Skip to main content

A hybrid machine learning framework to predict mortality in paralytic ileus patients using electronic health records (EHRs)

A Correction to this article was published on 08 September 2020

This article has been updated

Abstract

Paralytic ileus (PI) is the pseudo-obstruction of the intestine secondary to intestinal muscle paralysis. Causes of PI include electrolyte imbalances, gastroenteritis (inflammation or infection of the stomach or intestines), overuse of medications, abdominal surgery, etc. Predicting mortality in PI patients hospitalized to ICU is crucial for assessing the severity of illness and adjudicating the value of treatment strategy and resource planning. We have developed a Statistically Robust Machine Learning based Mortality Prediction framework namely SRML-MortalityPredictor that could potentially help intensivists, surgeons, and other medical professionals to carefully plan treatment strategies for critically ill PI patients. We used MIMIC III v1.4, a publicly available ICU database to extract patients data (with age > 18 years old) admitted to the ICU with paralytic ileus (PI) as their primary illness. At phase 1, the SRML-MortalityPredictor framework uses univariate statistical analysis to filter out those risk factors which are not associated with the label of the data. Subsequently, it uses the risk survival statistical methods such as cox-regression and Kaplan–Meier survival analyses. The cox-regression analysis provides the hazard ratio about the potential PI risk factors that later used in conjunction with the Kaplan–Meier analysis to generate a rank order list (highest to lowest risk factors). At phase 2, we used several machine learning classification approaches such as linear discriminant analysis (LDA), Gaussian naive bayes (GNB), decision tree (DT) model, k-nearest neighbor (KNN), and support vector machine (SVM) to find the one with highest predictive power using the rank order features extracted at phase 1. We have evaluated the SRML-MortalityPredictor framework and recorded the accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curves, and area under the curve (AUC) scores for each model. The SRML-MortalityPredictor framework with support vector machine (using RBF kernel) showed better performance and yielded an accuracy score: 81.30% and AUC score: 81.38% while predicting mortality in PI patients. We demonstrated a feasible framework for the mortality risk prediction in PI patients admitted to the ICU. The proposed framework could potentially be helpful for intensivists in clinical decision making. Further research is necessary to incorporate more risk factors associated with PI patients to ensure the adaptability of SRML-MortalityPredictor at the bedside.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Change history

References

  1. Ali L, Bukhari S (2020) An approach based on mutually informed neural networks to optimize the generalization capabilities of decision support systems developed for heart failure prediction. IRBM https://doi.org/10.1016/j.irbm.2020.04.003, http://www.sciencedirect.com/science/article/pii/S1959031820300828

  2. Ali L, Khan SU, Golilarz NA, Yakubu I, Qasim I, Noor A, Nour R (2019a) A feature-driven decision support system for heart failure prediction based on statistical model and Gaussian naive bayes. Computational and Mathematical Methods in Medicine, 2019

  3. Ali L, Niamat A, Golilarz NA, Ali A, Xingzhong X (2019b) An expert system based on optimized stacked support vector machines for effective diagnosis of heart disease. IEEE Access

  4. Ali L, Niamat A, Khan JA, Golilarz NA, Xingzhong X, Noor A, Nour R, Bukhari SAC (2019c) An optimized stacked support vector machines based expert system for the effective prediction of heart failure. IEEE Access 7:54007–54014

    Article  Google Scholar 

  5. Ali L, Wajahat I, Golilarz NA, Keshtkar F, Bukhari SAC (2020) Lda–ga–svm: improved hepatocellular carcinoma prediction through dimensionality reduction and genetically optimized support vector machine. Neural Comput Appl, pp. 1–10

  6. Amiri Golilarz N, Gao H, Kumar R, Ali L, Fu Y, Li C (2020) Adaptive wavelet based MRI brain image de-noising. Front Neurosci 14:728

    Article  Google Scholar 

  7. Arihan O, Wernly B, Lichtenauer M, Franz M, Kabisch B, Muessig J, Masyuk M, Lauten A, Schulze PC, Hoppe UC, et al (2018) Blood urea nitrogen (bun) is independently associated with mortality in critically ill patients admitted to ICU. PLoS One 13(1)

