Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Sep 16:12:35.
doi: 10.4103/jpi.jpi_26_21. eCollection 2021.

Artificial Intelligence in Plasma Cell Myeloma: Neural Networks and Support Vector Machines in the Classification of Plasma Cell Myeloma Data at Diagnosis

Ashwini K Yenamandra  1 , Caitlin Hughes  1 , Alexander S Maris  1
Affiliations

Artificial Intelligence in Plasma Cell Myeloma: Neural Networks and Support Vector Machines in the Classification of Plasma Cell Myeloma Data at Diagnosis

Ashwini K Yenamandra et al. J Pathol Inform. .

Abstract

Background: Plasma cell neoplasm and/or plasma cell myeloma (PCM) is a mature B-cell lymphoproliferative neoplasm of plasma cells that secrete a single homogeneous immunoglobulin called paraprotein or M-protein. Plasma cells accumulate in the bone marrow (BM) leading to bone destruction and BM failure. Diagnosis of PCM is based on clinical, radiologic, and pathological characteristics. The percent of plasma cells by manual differential (bone marrow morphology), the white blood cell (WBC) count, cytogenetics, fluorescence in situ hybridization (FISH), microarray, and next-generation sequencing of BM are used in the risk stratification of newly diagnosed PCM patients. The genetics of PCM is highly complex and heterogeneous with several genetic subtypes that have different clinical outcomes. National Comprehensive Cancer Network guidelines recommend targeted FISH analysis of plasma cells with specific DNA probes to detect genetic abnormalities for the staging of PCM (4.2021). Recognition of risk categories through training software for classification of high-risk PCM and a novel way of addressing the current approaches through bioinformatics will be a significant step toward automation of PCM analysis.

Methods: A new artificial neural network (ANN) classification model was developed and tested in Python programming language with a first data set of 301 cases and a second data set of 176 cases for a total of 477 cases of PCM at diagnosis. Classification model was also developed with support vector machines (SVM) algorithm in R studio and interactive data visuals using Tableau.

Results: The resulting ANN algorithm had 94% accuracy for the first and second data sets with a classification summary of precision (PPV): 0.97, recall (sensitivity): 0.76, f1 score: 0.83, and accuracy of logistic regression of 1.0. SVM of plasma cells versus TP53 revealed a 95% accuracy level.

Conclusion: A novel classification model based only on specific morphological and genetic variables was developed using a machine learning algorithm, the ANN. ANN identified an association of WBC and BM plasma cell percentage with two of the high-risk genetic categories in the diagnostic cases of PCM. With further training and testing of additional data sets that include morphologic and additional genetic rearrangements, the newly developed ANN model has the potential to develop an accurate classification of high-risk categories of PCM.

Keywords: Artificial neural network; National Comprehensive Cancer Network; Next Generation Sequencing; cytogenetics; fluorescence in situ hybridization; machine learning; microarray; plasma cell myeloma; support vector machines kernel trick.

PubMed Disclaimer

Conflict of interest statement

There are no conflicts of interest.

Figures

Figure 1
Figure 1
RoboSep™ stem cell technologies Canada
Figure 2
Figure 2
Tableau – Cohort 1 – Abnormal versus normal cases based on age in males and females
Figure 3
Figure 3
Fluorescence in situ hybridization with myeloma-specific probes (a) 13q14 (red)/13q34 (green) probes with normal pattern (b) CCND1 (red)/ IGH (green) probes with normal pattern. (c) FGFR3 (red)/IGH (green) probes with rearranged (fusion of red and green) pattern. (d) TP53 (red)/ centromere17 (green) with deletion (loss of on red) of TP53 locus
Figure 4
Figure 4
Tableau visual of Cohort 1 data: Male and female cases with low, standard, and high risk, low and standard risk: males higher than females, high risk: males and females similar in number
Figure 5
Figure 5
Python predictive models summary table
Figure 6
Figure 6
PCMQ3 with TensorFlow 2 and ReLU with a ratio of 40/60 training and testing respectively. (a) Receiver operating characteristic curve in logistic regression to determine the best cutoff value for predicting whether a new observation is 0 or 1. (b) Classification report
Figure 7
Figure 7
Tableau Cohort 1 data: TP53 and t(4;14) versus plasma call percent and white blood cell at zero-no deletion, peaks are number of cases with deletion
Figure 8
Figure 8
Tableau Cohort 1 data – Forecast indicator
Figure 9
Figure 9
Support vector machine with MM4 data of cohort 1 between TP53 and plasma cell percentage, training 75% and test 25%
Figure 10
Figure 10
Support vector machine with MM4 data of cohort 1 between TP53 and plasma cell percentage, training 75%, test 25%
Figure 11
Figure 11
Support vector machine with MM4 data of cohort 1 between TP53 and plasma cell percentage, training 60%, test 40%
Figure 12
Figure 12
Support vector machine with MM4 data of cohort 1 between TP53 and plasma cell percentage, training 60% and test 40%
See this image and copyright information in PMC

References

    1. LaCaria T. Case 411 -- A Solitary Bone Lesion [Internet]. University of Pittsburgh Department of Pathology. c2012. [updated 2004 Dec; cited 2021 Aug 04]. Available from: path.upmc.edu/cases/case411.html.
    1. Mikhael J, Ismaila N, Cheung MC, Costello C, Dhodapkar MV, Kumar S, et al. Treatment of multiple myeloma: ASCO and CCO joint clinical practice guideline. J Clin Oncol. 2019;37:1228–63. - PubMed
    1. NCCN.org [Internet] Washington, D.C: National Comprehensive Cancer Network; c2021. [cited 2020 Apr]. Available from: https://NCCN.org/store/login/login.aspx?ReturnURL=https://www.nccn.org/p... .
    1. Cancer.org [Internet] Washington, D.C: American Cancer Society; c2021. [cited 2020 Apr]. Available from: https://cancer.org/cancer/multiple-myeloma.html .
    1. National Institute of Health (NIH) //www.nih.gov.