Interpretable machine learning for the prediction of death risk in patients with acute diquat poisoning.
Diquat poisoning
Machine learning
Risk of death
Shapley additive explanations
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
12 Jul 2024
12 Jul 2024
Historique:
received:
29
03
2024
accepted:
09
07
2024
medline:
13
7
2024
pubmed:
13
7
2024
entrez:
12
7
2024
Statut:
epublish
Résumé
The aim of this study was to develop and validate predictive models for assessing the risk of death in patients with acute diquat (DQ) poisoning using innovative machine learning techniques. Additionally, predictive models were evaluated through the application of SHapley Additive ExPlanations (SHAP). A total of 201 consecutive patients from the emergency departments of the First Hospital and Shengjing Hospital of China Medical University admitted for deliberate oral intake of DQ from February 2018 to August 2023 were analysed. The initial clinical data of the patients with acute DQ poisoning were collected. Machine learning methods such as logistic regression, random forest, support vector machine (SVM), and gradient boosting were applied to build the prediction models. The whole sample was split into a training set and a test set at a ratio of 8:2. The performances of these models were assessed in terms of discrimination, calibration, and clinical decision curve analysis (DCA). We also used the SHAP interpretation tool to provide an intuitive explanation of the risk of death in patients with DQ poisoning. Logistic regression, random forest, SVM, and gradient boosting models were established, and the areas under the receiver operating characteristic curves (AUCs) were 0.91, 0.98, 0.96 and 0.94, respectively. The net benefits were similar across all four models. The four machine learning models can be reliable tools for predicting death risk in patients with acute DQ poisoning. Their combination with SHAP provides explanations for individualized risk prediction, increasing the model transparency.
Identifiants
pubmed: 38997450
doi: 10.1038/s41598-024-67257-6
pii: 10.1038/s41598-024-67257-6
doi:
Substances chimiques
Diquat
A9A615U4MP
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
16101Informations de copyright
© 2024. The Author(s).
Références
Ko, D. R. et al. Effects of paraquat ban on herbicide poisoning-related mortality. Yonsei Med. J. 58, 859–866 (2017).
doi: 10.3349/ymj.2017.58.4.859
pubmed: 28541002
pmcid: 5447120
Huang, Y., Zhang, R., Meng, M., Chen, D. & Deng, Y. High-dose diquat poisoning: A case report. J. Int. Med. Res. 49, 3000605211026117 (2021).
doi: 10.1177/03000605211026117
pubmed: 34182818
Zhou, J. N. & Lu, Y. Q. Lethal diquat poisoning manifests as acute central nervous system injury and circulatory failure: A retrospective cohort study of 50 cases. EClinicalMedicine 52, 101609 (2022).
doi: 10.1016/j.eclinm.2022.101609
pubmed: 35990582
pmcid: 9386369
Magalhães, N., Carvalho, F. & Dinis-Oliveira, R. J. Human and experimental toxicology of diquat poisoning: Toxicokinetics, mechanisms of toxicity, clinical features, and treatment. Hum. Exp. Toxicol. 37, 1131–1160 (2018).
doi: 10.1177/0960327118765330
pubmed: 29569487
Saeed, S. A., Wilks, M. F. & Coupe, M. Acute diquat poisoning with intracerebral bleeding. Postgrad. Med. J. 77, 329–332 (2001).
doi: 10.1136/pmj.77.907.329
pubmed: 11320278
pmcid: 1742045
Subbiah, R. & Tiwari, R. R. The herbicide paraquat-induced molecular mechanisms in the development of acute lung injury and lung fibrosis. Crit. Rev. Toxicol. 51, 36–64 (2021).
doi: 10.1080/10408444.2020.1864721
pubmed: 33528289
Liu, X., Yang, H. & Liu, Z. Signaling pathways involved in paraquat-induced pulmonary toxicity: Molecular mechanisms and potential therapeutic drugs. Int. Immunopharmacol. 113, 109301 (2022).
doi: 10.1016/j.intimp.2022.109301
pubmed: 36279672
Lu, S. et al. Development and validation of a radiomics nomogram for prognosis prediction of patients with acute paraquat poisoning: A retrospective cohort study. Biomed. Res. Int. 2021, 6621894 (2021).