  8. Balasubramanian K, Ananthamoorthy N (2019) Robust retinal blood vessel segmentation using convolutional neural network and support vector machine. J Ambient Intell Human Comput, pp. 1–11

  9. Bode WE, Beart RW Jr, Spencer RJ, Cuip CE, Wolff BG, Taylor BM (1984) Colonoscopic decompression for acute pseueteobstruction of the colon (ogilvie’s syndrome): report of 22 cases and review of the literature. Am J Surg 147(2):243–245

    Article  Google Scholar 

  10. Bukhari AC, Kim YG (2012) Integration of a secure type-2 fuzzy ontology with a multi-agent platform: a proposal to automate the personalized flight ticket booking domain. Inf Sci 198:24–47

    Article  Google Scholar 

  11. Bukhari AC, Kim YG (2013) A research on an intelligent multipurpose fuzzy semantic enhanced 3d virtual reality simulator for complex maritime missions. Appl Intell 38(2):193–209

    Article  Google Scholar 

  12. Bukhari AC, Tusseyeva I, Kim YG et al (2013) An intelligent real-time multi-vessel collision risk assessment system from vts view point based on fuzzy inference system. Expert Syst Appl 40(4):1220–1230

    Article  Google Scholar 

  13. Carley ME, Bosquet JG, Stanhope CR (2003) Small bowel obstruction associated with post-hysterectomy vaginal vault prolapse. Obstet Gynecol 102(3):524–526

    Google Scholar 

  14. Chicharro D, Panzeri S (2017) Synergy and redundancy in dual decompositions of mutual information gain and information loss. Entropy 19(2):71

    MathSciNet  Article  Google Scholar 

  15. Chudzinski AP, Thompson EV, Ayscue JM (2015) Acute colonic pseudoobstruction. Clin Colon Rectal Surg 28(02):112–117

    Article  Google Scholar 

  16. Conklin JL, Anuras S (1981) Radiation-induced recurrent intestinal pseudo-obstruction. Am J Gastroenterol 75(6)

  17. Cover T, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theory 13(1):21–27

    Article  Google Scholar 

  18. Cox DR (1972) Regression models and life-tables. J R Stat Soc: Ser B (Methodol) 34(2):187–202

    MathSciNet  MATH  Google Scholar 

  19. De Giorgio R, Barbara G, Stanghellini V, Tonini M, Vasina V, Cola B, Corinaldesi R, Biagi G, De Ponti F (2001) The pharmacological treatment of acute colonic pseudo-obstruction. Aliment Pharmacol Ther 15(11):1717–1727

    Article  Google Scholar 

  20. Dudley H, Paterson-Brown S (1986) Pseudo-obstruction. Br Med J (Clin Res Ed) 292(6529):1157

    Article  Google Scholar 

  21. Giraldo BF, Rodriguez J, Caminal P, Bayés-Genís A, Voss A (2015) Cardiorespiratory and cardiovascular interactions in cardiomyopathy patients using joint symbolic dynamic analysis. In: 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, pp. 306–309

  22. Golilarz NA, Addeh A, Gao H, Ali L, Roshandeh AM, Munir HM, Khan RU (2019) A new automatic method for control chart patterns recognition based on convnet and harris hawks meta heuristic optimization algorithm. IEEE Access 7:149398–149405

    Article  Google Scholar 

  23. Hannon B, Zimmermann C, Bryson JR (2013) The role of fentanyl in refractory opioid-related acute colonic pseudo-obstruction. J Pain Symptom Manag 45(3):e1–e3

    Article  Google Scholar 

  24. Hiesmayr M, Schindler K, Pernicka E, Schuh C, Schoeniger-Hekele A, Bauer P, Laviano A, Lovell A, Mouhieddine M, Schuetz T et al (2009) Decreased food intake is a risk factor for mortality in hospitalised patients: the nutrition day survey 2006. Clin Nutr 28(5):484–491

    Article  Google Scholar 

  25. Ho R (2017) Understanding statistics for the social sciences with IBM SPSS. CRC Press, Boca Raton

    Book  Google Scholar 

  26. Iida H, Ohkubo H, Inamori M, Nakajima A, Sato H (2013) Epidemiology and clinical experience of chronic intestinal pseudo-obstruction in Japan: a nationwide epidemiologic survey. J Epidemiol 23(4):288–294

