Implementación de un prototipo de software para predecir complicaciones en pacientes en unidad de cuidados intensivos pediátricos (UCIP), a través de modelos de aprendizaje automático
ilustraciones, graficas
- Autores:
-
Baquero Tibocha, Diego Andrés
- Tipo de recurso:
- Fecha de publicación:
- 2023
- Institución:
- Universidad Nacional de Colombia
- Repositorio:
- Universidad Nacional de Colombia
- Idioma:
- spa
- OAI Identifier:
- oai:repositorio.unal.edu.co:unal/83874
- Palabra clave:
- 620 - Ingeniería y operaciones afines::629 - Otras ramas de la ingeniería
APRENDIZAJE
APRENDIZAJE AUTOMATICO (INTELIGENCIA ARTIFICIAL)
Learning
Machine learning
Signos vitales
Aprendizaje automático
Predicción
Estado clínico
Cuidado intensivo pediátrico
Vital signs
Prediction
Clinical status
Pediatric intensive care
- Rights
- openAccess
- License
- Atribución-NoComercial 4.0 Internacional
| id |
UNACIONAL2_676eb5c1f03d76642aeececed2123cdf |
|---|---|
| oai_identifier_str |
oai:repositorio.unal.edu.co:unal/83874 |
| network_acronym_str |
UNACIONAL2 |
| network_name_str |
Universidad Nacional de Colombia |
| repository_id_str |
|
| dc.title.spa.fl_str_mv |
Implementación de un prototipo de software para predecir complicaciones en pacientes en unidad de cuidados intensivos pediátricos (UCIP), a través de modelos de aprendizaje automático |
| dc.title.translated.eng.fl_str_mv |
Implementation of a software prototype to predict complications in patients in a pediatric intensive care unit (PICU), through machine learning models |
| title |
Implementación de un prototipo de software para predecir complicaciones en pacientes en unidad de cuidados intensivos pediátricos (UCIP), a través de modelos de aprendizaje automático |
| spellingShingle |
Implementación de un prototipo de software para predecir complicaciones en pacientes en unidad de cuidados intensivos pediátricos (UCIP), a través de modelos de aprendizaje automático 620 - Ingeniería y operaciones afines::629 - Otras ramas de la ingeniería APRENDIZAJE APRENDIZAJE AUTOMATICO (INTELIGENCIA ARTIFICIAL) Learning Machine learning Signos vitales Aprendizaje automático Predicción Estado clínico Cuidado intensivo pediátrico Vital signs Prediction Clinical status Pediatric intensive care |
| title_short |
Implementación de un prototipo de software para predecir complicaciones en pacientes en unidad de cuidados intensivos pediátricos (UCIP), a través de modelos de aprendizaje automático |
| title_full |
Implementación de un prototipo de software para predecir complicaciones en pacientes en unidad de cuidados intensivos pediátricos (UCIP), a través de modelos de aprendizaje automático |
| title_fullStr |
Implementación de un prototipo de software para predecir complicaciones en pacientes en unidad de cuidados intensivos pediátricos (UCIP), a través de modelos de aprendizaje automático |
| title_full_unstemmed |
Implementación de un prototipo de software para predecir complicaciones en pacientes en unidad de cuidados intensivos pediátricos (UCIP), a través de modelos de aprendizaje automático |
| title_sort |
Implementación de un prototipo de software para predecir complicaciones en pacientes en unidad de cuidados intensivos pediátricos (UCIP), a través de modelos de aprendizaje automático |
| dc.creator.fl_str_mv |
Baquero Tibocha, Diego Andrés |
| dc.contributor.advisor.none.fl_str_mv |
Niño Vásquez, Luis Fernando Izquierdo Borrero, Ledys María |
| dc.contributor.author.none.fl_str_mv |
Baquero Tibocha, Diego Andrés |
| dc.contributor.researchgroup.spa.fl_str_mv |
laboratorio de Investigación en Sistemas Inteligentes Lisi |
| dc.subject.ddc.spa.fl_str_mv |
620 - Ingeniería y operaciones afines::629 - Otras ramas de la ingeniería |
| topic |
620 - Ingeniería y operaciones afines::629 - Otras ramas de la ingeniería APRENDIZAJE APRENDIZAJE AUTOMATICO (INTELIGENCIA ARTIFICIAL) Learning Machine learning Signos vitales Aprendizaje automático Predicción Estado clínico Cuidado intensivo pediátrico Vital signs Prediction Clinical status Pediatric intensive care |
| dc.subject.lemb.spa.fl_str_mv |
APRENDIZAJE APRENDIZAJE AUTOMATICO (INTELIGENCIA ARTIFICIAL) |
| dc.subject.lemb.eng.fl_str_mv |
Learning Machine learning |
| dc.subject.proposal.spa.fl_str_mv |
Signos vitales Aprendizaje automático Predicción Estado clínico Cuidado intensivo pediátrico |
| dc.subject.proposal.eng.fl_str_mv |
Vital signs Prediction Clinical status Pediatric intensive care |
| description |
ilustraciones, graficas |
| publishDate |
2023 |
| dc.date.accessioned.none.fl_str_mv |
2023-05-25T19:48:30Z |
| dc.date.available.none.fl_str_mv |
2023-05-25T19:48:30Z |
| dc.date.issued.none.fl_str_mv |
2023 |
| dc.type.spa.fl_str_mv |
