Boosted decision tree analysis of surface-enhanced laser desorption/ionization mass spectral serum profiles discriminates prostate cancer from noncancer patients - PubMed (original) (raw)
. 2002 Oct;48(10):1835-43.
Affiliations
- PMID: 12324514
Boosted decision tree analysis of surface-enhanced laser desorption/ionization mass spectral serum profiles discriminates prostate cancer from noncancer patients
Yinsheng Qu et al. Clin Chem. 2002 Oct.
Abstract
Background: The low specificity of the prostate-specific antigen (PSA) test makes it a poor biomarker for early detection of prostate cancer (PCA). Because single biomarkers most likely will not be found that are expressed by all genetic forms of PCA, we evaluated and developed a proteomic approach for the simultaneous detection and analysis of multiple proteins for the differentiation of PCA from noncancer patients.
Methods: Serum samples from 386 men [197 with PCA, 92 with benign prostatic hyperplasia (BPH), and 96 healthy individuals], randomly divided into training (n = 326) and test (n = 60) sets, were analyzed by surface-enhanced laser desorption/ionization (SELDI) mass spectrometry. The 124 peaks detected by computer analyses were analyzed in the training set by a boosting tree algorithm to develop a classifier for separating PCA from the noncancer groups. The classifier was then challenged with the test set (30 PCA samples, 15 BPH samples, 15 samples from healthy men) to determine the validity and accuracy of the classification system.
Results: Two classifiers were developed. The AdaBoost classifier completely separated the PCA from the noncancer samples, achieving 100% sensitivity and specificity. The second classifier, the Boosted Decision Stump Feature Selection classifier, was easier to interpret and used only 21 (compared with 74) peaks and a combination of 21 (vs 500) base classifiers to achieve a sensitivity and specificity of 97% for the test set.
Conclusions: The high sensitivity and specificity achieved in this study provides support of the potential for SELDI, coupled with a bioinformatics learning algorithm, to improve the early detection/diagnosis of PCA.
Comment in
Similar articles
- Serum protein fingerprinting coupled with a pattern-matching algorithm distinguishes prostate cancer from benign prostate hyperplasia and healthy men.
Adam BL, Qu Y, Davis JW, Ward MD, Clements MA, Cazares LH, Semmes OJ, Schellhammer PF, Yasui Y, Feng Z, Wright GL Jr. Adam BL, et al. Cancer Res. 2002 Jul 1;62(13):3609-14. Cancer Res. 2002. PMID: 12097261 - A data-analytic strategy for protein biomarker discovery: profiling of high-dimensional proteomic data for cancer detection.
Yasui Y, Pepe M, Thompson ML, Adam BL, Wright GL Jr, Qu Y, Potter JD, Winget M, Thornquist M, Feng Z. Yasui Y, et al. Biostatistics. 2003 Jul;4(3):449-63. doi: 10.1093/biostatistics/4.3.449. Biostatistics. 2003. PMID: 12925511 - [Proteomic analysis of prostate cancer using surface enhanced laser desorption/ionization mass spectrometry].
Pan YZ, Xiao XY, Zhao D, Zhang L, Ji GY, Li Y, He DC, Zhao XJ, Yang BX. Pan YZ, et al. Zhonghua Yi Xue Za Zhi. 2005 Nov 30;85(45):3172-5. Zhonghua Yi Xue Za Zhi. 2005. PMID: 16405834 Chinese. - Proteomics in diagnosis of prostate cancer.
Davalieva K, Polenakovic M. Davalieva K, et al. Pril (Makedon Akad Nauk Umet Odd Med Nauki). 2015;36(1):5-36. Pril (Makedon Akad Nauk Umet Odd Med Nauki). 2015. PMID: 26076772 Review. - The early detection research network surface-enhanced laser desorption and ionization prostate cancer detection study: A study in biomarker validation in genitourinary oncology.
Grizzle WE, Semmes OJ, Basler J, Izbicka E, Feng Z, Kagan J, Adam BL, Troyer D, Srivastava S, Thornquist M, Zhang Z, Thompson IM. Grizzle WE, et al. Urol Oncol. 2004 Jul-Aug;22(4):337-43. doi: 10.1016/j.urolonc.2004.04.008. Urol Oncol. 2004. PMID: 15283893 Review.
Cited by
- Assessment of a Machine Learning Model Applied to Harmonized Electronic Health Record Data for the Prediction of Incident Atrial Fibrillation.
Tiwari P, Colborn KL, Smith DE, Xing F, Ghosh D, Rosenberg MA. Tiwari P, et al. JAMA Netw Open. 2020 Jan 3;3(1):e1919396. doi: 10.1001/jamanetworkopen.2019.19396. JAMA Netw Open. 2020. PMID: 31951272 Free PMC article. - A Classification Model to Predict the Rate of Decline of Kidney Function.
Subasi E, Subasi MM, Hammer PL, Roboz J, Anbalagan V, Lipkowitz MS. Subasi E, et al. Front Med (Lausanne). 2017 Jul 19;4:97. doi: 10.3389/fmed.2017.00097. eCollection 2017. Front Med (Lausanne). 2017. PMID: 28770199 Free PMC article. - Pairwise protein expression classifier for candidate biomarker discovery for early detection of human disease prognosis.
Kaur P, Schlatzer D, Cooke K, Chance MR. Kaur P, et al. BMC Bioinformatics. 2012 Aug 7;13:191. doi: 10.1186/1471-2105-13-191. BMC Bioinformatics. 2012. PMID: 22870920 Free PMC article. - Detection of bladder cancer using proteomic profiling of urine sediments.
Majewski T, Spiess PE, Bondaruk J, Black P, Clarke C, Benedict W, Dinney CP, Grossman HB, Tang KS, Czerniak B. Majewski T, et al. PLoS One. 2012;7(8):e42452. doi: 10.1371/journal.pone.0042452. Epub 2012 Aug 3. PLoS One. 2012. PMID: 22879988 Free PMC article. - Urinary proteomic analysis of chronic allograft nephropathy.
O'Riordan E, Orlova TN, Mendelev N, Patschan D, Kemp R, Chander PN, Hu R, Hao G, Gross SS, Iozzo RV, Delaney V, Goligorsky MS. O'Riordan E, et al. Proteomics Clin Appl. 2008 Jul;2(7-8):1025-35. doi: 10.1002/prca.200780137. Proteomics Clin Appl. 2008. PMID: 21136903 Free PMC article.
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources
Medical
Research Materials
Miscellaneous