Clustering on longitudinal quality‐of‐life measurements using growth mixture models for clinical prognosis: Implementation on CCTG/AGITG CO.20 trial
Abstract Introduction Analyzing longitudinal cancer quality‐of‐life (QoL) measurements and their impact on clinical outcomes may improve our understanding of patient trajectories during systemic therapy. We applied an unsupervised growth mixture modeling (GMM) approach to identify unobserved subpopu...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-03-01
|
| Series: | Cancer Medicine |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/cam4.5341 |
| _version_ | 1797866876413411328 |
|---|---|
| author | Jiahui Zhang Weili Kong Pingzhao Hu Derek Jonker Malcolm Moore Jolie Ringash Jeremy Shapiro John Zalcberg John Simes Dongsheng Tu Chris J. O'Callaghan Geoffrey Liu Wei Xu |
| author_facet | Jiahui Zhang Weili Kong Pingzhao Hu Derek Jonker Malcolm Moore Jolie Ringash Jeremy Shapiro John Zalcberg John Simes Dongsheng Tu Chris J. O'Callaghan Geoffrey Liu Wei Xu |
| author_sort | Jiahui Zhang |
| collection | DOAJ |
| description | Abstract Introduction Analyzing longitudinal cancer quality‐of‐life (QoL) measurements and their impact on clinical outcomes may improve our understanding of patient trajectories during systemic therapy. We applied an unsupervised growth mixture modeling (GMM) approach to identify unobserved subpopulations (“patient clusters”) in the CO.20 clinical trial longitudinal QoL data. Classes were then evaluated for differences in clinico‐epidemiologic characteristics and overall survival (OS). Methods and Materials In CO.20, 750 chemotherapy‐refractory metastatic colorectal cancer (CRC) patients were randomized to receive Brivanib+Cetuximab (n = 376, experimental arm) versus Cetuximab+Placebo (n = 374, standard arm) for 16 weeks. EORTC‐QLQ‐C30 QoL summary scores were calculated for each patient at seven time points, and GMM was applied to identify patient clusters (termed “classes”). Log‐rank/Kaplan–Meier and multivariable Cox regression analyses were conducted to analyze the survival performance between classes. Cox analyses were used to explore the relationship between baseline QoL, individual slope, and the quadratic terms from the GMM output with OS. Results In univariable analysis, the linear mixed effect model (LMM) identified sex and ECOG Performance Status as strongly associated with the longitudinal QoL score (p < 0.01). The patients within each treatment arm were clustered into three distinct QoL‐based classes by GMM, respectively. The three classes identified in the experimental (log‐rank p‐value = 0.00058) and in the control arms (p < 0.0001) each showed significantly different survival performance. The GMM's baseline, slope, and quadratic terms were each significantly associated with OS (p < 0.001). Conclusion GMM can be used to analyze longitudinal QoL data in cancer studies, by identifying unobserved subpopulations (patient clusters). As demonstrated by CO.20 data, these classes can have important implications, including clinical prognostication. |
| first_indexed | 2024-04-09T23:31:20Z |
| format | Article |
| id | doaj.art-e98604b9e01d429ab3224b63de1b5b33 |
| institution | Directory Open Access Journal |
| issn | 2045-7634 |
| language | English |
| last_indexed | 2024-04-09T23:31:20Z |
| publishDate | 2023-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | Cancer Medicine |
| spelling | doaj.art-e98604b9e01d429ab3224b63de1b5b332023-03-21T05:20:41ZengWileyCancer Medicine2045-76342023-03-011256117612810.1002/cam4.5341Clustering on longitudinal quality‐of‐life measurements using growth mixture models for clinical prognosis: Implementation on CCTG/AGITG CO.20 trialJiahui Zhang0Weili Kong1Pingzhao Hu2Derek Jonker3Malcolm Moore4Jolie Ringash5Jeremy Shapiro6John Zalcberg7John Simes8Dongsheng Tu9Chris J. O'Callaghan10Geoffrey Liu11Wei Xu12Dalla Lana School of Public Health University of Toronto Toronto Ontario CanadaDepartment of Otolaryngology, Head and Neck Surgery, West China Hospital Sichuan University Chengdu Sichuan People's Republic of ChinaDalla Lana School of Public Health University of Toronto Toronto Ontario CanadaOttawa Hospital Research Institute University of Ottawa Ottawa Ontario CanadaDepartment of Medicine and Pharmacology University of Toronto Toronto Ontario CanadaDepartment of Radiation Oncology The Princess Margaret Cancer Centre Toronto Ontario CanadaCabrini Hospital and Monash University Melbourne Victoria AustraliaPeter MacCallum Cancer Centre and University of MelbourneNHMRC Clinical Trials Centre University of Sydney Sydney New South Wales AustraliaCanadian Cancer Trials Group Queen's University Kingston Ontario CanadaCanadian Cancer Trials Group Queen's University Kingston Ontario CanadaDalla Lana School of Public Health University of Toronto Toronto Ontario CanadaDalla Lana School of Public Health University of Toronto Toronto Ontario CanadaAbstract Introduction Analyzing longitudinal cancer quality‐of‐life (QoL) measurements and their impact on clinical outcomes may improve our understanding of patient trajectories during systemic therapy. We applied an unsupervised growth mixture modeling (GMM) approach to identify unobserved subpopulations (“patient clusters”) in the CO.20 clinical trial longitudinal QoL data. Classes were then evaluated for differences in clinico‐epidemiologic characteristics and overall survival (OS). Methods and Materials In CO.20, 750 chemotherapy‐refractory metastatic colorectal cancer (CRC) patients were randomized to receive Brivanib+Cetuximab (n = 376, experimental arm) versus Cetuximab+Placebo (n = 374, standard arm) for 16 weeks. EORTC‐QLQ‐C30 QoL summary scores were calculated for each patient at seven time points, and GMM was applied to identify patient clusters (termed “classes”). Log‐rank/Kaplan–Meier and multivariable Cox regression analyses were conducted to analyze the survival performance between classes. Cox analyses were used to explore the relationship between baseline QoL, individual slope, and the quadratic terms from the GMM output with OS. Results In univariable analysis, the linear mixed effect model (LMM) identified sex and ECOG Performance Status as strongly associated with the longitudinal QoL score (p < 0.01). The patients within each treatment arm were clustered into three distinct QoL‐based classes by GMM, respectively. The three classes identified in the experimental (log‐rank p‐value = 0.00058) and in the control arms (p < 0.0001) each showed significantly different survival performance. The GMM's baseline, slope, and quadratic terms were each significantly associated with OS (p < 0.001). Conclusion GMM can be used to analyze longitudinal QoL data in cancer studies, by identifying unobserved subpopulations (patient clusters). As demonstrated by CO.20 data, these classes can have important implications, including clinical prognostication.https://doi.org/10.1002/cam4.5341cancer treatmentclusteringgrowth mixture modelquality of lifesurvival analysis |
| spellingShingle | Jiahui Zhang Weili Kong Pingzhao Hu Derek Jonker Malcolm Moore Jolie Ringash Jeremy Shapiro John Zalcberg John Simes Dongsheng Tu Chris J. O'Callaghan Geoffrey Liu Wei Xu Clustering on longitudinal quality‐of‐life measurements using growth mixture models for clinical prognosis: Implementation on CCTG/AGITG CO.20 trial Cancer Medicine cancer treatment clustering growth mixture model quality of life survival analysis |
| title | Clustering on longitudinal quality‐of‐life measurements using growth mixture models for clinical prognosis: Implementation on CCTG/AGITG CO.20 trial |
| title_full | Clustering on longitudinal quality‐of‐life measurements using growth mixture models for clinical prognosis: Implementation on CCTG/AGITG CO.20 trial |
| title_fullStr | Clustering on longitudinal quality‐of‐life measurements using growth mixture models for clinical prognosis: Implementation on CCTG/AGITG CO.20 trial |
| title_full_unstemmed | Clustering on longitudinal quality‐of‐life measurements using growth mixture models for clinical prognosis: Implementation on CCTG/AGITG CO.20 trial |
| title_short | Clustering on longitudinal quality‐of‐life measurements using growth mixture models for clinical prognosis: Implementation on CCTG/AGITG CO.20 trial |
| title_sort | clustering on longitudinal quality of life measurements using growth mixture models for clinical prognosis implementation on cctg agitg co 20 trial |
| topic | cancer treatment clustering growth mixture model quality of life survival analysis |
| url | https://doi.org/10.1002/cam4.5341 |
| work_keys_str_mv | AT jiahuizhang clusteringonlongitudinalqualityoflifemeasurementsusinggrowthmixturemodelsforclinicalprognosisimplementationoncctgagitgco20trial AT weilikong clusteringonlongitudinalqualityoflifemeasurementsusinggrowthmixturemodelsforclinicalprognosisimplementationoncctgagitgco20trial AT pingzhaohu clusteringonlongitudinalqualityoflifemeasurementsusinggrowthmixturemodelsforclinicalprognosisimplementationoncctgagitgco20trial AT derekjonker clusteringonlongitudinalqualityoflifemeasurementsusinggrowthmixturemodelsforclinicalprognosisimplementationoncctgagitgco20trial AT malcolmmoore clusteringonlongitudinalqualityoflifemeasurementsusinggrowthmixturemodelsforclinicalprognosisimplementationoncctgagitgco20trial AT jolieringash clusteringonlongitudinalqualityoflifemeasurementsusinggrowthmixturemodelsforclinicalprognosisimplementationoncctgagitgco20trial AT jeremyshapiro clusteringonlongitudinalqualityoflifemeasurementsusinggrowthmixturemodelsforclinicalprognosisimplementationoncctgagitgco20trial AT johnzalcberg clusteringonlongitudinalqualityoflifemeasurementsusinggrowthmixturemodelsforclinicalprognosisimplementationoncctgagitgco20trial AT johnsimes clusteringonlongitudinalqualityoflifemeasurementsusinggrowthmixturemodelsforclinicalprognosisimplementationoncctgagitgco20trial AT dongshengtu clusteringonlongitudinalqualityoflifemeasurementsusinggrowthmixturemodelsforclinicalprognosisimplementationoncctgagitgco20trial AT chrisjocallaghan clusteringonlongitudinalqualityoflifemeasurementsusinggrowthmixturemodelsforclinicalprognosisimplementationoncctgagitgco20trial AT geoffreyliu clusteringonlongitudinalqualityoflifemeasurementsusinggrowthmixturemodelsforclinicalprognosisimplementationoncctgagitgco20trial AT weixu clusteringonlongitudinalqualityoflifemeasurementsusinggrowthmixturemodelsforclinicalprognosisimplementationoncctgagitgco20trial |