Machine learning in predicting severe acute respiratory infection outbreaks
Abstract: Severe acute respiratory infection (SARI) outbreaks occur annually, with seasonal peaks varying among geographic regions. Case notification is important to prepare healthcare networks for patient attendance and hospitalization. Thus, health managers need adequate resource planning tools fo...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Escola Nacional de Saúde Pública, Fundação Oswaldo Cruz
2024-01-01
|
| Series: | Cadernos de Saúde Pública |
| Subjects: | |
| Online Access: | http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0102-311X2024000105005&lng=en&tlng=en |
| _version_ | 1797361107048857600 |
|---|---|
| author | Amauri Duarte da Silva Marcelo Ferreira da Costa Gomes Tatiana Schäffer Gregianini Leticia Garay Martins Ana Beatriz Gorini da Veiga |
| author_facet | Amauri Duarte da Silva Marcelo Ferreira da Costa Gomes Tatiana Schäffer Gregianini Leticia Garay Martins Ana Beatriz Gorini da Veiga |
| author_sort | Amauri Duarte da Silva |
| collection | DOAJ |
| description | Abstract: Severe acute respiratory infection (SARI) outbreaks occur annually, with seasonal peaks varying among geographic regions. Case notification is important to prepare healthcare networks for patient attendance and hospitalization. Thus, health managers need adequate resource planning tools for SARI seasons. This study aims to predict SARI outbreaks based on models generated with machine learning using SARI hospitalization notification data. In this study, data from the reporting of SARI hospitalization cases in Brazil from 2013 to 2020 were used, excluding SARI cases caused by COVID-19. These data were prepared to feed a neural network configured to generate predictive models for time series. The neural network was implemented with a pipeline tool. Models were generated for the five Brazilian regions and validated for different years of SARI outbreaks. By using neural networks, it was possible to generate predictive models for SARI peaks, volume of cases per season, and for the beginning of the pre-epidemic period, with good weekly incidence correlation (R2 = 0.97; 95%CI: 0.95-0.98, for the 2019 season in the Southeastern Brazil). The predictive models achieved a good prediction of the volume of reported cases of SARI; accordingly, 9,936 cases were observed in 2019 in Southern Brazil, and the prediction made by the models showed a median of 9,405 (95%CI: 9,105-9,738). The identification of the period of occurrence of a SARI outbreak is possible using predictive models generated with neural networks and algorithms that employ time series. |
| first_indexed | 2024-03-08T15:49:13Z |
| format | Article |
| id | doaj.art-d4d38c6b58664163a5533421e58996fe |
| institution | Directory Open Access Journal |
| issn | 1678-4464 |
| language | English |
| last_indexed | 2024-03-08T15:49:13Z |
| publishDate | 2024-01-01 |
| publisher | Escola Nacional de Saúde Pública, Fundação Oswaldo Cruz |
| record_format | Article |
| series | Cadernos de Saúde Pública |
| spelling | doaj.art-d4d38c6b58664163a5533421e58996fe2024-01-09T07:42:49ZengEscola Nacional de Saúde Pública, Fundação Oswaldo CruzCadernos de Saúde Pública1678-44642024-01-0140110.1590/0102-311xen122823Machine learning in predicting severe acute respiratory infection outbreaksAmauri Duarte da Silvahttps://orcid.org/0000-0001-6395-458XMarcelo Ferreira da Costa Gomeshttps://orcid.org/0000-0003-4693-5402Tatiana Schäffer Gregianinihttps://orcid.org/0000-0002-9912-9060Leticia Garay Martinshttps://orcid.org/0000-0002-5614-6952Ana Beatriz Gorini da Veigahttps://orcid.org/0000-0003-1462-5506Abstract: Severe acute respiratory infection (SARI) outbreaks occur annually, with seasonal peaks varying among geographic regions. Case notification is important to prepare healthcare networks for patient attendance and hospitalization. Thus, health managers need adequate resource planning tools for SARI seasons. This study aims to predict SARI outbreaks based on models generated with machine learning using SARI hospitalization notification data. In this study, data from the reporting of SARI hospitalization cases in Brazil from 2013 to 2020 were used, excluding SARI cases caused by COVID-19. These data were prepared to feed a neural network configured to generate predictive models for time series. The neural network was implemented with a pipeline tool. Models were generated for the five Brazilian regions and validated for different years of SARI outbreaks. By using neural networks, it was possible to generate predictive models for SARI peaks, volume of cases per season, and for the beginning of the pre-epidemic period, with good weekly incidence correlation (R2 = 0.97; 95%CI: 0.95-0.98, for the 2019 season in the Southeastern Brazil). The predictive models achieved a good prediction of the volume of reported cases of SARI; accordingly, 9,936 cases were observed in 2019 in Southern Brazil, and the prediction made by the models showed a median of 9,405 (95%CI: 9,105-9,738). The identification of the period of occurrence of a SARI outbreak is possible using predictive models generated with neural networks and algorithms that employ time series.http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0102-311X2024000105005&lng=en&tlng=enSevere Acute Respiratory InfectionMachine LearningComputer ModelsEpidemiologic SurveillanceNeural Networks (Computer) |
| spellingShingle | Amauri Duarte da Silva Marcelo Ferreira da Costa Gomes Tatiana Schäffer Gregianini Leticia Garay Martins Ana Beatriz Gorini da Veiga Machine learning in predicting severe acute respiratory infection outbreaks Cadernos de Saúde Pública Severe Acute Respiratory Infection Machine Learning Computer Models Epidemiologic Surveillance Neural Networks (Computer) |
| title | Machine learning in predicting severe acute respiratory infection outbreaks |
| title_full | Machine learning in predicting severe acute respiratory infection outbreaks |
| title_fullStr | Machine learning in predicting severe acute respiratory infection outbreaks |
| title_full_unstemmed | Machine learning in predicting severe acute respiratory infection outbreaks |
| title_short | Machine learning in predicting severe acute respiratory infection outbreaks |
| title_sort | machine learning in predicting severe acute respiratory infection outbreaks |
| topic | Severe Acute Respiratory Infection Machine Learning Computer Models Epidemiologic Surveillance Neural Networks (Computer) |
| url | http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0102-311X2024000105005&lng=en&tlng=en |
| work_keys_str_mv | AT amauriduartedasilva machinelearninginpredictingsevereacuterespiratoryinfectionoutbreaks AT marceloferreiradacostagomes machinelearninginpredictingsevereacuterespiratoryinfectionoutbreaks AT tatianaschaffergregianini machinelearninginpredictingsevereacuterespiratoryinfectionoutbreaks AT leticiagaraymartins machinelearninginpredictingsevereacuterespiratoryinfectionoutbreaks AT anabeatrizgorinidaveiga machinelearninginpredictingsevereacuterespiratoryinfectionoutbreaks |