Machine learning methods can more efficiently predict prostate cancer compared with prostate-specific antigen density and prostate-specific antigen velocity
Background: Prostate-specific antigen (PSA)–based screening for prostate cancer has been widely performed, but its accuracy is unsatisfactory. To improve accuracy, building an effective statistical model using machine learning methods (MLMs) is a promising approach. Methods: Data on continuous chang...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2019-09-01
|
| Series: | Prostate International |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2287888218301120 |
| _version_ | 1797722580748075008 |
|---|---|
| author | Satoshi Nitta Masakazu Tsutsumi Shotaro Sakka Tsuyoshi Endo Kenichiro Hashimoto Morikuni Hasegawa Takayuki Hayashi Koji Kawai Hiroyuki Nishiyama |
| author_facet | Satoshi Nitta Masakazu Tsutsumi Shotaro Sakka Tsuyoshi Endo Kenichiro Hashimoto Morikuni Hasegawa Takayuki Hayashi Koji Kawai Hiroyuki Nishiyama |
| author_sort | Satoshi Nitta |
| collection | DOAJ |
| description | Background: Prostate-specific antigen (PSA)–based screening for prostate cancer has been widely performed, but its accuracy is unsatisfactory. To improve accuracy, building an effective statistical model using machine learning methods (MLMs) is a promising approach. Methods: Data on continuous changes in the PSA level over the past 2 years were accumulated from 512 patients who underwent prostate biopsy after PSA screening. The age of the patients, PSA level, prostate volumes, and white blood cell count in urinalysis were used as input data for the MLMs. As MLMs, we evaluated the efficacy of three different techniques: artificial neural networks (ANNs), random forest, and support vector machine. Model performance was evaluated using area under the receiver operating characteristic curve (AUC) and compared with the PSA level and the conventional PSA–based parameters: PSA density and PSA velocity. Results: When using two annual PSA testing, all receiver operating characteristic curves of the three MLMs were above the curve for the PSA level, PSA density, and PSA velocity. The AUCs of ANNs, random forest, and support vector machine were 0.69, 0.64, and 0.63, respectively. Those values were higher than the AUCs of the PSA level, PSA density, and PSA velocity, 0.53, 0.41, and 0.55, respectively. The accuracies of the MLMs (71.6% to 72.1%) were also superior to those of the PSA level (39.1%), PSA density (49.7%), and PSA velocity (54.9%). Among the MLMs, ANNs showed the most favorable AUC. The MLMs showed higher sensitivity and specificity than conventional PSA–based parameters. The model performance did not improve when using three annual PSA testing. Conclusion: The present retrospective study results indicate that machine learning techniques can predict prostate cancer with significantly better AUCs than those of PSA density and PSA velocity. Keywords: Machine leaning method, Prostate cancer, Prostate-specific antigen |
| first_indexed | 2024-03-12T09:50:28Z |
| format | Article |
| id | doaj.art-c0b677899c344e329cd1fee3f5e924a5 |
| institution | Directory Open Access Journal |
| issn | 2287-8882 |
| language | English |
| last_indexed | 2024-03-12T09:50:28Z |
| publishDate | 2019-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Prostate International |
| spelling | doaj.art-c0b677899c344e329cd1fee3f5e924a52023-09-02T12:38:12ZengElsevierProstate International2287-88822019-09-0173114118Machine learning methods can more efficiently predict prostate cancer compared with prostate-specific antigen density and prostate-specific antigen velocitySatoshi Nitta0Masakazu Tsutsumi1Shotaro Sakka2Tsuyoshi Endo3Kenichiro Hashimoto4Morikuni Hasegawa5Takayuki Hayashi6Koji Kawai7Hiroyuki Nishiyama8The Department of Urology, Hitachi General Hospital, Hitachi City, Japan; Corresponding author. The Department of Urology, Hitachi General Hospital, 2-1-1, Jonan-cho, Hitachi City, Ibaraki Prefecture, 317-0077, Japan.The Department of Urology, Hitachi General Hospital, Hitachi City, JapanThe Department of Urology, Hitachi General Hospital, Hitachi City, JapanThe Department of Urology, Hitachi General Hospital, Hitachi City, JapanThe Department of Information Systems, Hitachi General Hospital, Hitachi City, JapanInformation and Communication Technology Business Division, Hitachi Ltd., Chiyoda City, JapanInformation and Communication Technology Business Division, Hitachi Ltd., Chiyoda City, JapanThe Department of Urology, Faculty of Medicine, University of Tsukuba, Tsukuba City, JapanThe Department of Urology, Faculty of Medicine, University of Tsukuba, Tsukuba City, JapanBackground: Prostate-specific antigen (PSA)–based screening for prostate cancer has been widely performed, but its