Predicting survival in metastatic non‐small cell lung cancer patients with poor ECOG‐PS: A single‐arm prospective study
Abstract Background Patients with advanced non‐small cell lung cancer (NSCLC) are a heterogeneous population with short lifespan. We aimed to develop methods to better differentiate patients whose survival was >90 days. Methods We evaluated 83 characteristics of 106 treatment‐naïve, stage IV NSCL...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-02-01
|
| Series: | Cancer Medicine |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/cam4.5254 |
| _version_ | 1797893166044545024 |
|---|---|
| author | Mateus Trinconi Cunha Ana Paula deSouza Borges Vinicius Carvalho Jardim André Fujita Gilberto deCastro Jr |
| author_facet | Mateus Trinconi Cunha Ana Paula deSouza Borges Vinicius Carvalho Jardim André Fujita Gilberto deCastro Jr |
| author_sort | Mateus Trinconi Cunha |
| collection | DOAJ |
| description | Abstract Background Patients with advanced non‐small cell lung cancer (NSCLC) are a heterogeneous population with short lifespan. We aimed to develop methods to better differentiate patients whose survival was >90 days. Methods We evaluated 83 characteristics of 106 treatment‐naïve, stage IV NSCLC patients with Eastern Cooperative Oncology Group Performance Status (ECOG‐PS) >1. Automated machine learning was used to select a model and optimize hyperparameters. 100‐fold bootstrapping was performed for dimensionality reduction for a second (“lite”) model. Performance was measured by C‐statistic and accuracy metrics in an out‐of‐sample validation cohort. The “lite” model was validated on a second independent, prospective cohort (N = 42). Network analysis (NA) was performed to evaluate the differences in centrality and connectivity of features. Results The selected method was ExtraTrees Classifier, with C‐statistic of 0.82 (p < 0.01) and accuracy of 0.81 (p = 0.01). The “lite” model had 16 variables and obtained C‐statistic of 0.84 (p < 0.01) and accuracy of 0.75 (p = 0.039) in the first cohort, and C‐statistic of 0.706 (p < 0.01) and accuracy of 0.714 (p < 0.01) in the second cohort. The networks of patients with lower survival were more interconnected. Features related to cachexia, inflammation, and quality of life had statistically different prestige scores in NA. Conclusions Machine learning can assist in the prognostic evaluation of advanced NSCLC. The model generated with a reduced number of features showed high accessibility and reasonable metrics. Features related to quality of life, cachexia, and performance status had increased correlation and importance scores, suggesting that they play a role at later disease stages, in line with the biological rationale already described. |
| first_indexed | 2024-04-10T06:49:44Z |
| format | Article |
| id | doaj.art-a50ac89d77c04dc8a9a4ba96718e3931 |
| institution | Directory Open Access Journal |
| issn | 2045-7634 |
| language | English |
| last_indexed | 2024-04-10T06:49:44Z |
| publishDate | 2023-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | Cancer Medicine |
| spelling | doaj.art-a50ac89d77c04dc8a9a4ba96718e39312023-02-28T08:51:58ZengWileyCancer Medicine2045-76342023-02-011245099510910.1002/cam4.5254Predicting survival in metastatic non‐small cell lung cancer patients with poor ECOG‐PS: A single‐arm prospective studyMateus Trinconi Cunha0Ana Paula deSouza Borges1Vinicius Carvalho Jardim2André Fujita3Gilberto deCastro Jr4Serviço de Oncologia Clínica, Instituto do Câncer do Estado de São Paulo, Hospital das Clínicas HCFMUSP, Faculdade de Medicina Universidade de São Paulo São Paulo BrazilFaculdade de Medicina FMUSP Universidade de São Paulo São Paulo BrazilDepartamento de Ciência da Computação, Instituto de Matemática e Estatística Universidade de São Paulo São Paulo BrazilDepartamento de Ciência da Computação, Instituto de Matemática e Estatística Universidade de São Paulo São Paulo BrazilServiço de Oncologia Clínica, Instituto do Câncer do Estado de São Paulo, Hospital das Clínicas HCFMUSP, Faculdade de Medicina Universidade de São Paulo São Paulo BrazilAbstract Background Patients with advanced non‐small cell lung cancer (NSCLC) are a heterogeneous population with short lifespan. We aimed to develop methods to better differentiate patients whose survival was >90 days. Methods We evaluated 83 characteristics of 106 treatment‐naïve, stage IV NSCLC patients with Eastern Cooperative Oncology Group Performance Status (ECOG‐PS) >1. Automated machine learning was used to select a model and optimize hyperparameters. 