Machine learning algorithms using national registry data to predict loss to follow-up during tuberculosis treatment.
Loss to follow-up
Machine learning
Score prediction
Tuberculosis
Journal
BMC public health
ISSN: 1471-2458
Titre abrégé: BMC Public Health
Pays: England
ID NLM: 100968562
Informations de publication
Date de publication:
23 May 2024
23 May 2024
Historique:
received:
04
12
2023
accepted:
09
05
2024
medline:
24
5
2024
pubmed:
24
5
2024
entrez:
23
5
2024
Statut:
epublish
Résumé
Identifying patients at increased risk of loss to follow-up (LTFU) is key to developing strategies to optimize the clinical management of tuberculosis (TB). The use of national registry data in prediction models may be a useful tool to inform healthcare workers about risk of LTFU. Here we developed a score to predict the risk of LTFU during anti-TB treatment (ATT) in a nationwide cohort of cases using clinical data reported to the Brazilian Notifiable Disease Information System (SINAN). We performed a retrospective study of all TB cases reported to SINAN between 2015 and 2022; excluding children (< 18 years-old), vulnerable groups or drug-resistant TB. For the score, data before treatment initiation were used. We trained and internally validated three different prediction scoring systems, based on Logistic Regression, Random Forest, and Light Gradient Boosting. Before applying our models we splitted our data into training (~ 80% data) and test (~ 20%) sets, and then compared the model metrics using the test data set. Of the 243,726 cases included, 41,373 experienced LTFU whereas 202,353 were successfully treated. The groups were different with regards to several clinical and sociodemographic characteristics. The directly observed treatment (DOT) was unbalanced between the groups with lower prevalence in those who were LTFU. Three models were developed to predict LTFU using 8 features (prior TB, drug use, age, sex, HIV infection and schooling level) with different score composition approaches. Those prediction scoring systems exhibited an area under the curve (AUC) ranging between 0.71 and 0.72. The Light Gradient Boosting technique resulted in the best prediction performance, weighting specificity and sensitivity. A user-friendly web calculator app was developed ( https://tbprediction.herokuapp.com/ ) to facilitate implementation. Our nationwide risk score predicts the risk of LTFU during ATT in Brazilian adults prior to treatment commencement utilizing schooling level, sex, age, prior TB status, and substance use (drug, alcohol, and/or tobacco). This is a potential tool to assist in decision-making strategies to guide resource allocation, DOT indications, and improve TB treatment adherence.
Sections du résumé
BACKGROUND
BACKGROUND
Identifying patients at increased risk of loss to follow-up (LTFU) is key to developing strategies to optimize the clinical management of tuberculosis (TB). The use of national registry data in prediction models may be a useful tool to inform healthcare workers about risk of LTFU. Here we developed a score to predict the risk of LTFU during anti-TB treatment (ATT) in a nationwide cohort of cases using clinical data reported to the Brazilian Notifiable Disease Information System (SINAN).
METHODS
METHODS
We performed a retrospective study of all TB cases reported to SINAN between 2015 and 2022; excluding children (< 18 years-old), vulnerable groups or drug-resistant TB. For the score, data before treatment initiation were used. We trained and internally validated three different prediction scoring systems, based on Logistic Regression, Random Forest, and Light Gradient Boosting. Before applying our models we splitted our data into training (~ 80% data) and test (~ 20%) sets, and then compared the model metrics using the test data set.
RESULTS
RESULTS
Of the 243,726 cases included, 41,373 experienced LTFU whereas 202,353 were successfully treated. The groups were different with regards to several clinical and sociodemographic characteristics. The directly observed treatment (DOT) was unbalanced between the groups with lower prevalence in those who were LTFU. Three models were developed to predict LTFU using 8 features (prior TB, drug use, age, sex, HIV infection and schooling level) with different score composition approaches. Those prediction scoring systems exhibited an area under the curve (AUC) ranging between 0.71 and 0.72. The Light Gradient Boosting technique resulted in the best prediction performance, weighting specificity and sensitivity. A user-friendly web calculator app was developed ( https://tbprediction.herokuapp.com/ ) to facilitate implementation.
CONCLUSIONS
CONCLUSIONS
Our nationwide risk score predicts the risk of LTFU during ATT in Brazilian adults prior to treatment commencement utilizing schooling level, sex, age, prior TB status, and substance use (drug, alcohol, and/or tobacco). This is a potential tool to assist in decision-making strategies to guide resource allocation, DOT indications, and improve TB treatment adherence.
