Online prediction of ovarian cancer

04/09/2009
by   Fedor Zhdanov, et al.
0

In this paper we apply computer learning methods to diagnosing ovarian cancer using the level of the standard biomarker CA125 in conjunction with information provided by mass-spectrometry. We are working with a new data set collected over a period of 7 years. Using the level of CA125 and mass-spectrometry peaks, our algorithm gives probability predictions for the disease. To estimate classification accuracy we convert probability predictions into strict predictions. Our algorithm makes fewer errors than almost any linear combination of the CA125 level and one peak's intensity (taken on the log scale). To check the power of our algorithm we use it to test the hypothesis that CA125 and the peaks do not contain useful information for the prediction of the disease at a particular time before the diagnosis. Our algorithm produces p-values that are better than those produced by the algorithm that has been previously applied to this data set. Our conclusion is that the proposed algorithm is more reliable for prediction on new data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/26/2021

Predicting invasive ductal carcinoma using a Reinforcement Sample Learning Strategy using Deep Learning

Invasive ductal carcinoma is a prevalent, potentially deadly disease ass...
research
12/10/2020

Performance Comparison of Balanced and Unbalanced Cancer Datasets using Pre-Trained Convolutional Neural Network

Cancer disease is one of the leading causes of death all over the world....
research
10/31/2019

Peak detection for MALDI mass spectrometry imaging data using sparse frame multipliers

MALDI mass spectrometry imaging (MALDI MSI) is a spatially resolved anal...
research
01/08/2016

A Predictive Model using the Markov Property

Given a data set of numerical values which are sampled from some unknown...
research
10/07/2018

Online Center of Mass Estimation for a Humanoid Wheeled Inverted Pendulum Robot

We present a novel application of robust control and online learning for...
research
04/21/2022

Multiple EffNet/ResNet Architectures for Melanoma Classification

Melanoma is the most malignant skin tumor and usually cancerates from no...
research
11/16/2022

On the Power of Learning-Augmented BSTs

We present the first Learning-Augmented Binary Search Tree(BST) that att...

Please sign up or login with your details

Forgot password? Click here to reset