Implementación de una interfaz software para establecer grupos de riesgo de pacientes sospechosos de Tuberculosis Pulmonar
Pulmonary tuberculosis (TB) is an infectious disease that usually affects the lungs, this disease is curable and preventable, however, delayed diagnosis and treatment can cause death. In 2019 an estimated 10 million people worldwide fell ill with tuberculosis and a total of 1.4 million people died a...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Trabajo de grado (Pregrado y/o Especialización) |
| Language: | spa |
| Published: |
Universidad Antonio Nariño
2022
|
| Subjects: | |
| Online Access: | http://repositorio.uan.edu.co/handle/123456789/7248 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1812647277527826432 |
|---|---|
| author | Silva Soche, Lenny Tatiana |
| author2 | Jutinico, Andres Leonardo |
| author_facet | Jutinico, Andres Leonardo Silva Soche, Lenny Tatiana |
| author_sort | Silva Soche, Lenny Tatiana |
| collection | DSpace |
| description | Pulmonary tuberculosis (TB) is an infectious disease that usually affects the lungs, this
disease is curable and preventable, however, delayed diagnosis and treatment can cause
death. In 2019 an estimated 10 million people worldwide fell ill with tuberculosis and a
total of 1.4 million people died according to the World Health Organization (WHO) in 2020
[1]. In Colombia, in 2020 11390 people became ill, of which 10632 were new cases, and on
average during the last 5 years, there have been 1077 deaths per year due to tuberculosis,
according to the National Public Health Surveillance System (SIVIGILA) in 2021 [2]. At
the national level the high demand for patients hinders the priority and quality of care by
the Health Service Provider Institutions (IPS). These problems originate due to the poor
management of resources and procedures, generating as a consequence the progression of the
disease or lethality due to TB, particularly in isolated regions. This project contributes to the
decision-making of health specialists under precarious conditions from an automated system,
which consists of a software interface that allows establishing the high or low risk group to
which suspected tuberculosis patients belong by entering a series of social, demographic and
health status characteristics of the patient. Three previously trained and validated automatic
learning algorithms Fuzzy C-means, K-means and Perceptron Multilayer were worked on,
of the three algorithms the Perceptron Multilayer network was chosen to perform the risk
prediction because it has the highest sensitivity with a value of 95 %. |
| format | Trabajo de grado (Pregrado y/o Especialización) |
| id | repositorio.uan.edu.co-123456789-7248 |
| institution | Repositorio Digital UAN |
| language | spa |
| publishDate | 2022 |
| publisher | Universidad Antonio Nariño |
| record_format | dspace |
| spelling | repositorio.uan.edu.co-123456789-72482024-10-09T22:47:52Z Implementación de una interfaz software para establecer grupos de riesgo de pacientes sospechosos de Tuberculosis Pulmonar Silva Soche, Lenny Tatiana Jutinico, Andres Leonardo Interfaz software, Tuberculosis pulmonar, algoritmos de aprendizaje automatico Matlab Software interface, Pulmonary tuberculosis, machine learning algorithms, Matlab Pulmonary tuberculosis (TB) is an infectious disease that usually affects the lungs, this disease is curable and preventable, however, delayed diagnosis and treatment can cause death. In 2019 an estimated 10 million people worldwide fell ill with tuberculosis and a total of 1.4 million people died according to the World Health Organization (WHO) in 2020 [1]. In Colombia, in 2020 11390 people became ill, of which 10632 were new cases, and on average during the last 5 years, there have been 1077 deaths per year due to tuberculosis, according to the National Public Health Surveillance System (SIVIGILA) in 2021 [2]. At the national level the high demand for patients hinders the priority and quality of care by the Health Service Provider Institutions (IPS). These problems originate due to the poor management