Predictive modeling for eosinophilic chronic rhinosinusitis: Nomogram and four machine learning approaches
Summary: Eosinophilic chronic rhinosinusitis (ECRS) is a distinct subset of chronic rhinosinusitis characterized by heightened eosinophilic infiltration and increased symptom severity, often resisting standard treatments. Traditional diagnosis requires invasive histological evaluation. This study ai...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-02-01
|
| Series: | iScience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589004224001494 |
| _version_ | 1797328606390648832 |
|---|---|
| author | Panhui Xiong Junliang Chen Yue Zhang Longlan Shu Yang Shen Yue Gu Yijun Liu Dayu Guan Bowen Zheng Yucheng Yang |
| author_facet | Panhui Xiong Junliang Chen Yue Zhang Longlan Shu Yang Shen Yue Gu Yijun Liu Dayu Guan Bowen Zheng Yucheng Yang |
| author_sort | Panhui Xiong |
| collection | DOAJ |
| description | Summary: Eosinophilic chronic rhinosinusitis (ECRS) is a distinct subset of chronic rhinosinusitis characterized by heightened eosinophilic infiltration and increased symptom severity, often resisting standard treatments. Traditional diagnosis requires invasive histological evaluation. This study aims to develop predictive models for ECRS based on patient clinical parameters, eliminating the need for invasive biopsy. Utilizing logistic regression with lasso regularization, random forest (RF), gradient-boosted decision tree (GBDT), and deep neural network (DNN), we trained models on common clinical data. The predictive performance was evaluated using metrics such as area under the curve (AUC) for receiver operator characteristics, decision curves, and feature ranking analysis. In a cohort of 437 eligible patients, the models identified peripheral blood eosinophil ratio, absolute peripheral blood eosinophil, and the ethmoidal/maxillary sinus density ratio (E/M) on computed tomography as crucial predictors for ECRS. This predictive model offers a valuable tool for identifying ECRS without resorting to histological biopsy, enhancing clinical decision-making. |
| first_indexed | 2024-03-08T06:54:07Z |
| format | Article |
| id | doaj.art-87b420fdae9144caab70cfdde1d4991d |
| institution | Directory Open Access Journal |
| issn | 2589-0042 |
| language | English |
| last_indexed | 2024-03-08T06:54:07Z |
| publishDate | 2024-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | iScience |
| spelling | doaj.art-87b420fdae9144caab70cfdde1d4991d2024-02-03T06:39:04ZengElsevieriScience2589-00422024-02-01272108928Predictive modeling for eosinophilic chronic rhinosinusitis: Nomogram and four machine learning approachesPanhui Xiong0Junliang Chen1Yue Zhang2Longlan Shu3Yang Shen4Yue Gu5Yijun Liu6Dayu Guan7Bowen Zheng8Yucheng Yang9Department of Otorhinolaryngology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, ChinaDepartment of Otorhinolaryngology, Xishui People’s Hospital, Xishui County, Zunyi, Guizhou Province 564600, ChinaDepartment of Otorhinolaryngology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, ChinaDepartment of Otorhinolaryngology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, ChinaDepartment of Otorhinolaryngology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, ChinaDepartment of Otorhinolaryngology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, ChinaDepartment of Otorhinolaryngology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, ChinaDepartment of Otorhinolaryngology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, ChinaDepartment of Otorhinolaryngology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, ChinaDepartment of Otorhinolaryngology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China; Corresponding authorSummary: Eosinophilic chronic rhinosinusitis (ECRS) is a distinct subset of chronic rhinosinusitis characterized by heightened eosinophilic infiltration and increased symptom severity, often resisting standard treatments. Traditional diagnosis requires invasive histological evaluation. This study aims to develop predictive models for ECRS based on patient clinical parameters, eliminating the need for invasive biopsy. Utilizing logistic regression with lasso regularization, random forest (RF), gradient-boosted decision tree (GBDT), and deep neural network (DNN), we trained models on common clinical data. The predictive performance was evaluated using metrics such as area under the curve (AUC) for receiver operator characteristics, decision curves, and feature ranking analysis. In a cohort of 437 eligible patients, the models identified peripheral blood eosinophil ratio, absolute peripheral blood eosinophil, and the ethmoidal/maxillary sinus density ratio (E/M) on computed tomography as crucial predictors for ECRS. This predictive model offers a valuable tool for identifying ECRS without resorting to histological biopsy, enhancing clinical decision-making.http://www.sciencedirect.com/science/article/pii/S2589004224001494Health sciencesMedicineMedical specialtyHealth informaticsHealth technology |
| spellingShingle | Panhui Xiong Junliang Chen Yue Zhang Longlan Shu Yang Shen Yue Gu Yijun Liu Dayu Guan Bowen Zheng Yucheng Yang Predictive modeling for eosinophilic chronic rhinosinusitis: Nomogram and four machine learning approaches iScience Health sciences Medicine Medical specialty Health informatics Health technology |
| title | Predictive modeling for eosinophilic chronic rhinosinusitis: Nomogram and four machine learning approaches |
| title_full | Predictive modeling for eosinophilic chronic rhinosinusitis: Nomogram and four machine learning approaches |
| title_fullStr | Predictive modeling for eosinophilic chronic rhinosinusitis: Nomogram and four machine learning approaches |
| title_full_unstemmed | Predictive modeling for eosinophilic chronic rhinosinusitis: Nomogram and four machine learning approaches |
| title_short | Predictive modeling for eosinophilic chronic rhinosinusitis: Nomogram and four machine learning approaches |
| title_sort | predictive modeling for eosinophilic chronic rhinosinusitis nomogram and four machine learning approaches |
| topic | Health sciences Medicine Medical specialty Health informatics Health technology |
| url | http://www.sciencedirect.com/science/article/pii/S2589004224001494 |
| work_keys_str_mv | AT panhuixiong predictivemodelingforeosinophilicchronicrhinosinusitisnomogramandfourmachinelearningapproaches AT junliangchen predictivemodelingforeosinophilicchronicrhinosinusitisnomogramandfourmachinelearningapproaches AT yuezhang predictivemodelingforeosinophilicchronicrhinosinusitisnomogramandfourmachinelearningapproaches AT longlanshu predictivemodelingforeosinophilicchronicrhinosinusitisnomogramandfourmachinelearningapproaches AT yangshen predictivemodelingforeosinophilicchronicrhinosinusitisnomogramandfourmachinelearningapproaches AT yuegu predictivemodelingforeosinophilicchronicrhinosinusitisnomogramandfourmachinelearningapproaches AT yijunliu predictivemodelingforeosinophilicchronicrhinosinusitisnomogramandfourmachinelearningapproaches AT dayuguan predictivemodelingforeosinophilicchronicrhinosinusitisnomogramandfourmachinelearningapproaches AT bowenzheng predictivemodelingforeosinophilicchronicrhinosinusitisnomogramandfourmachinelearningapproaches AT yuchengyang predictivemodelingforeosinophilicchronicrhinosinusitisnomogramandfourmachinelearningapproaches |