Improved ICU mortality prediction based on SOFA scores and gastrointestinal parameters
Autoři:
Yehudit Aperstein aff001; Lidor Cohen aff001; Itai Bendavid aff002; Jonathan Cohen aff002; Elad Grozovsky aff002; Tammy Rotem aff001; Pierre Singer aff002
Působiště autorů:
Department of Industrial Engineering and Management, Afeka Academic College of Engineering, Tel Aviv, Israel
aff001; Department of General Intensive Care and Institute for Nutrition Research, Rabin Medical Center, Beilinson Hospital, Petah Tikva, Israel
aff002
Vyšlo v časopise:
PLoS ONE 14(9)
Kategorie:
Research Article
doi:
https://doi.org/10.1371/journal.pone.0222599
Souhrn
Background
The Sequential Organ Failure Assessment (SOFA) score is commonly used in ICUs around the world, designed to assess the severity of the patient's clinical state based on function/dysfunction of six major organ systems. The goal of this work is to build a computational model to predict mortality based on a series of SOFA scores. In addition, we examined the possibility of improving the prediction by incorporating a new component designed to measure the performance of the gastrointestinal system, added to the other six components.
Methods
In this retrospective study, we used patients’ three latest SOFA scores recorded during an individual ICU stay as input to different machine learning models and ensemble learning models. We added three validated parameters representing gastrointestinal failure. Among others, we used classification models such as Support Vector Machines (SVMs), Neural Networks, Logistic Regression and a penalty function used to increase model robustness in regard to certain extreme cases, which may be found in ICU population. We used the Area under Curve (AUC) performance metric to examine performance.
Results
We found an ensemble model of linear and logistic regression achieves a higher AUC compared related works in past years. After incorporating the gastrointestinal failure score along with the penalty function, our best performing ensemble model resulted in an additional improvement in terms of AUC metrics. We implemented and compared 36 different models that were built using both the information from the SOFA score as well as that of the gastrointestinal system. All compared models have approximately similar and relatively large AUC (between 0.8645 and 0.9146) with the best results are achieved by incorporating the gastrointestinal parameters into the prediction models.
Conclusions
Our findings indicate that gastrointestinal parameters carry significant information as a mortality predictor in addition to the conventional SOFA score. This information improves the predictive power of machine learning models by extending the SOFA to include information related to gastrointestinal organ system. The described method improves mortality prediction by considering the dynamics of the extended SOFA score. Although tested on a limited data set, the results' stability across different models suggests robustness in real-time use.
Klíčová slova:
Artificial neural networks – Intensive care units – Machine learning – Machine learning algorithms – Polynomials – Support vector machines
Zdroje
1. Vincent JL, Moreno R, Takal J, Willatts S, De Mendonça A, Bruining H, et al. The SOFA (sepsis-related organ failure assessment) score to describe organ dysfunction/failure. On behalf of the working group on sepsis-related problems of the European society of intensive care medicine. Intensive Care Med 1996; 22:707–10. doi: 10.1007/bf01709751 8844239
2. Ferreira FL, Bota DP, Bross A, Mélot C, Vincent JL. Serial evaluation of the SOFA score to predict outcome in critically ill patients. JAMA 2001; 286:1754–8. doi: 10.1001/jama.286.14.1754 11594901
