Modeling strategies to analyse longitudinal biomarker data: An illustration on predicting immunotherapy non-response in non-small cell lung cancer

Frederik A. van Delft; Milou Schuurbiers; Mirte Muller; Sjaak A. Burgers; Huub H. van Rossum; Maarten J. IJzerman; Hendrik Koffijberg; Michel M. van den Heuvel

doi:10.1016/j.heliyon.2022.e10932

Modeling strategies to analyse longitudinal biomarker data: An illustration on predicting immunotherapy non-response in non-small cell lung cancer

Frederik A. van Delft, Milou Schuurbiers, Mirte Muller, Sjaak A. Burgers, Huub H. van Rossum, Maarten J. IJzerman, Hendrik Koffijberg^*, Michel M. van den Heuvel

^*Corresponding author for this work

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

5 Citations (Scopus)

79 Downloads (Pure)

Abstract

Serum tumor markers acquired through a blood draw are known to reflect tumor activity. Their non-invasive nature allows for more frequent testing compared to traditional imaging methods used for response evaluations. Our study aims to compare nine prediction methods to accurately, and with a low false positive rate, predict progressive disease despite treatment (i.e. non-response) using longitudinal tumor biomarker data. Bi-weekly measurements of CYFRA, CA-125, CEA, NSE, and SCC were available from a cohort of 412 advanced stage non-small cell lung cancer (NSCLC) patients treated up to two years with immune checkpoint inhibitors. Serum tumor marker measurements from the first six weeks after treatment initiation were used to predict treatment response at 6 months. Nine models with varying complexity were evaluated in this study, showing how longitudinal biomarker data can be used to predict non-response to immunotherapy in NSCLC patients.

Original language	English
Article number	e10932
Journal	Heliyon
Volume	8
Issue number	10
DOIs	https://doi.org/10.1016/j.heliyon.2022.e10932
Publication status	Published - Oct 2022

Keywords

CA-125
CEA
CYFRA
Immunotherapy
NSCLC
NSE
Response
SCC
Serum tumor markers
UT-Hybrid-D

UN SDGs

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

Access to Document

10.1016/j.heliyon.2022.e10932Licence: CC BY-NC-ND

Van-delft-2022-Modeling-strategies-to-analyse-longFinal published version, 1.77 MBLicence: CC BY-NC-ND

Cite this

van Delft, F. A., Schuurbiers, M., Muller, M., Burgers, S. A., van Rossum, H. H., IJzerman, M. J., Koffijberg, H., & van den Heuvel, M. M. (2022). Modeling strategies to analyse longitudinal biomarker data: An illustration on predicting immunotherapy non-response in non-small cell lung cancer. Heliyon, 8(10), Article e10932. https://doi.org/10.1016/j.heliyon.2022.e10932

@article{4da57fbb11d14cf8936185191c853a40,

title = "Modeling strategies to analyse longitudinal biomarker data: An illustration on predicting immunotherapy non-response in non-small cell lung cancer",

abstract = "Serum tumor markers acquired through a blood draw are known to reflect tumor activity. Their non-invasive nature allows for more frequent testing compared to traditional imaging methods used for response evaluations. Our study aims to compare nine prediction methods to accurately, and with a low false positive rate, predict progressive disease despite treatment (i.e. non-response) using longitudinal tumor biomarker data. Bi-weekly measurements of CYFRA, CA-125, CEA, NSE, and SCC were available from a cohort of 412 advanced stage non-small cell lung cancer (NSCLC) patients treated up to two years with immune checkpoint inhibitors. Serum tumor marker measurements from the first six weeks after treatment initiation were used to predict treatment response at 6 months. Nine models with varying complexity were evaluated in this study, showing how longitudinal biomarker data can be used to predict non-response to immunotherapy in NSCLC patients.",

keywords = "CA-125, CEA, CYFRA, Immunotherapy, NSCLC, NSE, Response, SCC, Serum tumor markers, UT-Hybrid-D",

author = "{van Delft}, {Frederik A.} and Milou Schuurbiers and Mirte Muller and Burgers, {Sjaak A.} and {van Rossum}, {Huub H.} and IJzerman, {Maarten J.} and Hendrik Koffijberg and {van den Heuvel}, {Michel M.}",

note = "Funding Information: None to declare. Publisher Copyright: {\textcopyright} 2022 The Author(s)",

year = "2022",

month = oct,

doi = "10.1016/j.heliyon.2022.e10932",

language = "English",

volume = "8",

journal = "Heliyon",

issn = "2405-8440",

publisher = "Elsevier",

number = "10",

}

TY - JOUR

T1 - Modeling strategies to analyse longitudinal biomarker data

T2 - An illustration on predicting immunotherapy non-response in non-small cell lung cancer

AU - van Delft, Frederik A.

AU - Schuurbiers, Milou

AU - Muller, Mirte

AU - Burgers, Sjaak A.

AU - van Rossum, Huub H.

AU - IJzerman, Maarten J.

AU - Koffijberg, Hendrik

AU - van den Heuvel, Michel M.

PY - 2022/10

Y1 - 2022/10

N2 - Serum tumor markers acquired through a blood draw are known to reflect tumor activity. Their non-invasive nature allows for more frequent testing compared to traditional imaging methods used for response evaluations. Our study aims to compare nine prediction methods to accurately, and with a low false positive rate, predict progressive disease despite treatment (i.e. non-response) using longitudinal tumor biomarker data. Bi-weekly measurements of CYFRA, CA-125, CEA, NSE, and SCC were available from a cohort of 412 advanced stage non-small cell lung cancer (NSCLC) patients treated up to two years with immune checkpoint inhibitors. Serum tumor marker measurements from the first six weeks after treatment initiation were used to predict treatment response at 6 months. Nine models with varying complexity were evaluated in this study, showing how longitudinal biomarker data can be used to predict non-response to immunotherapy in NSCLC patients.

AB - Serum tumor markers acquired through a blood draw are known to reflect tumor activity. Their non-invasive nature allows for more frequent testing compared to traditional imaging methods used for response evaluations. Our study aims to compare nine prediction methods to accurately, and with a low false positive rate, predict progressive disease despite treatment (i.e. non-response) using longitudinal tumor biomarker data. Bi-weekly measurements of CYFRA, CA-125, CEA, NSE, and SCC were available from a cohort of 412 advanced stage non-small cell lung cancer (NSCLC) patients treated up to two years with immune checkpoint inhibitors. Serum tumor marker measurements from the first six weeks after treatment initiation were used to predict treatment response at 6 months. Nine models with varying complexity were evaluated in this study, showing how longitudinal biomarker data can be used to predict non-response to immunotherapy in NSCLC patients.

KW - CA-125

KW - CEA

KW - CYFRA

KW - Immunotherapy

KW - NSCLC

KW - NSE

KW - Response

KW - SCC

KW - Serum tumor markers

KW - UT-Hybrid-D

UR - http://www.scopus.com/inward/record.url?scp=85139734744&partnerID=8YFLogxK

U2 - 10.1016/j.heliyon.2022.e10932

DO - 10.1016/j.heliyon.2022.e10932

M3 - Article

AN - SCOPUS:85139734744

SN - 2405-8440

VL - 8

JO - Heliyon

JF - Heliyon

IS - 10

M1 - e10932

ER -

Modeling strategies to analyse longitudinal biomarker data: An illustration on predicting immunotherapy non-response in non-small cell lung cancer

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this