Extended endocrine therapy in breast cancer: A basket of length-constraint feature selection metaheuristics to balance Type I against Type II errors

Hua-Ping Liu; Jian V Zhang; Dongwen Wang; Andreas Albrecht; Kathleen Steinhöfel; Hung-Ming Lai

doi:10.1016/j.jbi.2022.104112

Extended endocrine therapy in breast cancer: A basket of length-constraint feature selection metaheuristics to balance Type I against Type II errors

Hua-Ping Liu, Jian V Zhang, Dongwen Wang, Andreas Albrecht, Kathleen Steinhöfel, Hung-Ming Lai

Research output: Contribution to journal › Article › peer-review

36 Downloads (Pure)

Abstract

Extended endocrine therapy beyond 5 years is of major concern to ER+ breast cancer survivors. However, it might be unsuitable to apply routinely used genomic tests designed for early recurrence risks to distant recurrence within 10 years in extended treatment context. These tests initially aim at high sensitivities with Type I errors much higher than Type II. Having lower positive predictive values (PPVs), these tests can bring many false positives who might not need further treatment options to avoid adversely affecting quality of life. Alternatively, we proposed a top-down approach to the raised issues. We built 149 targeted genes from four genomic tests upon 381 ER-positive node-negative patients with either metastasis free beyond 10 years (n=202) or metastasis within 10 years (n=179). By a basket of SVM-wrapped length-constraint feature selection (LCFS), we discovered four genomic SVMs that traded off Type I against Type II errors. Two independent cohorts were used to validate disease outcome predictions. A 36-gene SVM balanced sensitivities with PPVs at good levels: 74% vs 76% on 10-fold cross validation (n=347) and 75% vs 71% on a test set (n=34). Neither Oncotype DX RS (cutoff=18, 31, 60.97) nor PAM50 ROR-S (cutoff=29, 53, 61.18) could. Independent cohorts showed the 36-gene SVM predicted disease free survival (n=136, HR=2.59; 95% CI, 1.4-4.8) and disease specific survival (n=127, HR=4.06; 95% CI, 1.63-10.11) better than RS (DFS, HR=2.15; DSS, HR=3.86) and ROR-S (DFS, HR=2.29; DSS, HR=2.76). The case study demonstrated how we identified a genomic test to balance Type I against Type II errors for risk stratification. The top-down approach centered around the LCFS-metaheuristics basket is a generic methodology for clinical decision-making and quality of life using targeted profiling data where the number of dimensions (p) is smaller than the number of samples (n).

Original language	English
Article number	104112
Journal	JOURNAL OF BIOMEDICAL INFORMATICS
Volume	131
Early online date	6 Jun 2022
DOIs	https://doi.org/10.1016/j.jbi.2022.104112
Publication status	Published - Jul 2022

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.jbi.2022.104112Licence: CC BY-NC-ND

Extended endocrine therapy_LIU_Publishedonline6June2022_GOLD VoR (CC BY-NC-ND)Final published version, 3.56 MBLicence: CC BY-NC-ND

Cite this

@article{1bb0f103322745cc89bfbed38c39f258,

title = "Extended endocrine therapy in breast cancer: A basket of length-constraint feature selection metaheuristics to balance Type I against Type II errors",

abstract = "Extended endocrine therapy beyond 5 years is of major concern to ER+ breast cancer survivors. However, it might be unsuitable to apply routinely used genomic tests designed for early recurrence risks to distant recurrence within 10 years in extended treatment context. These tests initially aim at high sensitivities with Type I errors much higher than Type II. Having lower positive predictive values (PPVs), these tests can bring many false positives who might not need further treatment options to avoid adversely affecting quality of life. Alternatively, we proposed a top-down approach to the raised issues. We built 149 targeted genes from four genomic tests upon 381 ER-positive node-negative patients with either metastasis free beyond 10 years (n=202) or metastasis within 10 years (n=179). By a basket of SVM-wrapped length-constraint feature selection (LCFS), we discovered four genomic SVMs that traded off Type I against Type II errors. Two independent cohorts were used to validate disease outcome predictions. A 36-gene SVM balanced sensitivities with PPVs at good levels: 74% vs 76% on 10-fold cross validation (n=347) and 75% vs 71% on a test set (n=34). Neither Oncotype DX RS (cutoff=18, 31, 60.97) nor PAM50 ROR-S (cutoff=29, 53, 61.18) could. Independent cohorts showed the 36-gene SVM predicted disease free survival (n=136, HR=2.59; 95% CI, 1.4-4.8) and disease specific survival (n=127, HR=4.06; 95% CI, 1.63-10.11) better than RS (DFS, HR=2.15; DSS, HR=3.86) and ROR-S (DFS, HR=2.29; DSS, HR=2.76). The case study demonstrated how we identified a genomic test to balance Type I against Type II errors for risk stratification. The top-down approach centered around the LCFS-metaheuristics basket is a generic methodology for clinical decision-making and quality of life using targeted profiling data where the number of dimensions (p) is smaller than the number of samples (n).",

author = "Hua-Ping Liu and Zhang, {Jian V} and Dongwen Wang and Andreas Albrecht and Kathleen Steinh{\"o}fel and Hung-Ming Lai",

note = "Funding Information: Jian V. Zhang is supported by Shenzhen Basic Research Program (JCYJ20170413165233512) and Shenzhen Key Laboratory of Metabolic Health. Dongwen Wang is supported by Shenzhen High-level Hospital Construction Fund and Sanming Project of Medicine in Shenzhen (No. SZSM202111003). The authors thanked Mr. Yuan-Yi Chang for a preliminary to preparing a Kaplan-Meier plot. Publisher Copyright: {\textcopyright} 2022",

year = "2022",

month = jul,

doi = "10.1016/j.jbi.2022.104112",

language = "English",

volume = "131",

journal = "JOURNAL OF BIOMEDICAL INFORMATICS",

issn = "1532-0464",

publisher = "ACADEMIC PRESS INC",

}

TY - JOUR

T1 - Extended endocrine therapy in breast cancer: A basket of length-constraint feature selection metaheuristics to balance Type I against Type II errors

