Unsupervised Clustering Successfully Predicts Prognosis in NSCLC Brain Metastasis Cohorts

<b>Background/Objectives</b>: Current developments in computer-aided systems rely heavily on complex and computationally intensive algorithms. However, even a simple approach can offer a promising solution to reduce the burden on clinicians. Addressing this, we aim to employ unsupervised...

Full description

Saved in:
Bibliographic Details
Main Authors: Emre Uysal, Gorkem Durak, Ayse Kotek Sedef, Ulas Bagci, Tanju Berber, Necla Gurdal, Berna Akkus Yildirim
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/14/1747
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849418153429303296
author Emre Uysal
Gorkem Durak
Ayse Kotek Sedef
Ulas Bagci
Tanju Berber
Necla Gurdal
Berna Akkus Yildirim
author_facet Emre Uysal
Gorkem Durak
Ayse Kotek Sedef
Ulas Bagci
Tanju Berber
Necla Gurdal
Berna Akkus Yildirim
author_sort Emre Uysal
collection DOAJ
description <b>Background/Objectives</b>: Current developments in computer-aided systems rely heavily on complex and computationally intensive algorithms. However, even a simple approach can offer a promising solution to reduce the burden on clinicians. Addressing this, we aim to employ unsupervised cluster analysis to identify prognostic subgroups of non-small-cell lung cancer (NSCLC) patients with brain metastasis (BM). Simple-yet-effective algorithms designed to identify similar group characteristics will assist clinicians in categorizing patients effectively. <b>Methods</b>: We retrospectively collected data from 95 NSCLC patients with BM treated at two oncology centers. To identify clinically distinct subgroups, two types of unsupervised clustering methods—two-step clustering (TSC) and hierarchical cluster analysis (HCA)—were applied to the baseline clinical data. Patients were categorized into prognostic classes according to the Diagnosis-Specific Graded Prognostic Assessment (DS-GPA). Survival curves for the clusters and DS-GPA classes were generated using Kaplan–Meier analysis, and the differences were assessed with the log-rank test. The discriminative ability of three categorical variables on survival was compared using the concordance index (C-index). <b>Results</b>: The mean age of the patients was 61.8 ± 0.9 years, and the majority (77.9%) were men. Extracranial metastasis was present in 71.6% of the patients, with most (63.2%) having a single BM. The DS-GPA classification significantly divided the patients into prognostic classes (<i>p</i> < 0.001). Furthermore, statistical significance was observed between clusters created by TSC (<i>p</i> < 0.001) and HCA (<i>p</i> < 0.001). HCA showed the highest discriminatory power (C-index = 0.721), followed by the DS-GPA (C-index = 0.709) and TSC (C-index = 0.650). <b>Conclusions</b>: Our findings demonstrated that the TSC and HCA models were comparable in prognostic performance to the DS-GPA index in NSCLC patients with BM. These results suggest that unsupervised clustering may offer a data-driven perspective on patient stratification, though further validation is needed to clarify its role in prognostic modeling.
format Article
id doaj-art-e78b67c3abfc489094ca201bbda09ef4
institution Kabale University
issn 2075-4418
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-e78b67c3abfc489094ca201bbda09ef42025-08-20T03:32:31ZengMDPI AGDiagnostics2075-44182025-07-011514174710.3390/diagnostics15141747Unsupervised Clustering Successfully Predicts Prognosis in NSCLC Brain Metastasis CohortsEmre Uysal0Gorkem Durak1Ayse Kotek Sedef2Ulas Bagci3Tanju Berber4Necla Gurdal5Berna Akkus Yildirim6Department of Radiation Oncology, University of Health Science, Prof. Dr. Cemil Tascioglu City Hospital, Istanbul 34390, TurkeyMachine & Hybrid Intelligence Lab, Department of Radiology, Northwestern University, Chicago, IL 60611, USADepartment of Radiation Oncology, Dr. Ersin Arslan Research and Training Hospital, Gaziantep 27000, TurkeyMachine & Hybrid Intelligence Lab, Department of Radiology, Northwestern University, Chicago, IL 60611, USADepartment of Radiation Oncology, University of Health Science, Prof. Dr. Cemil Tascioglu City Hospital, Istanbul 34390, TurkeyDepartment of Radiation Oncology, University of Health Science, Prof. Dr. Cemil Tascioglu City Hospital, Istanbul 34390, TurkeyDepartment of Radiation Oncology, University of Health Science, Prof. Dr. Cemil Tascioglu City Hospital, Istanbul 34390, Turkey<b>Background/Objectives</b>: Current developments in computer-aided systems rely heavily on complex and computationally intensive algorithms. However, even a simple approach can offer a promising solution to reduce the burden on clinicians. Addressing this, we aim to employ unsupervised cluster analysis to identify prognostic subgroups of non-small-cell lung cancer (NSCLC) patients with brain metastasis (BM). Simple-yet-effective algorithms designed to identify similar group characteristics will assist clinicians in categorizing patients effectively. <b>Methods</b>: We retrospectively collected data from 95 NSCLC patients with BM treated at two oncology centers. To identify clinically distinct subgroups, two types of unsupervised clustering methods—two-step clustering (TSC) and hierarchical cluster analysis (HCA)—were applied to the baseline clinical data. Patients were categorized into prognostic classes according to the Diagnosis-Specific Graded Prognostic Assessment (DS-GPA). Survival curves for the clusters and DS-GPA classes were generated using Kaplan–Meier analysis, and the differences were assessed with the log-rank test. The discriminative ability of three categorical variables on survival was compared using the concordance index (C-index). <b>Results</b>: The mean age of the patients was 61.8 ± 0.9 years, and the majority (77.9%) were men. Extracranial metastasis was present in 71.6% of the patients, with most (63.2%) having a single BM. The DS-GPA classification significantly divided the patients into prognostic classes (<i>p</i> < 0.001). Furthermore, statistical significance was observed between clusters created by TSC (<i>p</i> < 0.001) and HCA (<i>p</i> < 0.001). HCA showed the highest discriminatory power (C-index = 0.721), followed by the DS-GPA (C-index = 0.709) and TSC (C-index = 0.650). <b>Conclusions</b>: Our findings demonstrated that the TSC and HCA models were comparable in prognostic performance to the DS-GPA index in NSCLC patients with BM. These results suggest that unsupervised clustering may offer a data-driven perspective on patient stratification, though further validation is needed to clarify its role in prognostic modeling.https://www.mdpi.com/2075-4418/15/14/1747brain metastasesnon-small-cell lung cancerprognostic factorsunsupervised learningclustering
spellingShingle Emre Uysal
Gorkem Durak
Ayse Kotek Sedef
Ulas Bagci
Tanju Berber
Necla Gurdal
Berna Akkus Yildirim
Unsupervised Clustering Successfully Predicts Prognosis in NSCLC Brain Metastasis Cohorts
Diagnostics
brain metastases
non-small-cell lung cancer
prognostic factors
unsupervised learning
clustering
title Unsupervised Clustering Successfully Predicts Prognosis in NSCLC Brain Metastasis Cohorts
title_full Unsupervised Clustering Successfully Predicts Prognosis in NSCLC Brain Metastasis Cohorts
title_fullStr Unsupervised Clustering Successfully Predicts Prognosis in NSCLC Brain Metastasis Cohorts
title_full_unstemmed Unsupervised Clustering Successfully Predicts Prognosis in NSCLC Brain Metastasis Cohorts
title_short Unsupervised Clustering Successfully Predicts Prognosis in NSCLC Brain Metastasis Cohorts
title_sort unsupervised clustering successfully predicts prognosis in nsclc brain metastasis cohorts
topic brain metastases
non-small-cell lung cancer
prognostic factors
unsupervised learning
clustering
url https://www.mdpi.com/2075-4418/15/14/1747
work_keys_str_mv AT emreuysal unsupervisedclusteringsuccessfullypredictsprognosisinnsclcbrainmetastasiscohorts
AT gorkemdurak unsupervisedclusteringsuccessfullypredictsprognosisinnsclcbrainmetastasiscohorts
AT aysekoteksedef unsupervisedclusteringsuccessfullypredictsprognosisinnsclcbrainmetastasiscohorts
AT ulasbagci unsupervisedclusteringsuccessfullypredictsprognosisinnsclcbrainmetastasiscohorts
AT tanjuberber unsupervisedclusteringsuccessfullypredictsprognosisinnsclcbrainmetastasiscohorts
AT neclagurdal unsupervisedclusteringsuccessfullypredictsprognosisinnsclcbrainmetastasiscohorts
AT bernaakkusyildirim unsupervisedclusteringsuccessfullypredictsprognosisinnsclcbrainmetastasiscohorts