pubmed: 33604379
pmcid: 7872759
Jia, H. et al. Quercetin alleviates oxidative damage by activating nuclear factor erythroid 2-related factor 2 signaling in porcine enterocytes. Nutrients 13, 375 (2021).
doi: 10.3390/nu13020375
pubmed: 33530513
pmcid: 7911945
Yu, G. et al. Case series: Diquat poisoning with acute kidney failure, myocardial damage, and rhabdomyolysis. Front. Public Health 10, 991587 (2022).
doi: 10.3389/fpubh.2022.991587
pubmed: 36353285
pmcid: 9638031
Basilicata, P. et al. Diquat poisoning: Care management and medico-legal implications. Toxics 10, 166 (2022).
doi: 10.3390/toxics10040166
pubmed: 35448427
pmcid: 9030962
Zhang, Z., Ho, K. M. & Hong, Y. Machine learning for the prediction of volume responsiveness in patients with oliguric acute kidney injury in critical care. Crit. Care 23, 112 (2019).
doi: 10.1186/s13054-019-2411-z
pubmed: 30961662
pmcid: 6454725
Yue, S. et al. Machine learning for the prediction of acute kidney injury in patients with sepsis. J. Transl. Med. 20, 215 (2022).
doi: 10.1186/s12967-022-03364-0
pubmed: 35562803
pmcid: 9101823
Raita, Y. et al. Emergency department triage prediction of clinical outcomes using machine learning models. Crit. Care 23, 64 (2019).
doi: 10.1186/s13054-019-2351-7
pubmed: 30795786
pmcid: 6387562
Taylor, R. A. et al. Prediction of in-hospital mortality in emergency department patients with sepsis: A local big data-driven, machine learning approach. Acad. Emerg. Med. 23, 269–278 (2016).
doi: 10.1111/acem.12876
pubmed: 26679719
pmcid: 5884101
Kramer, A. A. & Zimmerman, J. E. Assessing the calibration of mortality benchmarks in critical care: The Hosmer-Lemeshow test revisited. Crit. Care Med. 35, 2052–2056 (2007).
doi: 10.1097/01.CCM.0000275267.64078.B0
pubmed: 17568333
Lei, T. et al. Establishment and validation of predictive model of tophus in gout patients. J. Clin. Med. 12, 1755 (2023).
doi: 10.3390/jcm12051755
pubmed: 36902542
pmcid: 10002994
Jones, G. M. & Vale, J. A. Mechanisms of toxicity, clinical features, and management of diquat poisoning: A review. J. Toxicol. Clin. Toxicol. 38, 123–128 (2000).
doi: 10.1081/CLT-100100926
pubmed: 10778908
Circu, M. L., Maloney, R. E. & Aw, T. Y. Diquat-induced cellular pyridine nucleotide redox changes and alteration of metabolic enzyme activities in colonic carcinoma cells. Chem. Biol. Interact. 264, 43–51 (2017).
doi: 10.1016/j.cbi.2017.01.007
pubmed: 28108222
Wu, K. C., Zhang, Y. & Klaassen, C. D. Nrf2 protects against diquat-induced liver and lung injury. Free Radic. Res. 46, 1220–1229 (2012).
doi: 10.3109/10715762.2012.700709
pubmed: 22762311
Xu, J. et al. Melatonin reduces mortality and oxidatively mediated hepatic and renal damage due to diquat treatment. J. Pineal Res. 42, 166–171 (2007).
doi: 10.1111/j.1600-079X.2006.00401.x
pubmed: 17286749
Lu, T. et al. Protective effects of forsythia suspensa extract against oxidative stress induced by diquat in rats. Food Chem. Toxicol. 48, 764–770 (2010).
doi: 10.1016/j.fct.2009.12.018
pubmed: 20036301
Shao, D. et al. A novel orellanine containing mushroom cortinarius armillatus. Toxicon 114, 65–74 (2016).
doi: 10.1016/j.toxicon.2016.02.010
pubmed: 26915341
Dinis-Oliveira, R. J., Soares, M., Rocha-Pereira, C. & Carvalho, F. Human and experimental toxicology of orellanine. Hum. Exp. Toxicol. 35, 1016–1029 (2016).
