z, Tsui B, Wu Z. Assessment system for child head injury from falls based on neural network learning. Sensors [Internet]. 2023; 23(18): 7896. Disponible en: https://doi.org/10.3390/s23187896
Bajwa J, Munir U, Nori A, Williams B. Artificial Intelligence in healthcare: transforming the practice of medicine. Future Healthc J [Internet]. 2021; 8(2): e188-e194. Disponible en: https://doi.org/10.7861/fhj.2021-0095
Clipper B. The influence of the COVID-19 pandemic on technology: adoption in health care. Nurse Lead [Internet]. 2020; 18(5): 500-503. Disponible en: https://doi.org/10.1016/j.mnl.2020.06.008
Pasricha M, Thakur V, Ghosh D. The future of work, artificial intelligence, and digital government: policy perspectives for Asia [Internet]. No. 202-20 (September). ADBInstitute; 2024. Disponible en:
https://doi.org/10.56506/TRYI4372
Han R, Acosta JN, Shakeri Z, Ionannidis JP, Topol EJ, Rajpurkar P. Randomised controlled trials evaluating artificial intelligence in clinical practice: a scoping review. Lancet Digit Health [Internet]. 2024; 6(5): e367-e373. Disponible en: https://doi.org/10.1016/S2589-7500(24)00047-5
Abbasi MH, Somai M, Saber H. The trend of Artificial Intelligence application in medicine and neurology; the state-of-the-art systematic scoping review 2010-2022. Intell-Based Med [Internet]. 2024; 10: 100179. Disponible en: https://doi.org/10.1016/j.ibmed.2024.100179
Ono S, Goto T. Introduction to supervised machine learning in clinical epidemiology. Ann Clin Epidemiol [Internet]. 2022; 4(3): 63-71. Disponible en: https://doi.org/10.37737/ace.22009
Egger J, Gsaxner C, Pepe A, Pomykala KL, Jonske F, Kurz M, et al. Medical deep learning-A systematic meta-review. Comput Methods Programs Biomed [Internet]. 2022; 221: 106874. Disponible en: https://doi.org/10.1016/j.cmpb.2022.106874
Meral Atiş G, Altay T, Atiş ŞE. Comparison of CATCH, PECARN, and CHALICE clinical decision rules in pediatric patients with mild head trauma. Eur J Trauma Emerg Surg [Internet]. 2022; 48(4): 3123-3130. Disponible en: https://doi.org/10.1007/s00068-021-01859-x
Easter JS, Bakes K, Dhaliwal J, Miller M, Caruso E, Haukoos JS. Comparison of PECARN, CATCH, and CHALICE rules for children with minor head injury: a prospective cohort study. Ann Emerg Med [Internet]. 2014; 64(2): 145-152.e5. Disponible en: https://doi.org/10.1016/j.annemergmed.2014.01.030
Smolen P, Dash PK, Redell JB. Traumatic brain injury-associated epigenetic changes and the risk for neurodegenerative diseases. Front Neurosci [Internet]. 2023; 17: 1259405. Disponible en: https://doi.org/10.3389/fnins.2023.1259405
Yuan T, Edelmann D, Fan Z, Alwers E, Kather JN, Brenner H, et al. Machine learning in the identification of prognostic DNA methylation biomarkers among patients with cancer: a systematic review of epigenome-wide studies. Artif Intell Med [Internet]. 2023; 143: 102589. Disponible en: https://doi.org/10.1016/j.artmed.2023.102589
Descargas
Publicado
Cómo citar
Número
Sección
Licencia
Derechos de autor 2025 Rogelio Saldaña Rimarachin, Eric Salvador Segura Surco, Carlos Salazar Ordoñez, Daniel Guillén Pinto
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial 4.0.