    Article  Google Scholar 

  27. Iyer S, Saunders WB, Stemkowski S (2009) Economic burden of postoperative ileus associated with colectomy in the United States. J Manag Care Pharm 15(6):485–494

    Article  Google Scholar 

  28. Izumi Y, Masuda T, Horimasu Y, Nakashima T, Miyamoto S, Iwamoto H, Fujitaka K, Hamada H, Hattori N (2017) Chronic intestinal pseudo-obstruction and orthostatic hypotension associated with small cell lung cancer that improved with tumor reduction after chemoradiotherapy. Intern Med 56(19):2627–2631

    Article  Google Scholar 

  29. Johnson AE, Pollard TJ, Shen L, Li-wei HL, Feng M, Ghassemi M, Moody B, Szolovits P, Celi LA, Mark RG (2016) Mimic-III, a freely accessible critical care database. Sci Data 3:160035

    Article  Google Scholar 

  30. Kang HR, Lee SN, Cho YJ, Jeon JS, Noh H, Han DC, Park S, Kwon SH (2017) A decrease in serum creatinine after ICU admission is associated with increased mortality. PloS one 12(8)

  31. Kaplan EL, Meier P (1958) Nonparametric estimation from incomplete observations. J Am Stat Assoc 53(282):457–481

    MathSciNet  Article  Google Scholar 

  32. Khan SU, Rahim M, Ali L (2018) Correction of array failure using grey wolf optimizer hybridized with an interior point algorithm. Front Inf Technol Electron Eng 19(9):1191–1202

    Article  Google Scholar 

  33. Libório AB, Noritomi DT, Leite TT, de Melo Bezerra CT, de Faria ER, Kellum JA (2015) Increased serum bicarbonate in critically ill patients: a retrospective analysis. Intensive Care Med 41(3):479–486

    Article  Google Scholar 

  34. Lokhandwala S, McCague N, Chahin A, Escobar B, Feng M, Ghassemi MM, Stone DJ, Celi LA (2018) One-year mortality after recovery from critical illness: a retrospective cohort study. PloS one 13(5)

  35. Lu W, Xiao Y, Huang J, Lu L, Tao Y, Yan W, Cao Y, Cai W (2018) Causes and prognosis of chronic intestinal pseudo-obstruction in 48 subjects: a 10-year retrospective case series. Medicine 97(36)

  36. Mafarja M, Aljarah I, Heidari AA, Hammouri AI, Faris H, Ala’M AZ, Mirjalili S (2018) Evolutionary population dynamics and grasshopper optimization approaches for feature selection problems. Knowl-Based Syst 145:25–45

    Article  Google Scholar 

  37. McCallum A, Nigam K, et al. (1998) A comparison of event models for naive bayes text classification. In: AAAI-98 workshop on learning for text categorization, Citeseer, 752: 41–48

  38. McEvoy MT, Shander A (2013) Anemia, bleeding, and blood transfusion in the intensive care unit: causes, risks, costs, and new strategies. Am J Crit Care 22(6):eS1–eS13

    Article  Google Scholar 

  39. Meraj T, Hassan A, Zahoor S, Rauf HT, Lali MI, Ali B Liaqat, Chan SA, Shoaib U (2020) Lungs nodule detection using semantic segmentation and classification with optimal features. Neural Comput Applhttps://doi.org/10.1007/s00521-020-04870-2, https://link.springer.com/article/10.1007/s00521-020-04870-2

  40. Mi ZS, Bukhari AC, Kim YG (2014) An obstacle recognizing mechanism for autonomous underwater vehicles powered by fuzzy domain ontology and support vector machine. Mathematical Problems in Engineering 2014

  41. Nanni C, Garbini A, Luchetti P, Nanni G, Ronconi P, Castagneto M (1982) Ogilvie’s syndrome (acute colonic pseudo-obstruction). Dis Colon Rectum 25(2):157–166

    Article  Google Scholar 

  42. Oh YK (2010) Acid–base disorders in ICU patients. Electrolytes Blood Press 8(2):66–71

    Article  Google Scholar 

  43. Oh DJ, Yang JN, Lim YJ, Kang JH, Park JH, Kim MY (2015) Intestinal pseudo-obstruction as an initial manifestation of systemic lupus erythematosus. Intest Res 13(3):282