3. Raith EP, Udy AA, Bailey M, McGloughlin S, MacIsaac C, Bellomo R, et al. Prognostic accuracy of the SOFA score, SIRS criteria and qSOFA score for in-hospital mortality among patients with suspected infection admitted to the intensive care unit. JAMA 2017; 317:290–300. doi: 10.1001/jama.2016.20328 28114553
4. Wong LS, Young JD. A comparison of ICU mortality prediction using the APACHE II scoring system and artificial neural networks. Anaesthesia 1999; 54:1048–54. doi: 10.1046/j.1365-2044.1999.01104.x 10540093
5. Moreno R, Vincent JL, Matos R, De Mendonça A, Cantraine F, Thijs L, et al. The use of maximum SOFA score to quantify organ dysfunction/failure in intensive care. Results of a prospective, multicenter study. Working group on sepsis related problems of ESICM. Intensive Care Med 1999; 25:686–96. doi: 10.1007/s001340050931 10470572
6. Toma T, Abu-Hanna A, Bosman RJ. Discovery and inclusion of SOFA score episodes in mortality prediction. J Biomed Inform 2007; 40:649–60. doi: 10.1016/j.jbi.2007.03.007 17485242
7. Minne L, Abu-Hanna A, de Jonge E. Evaluation of SOFA-based models for predicting mortality in the ICU: a systematic review. Crit Care 2008; 12:R161. doi: 10.1186/cc7160 19091120
8. Sandri M, Berchialla P, Baldi I, Gregori D, De Blasi RA. Dynamic Bayesian networks to predict sequences of organ failures in patients admitted to ICU. J Biomed Inform 2014; 48:106–13. doi: 10.1016/j.jbi.2013.12.008 24361388
9. Houthooft R, Ruyssinck J, van der Herten J, Stijven S, Couckuyt I, Gadeyne B, et al. Predictive modelling of survival and length of stay in critically ill patients using sequential organ failure scores. Artif Intell Med 2015; 63:191–207. doi: 10.1016/j.artmed.2014.12.009 25579436
10. Jain A, Palta S, Saroa R, Palta A, Sama S, Gombar S. Sequential organ failure assessment scoring and prediction of patient's outcome in intensive care unit of a tertiary care hospital. J Anaesthesiol Clin Pharmacol 2016; 32:364–8. doi: 10.4103/0970-9185.168165 27625487
11. Clark JA, Coopersmith CM. Intestinal crosstalk: a new paradigm for understanding the gut as the "motor" of critical illness. Shock 2007; 28:384–93. doi: 10.1097/shk.0b013e31805569df 17577136
12. Mittal R, Coopersmith CM. Redefining the gut as the motor of critical illness. Trends Mol Med 2014; 20:214–23. doi: 10.1016/j.molmed.2013.08.004 24055446
13. Patel JJ, Rosenthal MD, Miller KR, Martindale RG. The gut in trauma. Curr Opin Crit Care 2016; 22:339–46. doi: 10.1097/MCC.0000000000000331 27314259
14. Alverdy JC, Chang EB. The re-emerging role of the intestinal microflora in critical illness and inflammation: why the gut hypothesis of sepsis syndrome will not go away. J Leukoc Biol 2008; 83:461–6. doi: 10.1189/jlb.0607372 18160538
15. Vincent JL, de Mendonça A, Cantraine F, Moreno R, Takala J, Suter PM, et al. Use of the SOFA score to assess the incidence of organ dysfunction/failure in intensive care units: result of a multicenter, prospective study. Working group on "sepsis-related problems" on behalf of the European society of intensive care medicine. Crit Care Med 1998; 26:1793–800. 9824069
16. Reintam Blaser A, Poeze M, Malbrain ML, Björck M, Oudemans-van Straaten HM, Starkopf J; Gastrointestinal failure trial group. Gastrointestinal symptoms during the first week of intensive care are associated with poor outcome: a prospective multicenter study. Intensive Care Med 2013; 39:899–909. doi: 10.1007/s00134-013-2831-1 23370829
17. Reintam A, Parm P, Kitus R, Starkopf J, Kern H. Gastrointestinal failure score in critically ill patients: a prospective observational study. Crit Care 2008; 12:R90. doi: 10.1186/cc6958 18625051
18. Abed N, Mohammed L, Metwaly A, et al. Gastrointestinal failure score in combination with SOFA score in the assessment of the critically ill patients. Crit Care 2011; 15(Suppl 1):P509.
19. Sun JK, Li WQ, Ni HB, Ke L, Tong ZH, Li N, et al. Modified gastrointestinal failure score for patients with severe acute pancreatitis. Surg Today 2013; 45:506–13.
