R. Rask Kragh Jørgensen, Fanny Bergström, S. Eloranta, M. Tang Severinsen, K. Bjøro Smeland, Alexander Fosså, J. Haaber Christensen, Martin Hutchings, Rasmus Bo Dahl-Sørensen, P. Kamper, I. Glimelius, Karin E Smedby, Susan K Parsons, Angie Mae Rodday, Matthew J Maurer, Andrew M Evens, Tarec C El-Galaly, L. Hjort Jakobsen
{"title":"Machine Learning-Based Survival Prediction Models for Progression-Free and Overall Survival in Advanced-Stage Hodgkin Lymphoma.","authors":"R. Rask Kragh Jørgensen, Fanny Bergström, S. Eloranta, M. Tang Severinsen, K. Bjøro Smeland, Alexander Fosså, J. Haaber Christensen, Martin Hutchings, Rasmus Bo Dahl-Sørensen, P. Kamper, I. Glimelius, Karin E Smedby, Susan K Parsons, Angie Mae Rodday, Matthew J Maurer, Andrew M Evens, Tarec C El-Galaly, L. Hjort Jakobsen","doi":"10.1200/CCI.23.00255","DOIUrl":null,"url":null,"abstract":"PURPOSE\nPatients diagnosed with advanced-stage Hodgkin lymphoma (aHL) have historically been risk-stratified using the International Prognostic Score (IPS). This study investigated if a machine learning (ML) approach could outperform existing models when it comes to predicting overall survival (OS) and progression-free survival (PFS).\n\n\nPATIENTS AND METHODS\nThis study used patient data from the Danish National Lymphoma Register for model development (development cohort). The ML model was developed using stacking, which combines several predictive survival models (Cox proportional hazard, flexible parametric model, IPS, principal component, penalized regression) into a single model, and was compared with two versions of IPS (IPS-3 and IPS-7) and the newly developed aHL international prognostic index (A-HIPI). Internal model validation was performed using nested cross-validation, and external validation was performed using patient data from the Swedish Lymphoma Register and Cancer Registry of Norway (validation cohort).\n\n\nRESULTS\nIn total, 707 and 760 patients with aHL were included in the development and validation cohorts, respectively. Examining model performance for OS in the development cohort, the concordance index (C-index) for the ML model, IPS-7, IPS-3, and A-HIPI was found to be 0.789, 0.608, 0.650, and 0.768, respectively. The corresponding estimates in the validation cohort were 0.749, 0.700, 0.663, and 0.741. For PFS, the ML model achieved the highest C-index in both cohorts (0.665 in the development cohort and 0.691 in the validation cohort). The time-varying AUCs for both the ML model and the A-HIPI were consistently higher in both cohorts compared with the IPS models within the first 5 years after diagnosis.\n\n\nCONCLUSION\nThe new prognostic model for aHL on the basis of ML techniques demonstrated a substantial improvement compared with the IPS models, but yielded a limited improvement in predictive performance compared with the A-HIPI.","PeriodicalId":3,"journal":{"name":"ACS Applied Electronic Materials","volume":"39 5","pages":"e2300255"},"PeriodicalIF":4.3000,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS Applied Electronic Materials","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1200/CCI.23.00255","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0
Abstract
PURPOSE
Patients diagnosed with advanced-stage Hodgkin lymphoma (aHL) have historically been risk-stratified using the International Prognostic Score (IPS). This study investigated if a machine learning (ML) approach could outperform existing models when it comes to predicting overall survival (OS) and progression-free survival (PFS).
PATIENTS AND METHODS
This study used patient data from the Danish National Lymphoma Register for model development (development cohort). The ML model was developed using stacking, which combines several predictive survival models (Cox proportional hazard, flexible parametric model, IPS, principal component, penalized regression) into a single model, and was compared with two versions of IPS (IPS-3 and IPS-7) and the newly developed aHL international prognostic index (A-HIPI). Internal model validation was performed using nested cross-validation, and external validation was performed using patient data from the Swedish Lymphoma Register and Cancer Registry of Norway (validation cohort).
RESULTS
In total, 707 and 760 patients with aHL were included in the development and validation cohorts, respectively. Examining model performance for OS in the development cohort, the concordance index (C-index) for the ML model, IPS-7, IPS-3, and A-HIPI was found to be 0.789, 0.608, 0.650, and 0.768, respectively. The corresponding estimates in the validation cohort were 0.749, 0.700, 0.663, and 0.741. For PFS, the ML model achieved the highest C-index in both cohorts (0.665 in the development cohort and 0.691 in the validation cohort). The time-varying AUCs for both the ML model and the A-HIPI were consistently higher in both cohorts compared with the IPS models within the first 5 years after diagnosis.
CONCLUSION
The new prognostic model for aHL on the basis of ML techniques demonstrated a substantial improvement compared with the IPS models, but yielded a limited improvement in predictive performance compared with the A-HIPI.
期刊介绍:
ACS Applied Electronic Materials is an interdisciplinary journal publishing original research covering all aspects of electronic materials. The journal is devoted to reports of new and original experimental and theoretical research of an applied nature that integrate knowledge in the areas of materials science, engineering, optics, physics, and chemistry into important applications of electronic materials. Sample research topics that span the journal's scope are inorganic, organic, ionic and polymeric materials with properties that include conducting, semiconducting, superconducting, insulating, dielectric, magnetic, optoelectronic, piezoelectric, ferroelectric and thermoelectric.
Indexed/Abstracted:
Web of Science SCIE
Scopus
CAS
INSPEC
Portico