Técnica de minería de datos para identificar patrones de mortalidad en una cohorte de personas con tuberculosis pulmonar

Rocha, Marli Souza; Saraceni, Valéria; Coeli, Claudia Medina; Pacheco, Max Leonardo Chacón; Pinheiro, Rejane Sobrino

doi:10.1590/0102-311XEN203124

Tabla de contenido Anterior Actual Siguiente

Tabla de contenido

ARTICLE • Cad. Saúde Pública 42 • 2026 • https://doi.org/10.1590/0102-311XEN203124 linkcopiar

Técnica de minería de datos para identificar patrones de mortalidad en una cohorte de personas con tuberculosis pulmonar

Autoría SCIMAGO INSTITUTIONS RANKINGS

Resumen

Las muertes por tuberculosis (TB) se producen de forma temprana, principalmente durante los dos meses que comprende la fase de tratamiento intensivo, en comparación con otras causas de muerte. Comprender los distintos patrones de las personas que fallecen por TB permite mejorar la eficacia de la atención sanitaria para grupos específicos. El objetivo del estudio era aplicar una técnica de minería de datos para explorar si existen patrones de mortalidad distintos asociados a diversos perfiles de pacientes dentro de una cohorte de personas notificadas con TB en la ciudad de Río de Janeiro, Brasil. Realizamos un estudio de cohorte retrospectivo utilizando un enlace probabilístico entre la base de datos del Sistema de Información de Agravios de Notificación (SINAN) y el Sistema de Informaciones sobre Mortalidad (SIM). Se aplicó una técnica de minería de datos en reglas de asociación utilizando el algoritmo Apriori para evaluar los patrones asociados con las causas de muerte. Las muertes por TB se asociaron con hombres adultos con un tiempo de supervivencia corto. Las muertes por SIDA con TB se produjeron durante el periodo de tratamiento y se asociaron más con las mujeres. Por el contrario, las muertes por SIDA sin mención de TB fueron más frecuentes entre los hombres más jóvenes y los adultos negros/morenos. Las muertes por causas externas se produjeron más tarde, un año después del diagnóstico, y se relacionaron con los hombres jóvenes. Las muertes por otras causas relacionadas con una mayor supervivencia se asociaron con personas mayores, blancas y con un nivel educativo superior. El algoritmo Apriori permitió extraer información relevante de datos secundarios, como la identificación de subgrupos distintos de personas que pueden beneficiarse de medidas específicas, con un consecuente efecto positivo para el control de la TB.

Palabras-clave:
Tuberculosis; Mortalidad; Sistemas de Información; Registro Médico Coordinado

CHARACTERISTICS	ITEMS
Age	15-34 years, 35-59 years, 60 years or older
Sex	Female, male
Skin color	White, Black/Mixed-race, Yellow, Indigenous, ignored
Education	0-4 years, 5-8 years, 9-12 years, > 12 years, ignored
Type of entry	New case, relapse, return after default
HIV test result	Negative, in progress, not tested
Sputum smear test	Tested, not tested
Type of health care facility	Family Health Strategy, Municipal Health Care Center, TB clinic, hospital
Survival time (time elapsed from the date of diagnosis in SINAN to the date of death in SIM)	Notified after death, 0-60 days, 61-180 days, 181-365 days, greater than 365 days
Underlying cause of death	TB (A15-A19), AIDS with TB (B20.0), AIDS without TB (B20.1-B24), external causes (V01-Y98), other causes (other ICD-10 codes)

Items	n	%
Sex
Female	451	24.8
Male	1,368	75.2
Age (years)
16-34	367	20.2
35-59	786	43.2
60 or older	666	36.6
Education (years)
0-4	464	25.5
5-8	409	22.5
9-12	186	10.2
More than 12	66	3.6
Ignored	694	38.2
Skin color
White	699	38.4
Yellow	10	0.5
Indigenous	3	0.2
Black/Mixed-race	902	49.6
Ignored	205	11.3
HIV test
Negative	758	41.7
In progress	76	4.2
Not tested	985	54.1
Type of entry
New case	1,442	79.3
Relapse	138	7.6
Return after default	239	13.1
Type of health care facility
Family Health Strategy	67	3.7
Municipal Health Care Center	874	48.1
TB clinic	119	6.5
Hospital	755	41.5
Others *	4	0.2
Sputum smear test for TB diagnosis
Tested	962	52.9
Not tested	857	47.1
Survival time
Notified after death (days)	42	2.3
0-60	557	30.6
61-180	341	18.7
181-365	228	12.6
Over 365	651	35.8
Underlying cause of death
TB	655	36.0
AIDS without TB	26	1.4
AIDS with TB	38	2.1
External causes	155	8.5
Others	945	52.0
Total	1,819	100.0

