PMID- 31430304 OWN - NLM STAT- MEDLINE DCOM- 20200323 LR - 20200323 IS - 1932-6203 (Electronic) IS - 1932-6203 (Linking) VI - 14 IP - 8 DP - 2019 TI - Multi-group diagnostic classification of high-dimensional data using differential scanning calorimetry plasma thermograms. PG - e0220765 LID - 10.1371/journal.pone.0220765 [doi] LID - e0220765 AB - The thermoanalytical technique differential scanning calorimetry (DSC) has been applied to characterize protein denaturation patterns (thermograms) in blood plasma samples and relate these to a subject's health status. The analysis and classification of thermograms is challenging because of the high-dimensionality of the dataset. There are various methods for group classification using high-dimensional data sets; however, the impact of using high-dimensional data sets for cancer classification has been poorly understood. In the present article, we proposed a statistical approach for data reduction and a parametric method (PM) for modeling of high-dimensional data sets for two- and three- group classification using DSC and demographic data. We compared the PM to the non-parametric classification method K-nearest neighbors (KNN) and the semi-parametric classification method KNN with dynamic time warping (DTW). We evaluated the performance of these methods for multiple two-group classifications: (i) normal versus cervical cancer, (ii) normal versus lung cancer, (iii) normal versus cancer (cervical + lung), (iv) lung cancer versus cervical cancer as well as for three-group classification: normal versus cervical cancer versus lung cancer. In general, performance for two-group classification was high whereas three-group classification was more challenging, with all three methods predicting normal samples more accurately than cancer samples. Moreover, specificity of the PM method was mostly higher or the same as KNN and DTW-KNN with lower sensitivity. The performance of KNN and DTW-KNN decreased with the inclusion of demographic data, whereas similar performance was observed for the PM which could be explained by the fact that the PM uses fewer parameters as compared to KNN and DTW-KNN methods and is thus less susceptible to the risk of overfitting. More importantly the accuracy of the PM can be increased by using a greater number of quantile data points and by the inclusion of additional demographic and clinical data, providing a substantial advantage over KNN and DTW-KNN methods. FAU - Rai, Shesh N AU - Rai SN AUID- ORCID: 0000-0002-8377-353X AD - Biostatistics and Bioinformatics Facility, James Graham Brown Cancer Center, University of Louisville, Louisville, Kentucky, United States of America. AD - Department of Bioinformatics and Biostatistics, University of Louisville, Louisville, Kentucky, United States of America. FAU - Srivastava, Sudhir AU - Srivastava S AD - Department of Bioinformatics and Biostatistics, University of Louisville, Louisville, Kentucky, United States of America. AD - Centre for Agricultural Bioinformatics, ICAR-Indian Agricultural Statistics Research Institute, New Delhi, India. FAU - Pan, Jianmin AU - Pan J AD - Biostatistics and Bioinformatics Facility, James Graham Brown Cancer Center, University of Louisville, Louisville, Kentucky, United States of America. FAU - Wu, Xiaoyong AU - Wu X AD - Biostatistics and Bioinformatics Facility, James Graham Brown Cancer Center, University of Louisville, Louisville, Kentucky, United States of America. FAU - Rai, Somesh P AU - Rai SP AD - School of Public Health and Information Sciences, University of Louisville, Louisville, Kentucky, United States of America. FAU - Mekmaysy, Chongkham S AU - Mekmaysy CS AD - Department of Medicine, University of Louisville, Louisville, Kentucky, United States of America. FAU - DeLeeuw, Lynn AU - DeLeeuw L AD - Department of Medicine, University of Louisville, Louisville, Kentucky, United States of America. FAU - Chaires, Jonathan B AU - Chaires JB AD - Department of Medicine, University of Louisville, Louisville, Kentucky, United States of America. AD - Biophysical Core Facility, James Graham Brown Cancer Center, University of Louisville, Louisville, Kentucky, United States of America. FAU - Garbett, Nichola C AU - Garbett NC AD - Department of Medicine, University of Louisville, Louisville, Kentucky, United States of America. AD - Biophysical Core Facility, James Graham Brown Cancer Center, University of Louisville, Louisville, Kentucky, United States of America. LA - eng GR - P20 GM103482/GM/NIGMS NIH HHS/United States GR - P20 RR018733/RR/NCRR NIH HHS/United States GR - R01 AI129959/AI/NIAID NIH HHS/United States GR - R21 CA187345/CA/NCI NIH HHS/United States PT - Journal Article PT - Research Support, N.I.H., Extramural PT - Research Support, Non-U.S. Gov't PT - Research Support, U.S. Gov't, Non-P.H.S. DEP - 20190820 PL - United States TA - PLoS One JT - PloS one JID - 101285081 RN - 0 (Blood Proteins) SB - IM MH - Adolescent MH - Adult MH - Aged MH - Aged, 80 and over MH - Blood Proteins/*chemistry MH - Calorimetry, Differential Scanning/*methods MH - Female MH - Humans MH - Lung Neoplasms/blood/*diagnosis MH - Male MH - Middle Aged MH - *Protein Denaturation MH - Regression Analysis MH - Uterine Cervical Neoplasms/blood/*diagnosis MH - Young Adult PMC - PMC6701772 COIS- NCG is a co-inventor on a patent application describing approaches for the analysis of DSC plasma thermogram data and their use for diagnostic classification (Garbett, N.C., and Brock, G.N. "Methods of Characterizing and/or Predicting Risk Associated with a Biological Sample Using Thermal Stability Profiles," U.S. PCT Application PCT/US16/57416, Oct. 2016). NCG is a consultant for TA Instruments, Inc., a supplier of calorimetry instrumentation but not the supplier of the DSC instrument used to collect data for this study. This does not alter the authors' adherence to all journal policies on sharing data and materials. EDAT- 2019/08/21 06:00 MHDA- 2020/03/24 06:00 PMCR- 2019/08/20 CRDT- 2019/08/21 06:00 PHST- 2019/03/19 00:00 [received] PHST- 2019/07/23 00:00 [accepted] PHST- 2019/08/21 06:00 [entrez] PHST- 2019/08/21 06:00 [pubmed] PHST- 2020/03/24 06:00 [medline] PHST- 2019/08/20 00:00 [pmc-release] AID - PONE-D-19-07952 [pii] AID - 10.1371/journal.pone.0220765 [doi] PST - epublish SO - PLoS One. 2019 Aug 20;14(8):e0220765. doi: 10.1371/journal.pone.0220765. eCollection 2019.