DOI:https://doi.org/10.15407/kvt192.02.061
Kibern. vyčisl. teh., 2018, Issue 2 (192), pp.
Buzynovsky А.B.1,
PhD student,
e-mail: arturdoc1983@ukr.net
Kovalenko A.S.1,
D.Sci. (Medicine), Professor,
Head of Medical Information Systems Department
e-mail: alexkovalenko@yandex.ua
Bayazitov N.R.2,
D.Sci. (Mdicine),
Professor at the Surgery Department
e-mail: ics_video@ukr.net
Godlevsky L.S.2,
D.Sci. (Medicine), Professor,
Chief of the Department of Biophysics, Informatics and Medical Devices
e-mail: godlevskyleonid@yahoo.com
1International Research and Training Center for Information Technologies
and Systems of the National Academy of Sciences of Ukraine
and Ministry of Education and Science of Ukraine,
Acad. Glushkova av., 40, Kiev, 03187, Ukraine
2Odessa National Medical University,
Valekhovsky Lane, 2, Odessa, 65082, Ukraine
THE EFFECTIVENESS OF SURGEON DECISION ON PAIN SYNDROME OF PELVIC ORIGIN TREATMENT IN WOMEN ESTIMATED WITH THE MODEL OF DECISION TREE
Introduction. The problem of correct diagnostics with the decision on the consequent adequate treatment of diseases which are causative for pelvic pain syndrome in women is actual for 15–24% women of fertile age.
The purpose of the work is to investigate the effectiveness of different methods of treatment women with pain syndrome originated from pelvis and lower part of abdomen on the basis of retrospective analysis of 1092 histories of diseases during 2013–2017 р.р.
Methods. Method of decision tree building up was used. The probability of different outcomes — restoration of health, recurrence of the disease along with the perioperative complications as well as duration of treatment in each case were taken into consideration as informative indices for decision tree composing. On the basis of mentioned data the index of effective period of treatment (EPT) was calculated. Period of observation was six months from the moment of disease diagnostics.
Results. It was established that the probability of complete health restoration was 0,83 after surgical treatment and 0,62 after drug treatment. In case of initial inefficiency of drug treatment the probability of restoration of health as a result of surgical intervention was 0,40. The EPT in surgically treated patients was less than EPT in patients with therapeutic treatment by 3,29 times at the moment of making decision on the method of treatment.
Conclusions. It was concluded that early decision on surgical intervention as a method of diagnostics and treatment was more effective when compared with the drug method of treatment women with pelvic pain syndrome. Dependence of the treatment effects upon perioperative complications serve as forecasting data for individual medical care delivered during postoperative period.
Keywords: tree of decision, undertaking of decision in surgery, pain syndrome, the effectiveness of treatment estimation.
REFERENCES
1 Lyashenko A.V., Bayazitov N.R., Godlevsky L.S. et al. Informational-technical system for automatized laparoscopic diagnostics. Radioelectronics, computer sciences and control. 2016. No 4. P. 90–96. (in Ukrainian).
2 Egorov A.A., Mikshina V.S. The models of surgeon decision. Letters on New Medical Technologies, 2011, Vol. 7, No4. P. 178–81. (in Russian)
3 Litvin A.A., Litvin V.A. Systems of decision support in surgery. News of Surgery, 2014. No 1. P. 96–100. (in Russian)
4 Kucey D.S. Decision analys is for the surgeon. World J.Surg, 1999. Vol. 23. P. 1227–1231. https://doi.org/10.1007/s002689900653
5 Sears E.D., Chung K.C. Decision analysis in plastic surgery: A Primer. PlastReconstrSurg. 2010. Vol. 126, N4. P. 1373–1380. https://doi.org/10.1097/PRS.0b013e3181ead10a
6 Ozerskaya I.A., Ageeva M.I. Chronic pelvic pain in women of fertile age. Ultrasonic diagnostics. Moscow 2009. 299 p. (in Russian)
7 Kiryanov B.F., Tokmachov M.S. Mathematical models in health care: text-book. Novgorod, 2009. 279 p. (in Russian)
8 Rudenko S.V., Romanenko M.V., Katunina O.G., Kolesnikova E.V. Markov models of patients state changes in projects of delivering medical service. Control of complicated systems development. 2012. No12. P. 86–89. (in Ukrainian)
9 Detsky A.S., Nagile G., Krahnetal M.D. Primer on medical decision analysis: Part 2. Building a tree. MedDecis Making. 1997. 7. P. 126–135. https://doi.org/10.1177/0272989X9701700202
10 Breiman L., Friedman J.H., Olshen R.A., Stone C.J. Classification and regression trees. Monterey, CA 1984. 368 p.
Reseived 12.10.2017