Antecedent	Support (%)	Confidence (%)	Lift	n
Consequent - deaths from TB
(1) Age = 35-59 years, survival time = 0-60 days, education = ignored, skin color = White, sputum smear test = tested	0.8	100.0	2.8	15
(2) Sex = male, age = 35-59 years, survival time = 0-60 days, education = ignored, skin color = ignored, sputum smear test = not tested	0.7	100.0	2.8	14
(3) Sex = male, age = 35-59 years, survival time = 0-60 days, skin color = Black/Mixed-race, HIV test = negative	1.4	71.4	2.0	26
(4) Sex = male, age = 35-59 years, survival time = 0-60 days, education = ignored, HIV test = not tested, new case, sputum smear test = tested, hospital	0.7	100.0	2.8	14
(5) Sex = male, survival time = 0-60 days, relapse, sputum smear test = tested	0.6	100.0	2.8	11
(6) Sex = male, survival time = 0-60 days, education = 0-4, HIV test = negative, new case, Municipal Health Care Center	0.6	90.9	2.5	11
(7) Sex = male, age = 16-34 years, survival time = 0-60 days, new case, Municipal Health Care Center	0.7	86.7	2.4	14
(8) Sex = female, survival time = 0-60 days, relapse, hospital	0.5	90.9	2.5	10
(9) Sex = female, age = 16-34 years, survival time = 0-60 days, hospital	1.0	78.3	2.2	18
(10) Age = 35-59 years, survival time = notified after death, sputum smear test = not tested, hospital	0.6	83.3	2.3	11
(11) Age = 35-59 years, survival time = notified after death, HIVv test = not tested, hospital	0.6	83.3	2.3	11
(12) Survival time = notified after death, skin color = Black/Mixed-race, hiv test = not tested, sputum smear test = not tested, hospital	0.6	78.5	2.2	11
(13) Sex = male, survival time = notified after death, new case, sputum smear test = not tested, hospital	0.8	77.8	2.2	15
(14) Sex = male, survival time = notified after death, HIV test = not tested, new case, sputum smear test = not tested, hospital	0.7	76.5	2.2	14
(15) Age = 60 years or older, survival time = notified after death, new case, sputum smear test = not tested, hospital	0.6	71.4	2.0	11
(16) Sex = male, survival time = 61-180 days, HIV test = negative, return after default, hospital	0.6	83.3	2.3	11
(17) Sex = male, survival time = 181-365 days, HIV test = negative, return after default, sputum smear test = tested	0.6	83.3	2.3	11
(18) Sex = male, education = 0-4, skin color = Black/Mixed-race, return after default	1.3	72.7	2.0	24

Antecedents	Support (%)	Confidence (%)	Lift	n
Consequent - death from AIDS with TB
(19) Sex = female, HIV test = not tested, new case, hospital	0.5	12.5	6.0	10
(20) Sex = female, age = 35-59 years, HIV test = not tested	0.5	12.5	6.0	10
(21) Sex = female, education = ignored, HIV test = not tested	0.6	11.2	5.4	11
(22) Age = 35-59 years, sputum smear test = not tested, Municipal Health Care Center	0.5	7.0	3.4	10
(23) Survival time = 61-180 days, HIV test = not tested, new case	0.5	6.7	3.2	10
(24) Skin color = Black/Mixed-race, sputum smear test = not tested, Municipal Health Care Center	0.5	5.8	2.8	10
(25) HIV test = not tested, sputum smear test = not tested, Municipal Health Care Center	0.6	4.7	2.3	11
(26) Survival time = 61-180 days	0.8	4.4	2.1	15
(27) Age = 16-34 years	0.8	4.1	1.9	15
Consequent - death from aids without TB
(28) Age = 16-34 years	0.5	2.7	1.9	10
(29) Age = 35-59 years, HIV test = not tested	0.6	2.7	1.9	11
(30) Sex = male, HIV test = not tested, Sputum smear test = not tested	0.5	2.7	1.9	10
(31) Age = 35-59 years, Municipal Health Care Center	0.5	2.7	1.9	10
(32) Skin color = Black/Mixed-race, Municipal Health Care Center	0.6	2.5	1.8	11
(33) HIV test = not tested, new case, sputum smear test = not tested	0.5	2.3	1.6	10

