ISSN 2071-8594

Russian academy of sciences

Editor-in-Chief

Gennady Osipov

M. I. Zabezhailo, Y. Y. Trunin To the Reliability of Medical Diagnosis Based on Empirical Data

Abstract.

Some abilities to apply intelligent data analysis (IDA) tools to support medical diagnostic decision-making are discussed. There is described an original mathematical technique to identify and to delete artefacts of IDA and Machine Learning (e.g. overfitting, ets.) to be used in medical diagnostics. This IDA-scheme is based on the reasoning tools of the so called JSM-method of reasoning automation. Productivity of the proposed IDA-techniques demonstrated by examples of diagnostics of human brain tumor pseudoprogression.

Keywords:

artificial intelligence, decision-making, medical diagnostics, intelligent data analysis, reasoning automation, formalized similarity analysis, pseudoprogression of human brain tumor.

PP. 3-13.

DOI 10.14357/20718594200401

References

1. Fedoseev G. B. Vratchebnye oshibki: kharakter, pryitchiny, posledstviya i puty preodoleniya [Medical Errors: nature, reasons, consequences and recovering] // Terapiya [Therapy]. – 2018, №5. - P.109-115.
2. Zabezhailo M.I., Yrii Y., Trunin Y.O dokazatelnosty meditsinskogo diagnoza; intellectualnyi analiz empiritcheskikh dannykh o patsientakh v vyborkakh ogranitchennogo razmera [To the evidence of medical diagnosis: intelligent data analysis of limited size samples of describing patients empirical data]//Tsifrovoe zdravookhranenye: XX Kongress “Informatsionnye tekhnologii v medicine 2019 [Congress “Informational Technologies in Medicine – 2019”, Proc.], Moscow,М.: Консэф, 2019-P. 6-9. - https://itmcongress.ru/itm2019/proceedings/1.1.Zabezhailo_ITM2019.pdf
3. Zabezhailo M.I., TruninYu.Yu. On the Problem of Medical Diagnostic Evidence: Intelligent Analysis of Empirical Data on Patients in Samples of Limited Size // Automatic Documentation and Mathematical Linguistics. – 2019. – Vol. 53. – No. 6. – Pp. 322–328.
4. Zabezhailo M.I. To the complexity of characteristic function sets providing correct diagnostic solutions // 19 Vserossyiskaya Konferentsya “Matematicheskye metody raspoznavanya obrazov (MMRO-2019)” [Mathematical Methods in Pattern Recognition (MMPR-2019)], Moscow, Oct.25-28, 2019. – P/305-306.
5. Zabezhailo M. Ob otsenkakh razmerov semeystv kharakteristitcheskikh funktsyi, obespetchivayuschikh korrektnoe reshenie zadatch duagnostitcheskogo tipa [On the Complexity of Characteristic Function Sets Providing Correct Solutions for Diagnostic Type Tasks]// Comp. Math. and Math. Phys. – 2021. –V61, №5.
6. Zabezhailo M. O nekotorukh otsenkakh slozhnosty vytchislenyi pri prognozirovanii svoistv novikh ob’ektov sredstvami kharakteristitcheskikh funktsyi [On the Computational Complexity of Diagnostic Predictions Designed by Means of Characteristic Functions] //NTI, Ser.2.- 2020.-№12.
7. Grusho A., Zabezhailo M., Timonina E. O kauzalnoy representativnosty obutchayuschikh viborok pretsedentov v zadatchakh diagnostitcheskogo tipa [On Causal Representativeness of Training Samples of Precedents in Diagnostic Type Tasks] // Informatics and Applications. – V.14, №1, 2020. – P.80-86
8. Vorontsov K.V. Kombinatornaya teoryia nadezhnosty obitchenyia po pretsedentam [Combinatorial theory of learning by precedents] // D.Sc. Thesis (05.13.17 – Theoretical computer science). – M: CC RAS, 2010. – 273 P. - URL: https://www.dissercat.com/content/kombinatornaya-teoriya-nadezhnosti-obucheniya-po-pretsedentam
9. Vinogradov D.V. Veroyatnostno-kombinatornyi metod obutchenya, osnovannyi na teoryy reshotok [Probabilistic-combinatorial formal method of learning based on lattice theory] // D.Sc. Thesis (05.13.17 – Theoretical computer science).–М.:FRCCSC RAS, 2018. – 131 P. – URL: http://www.frccsc.ru/diss-council/00207305/diss/list/vinogradov_dv
10. Finn V.K. J.S. Mill’s inductive methods in artificial intelligence systems //Sci. Tech. Inf. Process. - Part I:2011, V. 38, pp. 385–402. PartII: 2012, V. 39, pp. 241–260.
11. Landau L.D. Fundamentalnue problemy [Fundamental problems] // In: Smorodinsky Ya.A. “Teoretitcheskaya fizika XX veka” [“Theoretical Physics of XX-th Century”] — М., 1962. - 443 P. - P.285-291.
12. Abrikosov A.A. Akadimik L.D.Landau [Academician L.D.Landau]. — М. – 1965. – 48 P.
13. Zabezhailo M.I. Some capabilities of enumeration control in the DSM method // Scientific and Technical Information Processing. -Part I: 2014, V.41, № 6, pp. 335-347. Part II: 2014, V.41, № 6, pp. 348-361.