Mariusz Jojczuk, Piotr Kamiński, Jakub Gajewski, Robert Karpiński, Przemysław Krakowski, Józef Jonak, Adam Nogalski, Dariusz Głuchowski
{"title":"在2006-2018年期间波兰卢布林省头颈部损伤患者中使用基于国际分类ICD-10的神经网络作为持续损伤结果的预测价值。","authors":"Mariusz Jojczuk, Piotr Kamiński, Jakub Gajewski, Robert Karpiński, Przemysław Krakowski, Józef Jonak, Adam Nogalski, Dariusz Głuchowski","doi":"10.26444/aaem/158872","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction and objective: </strong>Head and neck injuries are a heterogeneous group in terms of both clinical course and prognosis. For years, there have been attempts to create an ideal tool to predict the outcomes and severity of injuries. The aim of this study was evaluation of the use of selected artificial intelligence methods for outcome predictions of head and neck injuries.</p><p><strong>Material and methods: </strong>6,824 consecutive cases of patients who sustained head and neck injuries, treated in hospitals in the Lublin Province between 2006-2018, whose data was provided by National Institute of Public Health / National Institute of Hygiene, were analyzed retrospectively. Patients were qualified using International Statistical Classification of Diseases and Related Health Problems (10th Revision). The multilayer perceptron (MLP) structure was utilized in numerical studies. Neural network training was achieved with the Broyden-Fletcher-Goldfarb-Shanno (BFGS) method.</p><p><strong>Results: </strong>In the designed network, the highest classification efficiency was obtained for the group of deaths (80.7%). The average value of correct classifications for all analyzed cases was 66%. The most important variable influencing the prognosis of an injured patient was diagnosis (weight 1.929). Gender and age were variables of less significance with weight 1.08 and 1.073, respectively.</p><p><strong>Conclusions: </strong>Designing a neural network was hindered due to the large amount of cases and linking of a large number of deaths with specific diagnosis (S06). With a predictive value of 80.7% for mortality, ANN can be a promising tool in the future; however, additional variables should be introduced into the algorithm to increase the predictive value of the network. Further studies, including other types of injuries and additional variables, are needed to introduce this method into clinical use.</p>","PeriodicalId":50970,"journal":{"name":"Annals of Agricultural and Environmental Medicine","volume":"30 2","pages":"281-286"},"PeriodicalIF":1.3000,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Use of neural network based on international classification ICD-10 in patients with head and neck injuries in Lublin Province, Poland, between 2006-2018, as a predictive value of the outcomes of injury sustained.\",\"authors\":\"Mariusz Jojczuk, Piotr Kamiński, Jakub Gajewski, Robert Karpiński, Przemysław Krakowski, Józef Jonak, Adam Nogalski, Dariusz Głuchowski\",\"doi\":\"10.26444/aaem/158872\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Introduction and objective: </strong>Head and neck injuries are a heterogeneous group in terms of both clinical course and prognosis. For years, there have been attempts to create an ideal tool to predict the outcomes and severity of injuries. The aim of this study was evaluation of the use of selected artificial intelligence methods for outcome predictions of head and neck injuries.</p><p><strong>Material and methods: </strong>6,824 consecutive cases of patients who sustained head and neck injuries, treated in hospitals in the Lublin Province between 2006-2018, whose data was provided by National Institute of Public Health / National Institute of Hygiene, were analyzed retrospectively. Patients were qualified using International Statistical Classification of Diseases and Related Health Problems (10th Revision). The multilayer perceptron (MLP) structure was utilized in numerical studies. Neural network training was achieved with the Broyden-Fletcher-Goldfarb-Shanno (BFGS) method.</p><p><strong>Results: </strong>In the designed network, the highest classification efficiency was obtained for the group of deaths (80.7%). The average value of correct classifications for all analyzed cases was 66%. The most important variable influencing the prognosis of an injured patient was diagnosis (weight 1.929). Gender and age were variables of less significance with weight 1.08 and 1.073, respectively.</p><p><strong>Conclusions: </strong>Designing a neural network was hindered due to the large amount of cases and linking of a large number of deaths with specific diagnosis (S06). With a predictive value of 80.7% for mortality, ANN can be a promising tool in the future; however, additional variables should be introduced into the algorithm to increase the predictive value of the network. Further studies, including other types of injuries and additional variables, are needed to introduce this method into clinical use.</p>\",\"PeriodicalId\":50970,\"journal\":{\"name\":\"Annals of Agricultural and Environmental Medicine\",\"volume\":\"30 2\",\"pages\":\"281-286\"},\"PeriodicalIF\":1.3000,\"publicationDate\":\"2023-06-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Annals of Agricultural and Environmental Medicine\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.26444/aaem/158872\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ENVIRONMENTAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annals of Agricultural and Environmental Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.26444/aaem/158872","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
Use of neural network based on international classification ICD-10 in patients with head and neck injuries in Lublin Province, Poland, between 2006-2018, as a predictive value of the outcomes of injury sustained.
Introduction and objective: Head and neck injuries are a heterogeneous group in terms of both clinical course and prognosis. For years, there have been attempts to create an ideal tool to predict the outcomes and severity of injuries. The aim of this study was evaluation of the use of selected artificial intelligence methods for outcome predictions of head and neck injuries.
Material and methods: 6,824 consecutive cases of patients who sustained head and neck injuries, treated in hospitals in the Lublin Province between 2006-2018, whose data was provided by National Institute of Public Health / National Institute of Hygiene, were analyzed retrospectively. Patients were qualified using International Statistical Classification of Diseases and Related Health Problems (10th Revision). The multilayer perceptron (MLP) structure was utilized in numerical studies. Neural network training was achieved with the Broyden-Fletcher-Goldfarb-Shanno (BFGS) method.
Results: In the designed network, the highest classification efficiency was obtained for the group of deaths (80.7%). The average value of correct classifications for all analyzed cases was 66%. The most important variable influencing the prognosis of an injured patient was diagnosis (weight 1.929). Gender and age were variables of less significance with weight 1.08 and 1.073, respectively.
Conclusions: Designing a neural network was hindered due to the large amount of cases and linking of a large number of deaths with specific diagnosis (S06). With a predictive value of 80.7% for mortality, ANN can be a promising tool in the future; however, additional variables should be introduced into the algorithm to increase the predictive value of the network. Further studies, including other types of injuries and additional variables, are needed to introduce this method into clinical use.
期刊介绍：
All papers within the scope indicated by the following sections of the journal may be submitted:
Biological agents posing occupational risk in agriculture, forestry, food industry and wood industry and diseases caused by these agents (zoonoses, allergic and immunotoxic diseases).
Health effects of chemical pollutants in agricultural areas , including occupational and non-occupational effects of agricultural chemicals (pesticides, fertilizers) and effects of industrial disposal (heavy metals, sulphur, etc.) contaminating the atmosphere, soil and water.
Exposure to physical hazards associated with the use of machinery in agriculture and forestry: noise, vibration, dust.
Prevention of occupational diseases in agriculture, forestry, food industry and wood industry.
Work-related accidents and injuries in agriculture, forestry, food industry and wood industry: incidence, causes, social aspects and prevention.
State of the health of rural communities depending on various factors: social factors, accessibility of medical care, etc.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