20. Reintam Blaser A, Malbrain ML, Starkopf J, Fruhwald S, Jakob SM, De Waele J, et al. Gastrointestinal function in intensive care patients: terminology, definitions and management. Recommendations of the ESICM working group on abdominal problems. Intensive Care Med 2012; 38:384–94. doi: 10.1007/s00134-011-2459-y 22310869
21. Hu B, Sun R, Wu A, Ni Y, Liu J, Guo F, et al. Severity of acute gastrointestinal injury grade is a predictor of all-cause mortality in critically ill patients: a multicenter, prospective, observational study. Crit Care 2017; 21:188. doi: 10.1186/s13054-017-1780-4 28709443
22. Guillén J, Jiankun L, Furr M, Wang T, Strong S, Moore CC, et al. Predictive Models for Severe Sepsis in Adult ICU Patients. 2015 Systems and Information Engineering Design Symposium. doi: 10.1109/SIEDS.2015.7116970
23. Amato F, López A, Peña-Méndez EM, Vaňhara P, Hampi A, Havel J. Artificial neural networks in medical diagnosis.J Appl Biomed 2013; 11:47–58.
24. Faisy C, Guerot E, Diehl JL, Labrousse J, Fagon JY. Assessment of resting energy expenditure in mechanically ventilated patients. Am J Clin Nutr 2003; 78:241–9. doi: 10.1093/ajcn/78.2.241 12885704
25. Reintam Blaser A, Starkopf J, Malbrain ML. Abdominal signs and symptoms in intensive care patients. Anaesthesiol Intensive Ther 2015; 47:379–87. 25 doi: 10.5603/AIT.a2015.0022 25973664
26. Blaser Reintam A, Jakob SM, Starkopf J. Gastrointestinal failure in the ICU. Curr Opin Crit Care 2016; 22:128–41. 26 doi: 10.1097/MCC.0000000000000286 26835609
27. Piton G, Manzon C, Cypriani B, Carbonnel F, Capellier G. Acute intestinal failure in critically ill patients: is plasma citrulline the right marker? Intensive Care Med 2011; 37:911–7. 27 doi: 10.1007/s00134-011-2172-x 21400011
28. Reintam Blaser A, Starkopf L, Deane AM, Poeze M, Starkopf J. Comparison of different definitions of feeding intolerance: a retrospective observational study. Clin Nutr 2015; 34:956–61. 28 doi: 10.1016/j.clnu.2014.10.006 25467878
29. Reintam Blaser A, Malbrain MLNG, Regli A Abdominal pressure and gastrointestinal function: an inseperable couple? Anaesthesiol Intensive Ther 2017; 49:146–158.
Článek vyšel v časopise
PLOS One
2019 Číslo 9
- S diagnostikou Parkinsonovy nemoci může nově pomoci AI nástroj pro hodnocení mrkacího reflexu
- Je libo čepici místo mozkového implantátu?
- Pomůže v budoucnu s triáží na pohotovostech umělá inteligence?
- AI může chirurgům poskytnout cenná data i zpětnou vazbu v reálném čase
- Nová metoda odlišení nádorové tkáně může zpřesnit resekci glioblastomů
Nejčtenější v tomto čísle
- Graviola (Annona muricata) attenuates behavioural alterations and testicular oxidative stress induced by streptozotocin in diabetic rats
- CH(II), a cerebroprotein hydrolysate, exhibits potential neuro-protective effect on Alzheimer’s disease
- Comparison between Aptima Assays (Hologic) and the Allplex STI Essential Assay (Seegene) for the diagnosis of Sexually transmitted infections
- Assessment of glucose-6-phosphate dehydrogenase activity using CareStart G6PD rapid diagnostic test and associated genetic variants in Plasmodium vivax malaria endemic setting in Mauritania
Zvyšte si kvalifikaci online z pohodlí domova
Všechny kurzy