Recognition and Prediction of Leukemia With Artificial Neural
Background:Leukemia is one of the mostcommon cancers in children, comprising more than a third of all childhood cancers. Newly affected patients in USA are estimated as 10100cases, and if these cases are diagnosed late or proper treatment is not applied, then it can be mortal. Because rapid and prop...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Iran University of Medical Sciences
2011-05-01
|
| Series: | Medical Journal of The Islamic Republic of Iran |
| Subjects: | |
| Online Access: | http://mjiri.tums.ac.ir/browse.php?a_code=A-10-1-141&slc_lang=en&sid=1 |
| _version_ | 1818937088126484480 |
|---|---|
| author | Kobra Taheri Mahin Zohdi Seif Fereshte Vakili Tanha Fahimeh Abdolrahmani Saeid Afshar |
| author_facet | Kobra Taheri Mahin Zohdi Seif Fereshte Vakili Tanha Fahimeh Abdolrahmani Saeid Afshar |
| author_sort | Kobra Taheri |
| collection | DOAJ |
| description | Background:Leukemia is one of the mostcommon cancers in children, comprising more than a third of all childhood cancers. Newly affected patients in USA are estimated as 10100cases, and if these cases are diagnosed late or proper treatment is not applied, then it can be mortal. Because rapid and proper diagnosis of leukemia based on clinical or medicinal findings (without biopsy) is impossible, we decided to apply artificial neural network for rapid leukemia diagnosis. For this aim we used clinical and medical parameters taken from 131 patients of Sina hospital of Hamadan. Methods :We carried out independent sample T-test with SPSS software for 38 parameters. With regard to the results of this analysis we selected 8 parameters that had lowest sig for ANN analysis (among parameters, whose sig were less than 0.05). Selected parameters of 131 patients were applied for training network with Levenberg-Marquardt learning algorithm, with learning rate of 0.1.Results :Performance of learning was 0.094. The Relationship between the output of trained network for test data and real results of test data was high and the area under ROC curve was 0.967.Conclusions:With these results we can conclude that training process was done successfully and accurately. Therefore we can use artificial neural network for rapid and reliable leukemia recognition. |
| first_indexed | 2024-12-20T05:46:24Z |
| format | Article |
| id | doaj.art-37e3acf48d304ab780a69f2a7f3086bd |
| institution | Directory Open Access Journal |
| issn | 1016-1430 2251-6840 |
| language | English |
| last_indexed | 2024-12-20T05:46:24Z |
| publishDate | 2011-05-01 |
| publisher | Iran University of Medical Sciences |
| record_format | Article |
| series | Medical Journal of The Islamic Republic of Iran |
| spelling | doaj.art-37e3acf48d304ab780a69f2a7f3086bd2022-12-21T19:51:17ZengIran University of Medical SciencesMedical Journal of The Islamic Republic of Iran1016-14302251-68402011-05-012513539Recognition and Prediction of Leukemia With Artificial NeuralKobra TaheriMahin Zohdi SeifFereshte Vakili TanhaFahimeh AbdolrahmaniSaeid AfsharBackground:Leukemia is one of the mostcommon cancers in children, comprising more than a third of all childhood cancers. Newly affected patients in USA are estimated as 10100cases, and if these cases are diagnosed late or proper treatment is not applied, then it can be mortal. Because rapid and proper diagnosis of leukemia based on clinical or medicinal findings (without biopsy) is impossible, we decided to apply artificial neural network for rapid leukemia diagnosis. For this aim we used clinical and medical parameters taken from 131 patients of Sina hospital of Hamadan. Methods :We carried out independent sample T-test with SPSS software for 38 parameters. With regard to the results of this analysis we selected 8 parameters that had lowest sig for ANN analysis (among parameters, whose sig were less than 0.05). Selected parameters of 131 patients were applied for training network with Levenberg-Marquardt learning algorithm, with learning rate of 0.1.Results :Performance of learning was 0.094. The Relationship between the output of trained network for test data and real results of test data was high and the area under ROC curve was 0.967.Conclusions:With these results we can conclude that training process was done successfully and accurately. Therefore we can use artificial neural network for rapid and reliable leukemia recognition.http://mjiri.tums.ac.ir/browse.php?a_code=A-10-1-141&slc_lang=en&sid=1ANNArtificial Neural NetworkCancerLeukemiaPrediction |
| spellingShingle | Kobra Taheri Mahin Zohdi Seif Fereshte Vakili Tanha Fahimeh Abdolrahmani Saeid Afshar Recognition and Prediction of Leukemia With Artificial Neural Medical Journal of The Islamic Republic of Iran ANN Artificial Neural Network Cancer Leukemia Prediction |
| title | Recognition and Prediction of Leukemia With Artificial Neural |
| title_full | Recognition and Prediction of Leukemia With Artificial Neural |
| title_fullStr | Recognition and Prediction of Leukemia With Artificial Neural |
| title_full_unstemmed | Recognition and Prediction of Leukemia With Artificial Neural |
| title_short | Recognition and Prediction of Leukemia With Artificial Neural |
| title_sort | recognition and prediction of leukemia with artificial neural |
| topic | ANN Artificial Neural Network Cancer Leukemia Prediction |
| url | http://mjiri.tums.ac.ir/browse.php?a_code=A-10-1-141&slc_lang=en&sid=1 |
| work_keys_str_mv | AT kobrataheri recognitionandpredictionofleukemiawithartificialneural AT mahinzohdiseif recognitionandpredictionofleukemiawithartificialneural AT fereshtevakilitanha recognitionandpredictionofleukemiawithartificialneural AT fahimehabdolrahmani recognitionandpredictionofleukemiawithartificialneural AT saeidafshar recognitionandpredictionofleukemiawithartificialneural |