Jun Ma1, Hongyun Yin2, Xiaohui Hao1, Wei Sha1, Haiyan Cui1. 1. Department of Tuberculosis and Shanghai Key Lab of Tuberculosis, Shanghai Pulmonary Hospital Affiliated to Tongji University School of Medicine 507 Zhengmin Road, Shanghai 200433, China. 2. Clinic and Research Center of Tuberculosis, Shanghai Key Lab of Tuberculosis, Shanghai Pulmonary Hospital, Tongji University School of Medicine 507 Zhengmin Road, Shanghai 200433, China.
Abstract
OBJECTIVE: To identify significant diagnostic factors and establish a predictive model for diagnosis of sarcoidosis and tuberculosis. METHODS: This study included 252 patients (123 cases of lung sarcoidosis and 129 cases of lung tuberculosis) who underwent laboratory evaluation, including routine hematologic testing, serum immunology, blood coagulation, angiotensin-converting enzyme, and T lymphocyte subset. The factors that statistically different between the two groups were identified by an independent sample t test first, and then processed by the random forest model to distinguish two diseases with the classification function. Moreover, the diagnostic performance of the predictive random forest model was evaluated through the identification of individual contribution of various diagnostic factors conducted by the model. RESULTS: The random forest model revealed a classification error rate of 24.9%. Among all of the statistically significant diagnostic factors, the individual factors with the greatest and second contribution were angiotensin-converting enzyme and prothrombin time, respectively. The area under the receiver operating characteristic (ROC) curve of the random forest prediction model was 0.915. CONCLUSION: The random forest model can be used to distinguish between sarcoidosis and tuberculosis by incorporating statistically significant diagnostic factors, which is of potential clinical application value. AJTR
OBJECTIVE: To identify significant diagnostic factors and establish a predictive model for diagnosis of sarcoidosis and tuberculosis. METHODS: This study included 252 patients (123 cases of lung sarcoidosis and 129 cases of lung tuberculosis) who underwent laboratory evaluation, including routine hematologic testing, serum immunology, blood coagulation, angiotensin-converting enzyme, and T lymphocyte subset. The factors that statistically different between the two groups were identified by an independent sample t test first, and then processed by the random forest model to distinguish two diseases with the classification function. Moreover, the diagnostic performance of the predictive random forest model was evaluated through the identification of individual contribution of various diagnostic factors conducted by the model. RESULTS: The random forest model revealed a classification error rate of 24.9%. Among all of the statistically significant diagnostic factors, the individual factors with the greatest and second contribution were angiotensin-converting enzyme and prothrombin time, respectively. The area under the receiver operating characteristic (ROC) curve of the random forest prediction model was 0.915. CONCLUSION: The random forest model can be used to distinguish between sarcoidosis and tuberculosis by incorporating statistically significant diagnostic factors, which is of potential clinical application value. AJTR
Authors: Alexandra Csongrádi; Attila Enyedi; István Takács; Tamás Végh; Ivetta S Mányiné; Zsófia Pólik; István Tibor Altorjay; József Balla; György Balla; István Édes; János Kappelmayer; Attila Tóth; Zoltán Papp; Miklós Fagyas Journal: Clin Chem Lab Med Date: 2018-06-27 Impact factor: 3.694
Authors: David M Lewinsohn; Michael K Leonard; Philip A LoBue; David L Cohn; Charles L Daley; Ed Desmond; Joseph Keane; Deborah A Lewinsohn; Ann M Loeffler; Gerald H Mazurek; Richard J O'Brien; Madhukar Pai; Luca Richeldi; Max Salfinger; Thomas M Shinnick; Timothy R Sterling; David M Warshauer; Gail L Woods Journal: Clin Infect Dis Date: 2016-12-08 Impact factor: 9.079
Authors: Sergei M Danilov; Heinrich Lünsdorf; Henry T Akinbi; Andrew B Nesterovitch; Yuliya Epshtein; Eleftheria Letsiou; Olga V Kryukova; Tobias Piegeler; Elena Z Golukhova; David E Schwartz; Randal O Dull; Richard D Minshall; Olga A Kost; Joe G N Garcia Journal: Sci Rep Date: 2016-10-13 Impact factor: 4.379