Retrospective External Validation of the Status Epilepticus Severity Score (STESS) to Predict In-hospital Mortality in Adults with Nonhypoxic Status Epilepticus: A Machine Learning Analysis.
Mortality
Prediction
Prognosis
Status epilepticus
Journal
Neurocritical care
ISSN: 1556-0961
Titre abrégé: Neurocrit Care
Pays: United States
ID NLM: 101156086
Informations de publication
Date de publication:
04 2023
04 2023
Historique:
received:
24
03
2022
accepted:
09
09
2022
medline:
13
4
2023
pubmed:
14
10
2022
entrez:
13
10
2022
Statut:
ppublish
Résumé
The objective of this study was to validate the value of the Status Epilepticus Severity Score (STESS) in the prediction of the risk of in-hospital mortality in patients with nonhypoxic status epilepticus (SE) using a machine learning analysis. We included consecutive patients with nonhypoxic SE (aged ≥ 16 years) admitted from 2013 to 2021 at the Modena Academic Hospital. A decision tree analysis was performed using in-hospital mortality as a dependent variable and the STESS predictors as input variables. We evaluated the accuracy of STESS in predicting in-hospital mortality using the area under the receiver operating characteristic curve (AUROC) with 95% confidence interval (CI). Among 629 patients with SE, the in-hospital mortality rate was 23.4% (147 of 629). The median STESS in the entire cohort was 2.9 (SD 1.6); it was lower in surviving compared with deceased patients (2.7, SD 1.5 versus 3.9, SD 1.6; p < 0.001). Of deceased patients, 82.3% (121 of 147) had scores of 3-6, whereas 17.7% (26 of 147) had scores of 0-2 (p < 0.001). STESS was accurate in predicting mortality, with an AUROC of 0.688 (95% CI 0.641-0.734) only slightly reduced after bootstrap resampling. The most significant predictor was the seizure type, followed by age and level of consciousness at SE onset. Nonconvulsive SE in coma and age ≥ 65 years predicted a higher risk of mortality, whereas generalized convulsive SE and age < 65 years were associated with a lower risk of death. The decision tree analysis using STESS variables correctly classified 90% of survivors and 34% of nonsurvivors after the SE, with an overall risk of error of 23.1%. This validation study using a machine learning system showed that STESS is a valuable prognostic tool. The score appears particularly accurate and effective in identifying patients who are alive at discharge (high negative predictive value), whereas it has a lower predictive value for in-hospital mortality.
Sections du résumé
BACKGROUND
The objective of this study was to validate the value of the Status Epilepticus Severity Score (STESS) in the prediction of the risk of in-hospital mortality in patients with nonhypoxic status epilepticus (SE) using a machine learning analysis.
METHODS
We included consecutive patients with nonhypoxic SE (aged ≥ 16 years) admitted from 2013 to 2021 at the Modena Academic Hospital. A decision tree analysis was performed using in-hospital mortality as a dependent variable and the STESS predictors as input variables. We evaluated the accuracy of STESS in predicting in-hospital mortality using the area under the receiver operating characteristic curve (AUROC) with 95% confidence interval (CI).
RESULTS
Among 629 patients with SE, the in-hospital mortality rate was 23.4% (147 of 629). The median STESS in the entire cohort was 2.9 (SD 1.6); it was lower in surviving compared with deceased patients (2.7, SD 1.5 versus 3.9, SD 1.6; p < 0.001). Of deceased patients, 82.3% (121 of 147) had scores of 3-6, whereas 17.7% (26 of 147) had scores of 0-2 (p < 0.001). STESS was accurate in predicting mortality, with an AUROC of 0.688 (95% CI 0.641-0.734) only slightly reduced after bootstrap resampling. The most significant predictor was the seizure type, followed by age and level of consciousness at SE onset. Nonconvulsive SE in coma and age ≥ 65 years predicted a higher risk of mortality, whereas generalized convulsive SE and age < 65 years were associated with a lower risk of death. The decision tree analysis using STESS variables correctly classified 90% of survivors and 34% of nonsurvivors after the SE, with an overall risk of error of 23.1%.
CONCLUSIONS
This validation study using a machine learning system showed that STESS is a valuable prognostic tool. The score appears particularly accurate and effective in identifying patients who are alive at discharge (high negative predictive value), whereas it has a lower predictive value for in-hospital mortality.
Identifiants
pubmed: 36229575
doi: 10.1007/s12028-022-01610-3
pii: 10.1007/s12028-022-01610-3
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
254-262Informations de copyright
© 2022. Springer Science+Business Media, LLC, part of Springer Nature and Neurocritical Care Society.
