Laboratory blood parameters and machine learning for the prognosis of esophageal squamous cell carcinoma
BackgroundIn contemporary study, the death of esophageal squamous cell carcinoma (ESCC) patients need precise and expedient prognostic methodologies.ObjectiveTo develop and validate a prognostic model tailored to ESCC patients, leveraging the power of machine learning (ML) techniques and drawing ins...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-04-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2024.1367008/full |
| _version_ | 1797223764668186624 |
|---|---|
| author | Feng Lu Linlan Yang Zhenglian Luo Qiao He Lijuan Shangguan Mingfei Cao Lichun Wu |
| author_facet | Feng Lu Linlan Yang Zhenglian Luo Qiao He Lijuan Shangguan Mingfei Cao Lichun Wu |
| author_sort | Feng Lu |
| collection | DOAJ |
| description | BackgroundIn contemporary study, the death of esophageal squamous cell carcinoma (ESCC) patients need precise and expedient prognostic methodologies.ObjectiveTo develop and validate a prognostic model tailored to ESCC patients, leveraging the power of machine learning (ML) techniques and drawing insights from comprehensive datasets of laboratory-derived blood parameters.MethodsThree ML approaches, including Gradient Boosting Machine (GBM), Random Survival Forest (RSF), and the classical Cox method, were employed to develop models on a dataset of 2521 ESCC patients with 27 features. The models were evaluated by concordance index (C-index) and time receiver operating characteristics (Time ROC) curves. We used the optimal model to evaluate the correlation between features and prognosis and divide patients into low- and high-risk groups by risk stratification. Its performance was analyzed by Kaplan-Meier curve and the comparison with AJCC8 stage. We further evaluate the comprehensive effectiveness of the model in ESCC subgroup by risk score and KDE (kernel density estimation) plotting.ResultsRSF’s C-index (0.746) and AUC (three-year AUC 0.761, five-year AUC 0.771) had slight advantage over GBM and the classical Cox method. Subsequently, 14 features such as N stage, T stage, surgical margin, tumor length, age, Dissected LN number, MCH, Na, FIB, DBIL, CL, treatment, vascular invasion, and tumor grade were selected to build the model. Based on these, we found significant difference for survival rate between low-(3-year OS 81.8%, 5-year OS 69.8%) and high-risk (3-year OS 25.1%, 5-year OS 11.5%) patients in training set, which was also verified in test set (all P < 0.0001). Compared with the AJCC8th stage system, it showed a greater discriminative ability which is also in good agreement with its staging ability.ConclusionWe developed an ESCC prognostic model with good performance by clinical features and laboratory blood parameters. |
| first_indexed | 2024-04-24T13:42:25Z |
| format | Article |
| id | doaj.art-fc398ca8d014484985f691a7ec3c659f |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-04-24T13:42:25Z |
| publishDate | 2024-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-fc398ca8d014484985f691a7ec3c659f2024-04-04T08:12:25ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2024-04-011410.3389/fonc.2024.13670081367008Laboratory blood parameters and machine learning for the prognosis of esophageal squamous cell carcinomaFeng Lu0Linlan Yang1Zhenglian Luo2Qiao He3Lijuan Shangguan4Mingfei Cao5Lichun Wu6Department of Experimental Medicine, The People’s Hospital of Jianyang City, Jianyang, Sichuan, ChinaCollege of Medical Technology, Chengdu University of Traditional Chinese Medicine, Chengdu, ChinaDepartment of Transfusion Medicine, West China Hospital, Sichuan University, Chengdu, ChinaDepartment of Clinical Laboratory, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, Affiliated Cancer Hospital of University of Electronic Science and Technology of China, Chengdu, ChinaOutpatient Department, People’s Hospital of Jianyang, Jianyang, Sichuan, ChinaDepartment of Clinical Laboratory, Chuankong Hospital of Jianyang, Jianyang, Sichuan, ChinaDepartment of Clinical Laboratory, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, Affiliated Cancer Hospital of University of Electronic Science and Technology