The differential diagnosis of IgG4-related disease based on machine learning.
The differential diagnosis of IgG4-related disease based on machine learning.
复制标题
DOI：
10.1186/s13075-022-02752-7
复制
发表时间：
2022-03-19
影响因子：
4.9
通讯作者：
Tanaka H
中科院分区：
文献类型：
--
作者：
Yamamoto M;Nojima M;Kamekura R;Kuribara-Souta A;Uehara M;Yamazaki H;Yoshikawa N;Aochi S;Mizushima I;Watanabe T;Nishiwaki A;Komai T;Shoda H;Kitagori K;Yoshifuji H;Hamano H;Kawano M;Takano KI;Fujio K;Tanaka H
为了消除医生和医疗专业服务的差距和分布不均，正在推动使用人工智能开发罕见病诊断支持。免疫球蛋白G4（IgG 4）相关疾病（IgG 4-RD）是一种罕见的疾病，通常需要特殊的知识和经验来诊断。在这项研究中，我们研究了基于基本患者特征和使用机器学习的血液检查结果进行IgG 4-RD鉴别诊断的可能性。本研究纳入了602例IgG 4-RD患者和204例需要区分的非IgG 4-RD患者，这些患者访问了参与机构。10%的受试者被随机排除作为验证样本。在剩下的案例中，80%被用作训练样本，剩下的20%被用作测试样本。最后，对验证样品进行验证。使用决策树和随机森林模型进行分析。此外，在具有和不具有血清IgG 4浓度的条件之间进行比较。使用受试者工作特征（AUROC）曲线下面积评价准确性。在诊断IgG 4-RD时，当分析中包括血清IgG 4水平时，决策树和随机森林方法的AUROC曲线值分别为0.906和0.974。排除血清IgG 4水平，随机森林法分析的AUROC曲线值为0.925。基于多中心协作中的机器学习，无论有无血清IgG 4数据，仅基本患者特征和血液检查结果就足以区分IgG 4-RD与非IgG 4-RD。
To eliminate the disparity and maldistribution of physicians and medical specialty services, the development of diagnostic support for rare diseases using artificial intelligence is being promoted. Immunoglobulin G4 (IgG4)-related disease (IgG4-RD) is a rare disorder often requiring special knowledge and experience to diagnose. In this study, we investigated the possibility of differential diagnosis of IgG4-RD based on basic patient characteristics and blood test findings using machine learning. Six hundred and two patients with IgG4-RD and 204 patients with non-IgG4-RD that needed to be differentiated who visited the participating institutions were included in the study. Ten percent of the subjects were randomly excluded as a validation sample. Among the remaining cases, 80% were used as training samples, and the remaining 20% were used as test samples. Finally, validation was performed on the validation sample. The analysis was performed using a decision tree and a random forest model. Furthermore, a comparison was made between conditions with and without the serum IgG4 concentration. Accuracy was evaluated using the area under the receiver-operating characteristic (AUROC) curve. In diagnosing IgG4-RD, the AUROC curve values of the decision tree and the random forest method were 0.906 and 0.974, respectively, when serum IgG4 levels were included in the analysis. Excluding serum IgG4 levels, the AUROC curve value of the analysis by the random forest method was 0.925. Based on machine learning in a multicenter collaboration, with or without serum IgG4 data, basic patient characteristics and blood test findings alone were sufficient to differentiate IgG4-RD from non-IgG4-RD.
登录
查看更多内容
影响因子：
--
作者：
MASI, AT;HUNDER, GG;ZVAIFLER, NJ
通讯作者：
ZVAIFLER, NJ
DOI：
10.1002/art.39859
发表时间：
2017-01
期刊：
Arthritis & rheumatology (Hoboken, N.J.)
影响因子：
--
作者：
Shiboski CH;Shiboski SC;Seror R;Criswell LA;Labetoulle M;Lietman TM;Rasmussen A;Scofield H;Vitali C;Bowman SJ;Mariette X;International Sjögren's Syndrome Criteria Working Group
通讯作者：
International Sjögren's Syndrome Criteria Working Group
DOI：
10.2185/jrm.2020-022
发表时间：
2021-04
期刊：
Journal of rural medicine : JRM
影响因子：
--
作者：
Sakamoto N;Sawahata M;Yamanouchi Y;Konno S;Shijubo N;Yamaguchi T;Nakamura Y;Suzuki T;Hagiwara K;Bando M
通讯作者：
Bando M
影响因子：
2.2
作者：
Fujimoto, Shino;Koga, Tomohiro;Yoshizaki, Kazuyuki
通讯作者：
Yoshizaki, Kazuyuki
影响因子：
27.4
作者：
Lundberg IE;Tjärnlund A;Bottai M;Werth VP;Pilkington C;Visser M;Alfredsson L;Amato AA;Barohn RJ;Liang MH;Singh JA;Aggarwal R;Arnardottir S;Chinoy H;Cooper RG;Dankó K;Dimachkie MM;Feldman BM;Torre IG;Gordon P;Hayashi T;Katz JD;Kohsaka H;Lachenbruch PA;Lang BA;Li Y;Oddis CV;Olesinska M;Reed AM;Rutkowska-Sak L;Sanner H;Selva-O'Callaghan A;Song YW;Vencovsky J;Ytterberg SR;Miller FW;Rider LG;International Myositis Classification Criteria Project consortium, The Euromyositis register and The Juvenile Dermatomyositis Cohort Biomarker Study and Repository (JDRG) (UK and Ireland)
通讯作者：
International Myositis Classification Criteria Project consortium, The Euromyositis register and The Juvenile Dermatomyositis Cohort Biomarker Study and Repository (JDRG) (UK and Ireland)