Trabajo de grado - Maestría |
| dc.type.driver.spa.fl_str_mv |
info:eu-repo/semantics/masterThesis |
| dc.type.version.spa.fl_str_mv |
info:eu-repo/semantics/acceptedVersion |
| dc.type.content.spa.fl_str_mv |
Text |
| dc.type.redcol.spa.fl_str_mv |
http://purl.org/redcol/resource_type/TM |
| status_str |
acceptedVersion |
| dc.identifier.uri.none.fl_str_mv |
https://repositorio.unal.edu.co/handle/unal/83874 |
| dc.identifier.instname.spa.fl_str_mv |
Universidad Nacional de Colombia |
| dc.identifier.reponame.spa.fl_str_mv |
Repositorio Institucional Universidad Nacional de Colombia |
| dc.identifier.repourl.spa.fl_str_mv |
https://repositorio.unal.edu.co/ |
| url |
https://repositorio.unal.edu.co/handle/unal/83874 https://repositorio.unal.edu.co/ |
| identifier_str_mv |
Universidad Nacional de Colombia Repositorio Institucional Universidad Nacional de Colombia |
| dc.language.iso.spa.fl_str_mv |
spa |
| language |
spa |
| dc.relation.references.spa.fl_str_mv |
Abromavičius, V. y Serackis, A. (2019). Sepsis Prediction Model Based on Vital Signs Related Features. Amer, A.Y.A., Vranken, J., Wouters, F., Mesotten, D., Vandervoort, P., Storms, V., Luca, S., Vanrumste, B. y Aerts, J.-M. (2019). Feature engineering for ICU mortality prediction based on hourly to bi-hourly measurements. Applied Sciences (Switzerland), 9. AnalystPrep (s. f.). Machine Learning Process. [Ilustración]. https://analystprep.com/study-notes/wpcontent/uploads/2020/04/MachineLearingApproaches_img1.jpg Atashi, A., Ahmadian, L., Rahmatinezhad, Z., Miri, M., Nazeri, N. y Eslami, S. (2018). Development of a national core dataset for the Iranian ICU patients outcome prediction: A comprehensive approach. Journal of Innovation in Health Informatics, 25, 71-76. Awad, A., Bader-El-Den, M., McNicholas, J. y Briggs, J. (2017). Early hospital mortality prediction of intensive care unit patients using an ensemble learning approach. International Journal of Medical Informatics, 108, 185-195. Barnes, R., Clarke, D., Farina, Z., Sartorius, B., Brysiewicz, P., Laing, G., Bruce, J. y Kong, V. (2018). Vital sign based shock scores are poor at triaging South African trauma patients. American Journal of Surgery, 216, 235-239. Bedoya, A.D., Clement, M.E., Phelan, M., Steorts, R.C., O'Brien, C. y Goldstein, B.A. (2019). Minimal Impact of Implemented Early Warning Score and Best Practice Alert for Patient Deterioration. Critical Care Medicine, 47, 49-55. Bellew, S.D., Cabrera, D., Lohse, C.M. y Bellolio, M.F. (2017). Predicting Early Rapid Response Team Activation in Patients Admitted From the Emergency Department: The PeRRT Score. Academic Emergency Medicine, 24, 216-225. Brilej, D., Stropnik, D., Lefering, R. y Komadina, R. (2017). Algorithm for activation of coagulation support treatment in multiple injured patients––cohort study. European Journal of Trauma and Emergency Surgery, 43, 423-430. Brown, A., Ballal, A. y Al-Haddad, M. (2019). Recognition of the critically ill patient and escalation of therapy. Anaesthesia and Intensive Care Medicine, 20, 1-5. Carlin, C.S., Ho, L.V., Ledbetter, D.R., Aczon, M.D. y Wetzel, R.C. (2018). Predicting individual physiologically acceptable states at discharge from a pediatric intensive care unit. Journal of the American Medical Informatics Association, 25, 1600-1607. Chen, T., Xu, J., Ying, H., Chen, X., Feng, R., Fang, X., Gao, H. y Wu, J. (2019). Prediction of Extubation Failure for Intensive Care Unit Patients Using Light Gradient Boosting Machine. IEEE Access, 7, 150960-150968. De Pasquale, M., Moss, T.J., Cerutti, S., Calland, J.F., Lake, D.E., Moorman, J.R. y Ferrario, M. (2017). Hemorrhage prediction models in surgical intensive care: Bedside monitoring data adds information to lab values. IEEE Journal of Biomedical and Health Informatics, 21, 1703-1710. Ding, Y., Ma, X. y Wang, Y. (2018). Health status monitoring for ICU patients based on locally weighted principal component analysis. Computer Methods and Programs in Biomedicine, 156, 61-71. Fagerström, J., Bång, M., Wilhelms, D. y Chew, M.S. (2019). LiSep LSTM: A Machine Learning Algorithm for Early Detection of Septic Shock. Scientific Reports, 9. Géron, A. (2017). Hands-On Machine Learning with Scikit-Learn and TensorFlow: Techniques and Tools to Build Learning Machines. Van Duuren Media. Ge, W., Huh, J.-W., Park, Y.R., Lee, J.-H., Kim, Y.