Références
Trinka E, Cock H, Hesdorffer D, et al. A definition and classification of status epilepticus–report of the ILAE task force on classification of status epilepticus. Epilepsia. 2015;56(10):1515–23. https://doi.org/10.1111/epi.13121 .
doi: 10.1111/epi.13121
pubmed: 26336950
Leitinger M, Trinka E, Zimmermann G, Granbichler CA, Kobulashvili T, Siebert U. Epidemiology of status epilepticus in adults: apples, pears, and oranges - a critical review. Epilepsy Behav. 2020;103(Pt A): 106720. https://doi.org/10.1016/j.yebeh.2019.106720 .
doi: 10.1016/j.yebeh.2019.106720
pubmed: 31902646
Neligan A, Shorvon SD. Frequency and prognosis of convulsive status epilepticus of different causes: a systematic review. Arch Neurol. 2010;67(8):931–40. https://doi.org/10.1001/archneurol.2010.169 .
doi: 10.1001/archneurol.2010.169
pubmed: 20697043
Giovannini G, Monti G, Tondelli M, et al. Mortality, morbidity and refractoriness prediction in status epilepticus: comparison of STESS and EMSE scores. Seizure. 2017;46:31–7. https://doi.org/10.1016/j.seizure.2017.01.004 .
doi: 10.1016/j.seizure.2017.01.004
pubmed: 28226274
Yuan F, Gao Q, Jiang W. Prognostic scores in status epilepticus-a critical appraisal. Epilepsia. 2018;59(Suppl 2):170–5. https://doi.org/10.1111/epi.14483 .
doi: 10.1111/epi.14483
pubmed: 30159870
Rossetti AO, Logroscino G, Bromfield EB. A clinical score for prognosis of status epilepticus in adults. Neurology. 2006;66(11):1736–8. https://doi.org/10.1212/01.wnl.0000223352.71621.97 .
doi: 10.1212/01.wnl.0000223352.71621.97
pubmed: 16769951
Rossetti AO, Logroscino G, Milligan TA, Michaelides C, Ruffieux C, Bromfield EB. Status epilepticus severity score (STESS): a tool to orient early treatment strategy. J Neurol. 2008;255(10):1561–6. https://doi.org/10.1007/s00415-008-0989-1 .
doi: 10.1007/s00415-008-0989-1
pubmed: 18769858
Goyal MK, Chakravarthi S, Modi M, Bhalla A, Lal V. Status epilepticus severity score (STESS): a useful tool to predict outcome of status epilepticus. Clin Neurol Neurosurg. 2015;139:96–9. https://doi.org/10.1016/j.clineuro.2015.09.010 .
doi: 10.1016/j.clineuro.2015.09.010
pubmed: 26409183
Pacha MS, Orellana L, Silva E, et al. Role of EMSE and STESS scores in the outcome evaluation of status epilepticus. Epilepsy Behav. 2016;64(Pt A):140–2. https://doi.org/10.1016/j.yebeh.2016.09.036 .
doi: 10.1016/j.yebeh.2016.09.036
pubmed: 27741463
Aukland P, Lando M, Vilholm O, Christiansen EB, Beier CP. Predictive value of the status epilepticus severity score (STESS) and its components for long-term survival. BMC Neurol. 2016;16(1):213. https://doi.org/10.1186/s12883-016-0730-0 .
doi: 10.1186/s12883-016-0730-0
pubmed: 27816063
González-Cuevas M, Santamarina E, Toledo M, et al. A new clinical score for the prognosis of status epilepticus in adults. Eur J Neurol. 2016;23(10):1534–40. https://doi.org/10.1111/ene.13073 .
doi: 10.1111/ene.13073
pubmed: 27415411
Sutter R, Kaplan PW, Rüegg S. Independent external validation of the status epilepticus severity score. Crit Care Med. 2013;41(12):e475–9. https://doi.org/10.1097/CCM.0b013e31829eca06 .
doi: 10.1097/CCM.0b013e31829eca06
pubmed: 23982031
Leitinger M, Höller Y, Kalss G, et al. Epidemiology-based mortality score in status epilepticus (EMSE). Neurocrit Care. 2015;22(2):273–82. https://doi.org/10.1007/s12028-014-0080-y .
doi: 10.1007/s12028-014-0080-y
pubmed: 25412806
Kang BS, Kim DW, Kim KK, et al. Prediction of mortality and functional outcome from status epilepticus and independent external validation of STESS and EMSE scores. Crit Care. 2016;20:25. https://doi.org/10.1186/s13054-016-1190-z .
doi: 10.1186/s13054-016-1190-z
pubmed: 26812954
Wang P, Guan Y, Lin X, et al. Diagnostic value of status epilepticus severity score for survival conditions of patients with status epilepticus: a PRISMA-compliant systematic review and meta-analysis. Epilepsy Behav. 2018;82:104–10. https://doi.org/10.1016/j.yebeh.2018.02.033 .
doi: 10.1016/j.yebeh.2018.02.033
pubmed: 29604482
Leitinger M, Kalss G, Rohracher A, et al. Predicting outcome of status epilepticus. Epilepsy Behav. 2015;49:126–30. https://doi.org/10.1016/j.yebeh.2015.04.066 .
doi: 10.1016/j.yebeh.2015.04.066
pubmed: 26071999
Song YY, Lu Y. Decision tree methods: applications for classification and prediction. Shanghai Arch Psychiatry. 2015;27:130–5.
