Neural Network Based Tumor Marker Prediction

Witold Jacak; Karin Pröll

Neural Network Based Tumor Marker Prediction

Witold Jacak
, Karin Pröll

Research Center Hagenberg

Research output: Chapter in Book/Report/Conference proceedings › Conference contribution › peer-review

Abstract

In this paper a system for the prediction of tumor marker values based on standard blood is presented. Several neural networks are used to learn from blood examination measurements and predict tumor markers in case these values are missing. In a post processing step the predicted values are evaluated in a fuzzy logic like style against different hypotheses and the best hypothesis is used to optimize the predicted values and its plausibility. These predicted values can then be used as input for a second system to support decision making in cancer diagnosis. A variety of experiments with tumor marker C153 show that we can get a prediction accuracy of more than 90%. Our experiments are based on hundreds of samples of up to 27 different features (blood parameters) per vector. We try to predict distinct values, classes of values and a combination of classes and values for specific marker types.

Original language	English
Title of host publication	Proceedeings of 5th International Conference on Broadband Communication, Information Technology & Biomedical Applications, BroadCom 2010
Publisher	River Publishers (Series in Information Science)
Pages	1-6
Publication status	Published - 2010
Event	BroadCom 2010 - 5th International Conference on Broadband Communication, Information Technology & Biomedical Applications - Malaga, Spain Duration: 15 Dec 2010 → 19 Dec 2010

Conference

Conference	BroadCom 2010 - 5th International Conference on Broadband Communication, Information Technology & Biomedical Applications
Country/Territory	Spain
City	Malaga
Period	15.12.2010 → 19.12.2010

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

neural network
tumor marker prediction
decision support system

Cite this

@inproceedings{d9232da7ac434516b1ba03aa54c96efa,

title = "Neural Network Based Tumor Marker Prediction",

abstract = "In this paper a system for the prediction of tumor marker values based on standard blood is presented. Several neural networks are used to learn from blood examination measurements and predict tumor markers in case these values are missing. In a post processing step the predicted values are evaluated in a fuzzy logic like style against different hypotheses and the best hypothesis is used to optimize the predicted values and its plausibility. These predicted values can then be used as input for a second system to support decision making in cancer diagnosis. A variety of experiments with tumor marker C153 show that we can get a prediction accuracy of more than 90\%. Our experiments are based on hundreds of samples of up to 27 different features (blood parameters) per vector. We try to predict distinct values, classes of values and a combination of classes and values for specific marker types.",

keywords = "neural network, tumor marker prediction, decision support system, neural network, tumor marker prediction, decision support system",

author = "Witold Jacak and Karin Pr{\"o}ll",

year = "2010",

language = "English",

pages = "1--6",

booktitle = "Proceedeings of 5th International Conference on Broadband Communication, Information Technology \& Biomedical Applications, BroadCom 2010",

publisher = "River Publishers (Series in Information Science)",

note = "BroadCom 2010 - 5th International Conference on Broadband Communication, Information Technology \& Biomedical Applications ; Conference date: 15-12-2010 Through 19-12-2010",

}

Jacak, W & Pröll, K 2010, Neural Network Based Tumor Marker Prediction. in Proceedeings of 5th International Conference on Broadband Communication, Information Technology & Biomedical Applications, BroadCom 2010. River Publishers (Series in Information Science), pp. 1-6, BroadCom 2010 - 5th International Conference on Broadband Communication, Information Technology & Biomedical Applications, Malaga, Spain, 15.12.2010.

Neural Network Based Tumor Marker Prediction. / Jacak, Witold; Pröll, Karin.
Proceedeings of 5th International Conference on Broadband Communication, Information Technology & Biomedical Applications, BroadCom 2010. River Publishers (Series in Information Science), 2010. p. 1-6.

Research output: Chapter in Book/Report/Conference proceedings › Conference contribution › peer-review

TY - GEN

T1 - Neural Network Based Tumor Marker Prediction

AU - Jacak, Witold

AU - Pröll, Karin

PY - 2010

Y1 - 2010

N2 - In this paper a system for the prediction of tumor marker values based on standard blood is presented. Several neural networks are used to learn from blood examination measurements and predict tumor markers in case these values are missing. In a post processing step the predicted values are evaluated in a fuzzy logic like style against different hypotheses and the best hypothesis is used to optimize the predicted values and its plausibility. These predicted values can then be used as input for a second system to support decision making in cancer diagnosis. A variety of experiments with tumor marker C153 show that we can get a prediction accuracy of more than 90%. Our experiments are based on hundreds of samples of up to 27 different features (blood parameters) per vector. We try to predict distinct values, classes of values and a combination of classes and values for specific marker types.

AB - In this paper a system for the prediction of tumor marker values based on standard blood is presented. Several neural networks are used to learn from blood examination measurements and predict tumor markers in case these values are missing. In a post processing step the predicted values are evaluated in a fuzzy logic like style against different hypotheses and the best hypothesis is used to optimize the predicted values and its plausibility. These predicted values can then be used as input for a second system to support decision making in cancer diagnosis. A variety of experiments with tumor marker C153 show that we can get a prediction accuracy of more than 90%. Our experiments are based on hundreds of samples of up to 27 different features (blood parameters) per vector. We try to predict distinct values, classes of values and a combination of classes and values for specific marker types.

KW - neural network

KW - tumor marker prediction

KW - decision support system

KW - neural network

KW - tumor marker prediction

KW - decision support system

M3 - Conference contribution

SP - 1

EP - 6

BT - Proceedeings of 5th International Conference on Broadband Communication, Information Technology & Biomedical Applications, BroadCom 2010

PB - River Publishers (Series in Information Science)

T2 - BroadCom 2010 - 5th International Conference on Broadband Communication, Information Technology & Biomedical Applications

Y2 - 15 December 2010 through 19 December 2010

ER -

Neural Network Based Tumor Marker Prediction

Abstract

Conference

UN SDGs

Keywords

Other files and links

Fingerprint

Cite this