-H. y A. Turchin (2018). An Interpretable ICU Mortality Prediction Model Based on Logistic Regression and Recurrent Neural Networks with LSTM units. AMIA Annual Symposium proceedings. AMIA Symposium, 2018, 460-469. Haider, A., Con, J., Prabhakaran, K., Anderson, P., Policastro, A., Feeney, J. y Latifi, R. (2019). Developing a simple clinical score for predicting mortality and need for ICU in trauma patients. American Surgeon, 85, 733-737. Hever, G. , Cohen, L., O’Connor, M.F., Matot, I., Lerner, B. y Bitan, Y. (2020). Machine learning applied to multi-sensor information to reduce false alarm rate in the ICU. Journal of Clinical Monitoring and Computing, 34, 339-352. Hever, G., Cohen, L., O’Connor, M. F., Matot, I., Lerner, B., & Bitan, Y. (2019). Machine learning applied to multi-sensor information to reduce false alarm rate in the ICU. Journal of Clinical Monitoring and Computing, 34(2), 339–352. https://doi.org/10.1007/s10877-019-00307-x Hirano, Y., Kondo, Y., Hifumi, T., Yokobori, S., Kanda, J., Shimazaki, J., Hayashida, K., Moriya, T., Yagi, M., Takauji, S., Tanaka, H. y Yaguchi, A. (2021). Machine learningbased mortality prediction model for heat-related illness. Scientific Reports, 11. IBM Cloud Education. (2020, 15 julio). Machine Learning. IBM. https://www.ibm.com/cloud/learn/machine-learning Izquierdo, L. M., Nino, L. F., & Prieto Rojas, J. (2020). Modeling the vital sign space to detect the deterioration of patients in a pediatric intensive care unit. 16th International Symposium on Medical Information Processing and Analysis. Published. https://doi.org/10.1117/12.2579629 Izquierdo, L. M., Nino, L. F. (2021). Modelamiento del espacio de signos vitales para detectar el deterioro de los pacientes en una unidad de cuidados intensivos. Universidad Nacional de Colombia. Karimi Moridani, M. y Haghighi Bardineh, Y. (2018). Presenting an efficient approach based on novel mapping for mortality prediction in intensive care unit cardiovascular patients. MethodsX, 5, 1291-1298. Kefi, Z., Aloui, K. y Naceur, M.S. (2019). The early prediction of neonates mortality in Intensive Care Unit. (pp. 304-306). Koyner, J.L., Carey, K.A., Edelson, D.P. y Churpek, M.M. (2018). The development of a machine learning inpatient acute kidney injury prediction model. Critical Care Medicine, 46, 1070-1077. Li, X., Ge, P., Zhu, J., Li, H., Graham, J., Singer, A., Richman, P.S. y Duong, T.Q. (2020). Deep learning prediction of likelihood of ICU admission and mortality in COVID-19 patients using clinical variables. PeerJ, 8. Malycha, J., Farajidavar, N., Pimentel, M.A.F., Redfern, O., Clifton, D.A., Tarassenko, L., Meredith, P., Prytherch, D., Ludbrook, G., Young, J.D. y Watkinson, P.J. (2019). The effect of fractional inspired oxygen concentration on early warning score performance: A database analysis. Resuscitation, 139, 192-199. Marafino, B.J., Park, M., Davies, J.M., Thombley, R., Luft, H.S., Sing, D.C., Kazi, D.S. Dejong, C., Boscardin, W.J., Dean, M.L. y Dudley, R.A. (2018). Validation of Prediction Models for Critical Care Outcomes Using Natural Language Processing of Electronic Health Record Data. JAMA Network Open, 1. Masud, M.M., Cheratta, M. y Harahsheh, A.R.A. (2018). Survival prediction of ICU patients using knowledge intensive data grouping and selection. Matrices de confusión - Training. (s. f.). Microsoft Learn. https://learn.microsoft.com/eses/training/modules/machine-learning-confusion-matrix/2-confusion-matrices Mayampurath, A., Jani, P., Dai, Y., Gibbons, R., Edelson, D. y Churpek, M.M. (2020). A vital sign-based model to predict clinical deterioration in hospitalized children. Pediatric Critical Care Medicine, 820-826. Melinosky, C., Yang, S., Hu, P., Li, H., Miller, C.H.T., Khan, I., Mackenzie, C., Chang, W.- T., Parikh, G., Stein, D., Stein, D. y Badjatia, N. (2018). Continuous vital sign analysis to predict secondary neurological decline after traumatic brain injury. Frontiers in Neurology, 9. Messinger, A.I., Bui, N., Wagner, B.D., Szefler, S.J., Vu, T. y Deterding, R.R. (2019). Novel pediatric-automated respiratory score using physiologic data and machine learning in asthma. Pediatric Pulmonology, 54, 1149-1155. Monteiro, F., Meloni, F., Baranauskas, J.A. y Macedo, A.A. (2020). Prediction of mortality in Intensive Care Units: a multivariate feature selection. Journal of Biomedical Informatics, 107. Nielsen, A.B., Thorsen-Meyer, H.