Algorithm of minimally invasive surgical treatment option choice at patients with degenerative disease of lumbar spine based on current methods of mathematic database mining analysis

Objective: to obtain an algorithm to choose the method of minimally invasive treatment of degenerative diseases of the lumbar spine based on modern mathematical methods of data mining. Material and methods: The current minimally invasive surgical treatment of degenerative diseases of the lumbar spine includes microsurgery, endoscopy, puncture technique. Its success depends primarily on the choice of an appropriate method of intervention. An analysis of existing clinical data and the adoption of a decision depends on the personal experience of the surgeon and is a heuristic, intuitive operation. It is difficult for both reproduction and learning, as well as for third-party evaluation. Modern methods of predictive mathematical analysis were applied for reliable and efficient algorithm for selecting the form of surgical treatment. They included an analysis based on the algorithm of neural networks and decision tree algorithm. Choice of treatment was carried out between the laser percutaneous disc reconstruction, percutaneous hydrodiscectomy, transforaminal endoscopic discectomy, interlaminar endoscopic discectomy, lumbar microdiscectomy, lumbar microsurgical decompression, as well as combinations of these methods in the cohort of 80 patients with degenerative lesions of the lumbar spine. Estimated symptoms included clinical signs and morphological data on the basis of MRI. Results: an algorithm for selecting a minimally invasive method of surgery for the treatment of lumbar degenerative disease was obtained on the basis of modern predictive methods of mathematical analysis (Data Mining). Conclusion: the modern methods of mathematical analysis of clinical data (Data Mining) enable us to obtain efficient algorithms for selection of minimally invasive surgical treatment of degenerative disease of the lumbar spine. It is important to improve the effectiveness of treatment, the implementation of teaching and learning tasks, as well as for peer review and development of standards of care.

минимально-инвазивная спинальная хирургия, дегенеративная болезнь поясничного отдела позвоночника, интеллектуальный анализ данных, minimally invasive spine surgery, degenerative lumbar spine disease, Data Mining

1. Барсегян A.A., Куприянов М.С., Холод И.И. и др. Григорий Пятецкий-Шапиро, Data Mining и перегрузка информацией // Вступительная статья к книге // Анализ данных и процессов. З-е изд. перераб. и доп. СПб.: БХВ-Петербург, 2009. 512 C. C.13.

2. Борщенко И.А., Мигачев С.Л., Басков А.В. и др. Универсальная эндоскопическая чрезкожная поясничная дискэктомия: объединение заднебокового и междужкового доступа. Опыт использования. // Материалы съезда. 2009. C. 86-87.

3. Agatonovic-Kustrin S., Beresford R. Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research // J Pharm Biomed Anal. 2000. Vol. 22, № 5. P. 717-727.

4. Aleem I.S. et al. Transcatheter device versus surgical closure of ventricular septal defects: a clinical decision analysis // Catheter Cardiovasc Interv. 2006. Vol. 67, № 4. P. 630-636.

5. Bokov A. et al. Differential treatment of nerve root compression pain caused by lumbar disc herniation applying nucleoplasty // Pain Physician. 2010. Vol. 13, № 5. P. 469-480.

6. Carragee E.J. et al. Clinical outcomes after lumbar discectomy for sciatica: the effects of fragment type and anular competence // J Bone Joint Surg Am. 2003. Vol. 85-A, № 1. P. 102-108.

7. Castro W.H. et al. Restriction of indication for automated percutaneous lumbar discectomy based on computed tomographic discography // Spine. 1992. Vol. 17, № 10. P. 1239-1243.

8. Cohen S.P. et al. Nucleoplasty with or without intradiscal electrothermal therapy (IDET) as a treatment for lumbar herniated disc // J Spinal Disord Tech. 2005. Vol. 18 Suppl. P. S119-124.

9. Etchells E., O’Neill C., Bernstein M. Patient safety in surgery: error detection and prevention // World J Surg. 2003. Vol. 27, № 8. P. 936-941; discussion 941-942.

10. Fabri P.J., Zayas-Castro J.L. Human error, not communication and systems, underlies surgical complications // Surgery. 2008. Vol. 144, № 4. P. 557-563; discussion 563-565.

11. Gardino S.L., Jeruss J.S., Woodruff T.K. Using decision trees to enhance interdisciplinary team work: the case of oncofertility // J. Assist. Reprod. Genet. 2010. Vol. 27, № 5. P. 227-231.

12. Graham B., Detsky A.S. The application of decision analysis to the surgical treatment of early osteoarthritis of the wrist // J Bone Joint Surg Br. 2001. Vol. 83, № 5. P. 650-654.

13. Hirsch J.A. et al. Automated percutaneous lumbar discectomy for the contained herniated lumbar disc: a systematic assessment of evidence // Pain Physician. 2009. Vol. 12, № 3. P. 601-620.

14. Iavindrasana J. et al. Clinical data mining: a review // Yearb Med Inform. 2009. P. 121-133.

15. Krahn M.D. et al. Screening for prostate cancer. A decision analytic view // JAMA. 1994. Vol. 272, № 10. P. 773-780.

16. Mira J.J. et al. Perceptions of clinical safety after hospital discharge // Med Clin (Barc). 2008. Vol. 131 Suppl 3. P. 26-32.

17. Mirzai H. et al. The results of nucleoplasty in patients with lumbar herniated disc: a prospective clinical study of 52 consecutive patients // Spine J. 2007. Vol. 7, № 1. P. 88-92; discussion 92-93.

18. Moon C.T., Cho J., Chang S.K. Availability of discographic computed tomography in automated percutaneous lumbar discectomy // J. Korean Med. Sci. 1995. Vol. 10, № 5. P. 368-372.

19. Rosenberg W.M., Sackett D.L. On the need for evidence-based medicine // Therapie. 1996. Vol. 51, № 3. P. 212217.

20. Sackett D.L. Evidence-based medicine // Spine. 1998. Vol. 23, № 10. P. 1085-1086.

21. Savits. M.H., Chiu J.C., Rauschning W., Yeung E.T. The practice of minimally invasive spinal techniqie. AAMISS PRESS, New City. New York, 2005.

22. Traeger M. et al. Artificial neural networks. Theory and applications in anesthesia, intensive care and emergency medicine // Anaesthesist. 2003. Vol. 52, № 11. P. 1055-1061.

23. Trujillano J., March J., Sorribas A. Methodological approach to the use of artificial neural networks for predicting results in medicine // Med Clin (Barc). 2004. Vol. 122 Suppl 1. P. 59-67.