of China, Chengdu, ChinaBackgroundIn contemporary study, the death of esophageal squamous cell carcinoma (ESCC) patients need precise and expedient prognostic methodologies.ObjectiveTo develop and validate a prognostic model tailored to ESCC patients, leveraging the power of machine learning (ML) techniques and drawing insights from comprehensive datasets of laboratory-derived blood parameters.MethodsThree ML approaches, including Gradient Boosting Machine (GBM), Random Survival Forest (RSF), and the classical Cox method, were employed to develop models on a dataset of 2521 ESCC patients with 27 features. The models were evaluated by concordance index (C-index) and time receiver operating characteristics (Time ROC) curves. We used the optimal model to evaluate the correlation between features and prognosis and divide patients into low- and high-risk groups by risk stratification. Its performance was analyzed by Kaplan-Meier curve and the comparison with AJCC8 stage. We further evaluate the comprehensive effectiveness of the model in ESCC subgroup by risk score and KDE (kernel density estimation) plotting.ResultsRSF’s C-index (0.746) and AUC (three-year AUC 0.761, five-year AUC 0.771) had slight advantage over GBM and the classical Cox method. Subsequently, 14 features such as N stage, T stage, surgical margin, tumor length, age, Dissected LN number, MCH, Na, FIB, DBIL, CL, treatment, vascular invasion, and tumor grade were selected to build the model. Based on these, we found significant difference for survival rate between low-(3-year OS 81.8%, 5-year OS 69.8%) and high-risk (3-year OS 25.1%, 5-year OS 11.5%) patients in training set, which was also verified in test set (all P < 0.0001). Compared with the AJCC8th stage system, it showed a greater discriminative ability which is also in good agreement with its staging ability.ConclusionWe developed an ESCC prognostic model with good performance by clinical features and laboratory blood parameters.https://www.frontiersin.org/articles/10.3389/fonc.2024.1367008/fullesophageal squamous cell carcinomamachine learningrandom survival forestprognosislaboratory blood parameters |
| spellingShingle | Feng Lu Linlan Yang Zhenglian Luo Qiao He Lijuan Shangguan Mingfei Cao Lichun Wu Laboratory blood parameters and machine learning for the prognosis of esophageal squamous cell carcinoma Frontiers in Oncology esophageal squamous cell carcinoma machine learning random survival forest prognosis laboratory blood parameters |
| title | Laboratory blood parameters and machine learning for the prognosis of esophageal squamous cell carcinoma |
| title_full | Laboratory blood parameters and machine learning for the prognosis of esophageal squamous cell carcinoma |
| title_fullStr | Laboratory blood parameters and machine learning for the prognosis of esophageal squamous cell carcinoma |
| title_full_unstemmed | Laboratory blood parameters and machine learning for the prognosis of esophageal squamous cell carcinoma |
| title_short | Laboratory blood parameters and machine learning for the prognosis of esophageal squamous cell carcinoma |
| title_sort | laboratory blood parameters and machine learning for the prognosis of esophageal squamous cell carcinoma |
| topic | esophageal squamous cell carcinoma machine learning random survival forest prognosis laboratory blood parameters |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2024.1367008/full |
| work_keys_str_mv | AT fenglu laboratorybloodparametersandmachinelearningfortheprognosisofesophagealsquamouscellcarcinoma AT linlanyang laboratorybloodparametersandmachinelearningfortheprognosisofesophagealsquamouscellcarcinoma AT zhenglianluo laboratorybloodparametersandmachinelearningfortheprognosisofesophagealsquamouscellcarcinoma AT qiaohe laboratorybloodparametersandmachinelearningfortheprognosisofesophagealsquamouscellcarcinoma AT lijuanshangguan laboratorybloodparametersandmachinelearningfortheprognosisofesophagealsquamouscellcarcinoma AT mingfeicao laboratorybloodparametersandmachinelearningfortheprognosisofesophagealsquamouscellcarcinoma AT lichunwu laboratorybloodparametersandmachinelearningfortheprognosisofesophagealsquamouscellcarcinoma |