100‐fold bootstrapping was performed for dimensionality reduction for a second (“lite”) model. Performance was measured by C‐statistic and accuracy metrics in an out‐of‐sample validation cohort. The “lite” model was validated on a second independent, prospective cohort (N = 42). Network analysis (NA) was performed to evaluate the differences in centrality and connectivity of features. Results The selected method was ExtraTrees Classifier, with C‐statistic of 0.82 (p < 0.01) and accuracy of 0.81 (p = 0.01). The “lite” model had 16 variables and obtained C‐statistic of 0.84 (p < 0.01) and accuracy of 0.75 (p = 0.039) in the first cohort, and C‐statistic of 0.706 (p < 0.01) and accuracy of 0.714 (p < 0.01) in the second cohort. The networks of patients with lower survival were more interconnected. Features related to cachexia, inflammation, and quality of life had statistically different prestige scores in NA. Conclusions Machine learning can assist in the prognostic evaluation of advanced NSCLC. The model generated with a reduced number of features showed high accessibility and reasonable metrics. Features related to quality of life, cachexia, and performance status had increased correlation and importance scores, suggesting that they play a role at later disease stages, in line with the biological rationale already described.https://doi.org/10.1002/cam4.5254machine learningnetwork analysisnon‐small cell lung cancerpoor performance statusprognostic markers |
| spellingShingle | Mateus Trinconi Cunha Ana Paula deSouza Borges Vinicius Carvalho Jardim André Fujita Gilberto deCastro Jr Predicting survival in metastatic non‐small cell lung cancer patients with poor ECOG‐PS: A single‐arm prospective study Cancer Medicine machine learning network analysis non‐small cell lung cancer poor performance status prognostic markers |
| title | Predicting survival in metastatic non‐small cell lung cancer patients with poor ECOG‐PS: A single‐arm prospective study |
| title_full | Predicting survival in metastatic non‐small cell lung cancer patients with poor ECOG‐PS: A single‐arm prospective study |
| title_fullStr | Predicting survival in metastatic non‐small cell lung cancer patients with poor ECOG‐PS: A single‐arm prospective study |
| title_full_unstemmed | Predicting survival in metastatic non‐small cell lung cancer patients with poor ECOG‐PS: A single‐arm prospective study |
| title_short | Predicting survival in metastatic non‐small cell lung cancer patients with poor ECOG‐PS: A single‐arm prospective study |
| title_sort | predicting survival in metastatic non small cell lung cancer patients with poor ecog ps a single arm prospective study |
| topic | machine learning network analysis non‐small cell lung cancer poor performance status prognostic markers |
| url | https://doi.org/10.1002/cam4.5254 |
| work_keys_str_mv | AT mateustrinconicunha predictingsurvivalinmetastaticnonsmallcelllungcancerpatientswithpoorecogpsasinglearmprospectivestudy AT anapauladesouzaborges predictingsurvivalinmetastaticnonsmallcelllungcancerpatientswithpoorecogpsasinglearmprospectivestudy AT viniciuscarvalhojardim predictingsurvivalinmetastaticnonsmallcelllungcancerpatientswithpoorecogpsasinglearmprospectivestudy AT andrefujita predictingsurvivalinmetastaticnonsmallcelllungcancerpatientswithpoorecogpsasinglearmprospectivestudy AT gilbertodecastrojr predictingsurvivalinmetastaticnonsmallcelllungcancerpatientswithpoorecogpsasinglearmprospectivestudy |