Журнал «Труды Института системного анализа Российской академии наук» - Blagosklonov N.A., Donitova V.V., Kireev D.A., Kobrinskii B.A., Smirnov I.V. Linguistic analysis of electronic health records for extraction of stroke risk factors

Identification and assessment of risk factors associated with diseases are necessary to increase the effectiveness of preventive measures. This problem is particularly important for such a socially significant disease as stroke. The use of automated methods for analyzing large arrays of electronic health records can increase the efficiency of extracting information about risk factors. This work presents one of these methods, that is based on using the constructed rules and a linguistic parser..

1. Putaala J., Metso A.J., Metso T.M., Konkola N., Kraemer Y., Haapaniemi E., Kaste M. and Tatlisumak T. 2009. Analysis of 1008 consecutive patients aged 15 to 49 with first-ever ischemic stroke the Helsinki young stroke registry. Stroke 40(4):1195–1203.doi: 10.1161/STROKEAHA.108.529883.

2. Tibaek M., Dehlendorff C., Jørgensen H.S., Forchhammer H.B., Johnsen S.P. and Kammersgaard L.P. 2016. Increasing incidence of hospitalization for stroke and transient ischemic attack in young adults: a registry‐based study. Journal of the American Heart Association 5(5):e003158. doi: 10.1161/JAHA.115.003158.

3. Zhang F-L., Guo Z-N., Wu Y-H., Liu H.-Y., Luo Y., Sun M.-S., Xing Y.-Q. and Yang Y. 2017. Prevalence of stroke and associated risk factors: a population based cross sectional study from northeast China. BMJ Open 7(9):e015758. doi: 10.1136/ bmjopen-2016-015758.

4. Cesario E., Congiusta A., Talia D. and Trunfio P. 2008. Data analysis services in the knowledge grid. In: W. Dubitzky, ed. Data Mining Techniques in Grid Computing Environments. John Wiley & Sons. pp.17–36. doi: 10.1002/9780470699904.ch2

5. Flah P. 2015. Mashinnoe obuchenie. Nauka i iskusstvo postroenija algoritmov, kotorye izvlekajut znanija iz dannyh [Machine learning. Science and art of building algorithms that extract knowledge from data]. Moscow: DMK Press. 400 p.

6. Shelmanov A., Liventsev V., Kireev D., Khromov N., Panchenko A., Fedulova I. and Dylov D.V. 2019. Active Learning with Deep Pre-trained Models for Sequence Tagging of Clinical and Biomedical Texts. IEEE International Conference on Bioinformatics and Biomedicine (BIBM). 482-489. doi: 10.1109/ BIBM47256.2019.8983157.

7. Li X., Feng J., Meng Y., Han Q., Wu F. and Li J. 2019. A Unified MRC Framework for Named Entity Recognition. 2019. Available at: https://arxiv.org/abs/1910.11476 (accessed May 26, 2020).

8. Dligach D., Bethard S., Becker L., Miller T. and Savova G.K. 2014. Discovering body site and severity modifiers in clinical texts. Journal of the American Medical Informatics Association 21(3):448‐454. doi: 10.1136/amiajnl-2013-001766.

9. Banerjee Ch. and Chimowitz M.I. 2017. Stroke Caused by Atherosclerosis of the Major Intracranial Arteries. Circulation Research 120(3):502–513. doi: 10.1161/CIRCRESAHA.116.308441.

10. Price A.J., Wright F.L., Green J., Balkwill A., Kan S.W., Yang T.O., Floud S., Kroll M.E., Simpson R., Sudlow C.L.M., Beral V. and Reeves G.K. 2018. Differences in risk factors for 3 types of stroke: UK prospective study and meta-analyses. Neurology 90(4):e298-e306. doi: 10.1212/ WNL.0000000000004856.

11. Murakami K., Asayama K., Satoh M., Inoue R., Tsubota-Utsugi M., Hosaka M., Matsuda A., Nomura K., Murakami T., Kikuya M., Metoki H., Imai Y. and Ohkubo T. 2017. Risk Factors for Stroke among Young-Old and Old-Old Community-Dwelling Adults in Japan: The Ohasama Study. Journal of Atherosclerosis and Thrombosis 24(3):290-300. doi: 10.5551/jat.35766.

12. Lewington S., Clarke R., Qizilbash N., Peto R. and Collins R. 2002. Age-specific relevance of usual blood pressure to vascular mortality: a metaanalysis of individual data for one million adults in 61 prospective studies. Lancet 360(9349):1903–1913. doi: 10.1016/S0140-6736(02)11911-8.

13. Kroll M.E., Green J., Beral V., Sudlow C.L., Brown A., Kirichek O., Price A., Yang T.O. and Reeves G.K. 2016. Adiposity and ischemic and hemorrhagic stroke. Neurology 87(14):1473–1481. doi: 10.1212/WNL.0000000000003171.

14. Vereshhagin N.V. 2001. Nedostatochnost’ krovoobrashhenija v vertebro-baziljarnoj sisteme [Circulatory failure in the vertebro-basilar system]. Consilium Medicum. Golovokruzhenie (Prilozhenie) [Consilium Medicum. Dizziness (Appendix)] 3(15):13-18.

15. Kadykov A.S., Manvelov L.S. and Shahparonova N.V. 2018. Hronicheskie sosudistye zabolevanija golovnogo mozga. Discirkuljatornaja encefalopatija. 4-e izd [Chronic vascular diseases of the brain. Encephalopathy. 4th ed.]. Moscow: GEOTAR-Media. 288 p.

16. Zhang Y., Bai L., Shi M., Lu H., Wu Y., Tu J., Ni J., Wang J., Cao L., Lei P. and Ning X. 2017. Features and risk factors of carotid atherosclerosis in a population with high stroke incidence in China. Oncotarget 8(34):57477–57488. doi: 10.18632/ oncotarget.15415.

17. Mitchell A.B., Cole J.W., McArdle P.F., Cheng, Y.-Ch., Ryan, K.A., Sparks, M.J., Mitchell, B.D. and Kittner, S.J. 2015. Obesity Increases Risk of Ischemic Stroke in Young Adults. Stroke 46(6):1690–1692. doi: 10.1161/ STROKEAHA.115.008940.

18. Smirnov I.V. and Shelmanov A.O. 2013. Semantikosintaksicheskij analiz estestvennyh jazykov. Chast’ I. Obzor metodov sintaksicheskogo i semanticheskogo analiza tekstov [Semanticsyntactic analysis of natural languages. Part I. A review of methods for semantic and syntactic analysis of text]. Iskusstvennyj intellekt i prinjatie reshenij [Artificial Intelligence and Decision Making] (1):41-54.

19. Шелманов А.О., Смирнов И.В., Вишнева Е.А. Извлечение информации из клинических текстов на русском языке // Компьютерная лингвистика и интеллектуальные технологии: По материалам ежегодной Международной конференции «Диалог» (Москва, 27–30 мая 2015 г.). 2015. №2. С. 560-572. Shelmanov, A.O., Smirnov, I.V. and Vishneva, E.A. 2015. Information extraction from clinical texts in russian. Computational Linguistics and Intellectual Technologies Papers from the Annual International Conference “Dialogue”. Volume 1 of 2:560-572.