-C., Belling, K., Nielsen, A.P., Thomas, C.E., Chmura, P.J., Lademann, M., Moseley, P.L., Heimann, M., Dybdahl, L., Perner, A. y Brunak, S. (2019). Survival prediction in intensive-care units based on aggregation of long-term disease history and acute physiology: a retrospective study of the Danish National Patient Registry and electronic patient records. The Lancet Digital Health, 1, e78e89. Parreco, J., Soe-Lin, H., Parks, J.J., Byerly, S., Chatoor, M., Buicko, J.L., Namias, N. y Rattan, R. (2019). Comparing machine learning algorithms for predicting acute kidney injury. American Surgeon, 85, 725-729. Platzi: Cursos online profesionales de tecnología. (2018). Platzi. https://platzi.com/tutoriales/1269-probabilidad-estadistica/2308-coeficiente-decorrelacion-que-es-y-para-que-sirve/?utm_source=google Pollard, T.J., Johnson, A.E.W., Raffa, J.D., Celi, L.A., Mark, R.G. y Badawi, O. (2018). The eICU collaborative research database, a freely available multi-center database for critical care research. Scientific Data, 5. R.G. Barry, T.T. Wolbert, F.B. Mozaffari, P.D. Ray, E.C. Thompson, T.W. Gress, & D.A. Denning (2019). Comparison of geriatric trauma outcomes when admitted to a medical or surgical service after a fall. Journal of Surgical Research, 233, 391-396. Radhachandran, A., Garikipati, A., Zelin, N.S., Pellegrini, E., Ghandian, S., Calvert, J., Hoffman, J., Mao, Q. y Das, R. (2021). Prediction of short-term mortality in acute heart failure patients using minimal electronic health record data. BioData Mining, 14. Rubin, J., Potes, C., Xu-Wilson, M., Dong, J., Rahman, A., Nguyen, H. y Moromisato, D. (2018). An ensemble boosting model for predicting transfer to the pediatric intensive care unit. International Journal of Medical Informatics, 112, 15-20. Salahuddin, N., Shafquat, A., Marashly, Q., Zaza, K.J., Sharshir, M., Khurshid, M., Ali, Z., Malgapo, M., Jamil, M.G., Shoukri, M., Hijazi, M. y Al-Ghamdi, B. (2018). Increases in Heart Rate Variability Signal Improved Outcomes in Rapid Response Team Consultations: A Cohort Study. Cardiology Research and Practice, 2018. Satchidanand, N., Servoss, T.J., Singh, R., Bosinski, A.M., Tirpak, P., Horton, L.L. y Naughton, B.J. (2018). Development of a Risk Tool to Support Discussions of Care for Older Adults Admitted to the ICU With Pneumonia. American Journal of Hospice and Palliative Medicine, 35, 1201-1206. Shamout, F.E., Zhu, T., Sharma, P., Watkinson, P.J. y Clifton, D.A. (2020). Deep Interpretable Early Warning System for the Detection of Clinical Deterioration. IEEE Journal of Biomedical and Health Informatics, 24, 437-446. Tamir, M. (2021, 29 enero). What Is Machine Learning? UCB-UMT. https://ischoolonline.berkeley.edu/blog/what-is-machine-learning/ Timm, F.P., Zaremba, S., Grabitz, S.D., Farhan, H.N., Zaremba, S., Siliski, E., Shin, C.H., Muse, S., Friedrich, S., Mojica, J.E., Ramachandran, S.-K. y Eikermann, M. (2018). Effects of opioids given to facilitate mechanical ventilation on sleep apnea after extubation in the intensive care unit. Sleep, 41. Tsur, E., Last, M., Garcia, V.F., Udassin, R., Klein, M. y Brotfain, E. (2019). Hypotensive episode prediction in icus via observation window splitting. LNAI, Vol. 11053. Viegas, R., Salgado, C.M., Curto, S., Carvalho, J.P., Vieira, S.M. y Finkelstein, S.N. (2017). Daily prediction of ICU readmissions using feature engineering and ensemble fuzzy modeling. Expert Systems with Applications, 79, 244-253. Wang, Y., Wei, Y., Yang, H., Li, J., Zhou, Y. y Wu, Q. (2020). Utilizing imbalanced electronic health records to predict acute kidney injury by ensemble learning and time series model. BMC Medical Informatics and Decision Making, 20. Wellner, B., Grand, J., Canzone, E., Coarr, M., Brady, P.W., Simmons, J., Kirkendall, E., Dean, N. Kleinman, M. y Sylvester, P. (2017). Predicting unplanned transfers to the intensive care unit: A machine learning approach leveraging diverse clinical elements. JMIR Medical Informatics, 5. Yoon, J.H., Jeanselme, V., Dubrawski, A., Hravnak, M., Pinsky, M.R. y Clermont, G. (2020). Prediction of hypotension events with physiologic vital sign signatures in the intensive care unit. Critical Care, 24. Zachariasse J.M., Van Der Lee, D., Seiger, N., De Vos-Kerkhof, E., Oostenbrink, R. y Moll, H.A. (2017). The role of nurses' clinical impression in the first assessment of children at the emergency department. Archives of Disease in Childhood, 102, 1052- 1056. Zimmerman, L.P., Reyfman, P.A., Smith, A.D.R., Zeng, Z., Kho, A., Sanchez-Pinto, L.N. y Luo, Y. (2019). Early prediction of acute kidney injury following ICU admission using a multivariate panel of physiological measurements. BMC Medical Informatics and Decision Making, 19. |
| dc.rights.coar.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
| dc.rights.license.spa.fl_str_mv |
Atribución-NoComercial 4.0 Internacional |
| dc.rights.uri.spa.fl_str_mv |
http://creativecommons.org/licenses/by-nc/4.0/ |
| dc.rights.accessrights.spa.fl_str_mv |
info:eu-repo/semantics/openAccess |
| rights_invalid_str_mv |
Atribución-NoComercial 4.0 Internacional http://creativecommons.org/licenses/by-nc/4.0/ http://purl.org/coar/access_right/c_abf2 |
| eu_rights_str_mv |
openAccess |
| dc.format.extent.spa.fl_str_mv |
xiv, 87 páginas |
| dc.format.mimetype.spa.fl_str_mv |
application/pdf |
| dc.publisher.spa.fl_str_mv |
