Proper Choice of a Machine Learning Algorithm for Breast Cancer Prediction

2021 ◽  
pp. 1-12
Author(s):  
Arijit Das ◽  
Tanisha Khan ◽  
Subhram Das ◽  
D. K. Bhattacharya
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Learning Algorithm ◽  
Proper Choice ◽  
Machine Learning Algorithm ◽  
Cancer Prediction

scholarly journals AI3 PREDICTION OF BREAST CANCER USING K-NEAREST NEIGHBOUR: A SUPERVISED MACHINE LEARNING ALGORITHM

2020 ◽  
Vol 23 ◽  
pp. S1
Author(s):  
S. Pandey ◽  
A. Sharma ◽  
M.K. Siddiqui ◽  
D. Singla ◽  
J. Vanderpuye-Orgle
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Learning Algorithm ◽  
Supervised Machine Learning ◽  
Machine Learning Algorithm ◽  
Nearest Neighbour

scholarly journals Genomic risk prediction of aromatase inhibitor-related arthralgia in patients with breast cancer using a novel machine-learning algorithm

2017 ◽  
Vol 7 (1) ◽  
pp. 240-253 ◽  
Author(s):  
Raquel E. Reinbolt ◽  
Stephen Sonis ◽  
Cynthia D. Timmers ◽  
Juan Luis Fernández-Martínez ◽  
Ana Cernea ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Aromatase Inhibitor ◽  
Risk Prediction ◽  
Learning Algorithm ◽  
Machine Learning Algorithm ◽  
Genomic Risk

scholarly journals A ‘Real-Life’ Experience on Automated Digital Image Analysis of FGFR2 Immunohistochemistry in Breast Cancer

Diagnostics ◽  
2020 ◽  
Vol 10 (12) ◽  
pp. 1060
Author(s):  
Marcin Braun ◽  
Dominika Piasecka ◽  
Mateusz Bobrowski ◽  
Radzislaw Kordek ◽  
Rafal Sadej ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Life Experience ◽  
Learning Algorithm ◽  
Real Life ◽  
Growth Factor Receptor ◽  
Machine Learning Algorithm ◽  
Tissue Quality ◽  
Small Constant ◽  
Pathologic Assessment

We present here an assessment of a ‘real-life’ value of automated machine learning algorithm (AI) for examination of immunohistochemistry for fibroblast growth factor receptor-2 (FGFR2) in breast cancer (BC). Expression of FGFR2 in BC (n = 315) measured using a certified 3DHistech CaseViewer/QuantCenter software 2.3.0. was compared to the manual pathologic assessment in digital slides (PA). Results revealed: (i) substantial interrater agreement between AI and PA for dichotomized evaluation (Cohen’s kappa = 0.61); (ii) strong correlation between AI and PA H-scores (Spearman r = 0.85, p < 0.001); (iii) a small constant error and a significant proportional error (Passing–Bablok regression y = 0.51 × X + 29.9, p < 0.001); (iv) discrepancies in H-score in cases of extreme (strongest/weakest) or heterogeneous FGFR2 expression and poor tissue quality. The time of AI was significantly longer (568 h) than that of the pathologist (32 h). This study shows that the described commercial machine learning algorithm can reliably execute a routine pathologic assessment, however, in some instances, human expertise is essential.

Sign in / Sign up

Export Citation Format

Share Document