An artifiсial intelligence computer system for differential diagnosis of lysosomal storage diseases

Aim. To improve the efficiency of diagnosis of hereditary lysosomal storage diseases using an intelligent computerbased decision support system.

Materials and methods. Descriptions of 35 clinical cases from the literature and depersonalized data of 52 patients from electronic health records were used as material for clinical testing of the computer diagnostic system. Knowledge engineering techniques have been used to extract, structure, and formalize knowledge from texts and experts. Literary sources included online databases and publications (in Russian and English). On this basis, for each clinical form of lysosomal diseases, textological cards were created, the information in which was corrected by experts. Then matrices were formed, including certainty factors (coefficients) for the manifestation, severity, and relevance of signs for each age group (up to 1 year, from 1 to 3 years inclusive, from 4 to 6 years inclusive, 7 years and older). The knowledge base of the expert system was implemented on the ontology network and included a disease model with reference variants of clinical forms. Decision making was carried out using production rules.

Results. The expert computer system was developed to support clinical decision-making at the pre-laboratory stage of differential diagnosis of lysosomal storage diseases. The result of its operation was a ranked list of hypotheses, reflecting the degree of their compliance with reference descriptions of clinical disease forms in the knowledge base. Clinical testing was carried out on cases from literary sources and patient data from electronic health records. The criterion for assessing the effectiveness of disease recognition was inclusion of the verified diagnosis in the list of five hypotheses generated by the system. Based on the testing results, the accuracy was 87.4%.

Conclusion. The expert system for the diagnosis of hereditary diseases has shown fairly high efficiency at the stage of compiling a differential diagnosis list at the pre-laboratory stage, which allows us to speak about the possibility of its use in clinical practice.

1. Platt F.M., d’Azzo A., Davidson B.L. et al. Lysosomal storage diseases. Nature Reviews Disease Primers. 2018;4(1):27. DOI: 10.1038/s41572-018-0025-4.

2. Goyal M., Gupta A. Lysosomal storage disorders: clinical, biochemical and molecular profile from Rare disease centre, India. Ann. Indian Acad. Neurol. 2021;24(5):686–692. DOI: 10.4103/aian.AIAN_1009_20.

3. Назаренко Л.П., Назаренко М.С. Особенности раннего проявления лизосомных болезней накопления. Медицинская генетика. 2013;12(9):20–24.

4. Carbajal-Rodríguez L.M., Pérez-García M., Rodríguez-Herrera R., Rosales H.S., Olaya-Vargas A. Long-term evolution of mucopolysaccharidosis type I in twins treated with enzyme replacement therapy plus hematopoietic stem cells transplantation. Heliyon. 2021;7(8):e07740. DOI: 10.1016/j.heliyon.2021.e07740.

5. Николаева Е.А., Семячкина А.Н. Современные возможности лечения наследственных заболеваний у детей. Российский вестник перинатологии и педиатрии. 2018;63(4):6– 14. DOI: 10.21508/1027–4065–2018–63–4–6–14.

6. Gabrielli O., Clarke L.A., Ficcadenti A., Santoro L., Zampini L., Volpi N., Coppa G.V. 12 year follow up of enzyme-replacement therapy in two siblings with attenuated mucopolysaccharidosis I: the important role of early treatment. BMC Medical Genetics. 2016;17:19. DOI: 10.1186/s12881-016-0284-4.

7. Mohammad S.S., Paget S.P., Dalre R.C. Current therapies and therapeutic decision making for childhood-onset movement disorders. Movement Disorders. 2019;34(5):637–656. DOI: 10.1002/mds.27661.

8. Colmenares-Bonilla D., Colin-Gonzalez Ch., Gonzalez-Segoviano A., Garcia E.E., Vela-Huerta M.M., Lopez-Gomez F.G. Diagnosis of mucopolysaccharidosis based on history and clinical features: evidence from the Bajio region of Mexico. Cureus. 2018;10(11):e3617. DOI: 10.7759/cureus.3617.

9. Kuiper G.-A., Meijer O.L.M., Langereis E.J., Wijburg F.A. Failure to shorten the diagnostic delay in two ultra-orphan diseases (mucopolysaccharidosis types I and III): potential causes and implications. Orphanet Journal of Rare Diseases. 2018;13(1):2. DOI: 10.1186/s13023-017-0733-y.

10. Кобринский Б.А. Компьютерная поддержка врачебных решений в педиатрии: регистр и диагностическая система по наследственным болезням. Вестник ВОИВТ. 1991;(1):20–25.

11. Gouvernet J., Caraboenf M., Ayme S. GENDIAG: A computer assisted facility in medical genetics based on belief functions. Methods of Information in Medicine. 1985;24(4):177–180.

12. Fryer A. POSSUM (pictures of standard syndromes and undiagnosed malformations). Journal of Medical Genetics. 1991;28(1):66–67. DOI: 10.1136/jmg.28.1.66-a.

13. Allanson J.E., Cunniff C., Hoyme H.E., McGaughran J., Muenke M., Neri G. Elements of morphology: standard terminology for the head and face. American Journal of Medical Genetics Part A. 2009;149A(1):6–28. DOI: 10.1002/ajmg.a.32612.

14. Ronicke S., Hirsch M.C., Türk E., Larionov K., Tientcheu D., Wagner A.D. Can a decision support system accelerate rare disease diagnosis? Evaluating the potential impact of Ada DX in a retrospective study. Orphanet Journal of Rare Diseases. 2019;14(1):69. DOI: 10.1186/s13023-019-1040-6.

15. Kobrinskii B.A., Demikova N.S., Blagosklonov N.A. Knowledge engineering in construction of expert systems on hereditary diseases. Artificial Intelligence. 16th Russian Conference, RCAI 2018, Moscow, Russia, September 24–27, 2018, Proceedings. 2018;934:35–45. DOI: 10.1007/978-3-030-00617-4_4.

16. Гаврилова Т.А., Кудрявцев Д.В., Муромцев Д.И. Инженерия знаний. Модели и методы. СПб: Лань, 2021:324.

17. Blagosklonov N.A., Kobrinskii B.A. Model of integral evaluation of expert knowledge for the diagnosis of lysosomal storage diseases. CEUR Workshop Proceedings. 2020; 2648:250–264.

18. Байдакова Г.В., Бобрынина В.О., Бочков Н.П., Воскобоева Е.Ю., Гинтер Е.К., Голихина Т.А. и др. Наследственные болезни: Национальное руководство: краткое издание. М.: ГЭОТАР-Медиа, 2017:464.