The experience of neural network prediction of the need for surgical treatment in patients with the diseases of hepatopancreatoduodenal zone

Abstract

Aim. Using multilayer perceptron artificial neural network, to develop a mathematical model for predicting the need for surgical intervention in patients admitted for hepatopancreatoduodenal zone diseases and to assess the capabilities for its clinical application.

Methods. The study was performed using the data of 488 patients with peptic ulcer, cholecystitis or pancreatitis, analyzed using multilayer perceptron artificial neural network, trained to distinguish vectors of data on risk factors of patients who did or did not require surgical intervention during current hospitalization.

Results. Patients in the training sample who had required surgical intervention during hospitalization were different from patients who had undergone conservative treatment by such characteristics as gender, age, duration of the disease, state on admission, and the structure of risk factors. The acquired data made it possible to train the artificial neural network. The ROC analysis of the mathematical model demonstrated the area under the curve (AUC) equal to 0.880 for the training group (n=385) and 0.739 for the clinical approbation group (n=103).

Conclusion. The AUC indicators of the created model can be characterized as very good in terms of predicting the need for surgical treatment in the training group and good for the clinical approbation group: sensitivity and specificity of the model exceed 80% in the training group and are highest in patients with peptic ulcer disease; in the clinical approbation group these parameters were lower as expected, however, remained at the level of 60-70%.

Keywords

artificial neural networks / prognosis / peptic ulcer disease / cholecystitis / pancreatitis / surgical treatment

References

[1] Ivanenko V.A., Zolotareva R.I. Preoperation examination as a cornerstone of safe surgical treatment. In: Meditsina katastrof: obuchenie, nauka i praktika. Sbornik materialov nauchno-prakticheskoy konferentsii. (Medicine of catastrophes: education, science and practice. Collection of proceedings of scientific and practical conference.) 2015; 143–144. (In Russ.)

[2] Иваненко В.А., Золотарёва Р.И. Предоперационное обследование - залог безопасного хирургического вмешательства. В книге: Медицина катастроф: обучение, наука и практика. Сборник материалов научно-практической конференции. 2015; 143-144.

[3] Korochanskaya N.V., Rogal’ M.L., Makarenko A.V., Murashko N.V. Pre-opera­tive preparation of patients with complicated chronic pancreatitis. Vestnik MUZ GB №2. 2013; (1): 1–8. (In Russ.)

[4] Корочанская Н.В., Рогаль М.Л., Макаренко А.В., Мурашко Н.В. Предоперационная подготовка у больных с осложнённым хроническим панкреатитом. Вестн. МУЗ ГБ №2. 2013; (1): 1-8.

[5] Konstantinova E.D., Varaksin A.N., Zhovner I.V. Identification of the main risk factors for non-infectious diseases: method of classification trees. Gigiena i sanitarija. 2013; (5): 69–72. (In Russ.)

[6] Константинова Е.Д., Вараксин А.Н., Жовнер И.В. Определение основных факторов риска развития неинфекционных заболеваний: метод деревьев классификации. Гигиена и санитария. 2013; (5): 69-72.

[7] Skvorcova V.I. Seven principles of moernization of healthcare. Voprosy ekonomiki i upravleniya dlya rukovoditeley zdravookhraneniya. 2010; (5): 7–14. (In Russ.)

[8] Скворцова В.И. Семь принципов модернизации здравоохранения. Вопр. экономики и управл. для руководителей здравоохр. 2010; (5): 7-14.

[9] Greenes R.A. Clinical decision support: the road ahead Amsterdam. Boston: Elsevier. 2007; 581 p.

[10] Chubukova I.A. Data Mining. Moscow: BINOM. Laboratoriya znaniy. 2008; 324 p. (In Russ.)

[11] Чубукова И.А. Data Mining. М.: БИНОМ. Лаборатория знаний. 2008; 324 с.

[12] Shchepin V.O., Rastorgueva T.I., Proklova T.N. Towards prospective directions of healthcare development in the Russian Federation. Byulleten’ Natsional’nogo nauchno-issledova­tel’skogo instituta obshhestvennogo zdorov’ya imeni N.A. Semashko. 2012; (1): 147–152. (In Russ.)

[13] Щепин В.О., Расторгуева Т.И., Проклова Т.Н. К вопросу о перспективных направлениях развития здравоохранения Российской Федерации. Бюлл. Нац. научно-исслед. ин-та общественного здоровья им. Н.А. Семашко. 2012; (1): 147-152.

[14] Mustafaev A.G. Use of artificial neural networks in early diagnosis of diabetes mellitus. Kibernetika i programmirovanie. 2016; (2): 1–7. (In Russ.)

[15] Мустафаев А.Г. Применение искусственных нейронных сетей для ранней диагностики заболевания сахарным диабетом. Кибернетика и программирование. 2016; (2): 1-7. DOI: 10.7256/2306-4196.2016.2.17904.

[16] Medvedev N.V., Lobyntseva E.M. The possibilities of neural network analysis to evaluate the prognosis of chronic heart failure in elderly. Vestnik novykh meditsinskikh tekhnologiy. 2015; 22 (1): 6–11. (In Russ.)

[17] Медведев Н.В., Лобынцева Е.М. Возможности нейросетевого анализа для оценки прогноза больных хронической сердечной недостаточностью старшего возраста. Вестн. новых мед. технол. 2015; 22 (1): 6-11. DOI: 10.12737/9067.

[18] Yasnitsky L.N., Dumler A.A., Poleshchuk A.N. et al. Artificial neural networks for obtaining new medical knowledge: Diagnostics and prediction of cardiovascular disease progression. Biol. Med. (Aligarh.) 2015; 7 (2): BM-095-15,8.

[19] Prezident Rossii. Zasedanie Soveta po nauke i obrazovaniyu. (President of Russia. Meeting of the Council for Science and Education.) http://kremlin.ru/events/president/news/56827 (access date: 15.02.2018). (In Russ.)

[20] Президент России. Заседание Совета по науке и образованию. http://kremlin.ru/events/president/news/56827 (дата обращения: 15.02.2018).

[21] Lazarenko V.A., Antonov A.E. Experience of the development of the software package for neural network diagnosis and prediction of diseases of hepatopancreatoduodenal zone. Vrach i informatsionnye tekhnologii. 2017; (4): 132–140. (In Russ.)

[22] Лазаренко В.А., Антонов А.Е. Опыт разработки программного комплекса для нейросетевой диагностики и прогнозирования заболеваний гепатопанкреатодуоденальной зоны. Врач и информ. технол. 2017; (4): 132-140.

[23] Lazarenko V.A., Antonov A.E. Evaluation of the quality of functioning of artificial neural network with logic outputs in the diagnosis of diseases of hepatopancreatoduodenal zone. Kazanskiy meditsinskiy zhurnal. 2017; 98 (6): 928–932. (In Russ.)

[24] Лазаренко В.А., Антонов А.Е. Оценка качества функционирования искусственных нейронных сетей c логическими выходами в диагностике заболеваний гепатопанкреатодуоденальной зоны. Казанский мед. ж. 2017; 98 (6): 928-932. DOI: 10.17750/KMJ2017-928.

[25] Lazarenko V.A., Antonov A.E., Prasolov A.V., Churilin M.I. Evaluating the efficiency of neural network prognosis of health quantitative indicators in patients with diseases of the hepatopancreatoduodenal zone. Yakutsliy meditsinskiy zhurnal. 2017; (3): 83–85. (In Russ.)

[26] Лазаренко В.А., Антонов А.Е., Прасолов А.В., Чурилин М.И. Оценка эффективности нейросетевого прогнозирования количественных показателей здоровья у пациентов с заболеваниями гепатопанкреатодуоденальной зоны. Якутский мед. ж. 2017; (3): 83-85.

[27] BaseGroup Labs. Tekhnologii analiza dannykh Logisticheskaya regressiya i ROC-analiz — matematicheskiy apparat. (Technologies of Data Mining. Logistic Regression and ROC-Analysis. Mathematical Apparatus.) https://basegroup.ru/community/articles/logistic (access date: 15.02.2018). (In Russ.)

[28] BaseGroup Labs. Технологии анализа данных Логистическая регрессия и ROC-анализ - математический аппарат. https://basegroup.ru/community/articles/logistic (дата обращения: 15.02.2018).

RIGHTS & PERMISSIONS

Lazarenko V.A., Zarubina T.V., Antonov A.E., Sood S.