Universidad Nacional de Colombia |
| dc.publisher.program.spa.fl_str_mv |
Bogotá - Ingeniería - Maestría en Ingeniería - Ingeniería de Sistemas y Computación |
| dc.publisher.faculty.spa.fl_str_mv |
Facultad de Ingeniería |
| dc.publisher.place.spa.fl_str_mv |
Bogotá, Colombia |
| dc.publisher.branch.spa.fl_str_mv |
Universidad Nacional de Colombia - Sede Bogotá |
| institution |
Universidad Nacional de Colombia |
| bitstream.url.fl_str_mv |
https://repositorio.unal.edu.co/bitstream/unal/83874/1/license.txt https://repositorio.unal.edu.co/bitstream/unal/83874/2/1016036337.2023.pdf https://repositorio.unal.edu.co/bitstream/unal/83874/3/1016036337.2023.pdf.jpg |
| bitstream.checksum.fl_str_mv |
eb34b1cf90b7e1103fc9dfd26be24b4a b3f8dd78dea6ae5c7778aea4a0f21fa6 f0d842feabf463805810fe8616a15525 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio Institucional Universidad Nacional de Colombia |
| repository.mail.fl_str_mv |
repositorio_nal@unal.edu.co |
| _version_ |
1814089410095874048 |
| spelling |
Atribución-NoComercial 4.0 Internacionalhttp://creativecommons.org/licenses/by-nc/4.0/info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Niño Vásquez, Luis Fernandobc784b82735e16fe53653c3f5c8f3bbeIzquierdo Borrero, Ledys María54650b76117390c84015c76bc9d8afefBaquero Tibocha, Diego Andrés20fa8a6927db3b94650b5f441668e8fclaboratorio de Investigación en Sistemas Inteligentes Lisi2023-05-25T19:48:30Z2023-05-25T19:48:30Z2023https://repositorio.unal.edu.co/handle/unal/83874Universidad Nacional de ColombiaRepositorio Institucional Universidad Nacional de Colombiahttps://repositorio.unal.edu.co/ilustraciones, graficasLos cuidadores de pacientes en estado crítico no siempre tienen las habilidades o la experiencia para tratar este tipo de pacientes (Wheatley, 2006). Además, el deterioro fisiológico se puede detectar a partir de cambios sutiles en los signos vitales dentro de una Unidad de Cuidados Intensivos Pediátricos (UCIP) (Izquierdo, 2021). Esto conlleva dificultades para el personal médico al realizar un pronóstico sobre una futura complicación. De acuerdo con lo anterior, este estudio tiene como objetivo implementar un prototipo de software capaz de predecir estados fisiológicos a través de los signos vitales, siguiendo como metodología el Proceso de Aprendizaje Automático (Machine Learning Process, MLP) sobre el conjunto de datos seleccionado. El prototipo se implementó de forma exitosa y se obtuvieron resultados prometedores en cuanto al uso de técnicas de aprendizaje automático para representar el estado actual y futuro de los pacientes en UCIP. Por lo tanto, se debe seguir trabajando en el esfuerzo de complementar el conjunto de datos e implementar nuevas propuestas del uso de las técnicas de aprendizaje automático, y así lograr una monitorización constante sobre los pacientes (Texto tomado de la fuente)Caregivers of critically ill patients do not always have the skills or experience to treat these types of patients (Wheatley, 2006). Furthermore, physiological deterioration can be detected from subtle changes in vital signs within a Pediatric Intensive Care Unit (PICU) (Izquierdo, 2021). This leads to difficulties for medical personnel when making a prognosis about a future complication. Accordingly, this study aims to implement a software prototype capable of predicting physiological states through vital signs, following the Machine Learning Process (MLP) methodology on the selected data set. The prototype was successfully implemented, and promising results were obtained regarding the use of machine learning techniques to represent the current and future state of PICU patients. Therefore, work must continue in the effort to complement the data set and implement new methods for the use of machine learning techniques, and thus achieve constant monitoring of patients.MaestríaMagíster en Ingeniería - Ingeniería de Sistemas y ComputaciónSistemas inteligentesPara la implementación de esta aplicación del aprendizaje automático a la medicina y su interacción con el personal médico, se diseñó una plataforma que se divide en tres aplicaciones llamadas: Frontend (JavaScript/ReactJS), Backend (.NET Ciore 5), y Model API (Python/Keras/Scikit-learn). Las aplicaciones interoperan entre sí para recibir las entradas del usuario, leer los datos, y generar las clasificaciones y predicciones, respectivamente. Las aplicaciones fueron desplegadas en la nube a través de los servicios de Azure y fue necesaria la implementación de Docker para el despliegue del módulo Model API.xiv, 87 páginasapplication/pdfspaUniversidad Nacional de ColombiaBogotá - Ingeniería - Maestría en Ingeniería - Ingeniería de Sistemas y ComputaciónFacultad de