{"title":"Machine-learning based prediction model for acute kidney injury induced by multiple wasp stings","authors":"Wen Wu , Yupei Zhang , Yilan Zhang , Xingguang Qu , Zhaohui Zhang , Rong Zhang","doi":"10.1016/j.toxicon.2024.108112","DOIUrl":null,"url":null,"abstract":"<div><div>Acute kidney injury (AKI) following multiple wasp stings is a severe complication with potentially poor outcomes. Despite extensive research on AKI's risk factors, predictive models for wasp sting-related AKI are limited. This study aims to develop and validate a machine learning-based clinical prediction model for AKI in individuals with wasp stings. In this retrospective cohort study, conducted at a tertiary teaching hospital in Yichang, China, from July 2013 to April 2023, 214 patients with wasp sting injuries were analyzed. Using least absolute shrinkage and selection operator (LASSO) regression and multivariate logistic regression, prognostic variables for AKI were identified. A nomogram incorporating these four variables was constructed. The model's performance was assessed through internal validation, leave-one-out cross-validation, net reclassification improvement (NRI), integrated discrimination improvement (IDI), and decision curve analysis (DCA). Among 214 patients affected by wasp stings, 34.6% (74/214) developed AKI. Following LASSO regression and multivariate logistic regression, the number of stings, presence of gross hematuria, systemic inflammatory response index (SIRI), and platelet count were identified as prognostic factors. A nomogram was constructed and evaluated for its predictive accuracy, showing an area under the curve (AUC) of 0.757 (95% CI 0.711 to 0.804) and a concordance index (C-index) of 0.75. Validation confirmed the model's reliability and superior discrimination ability over existing models, as demonstrated by NRI, IDI, and DCA. The developed nomogram effectively predicts AKI risk in wasp sting patients, facilitating early identification and management of those at risk.</div></div>","PeriodicalId":23289,"journal":{"name":"Toxicon","volume":"250 ","pages":"Article 108112"},"PeriodicalIF":2.6000,"publicationDate":"2024-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Toxicon","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0041010124006846","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PHARMACOLOGY & PHARMACY","Score":null,"Total":0}
引用次数: 0
Abstract
Acute kidney injury (AKI) following multiple wasp stings is a severe complication with potentially poor outcomes. Despite extensive research on AKI's risk factors, predictive models for wasp sting-related AKI are limited. This study aims to develop and validate a machine learning-based clinical prediction model for AKI in individuals with wasp stings. In this retrospective cohort study, conducted at a tertiary teaching hospital in Yichang, China, from July 2013 to April 2023, 214 patients with wasp sting injuries were analyzed. Using least absolute shrinkage and selection operator (LASSO) regression and multivariate logistic regression, prognostic variables for AKI were identified. A nomogram incorporating these four variables was constructed. The model's performance was assessed through internal validation, leave-one-out cross-validation, net reclassification improvement (NRI), integrated discrimination improvement (IDI), and decision curve analysis (DCA). Among 214 patients affected by wasp stings, 34.6% (74/214) developed AKI. Following LASSO regression and multivariate logistic regression, the number of stings, presence of gross hematuria, systemic inflammatory response index (SIRI), and platelet count were identified as prognostic factors. A nomogram was constructed and evaluated for its predictive accuracy, showing an area under the curve (AUC) of 0.757 (95% CI 0.711 to 0.804) and a concordance index (C-index) of 0.75. Validation confirmed the model's reliability and superior discrimination ability over existing models, as demonstrated by NRI, IDI, and DCA. The developed nomogram effectively predicts AKI risk in wasp sting patients, facilitating early identification and management of those at risk.
期刊介绍:
Toxicon has an open access mirror Toxicon: X, sharing the same aims and scope, editorial team, submission system and rigorous peer review. An introductory offer Toxicon: X - full waiver of the Open Access fee.
Toxicon''s "aims and scope" are to publish:
-articles containing the results of original research on problems related to toxins derived from animals, plants and microorganisms
-papers on novel findings related to the chemical, pharmacological, toxicological, and immunological properties of natural toxins
-molecular biological studies of toxins and other genes from poisonous and venomous organisms that advance understanding of the role or function of toxins
-clinical observations on poisoning and envenoming where a new therapeutic principle has been proposed or a decidedly superior clinical result has been obtained.
-material on the use of toxins as tools in studying biological processes and material on subjects related to venom and antivenom problems.
-articles on the translational application of toxins, for example as drugs and insecticides
-epidemiological studies on envenoming or poisoning, so long as they highlight a previously unrecognised medical problem or provide insight into the prevention or medical treatment of envenoming or poisoning. Retrospective surveys of hospital records, especially those lacking species identification, will not be considered for publication. Properly designed prospective community-based surveys are strongly encouraged.
-articles describing well-known activities of venoms, such as antibacterial, anticancer, and analgesic activities of arachnid venoms, without any attempt to define the mechanism of action or purify the active component, will not be considered for publication in Toxicon.
-review articles on problems related to toxinology.
To encourage the exchange of ideas, sections of the journal may be devoted to Short Communications, Letters to the Editor and activities of the affiliated societies.