Using machine learning to predict patient-reported symptom clusters in prostate cancer patients receiving radiotherapy

Prostate cancer (PC) survivors frequently experience multiple co-occurring symptoms that adversely affect health-related quality of life (HRQoL). Identifying symptom clusters (SCs) may help to improve symptom management and patient care. The aim of this study is to investigate (1) SCs in PC patients, (2) associations of SCs with HRQoL, and (3) predictors of SCs. We used data from an international, multi-centre, prospective cohort study (REQUITE). SCs were identified from patient-reported outcomes collected with the EORTC Core Quality of Life questionnaire (EORTC QLQ-C30) and pelvic symptom questionnaires. Machine learning techniques identified SCs, associations with HRQoL and SCs predictors. The dataset was divided into training (80%) and validation (20%) cohorts. Data were analysed from 1538 (before radiotherapy (T0)), 1490 (end of radiotherapy (T1)), 1322 (12-months (T2)), and 1219 (24-months (T3)) patients. SCs identified at T0: SC1 (gastro-intestinal), SC2 (fatigue, urinary, emotional and cognitive functioning), and SC3 (pain, physical, role, and social functioning). SCs changed at T1: SC1 (gastro-intestinal symptoms), SC2 (fatigue, urinary problems, insomnia), SC3 (social and role functioning), and SC4 (pain, bowel problems, physical, emotional, and cognitive functioning). At T2, symptoms returned to baseline clusters. SCs including ‘fatigue’ or ‘urinary symptoms’ were most frequent across time-points. At T0, T2 and T3, HRQoL was best predicted by clusters 2 and 3 (35–45% explained variance). At T1, cluster 4 was the best predictor (52% explained variance). Planned radiotherapy target volume, prostate specific antigen (PSA) at pre-diagnostic biopsy, age and alcohol consumption were the best predictors of SC2 at T1 and SC3 and fatigue-dyspnoea at T3. Although SCs including fatigue and urinary symptoms were most common, the ‘pain, bowel problems, physical, emotional and cognitive functioning’ SC at T1 was associated most strongly with HRQoL. The predictors can help to identify men at risk for specific SCs.

Authors

Institutions

Publication Details

Journal
Health and Quality of Life Outcomes
Published
2025-11-29
DOI
https://doi.org/10.1186/s12955-025-02460-1
Primary Topic
Cancer survivorship and care
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Using machine learning to predict patient-reported symptom clusters in prostate cancer patients receiving radiotherapy

Lindsay Poppe, Jane Shortall, Peter Vermeulen, Alan McWilliam et al.
Health and Quality of Life Outcomes
Cancer survivorship and care
article

Using machine learning to predict patient-reported symptom clusters in prostate cancer patients receiving radiotherapy

Lindsay Poppe, Jane Shortall, Peter Vermeulen, Alan McWilliam, Chris J. Talbot, B. Avuzzi, Adam Webb, Filip Poelaert, Sofie Van Hoecke, Tim Rattay, Ana Vega, Liv Veldeman, Elke Rammant, D. Azria, Ann Van Hecke, B. Noris Chiorda, Ananya Choudhury, Gert De Meerleer, T. Rancati, Philipp Heumann, Kerstie Johnson, Karin Haustermans, Valérie Fonteyne, Ashley M. Hopkins, Piet R. Dirix, Emile Deman, Kato Rans, Antonio Gómez‐Caamaño, Nora Sundahl, Maarten Lambrecht, Miguel E. Aguado‐Barrera, Patricia Calvo, Petra Seibold, Catharine West, Elena Sperk, Bradley D. Menz, Renée Bultijnck, Barry S. Rosenstein, Jenny Chang-Claude, Dirk De Ruysscher
article en

Abstract

Prostate cancer (PC) survivors frequently experience multiple co-occurring symptoms that adversely affect health-related quality of life (HRQoL). Identifying symptom clusters (SCs) may help to improve symptom management and patient care. The aim of this study is to investigate (1) SCs in PC patients, (2) associations of SCs with HRQoL, and (3) predictors of SCs. We used data from an international, multi-centre, prospective cohort study (REQUITE). SCs were identified from patient-reported outcomes collected with the EORTC Core Quality of Life questionnaire (EORTC QLQ-C30) and pelvic symptom questionnaires. Machine learning techniques identified SCs, associations with HRQoL and SCs predictors. The dataset was divided into training (80%) and validation (20%) cohorts. Data were analysed from 1538 (before radiotherapy (T0)), 1490 (end of radiotherapy (T1)), 1322 (12-months (T2)), and 1219 (24-months (T3)) patients. SCs identified at T0: SC1 (gastro-intestinal), SC2 (fatigue, urinary, emotional and cognitive functioning), and SC3 (pain, physical, role, and social functioning). SCs changed at T1: SC1 (gastro-intestinal symptoms), SC2 (fatigue, urinary problems, insomnia), SC3 (social and role functioning), and SC4 (pain, bowel problems, physical, emotional, and cognitive functioning). At T2, symptoms returned to baseline clusters. SCs including ‘fatigue’ or ‘urinary symptoms’ were most frequent across time-points. At T0, T2 and T3, HRQoL was best predicted by clusters 2 and 3 (35–45% explained variance). At T1, cluster 4 was the best predictor (52% explained variance). Planned radiotherapy target volume, prostate specific antigen (PSA) at pre-diagnostic biopsy, age and alcohol consumption were the best predictors of SC2 at T1 and SC3 and fatigue-dyspnoea at T3. Although SCs including fatigue and urinary symptoms were most common, the ‘pain, bowel problems, physical, emotional and cognitive functioning’ SC at T1 was associated most strongly with HRQoL. The predictors can help to identify men at risk for specific SCs.

Health and Quality of Life OutcomesVol. 24(1)
HOGENT University of Applied Sciences and Arts (BE), Vrije Universiteit Brussel (BE), University of Antwerp (BE), University of Leicester (GB), Universität Hamburg (DE), Flinders University (AU), German Cancer Research Center (DE), Université de Montpellier (FR), Heidelberg University (DE), Maastricht University Medical Centre (NL), AZ Groeninge (BE), Ghent University Hospital (BE), University Hospital Heidelberg (DE), University of Manchester (GB), Ghent University (BE), Institut Agronomique Méditerranéen de Montpellier (FR), Complejo Hospitalario Universitario de Santiago (ES), University Medical Center Hamburg-Eppendorf (DE), Centre for Biomedical Network Research on Rare Diseases (ES), Province of Antwerp (BE), Fundación Pública Galega de Medicina Xenómica (ES), University Cancer Center Hamburg (DE), The Christie NHS Foundation Trust (GB), Iridium Kankernetwerk (BE), Institut de Recherche en Cancérologie de Montpellier (FR), Instituto de Investigación Sanitaria de Santiago (ES), University Medical Centre Mannheim (DE), Fondazione IRCCS Istituto Nazionale dei Tumori (IT), Maastro Clinic (NL), Icahn School of Medicine at Mount Sinai (US), KU Leuven (BE)
European Commission, Vedecká Grantová Agentúra MŠVVaŠ SR a SAV, Instituto de Salud Carlos III
Openalex Percentile: Top 48%
Cancer survivorship and care
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.