accuracy is unsatisfactory. To improve accuracy, building an effective statistical model using machine learning methods (MLMs) is a promising approach. Methods: Data on continuous changes in the PSA level over the past 2 years were accumulated from 512 patients who underwent prostate biopsy after PSA screening. The age of the patients, PSA level, prostate volumes, and white blood cell count in urinalysis were used as input data for the MLMs. As MLMs, we evaluated the efficacy of three different techniques: artificial neural networks (ANNs), random forest, and support vector machine. Model performance was evaluated using area under the receiver operating characteristic curve (AUC) and compared with the PSA level and the conventional PSA–based parameters: PSA density and PSA velocity. Results: When using two annual PSA testing, all receiver operating characteristic curves of the three MLMs were above the curve for the PSA level, PSA density, and PSA velocity. The AUCs of ANNs, random forest, and support vector machine were 0.69, 0.64, and 0.63, respectively. Those values were higher than the AUCs of the PSA level, PSA density, and PSA velocity, 0.53, 0.41, and 0.55, respectively. The accuracies of the MLMs (71.6% to 72.1%) were also superior to those of the PSA level (39.1%), PSA density (49.7%), and PSA velocity (54.9%). Among the MLMs, ANNs showed the most favorable AUC. The MLMs showed higher sensitivity and specificity than conventional PSA–based parameters. The model performance did not improve when using three annual PSA testing. Conclusion: The present retrospective study results indicate that machine learning techniques can predict prostate cancer with significantly better AUCs than those of PSA density and PSA velocity. Keywords: Machine leaning method, Prostate cancer, Prostate-specific antigenhttp://www.sciencedirect.com/science/article/pii/S2287888218301120 |
| spellingShingle | Satoshi Nitta Masakazu Tsutsumi Shotaro Sakka Tsuyoshi Endo Kenichiro Hashimoto Morikuni Hasegawa Takayuki Hayashi Koji Kawai Hiroyuki Nishiyama Machine learning methods can more efficiently predict prostate cancer compared with prostate-specific antigen density and prostate-specific antigen velocity Prostate International |
| title | Machine learning methods can more efficiently predict prostate cancer compared with prostate-specific antigen density and prostate-specific antigen velocity |
| title_full | Machine learning methods can more efficiently predict prostate cancer compared with prostate-specific antigen density and prostate-specific antigen velocity |
| title_fullStr | Machine learning methods can more efficiently predict prostate cancer compared with prostate-specific antigen density and prostate-specific antigen velocity |
| title_full_unstemmed | Machine learning methods can more efficiently predict prostate cancer compared with prostate-specific antigen density and prostate-specific antigen velocity |
| title_short | Machine learning methods can more efficiently predict prostate cancer compared with prostate-specific antigen density and prostate-specific antigen velocity |
| title_sort | machine learning methods can more efficiently predict prostate cancer compared with prostate specific antigen density and prostate specific antigen velocity |
| url | http://www.sciencedirect.com/science/article/pii/S2287888218301120 |
| work_keys_str_mv | AT satoshinitta machinelearningmethodscanmoreefficientlypredictprostatecancercomparedwithprostatespecificantigendensityandprostatespecificantigenvelocity AT masakazutsutsumi machinelearningmethodscanmoreefficientlypredictprostatecancercomparedwithprostatespecificantigendensityandprostatespecificantigenvelocity AT shotarosakka machinelearningmethodscanmoreefficientlypredictprostatecancercomparedwithprostatespecificantigendensityandprostatespecificantigenvelocity AT tsuyoshiendo machinelearningmethodscanmoreefficientlypredictprostatecancercomparedwithprostatespecificantigendensityandprostatespecificantigenvelocity AT kenichirohashimoto machinelearningmethodscanmoreefficientlypredictprostatecancercomparedwithprostatespecificantigendensityandprostatespecificantigenvelocity AT morikunihasegawa machinelearningmethodscanmoreefficientlypredictprostatecancercomparedwithprostatespecificantigendensityandprostatespecificantigenvelocity AT takayukihayashi machinelearningmethodscanmoreefficientlypredictprostatecancercomparedwithprostatespecificantigendensityandprostatespecificantigenvelocity AT kojikawai machinelearningmethodscanmoreefficientlypredictprostatecancercomparedwithprostatespecificantigendensityandprostatespecificantigenvelocity AT hiroyukinishiyama machinelearningmethodscanmoreefficientlypredictprostatecancercomparedwithprostatespecificantigendensityandprostatespecificantigenvelocity |