Prediction of fluctuations in a chaotic cancer model using machine learning

被引：4

作者：

Sayari, Elaheh ^{[1
]}

da Silva, Sidney T. ^{[1
,2
]}

Iarosz, Kelly C. ^{[3
,4
]}

Viana, Ricardo L. ^{[5
,6
]}

Szezech Jr, Jose D. ^{[1
,7
]}

Batista, Antonio M. ^{[1
,7
]}

机构：

[1] Univ Estadual Ponta Grossa, Grad Program Sci, Ponta Grossa, PR, Brazil

[2] Univ Fed Parana, Curitiba, PR, Brazil

[3] Univ Ctr UNIFATEB, Telemaco Borba, Parana, Brazil

[4] Fed Technol Univ Parana, Grad Program Chem Engn, Ponta Grossa, PR, Brazil

[5] Univ Fed Parana, Dept Phys, Curitiba, PR, Brazil

[6] Univ Sao Paulo, Inst Phys, Sao Paulo, SP, Brazil

[7] Univ Estadual Ponta Grossa, Math & Stat Dept, Ponta Grossa, PR, Brazil

来源：

CHAOS SOLITONS & FRACTALS | 2022年 / 164卷

基金：

巴西圣保罗研究基金会;

关键词：

Cancer; Mathematical methods; Chaotic attractor; Machine learning; Fluctuations; MATHEMATICAL-MODEL; TUMOR-GROWTH; CHEMOTHERAPY; IMMUNOTHERAPY; DYNAMICS;

D O I：

10.1016/j.chaos.2022.112616

中图分类号：

O1 [数学];

学科分类号：

0701 ; 070101 ;

摘要：

Cancer is a group of diseases and the second leading cause of death according to World Health Organization. Mathematical and computational methods have been used to explore the cancer cells spread and the mechanism of their growth. We study a cancer model that exhibits both periodic and chaotic attractors. It describes the interactions among host, effector immune, and cancer cells. It is observed fluctuations in the population of cells. The fluctuation range can be associated with the appearance of tumour cells. In this work, we use machine learning algorithms for the prediction of fluctuations. We show that our machine learning classification is able to identify fluctuations that are associated with the growth rate of cancer cells.

引用

页数：6

共 45 条

[1]

Adam JA., 1997, MODELING SIMULATION, V59

[2] FRACTALS AND CHAOS IN CANCER MODELS [J].

AHMED, E .

INTERNATIONAL JOURNAL OF THEORETICAL PHYSICS, 1993, 32 (02) :353-355

[3]

Bengio Y., 2007, ADV NEURAL INFORM PR, P153

[4]

Bianchi F., 2018, EUROPEAN S ARTIFICIA

[5] Reservoir Computing Approaches for Representation and Classification of Multivariate Time Series [J].

Bianchi, Filippo Maria ;

Scardapane, Simone ;

Lokse, Sigurd ;

Jenssen, Robert .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 32 (05) :2169-2179

[6] Investigating Echo-State Networks Dynamics by Means of Recurrence Analysis [J].

Bianchi, Filippo Maria ;

Livi, Lorenzo ;

Alippi, Cesare .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (02) :427-439

[7]

Blows WT, 2005, BIOL BASIS NURSING C

[8] Model for tumour growth with treatment by continuous and pulsed chemotherapy [J].

Borges, F. S. ;

Iarosz, K. C. ;

Ren, H. P. ;

Batista, A. M. ;

Baptista, M. S. ;

Viana, R. L. ;

Lopes, S. R. ;

Grebogi, C. .

BIOSYSTEMS, 2014, 116 :43-48

[9] Reservoir computing and extreme learning machines for non-linear time-series data analysis [J].

Butcher, J. B. ;

Verstraeten, D. ;

Schrauwen, B. ;

Day, C. R. ;

Haycock, P. W. .

NEURAL NETWORKS, 2013, 38 :76-89

[10] A general framework for modeling tumor-immune system competition and immunotherapy: Mathematical analysis and biomedical inferences [J].

d'Onofrio, A .

PHYSICA D-NONLINEAR PHENOMENA, 2005, 208 (3-4) :220-235

← 1 2 3 4 5 →