IngenieríaBogotá, ColombiaUniversidad Nacional de Colombia - Sede Bogotá620 - Ingeniería y operaciones afines::629 - Otras ramas de la ingenieríaAPRENDIZAJEAPRENDIZAJE AUTOMATICO (INTELIGENCIA ARTIFICIAL)LearningMachine learningSignos vitalesAprendizaje automáticoPredicciónEstado clínicoCuidado intensivo pediátricoVital signsPredictionClinical statusPediatric intensive careImplementación de un prototipo de software para predecir complicaciones en pacientes en unidad de cuidados intensivos pediátricos (UCIP), a través de modelos de aprendizaje automáticoImplementation of a software prototype to predict complications in patients in a pediatric intensive care unit (PICU), through machine learning modelsTrabajo de grado - Maestríainfo:eu-repo/semantics/masterThesisinfo:eu-repo/semantics/acceptedVersionTexthttp://purl.org/redcol/resource_type/TMAbromavičius, V. y Serackis, A. (2019). Sepsis Prediction Model Based on Vital Signs Related Features.Amer, A.Y.A., Vranken, J., Wouters, F., Mesotten, D., Vandervoort, P., Storms, V., Luca, S., Vanrumste, B. y Aerts, J.-M. (2019). Feature engineering for ICU mortality prediction based on hourly to bi-hourly measurements. Applied Sciences (Switzerland), 9.AnalystPrep (s. f.). Machine Learning Process. [Ilustración]. https://analystprep.com/study-notes/wpcontent/uploads/2020/04/MachineLearingApproaches_img1.jpgAtashi, A., Ahmadian, L., Rahmatinezhad, Z., Miri, M., Nazeri, N. y Eslami, S. (2018). Development of a national core dataset for the Iranian ICU patients outcome prediction: A comprehensive approach. Journal of Innovation in Health Informatics, 25, 71-76.Awad, A., Bader-El-Den, M., McNicholas, J. y Briggs, J. (2017). Early hospital mortality prediction of intensive care unit patients using an ensemble learning approach. International Journal of Medical Informatics, 108, 185-195.Barnes, R., Clarke, D., Farina, Z., Sartorius, B., Brysiewicz, P., Laing, G., Bruce, J. y Kong, V. (2018). Vital sign based shock scores are poor at triaging South African trauma patients. American Journal of Surgery, 216, 235-239.Bedoya, A.D., Clement, M.E., Phelan, M., Steorts, R.C., O'Brien, C. y Goldstein, B.A. (2019). Minimal Impact of Implemented Early Warning Score and Best Practice Alert for Patient Deterioration. Critical Care Medicine, 47, 49-55.Bellew, S.D., Cabrera, D., Lohse, C.M. y Bellolio, M.F. (2017). Predicting Early Rapid Response Team Activation in Patients Admitted From the Emergency Department: The PeRRT Score. Academic Emergency Medicine, 24, 216-225.Brilej, D., Stropnik, D., Lefering, R. y Komadina, R. (2017). Algorithm for activation of coagulation support treatment in multiple injured patients––cohort study. European Journal of Trauma and Emergency Surgery, 43, 423-430.Brown, A., Ballal, A. y Al-Haddad, M. (2019). Recognition of the critically ill patient and escalation of therapy. Anaesthesia and Intensive Care Medicine, 20, 1-5.Carlin, C.S., Ho, L.V., Ledbetter, D.R., Aczon, M.D. y Wetzel, R.C. (2018). Predicting individual physiologically acceptable states at discharge from a pediatric intensive care unit. Journal of the American Medical Informatics Association, 25, 1600-1607.Chen, T., Xu, J., Ying, H., Chen, X., Feng, R., Fang, X., Gao, H. y Wu, J. (2019). Prediction of Extubation Failure for Intensive Care Unit Patients Using Light Gradient Boosting Machine. IEEE Access, 7, 150960-150968.De Pasquale, M., Moss, T.J., Cerutti, S., Calland, J.F., Lake, D.E., Moorman, J.R. y Ferrario, M. (2017). Hemorrhage prediction models in surgical intensive care: Bedside monitoring data adds information to lab values. IEEE Journal of Biomedical and Health Informatics, 21, 1703-1710.Ding, Y., Ma, X. y Wang, Y. (2018). Health status monitoring for ICU patients based on locally weighted principal component analysis. Computer Methods and Programs in Biomedicine, 156, 61-71.Fagerström, J., Bång, M., Wilhelms, D. y Chew, M.S. (2019). LiSep LSTM: A Machine Learning Algorithm for Early Detection of Septic Shock. Scientific Reports, 9.Géron, A. (2017). Hands-On Machine Learning with Scikit-Learn and TensorFlow: Techniques and Tools to Build Learning Machines. Van Duuren Media.Ge, W., Huh, J.-W., Park, Y.R., Lee, J.-H., Kim, Y.