Mathematical Model of Two-Dimensional Disease Progression and Categorization of Underlying Vector Fields with Machine Learning
Journal of Disease and Global Health, Volume 16, Issue 1,
Page 37-46
DOI:
10.56557/jodagh/2023/v16i18205
Abstract
A mathematical model was created for simulating disease progression in two-dimension, by specifying a vector field. It was equivalent to observing how a lesion pattern on the skin, could change its shape over time. This model had a parameter that might control the resolution and signal of the pattern. By specifying two different vector fields, we established two sets of subtly different image sets. And, three different supervised machine learning algorithms such as nearest neighbor, decision tree, and support vector machine were used for binary classification. This study was done with Python's numerical (numpy), plotting (matplotlib), and machine learning (sklearn) libraries on the Google Colab platform. All machine learning algorithms were able to distinguish subtle differences produced by different vector fields. Furthermore, the performance of the algorithms were improved by concatenating the beginning and end stages of the pattern and helping the algorithms to pick up the temporal changes. These results demonstrated how AI and machine learning could be adopted in medicine for accurately diagnosing underlying diseases from images.
- Two-dimensional disease model
- learning machine
- underlying vector fields
How to Cite
References
Mayo Clinic. Diabetic retinopathy. Myo Clinic, Rochester, MN 55905, “n.d.”, Available:https://www.mayoclinic.org/about-mayo-clinic/contact.
Rick Whiting. 5 Emerging AI and machine learning trends to watch in 2021. CRN, The Channel Co. ; 2020.
Available:https://www.crn.com/news/cloud/5-emerging-ai-and-machine-learning-trends-to-watch-in-2021
Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S. Dermatologist-level classification of skin cancer with deep neural networks. Nature. Erratum in: Nature. 2017;546(7660):686. 2017;542(7639):115-118. DOI: 10.1038/nature21056. Epub 2017 Jan 25.
Lewis C. Rose. Recognizing neoplastic skin lesions: A photo guide. American Family Physician Mostafavi Ehsan. An introduction to sensitivity, specificity, positive and negative predictive values. 2017; 58(4):873-884. DOI:10.13140/RG.2.2.13863.96163
Titus J. Brinker, Achim Hekler, Alexander H. Enk, Joachim Klode, Axel Hauschild, et. al. Deep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification task”, European Journal of Cancer. 2019;113:47-54,
ISSN 0959-8049 Available:https://doi.org/10.1016/j.ejca.2019.04.001
Brinker, Titus, Hekler, Achim, Enk, Alexander, Klode, Joachim, Hauschild, Axel, Berking, Carola, Schilling, Bastian, Haferkamp, Sebastian, Utikal, Jochen, Kalle, Christof, Collaborators, Fröhling, Stefan, Weichenthal Michael. A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task. European Journal of Cancer. 2019;111: 148-154.
Sarker IH. Machine learning: Algorithms, real-world applications and research directions. SN Comput Sci. 2021;2(3):160.
DOI: 10.1007/s42979-021-00592-x. Epub 2021 Mar 22. PMID: 33778771; PMCID: PMC7983091.
Badreesh Shetty. Supervised machine learning classification: An in-depth guide. Built-In, 2022. Available:https://builtin.com/data-science/supervised-machine-learning-classification
Ada Parker. What is machine learning model training? Complete guide 2022. Machine Learning Pro; 2022.
Available:https://www.machinelearningpro.org/what-is-machine-learning-model-training/
Abdullah Alanazi. Using machine learning for healthcare challenges and opportunities. Informatics in Medicine Unlocked. 2022;30(100924). ISSN 2352-9148.
Available:https://doi.org/10.1016/j.imu.2022.100924.
Munnangi S, Boktor SW. Epidemiology of Study Design. In: Stat Pearls [Internet]. Treasure Island (FL): StatPearls Publishing; 2022.
PMID: 29262004
-
Abstract View: 0 times
PDF Download: 0 times