Skip to main content

On the Importance of Empirical Contradiction for Reliability Estimation of Intelligent Data Analysis Results

Abstract

Some ways to apply intelligent data analysis (IDA) to improve the reliability of computer data analysis in medical diagnostics and decision making are discussed. The procedure of IDA results in constructive falsification (refutability and reliability checking) with respect to collected empirical data is proposed. The approach is illustrated by medical diagnostics and decision-making examples. The effectiveness and practical significance of the proposed approach is demonstrated by examples of diagnostics of human brain tumor pseudoprogression.

This is a preview of subscription content, access via your institution.

Notes

  1. 1.

    See, for example, situations with virus mutations etc.

  2. 2.

    Correct extrapolation capabilities in the sense interpolation-extrapolation schemes for computer data analysis (see above).

  3. 3.

    The currently widely used PET technology (positron emission tomography) in the diagnosis of piloid astrocytomas may not be indicative: the diagnosis of tumor necrosis (caused, for example, by impaired blood supply to the tumor due to certain targeted therapeutic interventions), which is not brought to the level of “standardized” protocols.

  4. 4.

    In formal algebra, these are fixed points of some Galois closure [23].

  5. 5.

    Included in the “architecture” of the IDA tools, that is, mathematical models, methods, and algorithms.

REFERENCES

  1. 1

    Popper, K., The Logic of Scientific Discovery, Hutchinson & Co, 1959.

    MATH  Google Scholar 

  2. 2

    Chen, Ch. and Li, R., Matematicheskaya logika i avtomaticheskoe dokazatel’stvo teorem (Mathematical Logic and Automatic Theorem Proving), Moscow: Nauka, 1983.

  3. 3

    Artif. Intell., 1980, vol. 13, nos. 1–2.

  4. 4

    Anshakov, O.M., Skvortsov, D.P., and Finn, V.K., Logical means of expert systems such as JSM, Semiotika Inf., 1986, no. 28, pp. 65–102.

  5. 5

    Finn, V.K., Intellekt, informatsionnoe obshchestvo, gumanitarnoe znanie i obrazovanie (Intelligence, Information Society, Humanitarian Knowledge, and Education), Moscow: LENAND, 2021.

  6. 6

    Finn, V.K., J.S. Mill’s inductive methods in artificial intelligence systems. Part I, Sci. Tech. Inf. Proc., 2010, vol. 38, pp. 385–402; Finn, V.K., J.S. Mill’s inductive methods in artificial intelligence systems. Part II, Sci. Tech. Inf. Proc., 2012, vol. 39, pp. 241–260.

    Article  Google Scholar 

  7. 7

    Vorontsov, K.V., Combinatorial theory of the reliability of training by precedents, Doctoral (Phys.-Math.) Dissertation, Moscow: Comput. Cent., Russ. Acad. Sci., 2010. https://www.dissercat.com/content/kombinatornaya-teoriya-nadezhnosti-obucheniya-po-pretsedentam.

    Google Scholar 

  8. 8

    Vinogradov, D.V., Probabilistic-combinatorial formal training method based on lattice theory, Doctoral (Phys.-Math.) Dissertation, Moscow: Fed. Res. Center “Comput. Sci. Control,” Russ. Acad. Sci., 2018. http://www.frccsc.ru/diss-council/00207305/diss/list/vinogradov_dv.

  9. 9

    Finn, V.K., Mikheenkova, M.A., and Zabezhailo, M.I., Why I’m not a Deep Learner, Trudy 16-i natsional’noi konferentsii po iskusstvennomu intellektu s mezhdunarodnym uchastiem—KII-18 (24–27 sentyabrya 2018 g., Moscva, Rossiya) (Proc. 16th Natl. Conf. on Artificial Intelligence with International Participation—KII-18 (September 24–27, 2018, Moscow, Russia)), Moscow: RKP, 2018, vol. 1, pp. 245–252.

  10. 10

    Landau, L.D., Fundamental problems, in Teoreticheskaya fizika 20 veka (Theoretical Physics of the 20th Century), Moscow: Inostr. Lit., 1962.

  11. 11

    Abrikosov, A.A., Akademik L.D. Landau (Academician L.D. Landau), Moscow: Nauka, 1965.

  12. 12

    Nudnov, N.V., Zheludkova, O.G., Mnatsakanova, I.V., Sidorova, E.V., Podoksenova, T.V., and Shevtsov, A.I., Pseudo-progression in a patient with anaplastic ependymoma after radiation therapy, Med. Vizualizatsiya, 2018, no. 2, pp. 18–24.

  13. 13

    Hygino da Cruz, L.C., Rodriguez, I., Domingues, R.C., Gasparetto, E.L., and Sorrensen, A.G., Pseudoprogression and pseudoresponse: Imaging challenges in the assessment of posttreatment glioma, Am. J. Neuroradiol., 2011, vol. 32, no. 11, pp. 1978–1985.

