CoChat
Sign Up
Cited by 3,338AI in cancer detectionGene expression and cancer classificationArtificial Intelligence in Healthcare

Machine Learning Applications in Cancer Prognosis and Prediction

Open access
Kourou, Konstantina, Exarchos, Themis P., Exarchos, Konstantinos P., Karamouzis, Michalis V., Fotiadis, Dimitrios I.·2015·Computational and Structural Biotechnology Journal
DOI 10.1016/j.csbj.2014.11.005PMC PMC4348437
Open this paper in CoChat — free account

Abstract

Cancer has been characterized as a heterogeneous disease consisting of many different subtypes. The early diagnosis and prognosis of a cancer type have become a necessity in cancer research, as it can facilitate the subsequent clinical management of patients. The importance of classifying cancer patients into high or low risk groups has led many research teams, from the biomedical and the bioinformatics field, to study the application of machine learning (ML) methods. Therefore, these techniques have been utilized as an aim to model the progression and treatment of cancerous conditions. In addition, the ability of ML tools to detect key features from complex datasets reveals their importance. A variety of these techniques, including Artificial Neural Networks (ANNs), Bayesian Networks (BNs), Support Vector Machines (SVMs) and Decision Trees (DTs) have been widely applied in cancer research for the development of predictive models, resulting in effective and accurate decision making. Even though it is evident that the use of ML methods can improve our understanding of cancer progression, an appropriate level of validation is needed in order for these methods to be considered in the everyday clinical practice. In this work, we present a review of recent ML approaches employed in the modeling of cancer progression. The predictive models discussed here are based on various supervised ML techniques as well as on different input features and data samples. Given the growing trend on the application of ML methods in cancer research, we present here the most recent publications that employ these techniques as an aim to model cancer risk or patient outcomes.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.csbj.2014.11.005

Cites

72 of 72 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Traditional machine learning models have supported tumor classification, survival prediction, and risk stratification using structured clinical or genomic data.

    “traditional ML models, such as support vector machines (SVM), decision trees, and random forests, have supported tumor classification, survival prediction, and risk stratification using structured clinical or genomic data [6,12,13,14].”

    From Artificial Intelligence in Clinical Oncology: From Productivity Enhancement to Creative Discovery (2025) · cites this paper as [13]

  • Modern machine learning models, including deep neural networks, are black boxes that focus on predicting outputs from inputs without regard for the mechanism or rationale by which an outcome is brought about, a challenge particularly acute in biomedicine.

    “A second well-known challenge is that modern machine learning models, including deep neural networks, are black boxes, devices which focus on predicting outputs from inputs without regard for the mechanism or rationale by which a particular outcome is brought about.”

    From Visible Machine Learning for Biomedicine (2018) · cites this paper as Kourou et al., 2014

  • In biomedicine, many machine-learning methods are being developed to predict patient outcomes but typically do not link predictions to underlying mechanisms.

    “Similarly, in biomedicine, many machine-learning methods are being developed to predict patient outcomes (Kourou et al., 2014), but these approaches typically do not link predictions to underlying mechanisms (Figure 1B).”

    From Visible Machine Learning for Biomedicine (2018) · cites this paper as Kourou et al., 2014

  • Machine-learning systems face input heterogeneity as a challenge that is particularly acute in biomedical applications.

    “Machine-learning systems face two recognized challenges that become particularly acute in biomedical applications. The first is input heterogeneity.”

    From Visible Machine Learning for Biomedicine (2018) · cites this paper as Kourou et al., 2014

  • Cancer can arise from many different combinations of genetic alterations involving many potential genes, any one of which may be mutated only rarely, so each new patient presents a distinct constellation of molecular changes never before seen in nature.

    “For example, cancer can arise as the result of many different combinations of genetic alterations involving many potential genes, any one of which may be mutated only rarely; as a consequence, each new patient presents a distinct constellation of molecular changes never before seen in nature (Alvarez et al., 2016; Kourou et al., 2014).”

    From Visible Machine Learning for Biomedicine (2018) · cites this paper as Kourou et al., 2014

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 2

  1. [10]Bishop C.M. Pattern recognition and machine learning 2006 Springer New York
  2. [64]Howlader N. Noone A. Krapcho M. Garshell J. Neyman N. Aletkruse S. SEER Cancer Statistics Review, 1975–2010, [Online] National Cancer Institute 2013 National Cancer Institute Bethesda, MD [Online]

Cited by

Sorted by citations

Related

Authors
Kourou, K., Exarchos, T. P., Exarchos, K. P., Karamouzis, M. V., & Fotiadis, D. I.
Affiliations
  • University of Ioannina (GR)
  • National and Kapodistrian University of Athens (GR)
Corresponding author
Fotiadis, Dimitrios I.
ORCID
Venue
Computational and Structural Biotechnology Journal
Publisher
American Association for the Advancement of Science (AAAS)
Published
2014-11-15
Volume
13
Pages
8-17
ISSN
2001-0370 (ISSN-L)
DOI
10.1016/j.csbj.2014.11.005
PMC
PMC4348437
OpenAlex
W2111547563
Cited by
3,338
References
72
Citations by year
2026: 302 · 2025: 406 · 2024: 401 · 2023: 405 · 2022: 393 · 2021: 433 · 2020: 425 · 2019: 274 · 2018: 158 · 2017: 80 · 2016: 49 · 2015: 11 · 2014: 1
FWCI
4.98
Type
journal article
Language
en
Open access
Licence
Locations
  • Computational and Structural Biotechnology Journal (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
funded by the project NEOMARK (FP7-ICT 224483)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene expression and cancer classification
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
Keywords
cancer prognosis, cancer risk prediction, prediction model, artificial neural networks, Bayesian networks, support vector machine, decision tree, supervised learning, clinical decision support, tumor heterogeneity

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review