of resources and procedures, generating as a consequence the progression of the disease or lethality due to TB, particularly in isolated regions. This project contributes to the decision-making of health specialists under precarious conditions from an automated system, which consists of a software interface that allows establishing the high or low risk group to which suspected tuberculosis patients belong by entering a series of social, demographic and health status characteristics of the patient. Three previously trained and validated automatic learning algorithms Fuzzy C-means, K-means and Perceptron Multilayer were worked on, of the three algorithms the Perceptron Multilayer network was chosen to perform the risk prediction because it has the highest sensitivity with a value of 95 %. La tuberculosis pulmonar (TB) es una enfermedad infecciosa que suele afectar a los pulmones, esta enfermedad es curable y prevenible, sin embargo, el retraso diagn´ostico y de tratamiento puede causar la muerte. Se estima que en 2019 enfermaron de tuberculosis 10 millones de personas en todo el mundo y un total de 1.4 millones de personas murieron seg´un la Organizaci´on Mundial de la Salud (OMS) en 2020 [1]. En Colombia, en el 2020 se enfermaron 11390 personas, de las cuales 10632 fueron casos nuevos y en promedio durante los ´ultimos 5 a˜nos, se han presentado 1077 fallecidos por a˜no a causa de tuberculosis, seg´un el Sistema Nacional de Vigilancia en Salud P´ublica (SIVIGILA) en 2021 [2]. A nivel nacional la alta demanda de pacientes, dificulta la prioridad y calidad de atenci´on por las Instituciones Prestadoras de Servicio de Salud (IPS). Estos problemas se originan debido a la mala gesti´on de recursos y procedimientos generando como consecuencia el avance de la enfermedad o letalidad por TB, en particular en regiones aisladas. El presente proyecto contribuye en la toma de decisiones de los especialistas de la salud bajo condiciones precarias a partir de un sistema automatizado, el cual consiste en una interfaz software que permite establecer el grupo de riesgo alto o bajo al que pertenecen los pacientes sospechosos de tuberculosis al ingresar una serie de caracter´ısticas sociales, demogr´aficas y del estado de salud del paciente. Se trabajaron tres algoritmos de aprendizaje autom´atico previamente entrenados y validados Fuzzy C-means, K-means y Perceptron Multicapa, de los tres algoritmos se eligi´o la red Perceptron Multicapa para realizar la predicci´on del riesgo por tener la sensibilidad m´as alta con un valor del 95 %. Ingeniero(a) Biomédico(a) Pregrado Presencial Investigación 2022-11-15T16:00:33Z 2022-11-15T16:00:33Z 2022-06-03 Trabajo de grado (Pregrado y/o Especialización) info:eu-repo/semantics/acceptedVersion http://purl.org/coar/resource_type/c_7a1f http://purl.org/coar/version/c_970fb48d4fbd8a85 http://repositorio.uan.edu.co/handle/123456789/7248 [1] Organizaci´on Mundial de la Salud. Tuberculosis. Salud, Instituto Nacional de Salud, 10 2020. [2] Sistema Nacional de Vigilancia en Salud P´ublica. bolet´ın epidemiol´ogico semanal. Salud, Instituto Nacional de Salud, 07 2020. [3] B. Tortora, G.and Derrickson. Anatom´ıa y fisiolog´ıa. [4] World Health Organization’s 2021 Global TB report. Las muertes por tuberculosis aumentan por primera vez en m´as de una d´ecada por la covid. Agencia de noticias cient´ıficas de la Fundaci´on Espa˜nola para la Ciencia y la Tecnolog´ıa SINC, 14(30), 10 2021. [5] R. Natalia Programa Nacional de Control y Eliminaci´on de la Tuberculosis M. Tania, M. Fabiola. Manual operativo implementaci´on del genexpert mtb/rif en el programa de tuberculosis. 2017. [6] Vu D. Phan and Janet M. Poponick. Tuberculosis. McGraw-Hill Education, New York, NY, 2018. [7] Linux. Gnu/linux. la terminal o l´ınea de comandos. Blog para los amantes de Linux y el software libre, 07 2019. [8] Ian. Sommerville. Ingenieria del software. PEARSON EDUCACION S.A., 2005. ´ [9] S. Kumar. Agrupamiento difuso de c-means: ¿es mejor que el agrupamiento de k-means? Towards Data Science, 04 2021. [10] S. Kumar. Comprensi´on de los algoritmos de agrupaci´on en cl´usteres k-means, kmeans++ y k-medoids. Towards Data Science, 06 2020. [11] Z.Carlos. Evaluaci´on de modelos de clasificaci´on. RPubs, 05 2017. [12] J.D. Munera, L A. Montoya, J.A. Mosquera, et al. Casos de tuberculosis pulmonar y extrapulmonar notificados al programa de tuberculosis en el departamento del Choc´o, Colombia, periodo 2012-2015. Enf Infec Microbiol, 39(3):93–102, 09 2019. 