-H. y A. Turchin (2018). An Interpretable ICU Mortality Prediction Model Based on Logistic Regression and Recurrent Neural Networks with LSTM units. AMIA Annual Symposium proceedings. AMIA Symposium, 2018, 460-469.Haider, A., Con, J., Prabhakaran, K., Anderson, P., Policastro, A., Feeney, J. y Latifi, R. (2019). Developing a simple clinical score for predicting mortality and need for ICU in trauma patients. American Surgeon, 85, 733-737.Hever, G. , Cohen, L., O’Connor, M.F., Matot, I., Lerner, B. y Bitan, Y. (2020). Machine learning applied to multi-sensor information to reduce false alarm rate in the ICU. Journal of Clinical Monitoring and Computing, 34, 339-352.Hever, G., Cohen, L., O’Connor, M. F., Matot, I., Lerner, B., & Bitan, Y. (2019). Machine learning applied to multi-sensor information to reduce false alarm rate in the ICU. Journal of Clinical Monitoring and Computing, 34(2), 339–352. https://doi.org/10.1007/s10877-019-00307-xHirano, Y., Kondo, Y., Hifumi, T., Yokobori, S., Kanda, J., Shimazaki, J., Hayashida, K., Moriya, T., Yagi, M., Takauji, S., Tanaka, H. y Yaguchi, A. (2021). Machine learningbased mortality prediction model for heat-related illness. Scientific Reports, 11.IBM Cloud Education. (2020, 15 julio). Machine Learning. IBM. https://www.ibm.com/cloud/learn/machine-learningIzquierdo, L. M., Nino, L. F., & Prieto Rojas, J. (2020). Modeling the vital sign space to detect the deterioration of patients in a pediatric intensive care unit. 16th International Symposium on Medical Information Processing and Analysis. Published. https://doi.org/10.1117/12.2579629Izquierdo, L. M., Nino, L. F. (2021). Modelamiento del espacio de signos vitales para detectar el deterioro de los pacientes en una unidad de cuidados intensivos. Universidad Nacional de Colombia.Karimi Moridani, M. y Haghighi Bardineh, Y. (2018). Presenting an efficient approach based on novel mapping for mortality prediction in intensive care unit cardiovascular patients. MethodsX, 5, 1291-1298.Kefi, Z., Aloui, K. y Naceur, M.S. (2019). The early prediction of neonates mortality in Intensive Care Unit. (pp. 304-306).Koyner, J.L., Carey, K.A., Edelson, D.P. y Churpek, M.M. (2018). The development of a machine learning inpatient acute kidney injury prediction model. Critical Care Medicine, 46, 1070-1077.Li, X., Ge, P., Zhu, J., Li, H., Graham, J., Singer, A., Richman, P.S. y Duong, T.Q. (2020). Deep learning prediction of likelihood of ICU admission and mortality in COVID-19 patients using clinical variables. PeerJ, 8.Malycha, J., Farajidavar, N., Pimentel, M.A.F., Redfern, O., Clifton, D.A., Tarassenko, L., Meredith, P., Prytherch, D., Ludbrook, G., Young, J.D. y Watkinson, P.J. (2019). The effect of fractional inspired oxygen concentration on early warning score performance: A database analysis. Resuscitation, 139, 192-199.Marafino, B.J., Park, M., Davies, J.M., Thombley, R., Luft, H.S., Sing, D.C., Kazi, D.S. Dejong, C., Boscardin, W.J., Dean, M.L. y Dudley, R.A. (2018). Validation of Prediction Models for Critical Care Outcomes Using Natural Language Processing of Electronic Health Record Data. JAMA Network Open, 1.Masud, M.M., Cheratta, M. y Harahsheh, A.R.A. (2018). Survival prediction of ICU patients using knowledge intensive data grouping and selection.Matrices de confusión - Training. (s. f.). Microsoft Learn. https://learn.microsoft.com/eses/training/modules/machine-learning-confusion-matrix/2-confusion-matricesMayampurath, A., Jani, P., Dai, Y., Gibbons, R., Edelson, D. y Churpek, M.M. (2020). A vital sign-based model to predict clinical deterioration in hospitalized children. Pediatric Critical Care Medicine, 820-826.Melinosky, C., Yang, S., Hu, P., Li, H., Miller, C.H.T., Khan, I., Mackenzie, C., Chang, W.- T., Parikh, G., Stein, D., Stein, D. y Badjatia, N. (2018). Continuous vital sign analysis to predict secondary neurological decline after traumatic brain injury. Frontiers in Neurology, 9.Messinger, A.I., Bui, N., Wagner, B.D., Szefler, S.J., Vu, T. y Deterding, R.R. (2019). Novel pediatric-automated respiratory score using physiologic data and machine learning in asthma. Pediatric Pulmonology, 54, 1149-1155.Monteiro, F., Meloni, F., Baranauskas, J.A. y Macedo, A.A. (2020). Prediction of mortality in Intensive Care Units: a multivariate feature selection. Journal of Biomedical Informatics, 107.Nielsen, A.B., Thorsen-Meyer, H.-C., Belling, K., Nielsen, A.P., Thomas, C.E., Chmura, P.J., Lademann, M., Moseley, P.L., Heimann, M., Dybdahl, L., Perner, A. y Brunak, S. (2019). Survival prediction in intensive-care units based on aggregation of long-term disease history and acute physiology: a retrospective study of the Danish National Patient Registry and electronic patient records. The Lancet Digital Health, 1, e78e89.Parreco, J., Soe-Lin, H., Parks, J.J., Byerly, S., Chatoor, M., Buicko, J.L., Namias, N. y Rattan, R. (2019). Comparing machine learning algorithms for predicting acute kidney injury. American Surgeon, 85, 725-729.Platzi: Cursos online profesionales de tecnología. (2018). Platzi. https://platzi.com/tutoriales/1269-probabilidad-estadistica/2308-coeficiente-decorrelacion-que-es-y-para-que-sirve/?utm_source=googlePollard, T.J., Johnson, A.E.W., Raffa, J.D., Celi, L.A., Mark, R.G. y