- Physical Review Journals
All JournalsPhysics Magazine
Access Provided by Xinjiang University

Physical Review E

Export citation

Export citation

Choose format for download:

Download Citation
  • Access by Xinjiang University

Statistical physics of medical diagnostics: Study of a probabilistic model

Alireza Mashaghi1,2,* and Abolfazl Ramezanpour1,3

  • 1Leiden Academic Centre for Drug Research, Faculty of Mathematics and Natural Sciences, Leiden University, Leiden, The Netherlands
  • 2Harvard Medical School, Harvard University, Boston, Massachusetts, USA
  • 3Department of Physics, University of Neyshabur, Neyshabur, Iran

  • *Corresponding author: a.mashaghi.tabari@lacdr.leidenuniv.nl
PDF

Phys. Rev. E 97, 032118 – Published 16 March, 2018

DOI: https://doi.org/10.1103/PhysRevE.97.032118

Abstract

We study a diagnostic strategy which is based on the anticipation of the diagnostic process by simulation of the dynamical process starting from the initial findings. We show that such a strategy could result in more accurate diagnoses compared to a strategy that is solely based on the direct implications of the initial observations. We demonstrate this by employing the mean-field approximation of statistical physics to compute the posterior disease probabilities for a given subset of observed signs (symptoms) in a probabilistic model of signs and diseases. A Monte Carlo optimization algorithm is then used to maximize an objective function of the sequence of observations, which favors the more decisive observations resulting in more polarized disease probabilities. We see how the observed signs change the nature of the macroscopic (Gibbs) states of the sign and disease probability distributions. The structure of these macroscopic states in the configuration space of the variables affects the quality of any approximate inference algorithm (so the diagnostic performance) which tries to estimate the sign-disease marginal probabilities. In particular, we find that the simulation (or extrapolation) of the diagnostic process is helpful when the disease landscape is not trivial and the system undergoes a phase transition to an ordered phase.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (33)

  1. R. S. Ledley and L. B. Lusted, Reasoning foundations of medical diagnosis; symbolic logic, probability, and value theory aid our understanding of how physicians reason, Science 130, 9 (1959).
  2. R. A. Miller and A. Geissbuhler, Clinical Diagnostic Decision Support Systems–An Overview (Springer, New York, 1999), pp. 3–34.
  3. M. Papadakis, S. J. McPhee, and M. W. Rabow, Current Medical Diagnosis and Treatment, 55th ed., LANGE CURRENT Series (McGraw-Hill Education, New York, 2016).
  4. New Optimization Algorithms in Physics, edited by A. K. Hartmann and H. Rieger (John Wiley & Sons, New York, 2006).
  5. M. Mezard and A. Montanari, Information, Physics, and Computation (Oxford University Press, Oxford, 2009).
  6. D. J. Spielgelharter, Probabilistic expert systems in medicine, Stat. Sci. 2, 3 (1987).
  7. M. A. Shwe, B. Middleton, D. E. Heckerman, M. Henrion, E. J. Horvitz, H. P. Lehmann, and G. F. Cooper, Probabilistic diagnosis using a reformulation of the INTERNIST-1/QMR knowledge base. I. The probabilistic model and inference algorithms, Methods Inf. Med. 30, 241 (1991).
  8. D. E. Heckerman and E. H. Shortliffe, From certainty factors to belief networks, Artific. Intel. Med. 4, 35 (1992).
  9. R. A. Miller, Medical diagnostic decision support systems—past, present, and future: a threaded bibliography and commentary, J. Am. Med. Inform. Assoc. 1, 8 (1994).
  10. D. Nikovski, Constructing Bayesian networks for medical diagnosis from incomplete and partially correct statistics, IEEE Trans. Know. Data Eng. 12, 509 (2000).
  11. W. G. Baxt, Use of an artificial neural network for data analysis in clinical decision-making: the diagnosis of acute coronary occlusion, Neural Comput. 2480 (1990).
  12. M. G. Penedo et al., Computer-aided diagnosis: a neural-network-based approach to lung nodule detection, IEEE Trans. Med. Imag. 17, 872 (1998).
  13. J. Khan et al., Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks, Nat. Med. 7, 673 (2001).
  14. K. P. Murphy, Machine Learning: A Probabilistic Perspective (MIT Press, Cambridge, MA, 2012).
  15. K.-I. Goh et al., The human disease network, Proc. Natl. Acad. Sci. USA 104, 8685 (2007).
  16. A. L. Barabási, N. Gulbahce, and J. Loscalzo, Network medicine: a network-based approach to human disease, Nat. Rev. Genet. 12, 56 (2011).
  17. M. Gustafsson et al., Modules, networks and systems medicine for understanding disease and aiding diagnosis, Gen. Med. 6, 82 (2014).
  18. K. Sun et al., Predicting disease associations via biological network analysis, BMC Bioinf. 15, 304 (2014).
  19. W. Liu et al., Integrative analysis of human protein, function and disease networks, Sci. Rep. 5, 14344 (2015).
  20. A. Suratanee and K. Plaimas, DDA: A novel network-based scoring method to identify disease-disease associations, Bioinform. Biol. Insights 9, 175 (2015).
  21. G. F. Cooper, The computational complexity of probabilistic inference using Bayesian belief networks, Artif. Intell. 42, 393 (1990).
  22. M. I. Jordan, Graphical models, Stat. Sci. 19, 140 (2004).
  23. A. Ramezanpour and A. Mashaghi, Toward first principle medical diagnostics: On the importance of disease-disease and sign-sign interactions, Front. Phys. 5, 32 (2017).
  24. A. Ramezanpour and A. Mashaghi, Uncovering a hidden disease pattern by simulating the clinical diagnostic process, Sci. Rep. 8, 2436 (2018).
  25. Advanced Mean Field Methods: Theory and Practice, edited by M. Opper and S. David (MIT Press, Cambridge, MA, 2001).
  26. M. Mezard and A. Montanari, Reconstruction on trees and spin glass transition, J. Stat. Phys. 124, 1317 (2006).
  27. F. Krzakała et al., Gibbs states and the set of solutions of random constraint satisfaction problems, Proc. Natl. Acad. Sci. USA 104, 10318 (2007).
  28. H. J. Kappen and F. B. Rodriguez, Efficient learning in Boltzmann machines using linear response theory, Neural Comput. 10, 1137 (1998).
  29. T. Tanaka, Mean-field theory of Boltzmann machine learning, Phys. Rev. E 58, 2302 (1998).
  30. F. Ricci-Tersenghi, The Bethe approximation for solving the inverse Ising problem: a comparison with other inference methods, J. Stat. Mech.: Theory Exp. (2012) P08015.
  31. H. C. Nguyen, R. Zecchina, and J. Berg, Inverse statistical problems: from the inverse Ising problem to data science, Adv. Phys. 66, 197 (2017).
  32. J. R. Birge and F. Louveaux, Introduction to Stochastic Programming (Springer Science & Business Media, New York, 2011).
  33. F. Altarelli, A. Braunstein, A. Ramezanpour, and R. Zecchina, Stochastic Matching Problem, Phys. Rev. Lett. 106, 190601 (2011).

Outline

Information

Phys. Rev. E 97, 032118– Published 16 March, 2018
  • Received 13 November 2017
  • Revised 22 January 2018
Crossmark - Check for updates button

©2018 American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation