Investigating the Power of Artificial Intelligence Algorithms in Predicting Mortality Rates in Patients with Gastrointestinal Malignancies in ICU

Ariaiinezhad, Shiva; Mahdavi, Maryam; Kordestani Moghaddam, Parastou; Heidarizadeh, Khadijeh; Eskandarzadeh, Ahmad; Mohammadi, Rasool

doi:10.22087/ijac.2020.207430

Investigating the Power of Artificial Intelligence Algorithms in Predicting Mortality Rates in Patients with Gastrointestinal Malignancies in ICU

Document Type : Research

Authors

Shiva Ariaiinezhad ¹

Maryam Mahdavi ¹

Parastou Kordestani Moghaddam ²

Khadijeh Heidarizadeh ³

Ahmad Eskandarzadeh ⁴

Rasool Mohammadi ⁵

¹ Student Research Committee, School of Nursing and Midwifery, Lorestan University of Medical Sciences, Khorramabad, Iran

² Lorestan University of Medical Sciences Faculty of Khorramabad Nursing &Midwifery

³ Critical Care and Emergency Nursing Department, Lorestan University of Medical Sciences, Khorramabad, Iran.

⁴ Lorestan University of Medical Sciences, Khorramabad, Iran

⁵ Nutritional Health Research Center, School of Health and Nutrition, Lorestan University of Medical Sciences, Khorramabad, Iran

10.22087/ijac.2020.207430

Abstract

This study aimed to investigate the efficacy of artificial intelligence algorithms in predicting mortality among patients with gastrointestinal malignancie.. In this retrospective cohort study, all the files of patients with gastrointestinal malignancies hospitalized in the intensive care and surgery departments of Imam Khomeini Hospital in Ahvaz from 2013-2018 were reviewed, and 200 patients met the inclusion criteria. Data on laboratory test results, clinical information, and hospitalization outcomes in the intensive care unit was collected. The model was presented utilizing artificial intelligence, a genetic algorithm, and the nearest neighbor method. The artificial intelligence algorithm demonstrated a diagnostic accuracy of 90%, a specificity of 91.67%, and a sensitivity of 83.34% for mortality. The genetic algorithm assigned a high weight to the following variables: gastrointestinal cancer type and hematocrit (0.98), illness status upon admission to the intensive care unit (0.94), bicarbonate rate (0.87), background infection and body temperature (0.86), duration of hospitalization (0.84), and CRP (0.83). These variables were significant and influential in determining mortality. Genetic algorithms are highly effective in predicting the mortality of patients with gastrointestinal malignancies hospitalized in intensive care units.

Keywords

Gastrointestinal Malignancies, Artificial Intelligence Algorithms, Mortality Prediction

Intensive Care Unit

1. Wu C, Li M, Meng H, Liu Y, Niu W, Zhou Y, et al. Analysis of status and countermeasures of cancer incidence and mortality in China. Science China Life Sciences. 2019;62(5):640-7.
2. Shadmani FK, Farzadfar F, Yoosefi M, Mansori K, Shadman RK, Haghdoost A. Premature mortality of gastrointestinal cancer in Iran: trends and projections 2001–2030. BMC cancer. 2020;20(1):1-10.
3. Arnold M, Abnet CC, Neale RE, Vignat J, Giovannucci EL, McGlynn KA, et al. Global burden of 5 major types of gastrointestinal cancer. Gastroenterology. 2020;159(1):335-49.
4. Malekzadeh R, Semnani S, Sadjadi A. Esophageal Cancer in Iran A Review. Govaresh. 2008;13(1):25-34.
5. Biglu MH, Tabatabaei S. Gastrointestinal cancers in Iran: Iranian scientists’ approach to gastrointestinal cancers researches in international databases. Koomesh. 2017;19(1).
6. Parvareh M, Rezaei S, Roshani D, Ghaderi E, Nouri B. Assessment and prediction of incidence trend of stomach, colorectal and esophagus cancers using time-series models in Kurdistan, West of Iran. Scientific Journal of Kurdistan University of Medical Sciences. 2020;25(3):72-86.
7. Kingah P, Alzubaidi N, Yafawi JZD, Shehada E, Alshabani K, Soubani AO. Factors associated with mortality in patients with a solid malignancy admitted to the intensive care unit-a prospective observational study. The Journal of Critical Care Medicine. 2018;4(4):137.
8. Mousavi S. Evaluation of mortality rate with APACHE II scoring system in patients admitted to trauma ICU of Shahid Beheshti Hospital of Qom. Journal of Ilam University of Medical Sciences 2014, 22(2): 66-72
9. Gohari MR, Mokhtari P, Pourhoseingholi MA, Biglarian A. Artificial Neural Network in survival analysis of gastric cancer patients. Payesh (Health Monitor). 2014;13(3):285-91.
10. Biglarian A, Bakhshi E, Rahgozar M, Karimloo M. Comparison of artificial neural network and logistic regression in predicting of binary response for medical data:The stage of disease in gastric cancer. Journal of North Khorasan University of Medical Sciences. 2012;3(5):15-21.
11.Biglarian A, HajiZadeh E, Kazemnejad A. Comparison of artificial neural network and Cox regression models in survival prediction of gastric cancer patients. koomesh. 2010;11(3): e153802.
12. Biglarian A, Hajizadeh E, Kazemnejad A. Comparison of Artificial Neural Network and Parametric Regression Models in Survival Prediction of Patients with Gastric Cancer. Iranian Journal of Epidemiology 2010; 6 (3) :22-2713.
13. Niu P-H, Zhao L-L, Wu H-L, Zhao D-B, Chen Y-T. Artificial intelligence in gastric cancer: Application and future perspectives. World journal of gastroenterology. 2020;26(36):5408.
14. Sadeghi S, Golabpour A. An Algorithm for Predicting Recurrence of Breast Cancer Using Genetic Algorithm and Nearest Neighbor Algorithm. Journal of Health and Biomedical Informatics. 2020;6(4):309-19.
15. Charati JY, Janbabaei G, Alipour N, Mohammadi S, Gholiabad SG, Fendereski A. Survival prediction of gastric cancer patients by Artificial Neural Network model. Gastroenterology and hepatology from bed to bench. 2018 Spring;11(2):110-117
16. Emmert-Streib F, Yang Z, Feng H, Tripathi S, Dehmer M. An introductory review of deep learning for prediction models with big data. Frontiers in artificial intelligence. 2020 Feb 28;3:4.
17. Collins GS, Moons KG. Reporting of artificial intelligence prediction models. The Lancet. 2019 Apr 20;393(10181):1577-9.
18. Li Z, Keel S, He M. Can artificial intelligence make screening faster, more accurate, and more accessible?. Asia-Pacific Journal of Ophthalmology. 2018 Nov 1;7(6):436-41.
19. Sabouri S, Esmaily H, Shahid Sales S, Emadi M. Determining related factors to survival of colorectal cancer patients using cox regression. medical journal of Mashhad university of medical sciences. 2018;61(4):1083-92.
20. Carson SS, Garrett J, Hanson LC, Lanier J, Govert J, Brake MC, Landucci DL, Cox CE, Carey TS. A prognostic model for one-year mortality in patients requiring prolonged mechanical ventilation. Critical care medicine. 2008 Jul 1;36(7):2061-9.
21. Kruhlikava I, Kirkegård J, Mortensen F, Kjaer D. Impact of body mass index on complications and survival after surgery for esophageal and gastro-esophageal-junction cancer. Scandinavian Journal of Surgery. 2017;106(4):305-10.
22. Lee JH, Park B, Joo J, Kook M-C, Kim Y-I, Lee JY, et al. Body mass index and mortality in patients with gastric cancer: a large cohort study. Gastric Cancer. 2018;21(6):913-24.
23. Asgari P, Atashi A, Meraji M, Miri M. The Comparison of Selected Data-mining techniques in ICU Mortality Risk Prediction in Imam Hossein hospital. Journal of Modern Medical Information Sciences. 2019;5(2):59-67.
24. Mahmoodi SA, Mirzaie K, Mahmoodi SM. Determining the effective factors in the incidence of gastric cancer by using data mining approach. Payavard Salamat. 2017;11(3):332-41.
25. Das V, Boelle PY, Galbois A, Guidet B, Maury E, Carbonell N, Moreau R, Offenstadt G. Cirrhotic patients in the medical intensive care unit: early prognosis and long-term survival. Critical care medicine. 2010 Nov 1;38(11):2108-16.
26. Chang Junior J, Binuesa F, Caneo LF, Turquetto AL, Arita EC, Barbosa AC, Fernandes AM, Trindade EM, Jatene FB, Dossou PE, Jatene MB. Improving preoperative risk-of-death prediction in surgery congenital heart defects using artificial intelligence model: A pilot study. PLoS One. 2020 Sep 4;15(9):e0238199