    Article  Google Scholar 

  44. Panganamamula KV, Parkman HP (2005) Chronic intestinal pseudo-obstruction. Curr Treatment Options Gastroenterol 8(1):3–11

    Article  Google Scholar 

  45. Ross SM (2014) Introduction to probability and statistics for engineers and scientists. Academic Press, Cambridge

    MATH  Google Scholar 

  46. Sowmiya C, Sumitra P (2020) A hybrid approach for mortality prediction for heart patients using aco-hknn. J Ambient Intell Human Comput

  47. Stanghellini V, Cogliandro R, De Giorgio R, Barbara G, Salvioli B, Corinaldesi R (2007) Chronic intestinal pseudo-obstruction: manifestations, natural history and management. Neurogastroenterol Motili 19(6):440–452

    Article  Google Scholar 

  48. Sutton DH, Harrell SP, Wo JM (2006) Diagnosis and management of adult patients with chronic intestinal pseudoobstruction. Nutr Clin Pract 21(1):16–22

    Article  Google Scholar 

  49. Tateno F, Sakakibara R, Kishi M, Ogawa E, Yoshimatsu Y, Takada N, Suzuki Y, Mouri T, Uchiyama T, Yamamoto T (2011) Incidence of emergency intestinal pseudo-obstruction in Parkinson’s disease. J Am Geriatr Soc 59(12):2373–2375

    Article  Google Scholar 

  50. Tzanos G, Kachris C, Soudris D (2019) Hardware acceleration on gaussian naive bayes machine learning algorithm. In: 2019 8th International Conference on Modern Circuits and Systems Technologies (MOCAST), IEEE, pp. 1–5

  51. Valenzuela A, Li S, Becker L, Fernandez-Becker N, Khanna D, Nguyen L, Chung L (2016) Intestinal pseudo-obstruction in patients with systemic sclerosis: an analysis of the nationwide inpatient sample. Rheumatology 55(4):654–658

    Article  Google Scholar 

  52. Wang C, Cao L, Miao B (2013) Optimal feature selection for sparse linear discriminant analysis and its applications in gene expression data. Comput Stat Data Anal 66:140–149

    MathSciNet  Article  Google Scholar 

  53. Yeh TL, Hwang LC, Chang WH (2009) Successful treatment of acute colonic pseudo-obstruction in an elderly patient. Int J Gerontol 3(3):181–184

    Article  Google Scholar 

  54. Zeng X, Liao Y, Liu Y, Zou Q (2016) Prediction and validation of disease genes using hetesim scores. IEEE/ACM Trans Comput Biol Bioinform 14(3):687–695

    Article  Google Scholar 

  55. Zhai R, Sheu CC, Su L, Gong MN, Tejera P, Chen F, Wang Z, Convery M, Thompson B, Christiani DC (2009) Serum bilirubin levels on ICU admission are associated with ards development and mortality in sepsis. Thorax 64(9):784–790

    Article  Google Scholar 

  56. Zhu P, Hu Q, Hu Q, Zhang C, Feng Z (2018) Multi-view label embedding. Pattern Recognit 84:126–135

    Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Contributions

Fahad-Liaqat-Syed Ahmad: conceptualization, formal analysis, methodology, software, validation, writing-original draft, writing-review and editing. Raza-Hasan-Tahir-Iram-Seifedine: investigation, resources, validation, writing-review and editing.

Corresponding author

Correspondence to Syed Ahmad Chan Bukhari.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Informed consent

Informed consent was obtained from all individual participants included in the study.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (docx 1316 KB)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Ahmad, F.S., Ali, L., Raza-Ul-Mustafa et al. A hybrid machine learning framework to predict mortality in paralytic ileus patients using electronic health records (EHRs). J Ambient Intell Human Comput 12, 3283–3293 (2021). https://doi.org/10.1007/s12652-020-02456-3

Download citation

Keywords

  • Paralytic ileus
  • Mortality prediction
  • Machine learning
  • MIMIC III database
  • Statistical feature analysis