The use of ridge regression for estimating the severity of acute pancreatitis

Purpose. Increasing of treatment efficiency for patients with acute pancreatitis by improving objective means of determining the severity of acute pancreatitis.

Materials and method. The study was based on a retrospective analysis of 130 cases of acute pancreatitis: 47 cases from «Krasnoyarsk Regional Clinical Hospital» and 83 cases from «Regional Interdistrict Clinical Hospital No 20 named after I.S. Berzon» in the period from 2015 to 2017. The raw data was pre-processed. In particular, different methods (median, linear regression) were used to fill the missing values in the observation matrix. The initial dataset contained features measured in various quantitative and categorical scales. For some features with a pronounced asymmetric distribution, a quantile transformation was applied to initial values. The quantile transformation allows features to be brought to a uniform distribution in order to reduce the risk of excluding significant features. Ridge regression was used in combination with an algorithm for sequential reduction of attribute space.

Results. The classifier of three degrees of acute pancreatitis severity was developed. This classifier can help to determine better treatment tactics. During validation, the method of determining the severity of acute pancreatitis classification has proven to be effective. The average accuracy was 92% compared to the experts’ decisions. This procedure for constructing a classifier can be used as part of the basis to the medical decision support system.

Conclusion. The results of this study will help to make the choice of a necessary starting therapy, assess the need for surgical intervention and in severe cases, prescribe enhanced antibacterial and detoxification therapy. This will predictably reduce the percentage of septic complications of acute pancreatitis, and consequently will reduce the frequency of fatal outcomes. 

1. Savel’ev V.S., Filimonov M.I., Burnevig S.Z. Acute pancreatitis. Epidemiology, prevention, classification. (in Russ.). URL: https://medbe.ru/materials/khirurgiya-podzheludochnoy-zhelezy/ostryy-pankreatit-epidemiologiya-profilaktika-klassifikatsiya/.

2. Kurti F., Shpata V., Kuqo A., Duni A., Roshi E., Basho J. Incidence of acute pancreatitis in Albanian population. Mater Sociomed. 2015; 27 (6): 376–369. DOI: 10.5455/msm.2015.27.376-379.

3. Munigala S., Yadav D. Case-fatality from acute pancreatitis is decreasing but its population mortality shows little change. Pancreatology. 2016; 16 (4): 542–550. DOI: 10.1016/j.pan.2016.04.008.

4. Karakayali F.Y. Surgical and interventional management of complications caused by acute pancreatitis. World J. Gastroenterol. 2014; 20 (37): 13412–13423. DOI: 10.3748/wjg.v20.i37.13412.

5. Borodin N.A., Mal’tseva O.V., Gibert B.K., Zaitsev E.Yu. Modern approaches in the treatment of destructive forms of pancreatitis, ways to reduce mortality. Medical Science and Education of the Urals. 2015; 16 (82): 70–73 (in Russ.).

6. Imaeva A.K., Mustafin T.I., Sharifgaliev I.A. Acute destructive pancreatitis. Siberian Medical Journal (Irkutsk). 2014; 131 (8): 14–20 (in Russ.).

7. Valeev A.A. Assessment of the severity of the patients with acute destructive pancreatitis in the selection of treatment. Kazan Medical Journal. 2013; 94 (5): 633–636 (in Russ.).

8. Rizaev K.S., Khadzhibaev F.A., Baimuradov Sh.E. Determination of acute pancreatitis severity and treatment: materials of the plenum of the board of the Association of hepatopancreatobiliary surgeons of the CIS countries. 2015: 123–125 (in Russ.).

9. Kuo D.C., Rider A.C., Estrada P., Kim D., Pillow M.T. Acute Pancreatitis: What’s the Score? J. Emerg. Med. 2015; 48 (6): 762–770. DOI: 10.1016/j.jemermed.2015.02.018.

10. Litvin A.A., Zharikov O.G., Kovalev V.A. Decision support system in predicting and diagnosing infected pancreatic necrosis. Information technologies for the Physician. 2012; 2: 54–63 (in Russ.).

11. Vinnik Yu.S., Dunaevskaya S.S., Antyufrieva D.A. Diagnostic value of integral scoring systems in assessing the severity of acute pancreatitis and patient’s condition. Annals of the Russian Academy of Medical Sciences. 2015; 70 (1): 90–94 (in Russ.).

12. Diagnosis and treatment of acute pancreatitis (Russian clinical guidelines). Russian Society of Surgeons, Hepato-Pancreato-Biliary Association of Commonwealth of Independent States, Russian Society of Emergency Medicine. 30.10.2014 (in Russ.).

13. Hoerl A.E., Kennard R.W. Ridge regression: Biased estimation for nonorthogonal problems Technometrics. 1970; 12 (1): 55–67.

14. Huang J., Ling C. X. Using AUC and accuracy in evaluating learning algorithms. IEEE Transactions on Knowledge and Data Engineering. 2005; 17 (3): 299–310.

15. Xu Q. S., Liang Y. Z. Monte Carlo cross validation. Chemometrics and Intelligent Laboratory Systems. 2001; 56 (1): 1–11.

16. Merill T., Green O. M. On the effectiveness of receptors in recognition systems. IEEE Trans. Inform. Theory. 1963; 9 (1): 11–17. DOI: 10.1109/TIT.1963.1057810.