122 Bibliograf´ıa [13] M.J. Gonzalez, B. Gonzales, J.A. Sotolongo, et al. Programa de intervencion comunitaria dirigido a pacientes con riesgo de tuberculosis pulmonar. Revista Cubana de Salud Publica, 45(3), 09 2019. [14] J.E. Polanco-Pasaje, L. Rodriguez Marquez, K.Y. Tello-Hoyos, et al. Cascada de atenci´on de la tuberculosis para la poblaci´on ind´ıgena en colombia: una investigaci´on operativa. Pan American Journal of Public Health, 44, 12 2020. [15] M.A. Sanchez, J. Pino, R. Pacheco, et al. An´alisis de letalidad en pacientes con diagn´ostico de tuberculosis en un centro de alta complejidad en cali, colombia. Ingenieria clinica, Universidad Icesi, Cali-Colombia, 02 2018. [16] Ke Yuan, Yabing Huang, and Qian Tang. The impact of social and economic development on the spread of infectious respiratory diseases, push or constrain? empirical research from china based on machine learning methods. In 2020 IEEE 22nd International Conference on High Performance Computing and Communications; IEEE 18th International Conference on Smart City; IEEE 6th International Conference on Data Science and Systems (HPCC/SmartCity/DSS), pages 1364–1369, 2020. [17] Sophie Khaddaj and Hussain Chrief. Prevention and control of emerging infectious diseases in human populations. In 2020 19th International Symposium on Distributed Computing and Applications for Business Engineering and Science (DCABES), pages 336–339, 2020. [18] PMA. Alvarez, PXA. Morales, A. Rodriguez-Ramirez, et al. Costo-efectividad de tres pruebas diagn´osticas de tuberculosis pulmonar en dos ciudades de colombia, 2015. Enf Infec Microbiol, 39(4):129–133, 2015. instname:Universidad Antonio Nariño reponame:Repositorio Institucional UAN repourl:https://repositorio.uan.edu.co/ spa Acceso abierto Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) https://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess http://purl.org/coar/access_right/c_abf2 application/pdf application/pdf application/pdf Colombia(Bogotá,Dc) Universidad Antonio Nariño Ingeniería Biomédica Facultad de Ingeniería Mecánica, Electrónica y Biomédica Bogotá - Sur |
| spellingShingle | Interfaz software, Tuberculosis pulmonar, algoritmos de aprendizaje automatico Matlab Software interface, Pulmonary tuberculosis, machine learning algorithms, Matlab Silva Soche, Lenny Tatiana Implementación de una interfaz software para establecer grupos de riesgo de pacientes sospechosos de Tuberculosis Pulmonar |
| title | Implementación de una interfaz software para establecer grupos de riesgo de pacientes sospechosos de Tuberculosis Pulmonar |
| title_full | Implementación de una interfaz software para establecer grupos de riesgo de pacientes sospechosos de Tuberculosis Pulmonar |
| title_fullStr | Implementación de una interfaz software para establecer grupos de riesgo de pacientes sospechosos de Tuberculosis Pulmonar |
| title_full_unstemmed | Implementación de una interfaz software para establecer grupos de riesgo de pacientes sospechosos de Tuberculosis Pulmonar |
| title_short | Implementación de una interfaz software para establecer grupos de riesgo de pacientes sospechosos de Tuberculosis Pulmonar |
| title_sort | implementacion de una interfaz software para establecer grupos de riesgo de pacientes sospechosos de tuberculosis pulmonar |
| topic | Interfaz software, Tuberculosis pulmonar, algoritmos de aprendizaje automatico Matlab Software interface, Pulmonary tuberculosis, machine learning algorithms, Matlab |
| url | http://repositorio.uan.edu.co/handle/123456789/7248 |
| work_keys_str_mv | AT silvasochelennytatiana implementaciondeunainterfazsoftwareparaestablecergruposderiesgodepacientessospechososdetuberculosispulmonar |