    Article  Google Scholar 

  14. 14

    Parvez, K., Parvez, A., and Zadeh, G., The diagnosis and treatment of pseudoprogression, radiation necrosis and brain tumor recurrence, Int. J. Mol. Sci., 2014, vol. 15, no. 7, pp. 11832–11846.

    Article  Google Scholar 

  15. 15

    Trunin, Yu.Yu., Golanov, A.V., Kostyuchenko, V.V., Galkin, M.V., Khukhlaeva, E.A., and Konovalov, A.N., Pseudo-progression of benign glioma on the example of piloid astrocytoma of the midbrain. Clinical observation, Onkol. Zh.: Luchevaya Diagn., Luchevaya Terap., 2018, vol. 1, no. 1, pp. 94–97.

    Google Scholar 

  16. 16

    Trunin, Yu.Yu., Golanov, A.V., Kostyuchenko, V.V., Galkin, M.V., Khukhlaeva, E.A., and Konovalov, A.N., Increased volume of piloid astrocytoma of the midbrain: Relapse or pseudo progression? Clinical observation, Onkol. Zh.: Opukholi Golovy Shei, 2016, vol. 6, no. 1, pp. 68–75.

    Google Scholar 

  17. 17

    Trunin, Y., Golanov, A.V., Kostjuchenko, V.V., Galkin, M.V., and Konovalov, A.N., Pilocytic astrocytoma enlargement following irradiation: Relapse or pseudoprogression?, Cureus, 2017. https://www.c-ureus.com/articles/3962-pilocytic-astrocytoma-enlargement-following-irradiation-relapse-or-pseudoprogression.

  18. 18

    Ellingson, B.M., Wen, P.Y., and Clouhesy, T.F., Modified criteria for radiographic response assessment in glioblastoma clinical trials, Neurotherapeutics, 2017, vol. 14, pp. 307–320.

    Article  Google Scholar 

  19. 19

    Zabezhailo, M.I. and Trunin, Yu.Yu., On the problem of medical diagnostic evidence: Intelligent analysis of empirical data on patients in samples of limited size, Autom. Doc. Math. Linguist., 2019, vol. 53, no. 6, pp. 322–328.

    Article  Google Scholar 

  20. 20

    Zabezhailo, M.I. and Trunin, Yu.Yu., On the problem of the reliability of medical diagnosis formed on the basis of empirical data, Iskusstv. Intellekt Prinyatie Reshenii, 2020, no. 4, pp. 3–13.

  21. 21

    Grusho, A.A., Zabezhailo, M.I., and Timonina, E.E., On the causal representativeness of training sets of precedents in problems of diagnostic type, Inf. Ee Primen., 2020, vol. 14, no. 1, pp. 80–86.

    Google Scholar 

  22. 22

    Zabezhailo, M.I., Some estimates of computational complexity when predicting the properties of new objects using characteristic functions, Autom. Doc. Math. Linguist., 2020, vol. 54, no. 6, pp. 298–305.

    Article  Google Scholar 

  23. 23

    Cohn, P.M., Universal Algebra, Harper & Row, 1965.

    MATH  Google Scholar 

  24. 24

    Zabezhailo, M.I., On the heritability of diagnostic conclusions when replenishing the training sample with new empirical data, Tezisy dokladov 13-i Mezhdunarodnoi konferentsii “Intellektualizatsiya obrabotki informatsii” IOI-2020 (Moscow, 8–11 dekabrya, 2020 g) (Abstracts of the 13th International Conference “Intellectualization of Information Processing” IOI-2020 (Moscow, December 8–11, 2020)), Moscow: Ross. Akad. Nauk, 2020, pp. 10–15.

  25. 25

    Zabezhailo, M.I., On the capacity of families of characteristic functions that ensure the correct solution of diagnostic problems, Iskusstv. Intell. Prinyatie Reshenii, 2021, no. 2, pp. 44–54. https://doi.org/10.14357/20718594210205

  26. 26

    Zabezhailo, M.I., Some capabilities of enumeration control in the JSM-method. Part one, Sci. Tech. Inf. Proc., 2014, vol. 41, pp. 335–347.

  27. 27

    Zabezhailo, M.I., Some capabilities of enumeration control in the JSM-method. Part two, Sci. Tech. Inf. Proc., 2014, vol. 41, pp. 348–361.

Download references

Author information

Affiliations

Authors

Corresponding authors

Correspondence to M. I. Zabezhailo or Yu. Yu. Trunin.

About this article

Verify currency and authenticity via CrossMark

Cite this article

Zabezhailo, M.I., Trunin, Y.Y. On the Importance of Empirical Contradiction for Reliability Estimation of Intelligent Data Analysis Results. Autom. Doc. Math. Linguist. 55, 94–100 (2021). https://doi.org/10.3103/S0005105521030092

Download citation

Keywords:

  • artificial intelligence
  • decision making
  • intelligent data analysis
  • reasoning automation
  • similarity analysis
  • medical diagnostics
  • pseudoprogression of human brain tumor