Identifiants
pubmed: 38783264
doi: 10.1186/s12889-024-18815-0
pii: 10.1186/s12889-024-18815-0
doi:
Substances chimiques
Antitubercular Agents
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1385Subventions
Organisme : Fundação Oswaldo Cruz
ID : Programa Inova FIOCRUZ/Edital Inovação Amazônia
Organisme : Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
ID : Finance code 001
Organisme : National Institute of Allergy and Infectious Diseases
ID : U01-AI069923
Organisme : Ministério da Saúde
ID : 25029.000507/2013-07
Organisme : Conselho Nacional de Desenvolvimento Científico e Tecnológico
ID : Senior Fellowship
Informations de copyright
© 2024. The Author(s).
Références
WHO. Global tuberculosis report 2023 [Internet]. [cited 2023 Nov 28]. https://www.who.int/publications-detail-redirect/9789240083851 .
Rapid communication. key changes to the treatment of drug-resistant tuberculosis [Internet]. [cited 2023 Dec 4]. https://www.who.int/publications-detail-redirect/WHO-UCN-TB-2022-2 .
WHO consolidated guidelines on tuberculosis. module 4: treatment: drug-susceptible tuberculosis treatment [Internet]. [cited 2023 Dec 4]. https://www.who.int/publications-detail-redirect/9789240048126 .
The World Bank Group. The World Bank In Brazil [Internet]. World Bank. [cited 2023 Dec 4]. https://www.worldbank.org/en/country/brazil/overview .
Campos T. Manual SINAN – Normas e Rotinas 2
Rocha MS, Bartholomay P, Cavalcante MV, et al. Notifiable diseases Information System (SINAN): main features of tuberculosis notification and data analysis. Epidemiol Serv Saude. 2020;29(1):e2019017.
pubmed: 32074197
BRASIL. Manual de Recomendações para o Controle da Tuberculose no Brasil [Internet]. 2023. https://portaldeboaspraticas.iff.fiocruz.br/biblioteca/manual-de-recomendacoes-para-o-controle-da-tuberculose-no-brasil/ .
Boletim Epidemiológico de Tuberculose. – 2022 | Departamento de Doenças de Condições Crônicas e Infecções Sexualmente Transmissíveis [Internet]. [cited 2023 Mar 15]. http://antigo.aids.gov.br/pt-br/pub/2022/boletim-epidemiologico-de-tuberculose-2022 .
Tanha J, Abdi Y, Samadi N, Razzaghi N, Asadpour M. Boosting methods for multi-class imbalanced data classification: an experimental review. J Big Data. 2020;7(1):70.
doi: 10.1186/s40537-020-00349-y
Pedregosa F, Varoquaux G, Gramfort A et al. Scikit-learn: Machine Learning in Python [Internet]. arXiv; 2018 [cited 2023 Mar 20]. http://arxiv.org/abs/1201.0490 .
Misra P, Singh A, with Cross-Validation. Improving the Classification Accuracy using Recursive Feature Elimination. 2020 [cited 2024 Mar 21]. https://www.semanticscholar.org/paper/Improving-the-Classification-Accuracy-using-Feature-Misra-Singh/26edc4f0e9f7f3933e5a39feda3b8bb51e072cc4 .
Ke G, Meng Q, Finley T et al. LightGBM: a highly efficient gradient boosting decision tree. Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, NY, USA: Curran Associates Inc.; 2017. pp. 3149–3157.
Ferreira AJ, Figueiredo MAT, Boosting Algorithms. A Review of Methods, Theory, and Applications. In: Zhang C, Ma Y, editors. Ensemble Machine Learning: Methods and Applications [Internet]. New York, NY: Springer; 2012 [cited 2023 Dec 4]. pp. 35–85. https://doi.org/10.1007/978-1-4419-9326-7_2 .
Steyerberg EW, Vickers AJ, Cook NR, et al. Assessing the performance of prediction models: a framework for traditional and novel measures. Epidemiology. 2010;21(1):128–38.
doi: 10.1097/EDE.0b013e3181c30fb2
pubmed: 20010215
pmcid: 3575184
Fawcett T. An introduction to ROC analysis. Pattern Recognit Lett. 2006;27(8):861–74.
doi: 10.1016/j.patrec.2005.10.010
Lundberg SM, Erion G, Chen H, et al. From local explanations to Global understanding with explainable AI for trees. Nat Mach Intell. 2020;2(1):56–67.
doi: 10.1038/s42256-019-0138-9
pubmed: 32607472
pmcid: 7326367
Explainable AI. from black box to glass box [Internet]. springerprofessional.de. [cited 2023 Mar 20]. https://www.springerprofessional.de/en/explainable-ai-from-black-box-to-glass-box/17514128 .
Partership STB. Global Plan to End TB 2018–2022: The Paradigm Shift [Internet]. 2023. https://npin.cdc.gov/publication/global-plan-end-tb-2018%E2%80%932022-paradigm-shift .
Walker IF, Shi O, Hicks JP et al. Analysis of loss to follow-up in 4099 multidrug-resistant pulmonary tuberculosis patients. Eur Respir J. 2019; 54(1).
Novel stepwise approach. to assess representativeness of a large multicenter observational cohort of tuberculosis patients: The example of RePORT Brazil - International Journal of Infectious Diseases [Internet]. [cited 2023 Dec 4]. https://www.ijidonline.com/article/S1201-9712(20)32452-8/fulltext .
Clinical Prediction Model for Unsuccessful Pulmonary Tuberculosis Treatment Outcomes. | Clinical Infectious Diseases | Oxford Academic [Internet]. [cited 2023 Dec 4]. https://academic.oup.com/cid/article/74/6/973/6313211?login=false .
Mendelsohn SC, Fiore-Gartland A, Awany D, et al. Clinical predictors of pulmonary tuberculosis among South African adults with HIV. EClinicalMedicine. 2022;45:101328.
doi: 10.1016/j.eclinm.2022.101328
pubmed: 35274090
pmcid: 8902614
Singano V, Kip E, Ching’ani W, Chiwaula L. Tuberculosis treatment outcomes among prisoners and general population in Zomba, Malawi. BMC Public Health. 2020;20(1):700.
doi: 10.1186/s12889-020-08841-z
pubmed: 32414357
pmcid: 7227331
Unsuccessful TB. treatment outcomes with a focus on HIV co-infected cases: a cross-sectional retrospective record review in a high-burdened province of South Africa | BMC Health Services Research | Full Text [Internet]. [cited 2023 Dec 4]. https://bmchealthservres.biomedcentral.com/articles/ https://doi.org/10.1186/s12913-017-2406-x .
Systematic review of prediction models. for pulmonary tuberculosis treatment outcomes in adults | BMJ Open [Internet]. [cited 2023 Dec 4]. https://bmjopen.bmj.com/content/11/3/e044687.long .
The impact of alcohol use on tuberculosis. treatment outcomes: a s… Ingenta Connect [Internet]. [cited 2023 Dec 4]. https://www.ingentaconnect.com/content/iuatld/ijtld/2020/00000024/00000001/art00012;jsessionid=3d3ck2jiq0o72.x-ic-live-02 .
You N, Pan H, Zeng Y, et al. A risk score for prediction of poor treatment outcomes among tuberculosis patients with diagnosed diabetes mellitus from eastern China. Sci Rep Nat Publishing Group. 2021;11(1):11219.
Caminero JA. Multidrug-resistant tuberculosis: epidemiology, risk factors and case finding [State of the art series. Drug-resistant tuberculosis. Edited by C-Y. Chiang. Number 4 in the series]. The International Journal of Tuberculosis and Lung Disease. 2010; 14(4):382–390.
Abubakar I, Lipman M. Reducing loss to follow-up during treatment for drug-resistant tuberculosis. European Respiratory Journal [Internet]. European Respiratory Society; 2019 [cited 2024 Mar 21]; 53(1). https://erj.ersjournals.com/content/53/1/1802268 .
Soedarsono S, Mertaniasih NM, Kusmiati T, et al. Determinant factors for loss to follow-up in drug-resistant tuberculosis patients: the importance of psycho-social and economic aspects. BMC Pulm Med. 2021;21(1):360.
doi: 10.1186/s12890-021-01735-9
pubmed: 34758794
pmcid: 8579625
Jiang Y, Chen J, Ying M, et al. Factors associated with loss to follow-up before and after treatment initiation among patients with tuberculosis: a 5-year observation in China. Front Med (Lausanne). 2023;10:1136094.
doi: 10.3389/fmed.2023.1136094
pubmed: 37181365
Barreto-Duarte B, Villalva-Serra K, Miguez-Pinto JP, Retreatment and Antituberculosis Therapy Outcomes in Brazil between 2015 and 2022: A Nationwide Study of Disease Registry Data [Internet]., Rochester NY et al. 2023 [cited 2024 Mar 21]. https://papers.ssrn.com/abstract=4654261 .