AU - Liu, Hua-Ping

AU - Zhang, Jian V

AU - Wang, Dongwen

AU - Albrecht, Andreas

AU - Steinhöfel, Kathleen

AU - Lai, Hung-Ming

N1 - Funding Information: Jian V. Zhang is supported by Shenzhen Basic Research Program (JCYJ20170413165233512) and Shenzhen Key Laboratory of Metabolic Health. Dongwen Wang is supported by Shenzhen High-level Hospital Construction Fund and Sanming Project of Medicine in Shenzhen (No. SZSM202111003). The authors thanked Mr. Yuan-Yi Chang for a preliminary to preparing a Kaplan-Meier plot. Publisher Copyright: © 2022

PY - 2022/7

Y1 - 2022/7

N2 - Extended endocrine therapy beyond 5 years is of major concern to ER+ breast cancer survivors. However, it might be unsuitable to apply routinely used genomic tests designed for early recurrence risks to distant recurrence within 10 years in extended treatment context. These tests initially aim at high sensitivities with Type I errors much higher than Type II. Having lower positive predictive values (PPVs), these tests can bring many false positives who might not need further treatment options to avoid adversely affecting quality of life. Alternatively, we proposed a top-down approach to the raised issues. We built 149 targeted genes from four genomic tests upon 381 ER-positive node-negative patients with either metastasis free beyond 10 years (n=202) or metastasis within 10 years (n=179). By a basket of SVM-wrapped length-constraint feature selection (LCFS), we discovered four genomic SVMs that traded off Type I against Type II errors. Two independent cohorts were used to validate disease outcome predictions. A 36-gene SVM balanced sensitivities with PPVs at good levels: 74% vs 76% on 10-fold cross validation (n=347) and 75% vs 71% on a test set (n=34). Neither Oncotype DX RS (cutoff=18, 31, 60.97) nor PAM50 ROR-S (cutoff=29, 53, 61.18) could. Independent cohorts showed the 36-gene SVM predicted disease free survival (n=136, HR=2.59; 95% CI, 1.4-4.8) and disease specific survival (n=127, HR=4.06; 95% CI, 1.63-10.11) better than RS (DFS, HR=2.15; DSS, HR=3.86) and ROR-S (DFS, HR=2.29; DSS, HR=2.76). The case study demonstrated how we identified a genomic test to balance Type I against Type II errors for risk stratification. The top-down approach centered around the LCFS-metaheuristics basket is a generic methodology for clinical decision-making and quality of life using targeted profiling data where the number of dimensions (p) is smaller than the number of samples (n).

AB - Extended endocrine therapy beyond 5 years is of major concern to ER+ breast cancer survivors. However, it might be unsuitable to apply routinely used genomic tests designed for early recurrence risks to distant recurrence within 10 years in extended treatment context. These tests initially aim at high sensitivities with Type I errors much higher than Type II. Having lower positive predictive values (PPVs), these tests can bring many false positives who might not need further treatment options to avoid adversely affecting quality of life. Alternatively, we proposed a top-down approach to the raised issues. We built 149 targeted genes from four genomic tests upon 381 ER-positive node-negative patients with either metastasis free beyond 10 years (n=202) or metastasis within 10 years (n=179). By a basket of SVM-wrapped length-constraint feature selection (LCFS), we discovered four genomic SVMs that traded off Type I against Type II errors. Two independent cohorts were used to validate disease outcome predictions. A 36-gene SVM balanced sensitivities with PPVs at good levels: 74% vs 76% on 10-fold cross validation (n=347) and 75% vs 71% on a test set (n=34). Neither Oncotype DX RS (cutoff=18, 31, 60.97) nor PAM50 ROR-S (cutoff=29, 53, 61.18) could. Independent cohorts showed the 36-gene SVM predicted disease free survival (n=136, HR=2.59; 95% CI, 1.4-4.8) and disease specific survival (n=127, HR=4.06; 95% CI, 1.63-10.11) better than RS (DFS, HR=2.15; DSS, HR=3.86) and ROR-S (DFS, HR=2.29; DSS, HR=2.76). The case study demonstrated how we identified a genomic test to balance Type I against Type II errors for risk stratification. The top-down approach centered around the LCFS-metaheuristics basket is a generic methodology for clinical decision-making and quality of life using targeted profiling data where the number of dimensions (p) is smaller than the number of samples (n).

UR - http://www.scopus.com/inward/record.url?scp=85133103319&partnerID=8YFLogxK

U2 - 10.1016/j.jbi.2022.104112

DO - 10.1016/j.jbi.2022.104112

M3 - Article

C2 - 35680073

SN - 1532-0464

VL - 131

JO - JOURNAL OF BIOMEDICAL INFORMATICS

JF - JOURNAL OF BIOMEDICAL INFORMATICS

M1 - 104112

ER -

Extended endocrine therapy in breast cancer: A basket of length-constraint feature selection metaheuristics to balance Type I against Type II errors

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this