Antecedents	Support (%)	Confidence (%)	Lift	n
Consequent - death from external causes
(34) Sex = male, age = 16-34 years, survival time = over 365 days, education = 9-12, new case	0.6	84.6	9.9	11
(35) Sex = male, age = 16-34 years, survival time = over 365 days, education = 5-8, skin color = Black/Mixed-race, HIV test = not tested	0.7	80.0	9.4	12
(36) Sex = male, age = 16-34 years, survival time = 181-365 days, sputum smear test = tested, Municipal Health Care Center	0.5	52.6	6.2	10
(37) Sex = male, skin color = Black/Mixed-race, return after default, Municipal Health Care Center	0.6	20.4	2.4	11
Consequent - death from other causes
(38) Age = 60 years or older, survival time = over 365 days, skin color = White, HIV test = not tested, sputum smear test = not tested	2.0	100.0	1.9	37
(39) Age = 60 years or older, survival time = over 365 days, HIV test = not tested, new case, sputum smear test = not tested, Municipal Health Care Center	1.8	100.0	1.9	33
(40) Survival time = over 365 days, education = over 12, skin color = White, HIV test = not tested	0.7	100.0	1.9	13
(41) Sex = female, age = 60 years or older, survival time = over 365 days, HIV test = not tested, Municipal Health Care Center	1.1	100.0	1.9	20
(42) Sex = male, age = 60 years or older, survival time = over 365 days, skin color = White, HIV test = not tested, new case, sputum smear test = not tested, Municipal Health Care Center	0.8	100.0	1.9	15
(43) Sex = male, age = 60 years or older, survival time = over 365 days, skin color = White, HIV test = negative, new case, sputum smear test = not tested, Municipal Health Care Center	0.6	100.0	1.9	11
(44) Sex = male, age = 35-59 years, survival time = over 365 days, skin color = White, HIV test = negative, new case, sputum smear test = tested, Municipal Health Care Center	0.8	77.8	1.5	15
(45) Sex = male, age = 35-59 years, survival time = over 365 days, skin color = Black/Mixed-race, new case, sputum smear test = tested, Municipal Health Care Center	1.6	75.0	1.4	30
(46) Age = 60 years or older, survival time = 181-365 days, skin color = Black/Mixed-race, HIV test = not tested	0.7	100.0	1.9	13
(47) Age = 60 years or older, education = 5-8, HIV test = negative, TB clinic	0.5	100.0	1.9	10
(48) Age = 35-59 years, HIV test = negative, TB clinic, sputum smear test = not tested	0.6	100.0	1.9	11
(49) Survival time = over 365 days, education = 0-4, HIV test = not tested, relapse	0.5	100.0	1.9	10

location_on

Escola Nacional de Saúde Pública Sergio Arouca, Fundação Oswaldo Cruz Rua Leopoldo Bulhões, 1480 , 21041-210 Rio de Janeiro RJ Brazil, Tel.:+55 21 2598-2511, Fax: +55 21 2598-2737 / +55 21 2598-2514 - Rio de Janeiro - RJ - Brazil
E-mail: cadernos@ensp.fiocruz.br

rss_feed Acompañe los números de esta revista en su lector de RSS

[TFN1] ICD-10: International Classification of Diseases - 10th revision; SIM: Brazilian Mortality Information System; SINAN: Brazilian Information System for Notifiable Diseases.