Badawi, O. (2018). The eICU collaborative research database, a freely available multi-center database for critical care research. Scientific Data, 5.R.G. Barry, T.T. Wolbert, F.B. Mozaffari, P.D. Ray, E.C. Thompson, T.W. Gress, & D.A. Denning (2019). Comparison of geriatric trauma outcomes when admitted to a medical or surgical service after a fall. Journal of Surgical Research, 233, 391-396.Radhachandran, A., Garikipati, A., Zelin, N.S., Pellegrini, E., Ghandian, S., Calvert, J., Hoffman, J., Mao, Q. y Das, R. (2021). Prediction of short-term mortality in acute heart failure patients using minimal electronic health record data. BioData Mining, 14.Rubin, J., Potes, C., Xu-Wilson, M., Dong, J., Rahman, A., Nguyen, H. y Moromisato, D. (2018). An ensemble boosting model for predicting transfer to the pediatric intensive care unit. International Journal of Medical Informatics, 112, 15-20.Salahuddin, N., Shafquat, A., Marashly, Q., Zaza, K.J., Sharshir, M., Khurshid, M., Ali, Z., Malgapo, M., Jamil, M.G., Shoukri, M., Hijazi, M. y Al-Ghamdi, B. (2018). Increases in Heart Rate Variability Signal Improved Outcomes in Rapid Response Team Consultations: A Cohort Study. Cardiology Research and Practice, 2018.Satchidanand, N., Servoss, T.J., Singh, R., Bosinski, A.M., Tirpak, P., Horton, L.L. y Naughton, B.J. (2018). Development of a Risk Tool to Support Discussions of Care for Older Adults Admitted to the ICU With Pneumonia. American Journal of Hospice and Palliative Medicine, 35, 1201-1206.Shamout, F.E., Zhu, T., Sharma, P., Watkinson, P.J. y Clifton, D.A. (2020). Deep Interpretable Early Warning System for the Detection of Clinical Deterioration. IEEE Journal of Biomedical and Health Informatics, 24, 437-446.Tamir, M. (2021, 29 enero). What Is Machine Learning? UCB-UMT. https://ischoolonline.berkeley.edu/blog/what-is-machine-learning/Timm, F.P., Zaremba, S., Grabitz, S.D., Farhan, H.N., Zaremba, S., Siliski, E., Shin, C.H., Muse, S., Friedrich, S., Mojica, J.E., Ramachandran, S.-K. y Eikermann, M. (2018). Effects of opioids given to facilitate mechanical ventilation on sleep apnea after extubation in the intensive care unit. Sleep, 41.Tsur, E., Last, M., Garcia, V.F., Udassin, R., Klein, M. y Brotfain, E. (2019). Hypotensive episode prediction in icus via observation window splitting. LNAI, Vol. 11053.Viegas, R., Salgado, C.M., Curto, S., Carvalho, J.P., Vieira, S.M. y Finkelstein, S.N. (2017). Daily prediction of ICU readmissions using feature engineering and ensemble fuzzy modeling. Expert Systems with Applications, 79, 244-253.Wang, Y., Wei, Y., Yang, H., Li, J., Zhou, Y. y Wu, Q. (2020). Utilizing imbalanced electronic health records to predict acute kidney injury by ensemble learning and time series model. BMC Medical Informatics and Decision Making, 20.Wellner, B., Grand, J., Canzone, E., Coarr, M., Brady, P.W., Simmons, J., Kirkendall, E., Dean, N. Kleinman, M. y Sylvester, P. (2017). Predicting unplanned transfers to the intensive care unit: A machine learning approach leveraging diverse clinical elements. JMIR Medical Informatics, 5.Yoon, J.H., Jeanselme, V., Dubrawski, A., Hravnak, M., Pinsky, M.R. y Clermont, G. (2020). Prediction of hypotension events with physiologic vital sign signatures in the intensive care unit. Critical Care, 24.Zachariasse J.M., Van Der Lee, D., Seiger, N., De Vos-Kerkhof, E., Oostenbrink, R. y Moll, H.A. (2017). The role of nurses' clinical impression in the first assessment of children at the emergency department. Archives of Disease in Childhood, 102, 1052- 1056.Zimmerman, L.P., Reyfman, P.A., Smith, A.D.R., Zeng, Z., Kho, A., Sanchez-Pinto, L.N. y Luo, Y. (2019). Early prediction of acute kidney injury following ICU admission using a multivariate panel of physiological measurements. BMC Medical Informatics and Decision Making, 19.Público generalLICENSElicense.txtlicense.txttext/plain; charset=utf-85879https://repositorio.unal.edu.co/bitstream/unal/83874/1/license.txteb34b1cf90b7e1103fc9dfd26be24b4aMD51ORIGINAL1016036337.2023.pdf1016036337.2023.pdfTesis de Maestría en Ingeniería de Sistemas y Computaciónapplication/pdf1987713https://repositorio.unal.edu.co/bitstream/unal/83874/2/1016036337.2023.pdfb3f8dd78dea6ae5c7778aea4a0f21fa6MD52THUMBNAIL1016036337.2023.pdf.jpg1016036337.2023.pdf.jpgGenerated Thumbnailimage/jpeg5765https://repositorio.unal.edu.co/bitstream/unal/83874/3/1016036337.2023.pdf.jpgf0d842feabf463805810fe8616a15525MD53unal/83874oai:repositorio.unal.edu.co:unal/838742023-08-05 23:04:24.188Repositorio Institucional Universidad Nacional de Colombiarepositorio_nal@unal.edu.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 |