doi: 10.1177/0960327115613845
pubmed: 26553321
Yu, G. et al. Acute diquat poisoning resulting in toxic encephalopathy: A report of three cases. Clin. Toxicol. 60, 647–650 (2022).
doi: 10.1080/15563650.2021.2013495
Manabe, J. & Ogata, T. The toxic effect of diquat on the rat lung after intratracheal administration. Toxicol. Lett. 30, 7–12 (1986).
doi: 10.1016/0378-4274(86)90172-4
pubmed: 3952774
Lam, H. F., Takezawa, J., Gupta, B. N. & van Stee, E. W. A comparison of the effects of paraquat and diquat on lung compliance, lung volumes and single breath diffusing capacity in the rat. Toxicology 18, 111–123 (1980).
doi: 10.1016/0300-483X(80)90074-8
pubmed: 7256779
Charles, J. M., Abou-Donia, M. B. & Menzel, D. B. Absorption of paraquat and diquat from the airways of the perfused rat lung. Toxicology 9, 59–67 (1978).
doi: 10.1016/0300-483X(78)90031-8
pubmed: 653742
Jović-Stosić, J., Babić, G. & Todorović, V. Fatal diquat intoxication. Vojnosanit. Pregl. 66, 477–481 (2009).
doi: 10.2298/VSP0906477J
pubmed: 19583147
Goecks, J., Jalili, V., Heiser, L. M. & Gray, J. W. How machine learning will transform biomedicine. Cell 181, 92–101 (2020).
doi: 10.1016/j.cell.2020.03.022
pubmed: 32243801
pmcid: 7141410
Waljee, A. K. et al. Development and validation of machine learning models in prediction of remission in patients with moderate to severe crohn disease. JAMA Netw. Open 2, e193721 (2019).
doi: 10.1001/jamanetworkopen.2019.3721
pubmed: 31074823
pmcid: 6512283
Jahandideh, S. et al. Evaluation of machine learning-based models for prediction of clinical deterioration: A systematic literature review. Int. J. Med. Inform. 175, 105084 (2023).
doi: 10.1016/j.ijmedinf.2023.105084
pubmed: 37156168
McCarthy, L. G. & Speth, C. P. Diquat intoxication. Ann. Emerg. Med. 12, 394–396 (1983).
doi: 10.1016/S0196-0644(83)80474-0
pubmed: 6859638
Jansen, T. C., van Bommel, J. & Bakker, J. Blood lactate monitoring in critically ill patients: A systematic health technology assessment. Crit. Care Med. 37, 2827–2839 (2009).
pubmed: 19707124
Liu, X. W., Ma, T., Qu, B., Ji, Y. & Liu, Z. Prognostic value of initial arterial lactate level and lactate metabolic clearance rate in patients with acute paraquat poisoning. Am. J. Emerg. Med. 31, 1230–1235 (2013).
doi: 10.1016/j.ajem.2013.04.019
pubmed: 23706581
Lee, Y. et al. Arterial lactate as a predictor of mortality in emergency department patients with paraquat intoxication. Clin. Toxicol. 50, 52–56 (2012).
doi: 10.3109/15563650.2011.639716
Hoiland, R. L., Fisher, J. A. & Ainslie, P. N. Regulation of the cerebral circulation by arterial carbon dioxide. Compr. Physiol. 9, 1101–1154 (2019).
doi: 10.1002/cphy.c180021
pubmed: 31187899
Dong, N. et al. Prognostic nomogram for the severity of acute organophosphate insecticide self-poisoning: A retrospective observational cohort study. BMJ Open 11, e042765 (2021).
doi: 10.1136/bmjopen-2020-042765
pubmed: 34031108
pmcid: 8149305
Gao, Y. et al. A novel simple risk model to predict the prognosis of patients with paraquat poisoning. Sci. Rep. 11, 237 (2021).
doi: 10.1038/s41598-020-80371-5
pubmed: 33420265
pmcid: 7794476
Collins, G. S., Reitsma, J. B., Altman, D. G. & Moons, K. G. M. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. BMJ 350, g7594. https://doi.org/10.1136/bmj.g7594 (2015).