pubmed: 26120265
Shirali GA, Noroozi MV, Malehi AS. Predicting the outcome of occupational accidents by CART and CHAID methods at a steel factory in Iran. J Public Health Res. 2018;7:1361.
doi: 10.4081/jphr.2018.1361
pubmed: 30581805
Brigo F, Turcato G, Lattanzi S, et al. Machine-learning validation through decision-tree analysis of the epidemiology-based mortality score in status epilepticus. Epilepsia. 2022. https://doi.org/10.1111/epi.17372 .
doi: 10.1111/epi.17372
pubmed: 35869796
Leitinger M, Beniczky S, Rohracher A, et al. Salzburg consensus criteria for non-convulsive status epilepticus–approach to clinical application. Epilepsy Behav. 2015;49:158–63. https://doi.org/10.1016/j.yebeh.2015.05.007 .
doi: 10.1016/j.yebeh.2015.05.007
pubmed: 26092326
Leitinger M, Trinka E, Gardella E, et al. Diagnostic accuracy of the Salzburg EEG criteria for non-convulsive status epilepticus: a retrospective study. Lancet Neurol. 2016;15(10):1054–62. https://doi.org/10.1016/S1474-4422(16)30137-5 .
doi: 10.1016/S1474-4422(16)30137-5
pubmed: 27571157
Brophy GM, Bell R, Claassen J, et al. Guidelines for the evaluation and management of status epilepticus. Neurocrit Care. 2012;17(1):3–23. https://doi.org/10.1007/s12028-012-9695-z .
doi: 10.1007/s12028-012-9695-z
pubmed: 22528274
Glauser T, Shinnar S, Gloss D, et al. Evidence-based guideline: treatment of convulsive status epilepticus in children and adults: report of the guideline committee of the American epilepsy society. Epilepsy Curr. 2016;16(1):48–61. https://doi.org/10.5698/1535-7597-16.1.48 .
doi: 10.5698/1535-7597-16.1.48
pubmed: 26900382
Minicucci F, Ferlisi M, Brigo F, et al. Management of status epilepticus in adults position paper of the Italian League against epilepsy. Epilepsy Behav. 2020;102:106675. https://doi.org/10.1016/j.yebeh.2019.106675 .
doi: 10.1016/j.yebeh.2019.106675
pubmed: 31766004
Hajian-Tilaki K. Receiver operating characteristic (ROC) curve analysis for medical diagnostic test evaluation. Caspian J Intern Med. 2013;4(2):627–35.
pubmed: 24009950
Park SH, Goo JM, Jo CH. Receiver operating characteristic (ROC) curve: practical review for radiologists. Korean J Radiol. 2004;5(1):11–8.
doi: 10.3348/kjr.2004.5.1.11
pubmed: 15064554
Turcato G, Zaboli A, Pfeifer N, et al. Decision tree analysis to predict the risk of intracranial haemorrhage after mild traumatic brain injury in patients taking DOACs. Am J Emerg Med. 2021;50:388–93.
doi: 10.1016/j.ajem.2021.08.048
pubmed: 34478944
Song YY, Lu Y. Decision tree methods: applications for classification and prediction. Shanghai Arch Psychiatry. 2015;27(2):130–5. https://doi.org/10.11919/j.issn.1002-0829.215044 .
doi: 10.11919/j.issn.1002-0829.215044
pubmed: 26120265
Shirali GA, Noroozi MV, Malehi AS. Predicting the outcome of occupational accidents by CART and CHAID methods at a steel factory in Iran. J Public Health Res. 2018;7(2):1361. https://doi.org/10.4081/jphr.2018.1361 .
doi: 10.4081/jphr.2018.1361
pubmed: 30581805
Towne AR, Pellock JM, Ko D, DeLorenzo RJ. Determinants of mortality in status epilepticus. Epilepsia. 1994;35(1):27–34. https://doi.org/10.1111/j.1528-1157.1994.tb02908.x .
doi: 10.1111/j.1528-1157.1994.tb02908.x
pubmed: 8112254
Logroscino G, Hesdorffer DC, Cascino G, Annegers JF, Hauser WA. Short-term mortality after a first episode of status epilepticus. Epilepsia. 1997;38(12):1344–9. https://doi.org/10.1111/j.1528-1157.1997.tb00073.x .
doi: 10.1111/j.1528-1157.1997.tb00073.x
pubmed: 9578531
Koubeissi M, Alshekhlee A. In-hospital mortality of generalized convulsive status epilepticus: a large US sample. Neurology. 2007;69(9):886–93. https://doi.org/10.1212/01.wnl.0000269791.96189.70 .
doi: 10.1212/01.wnl.0000269791.96189.70
pubmed: 17724291
Leitinger M, Trinka E, Giovannini G, et al. Epidemiology of status epilepticus in adults: a population-based study on incidence, causes, and outcomes. Epilepsia. 2019;60(1):53–62. https://doi.org/10.1111/epi.14607 .
doi: 10.1111/epi.14607
pubmed: 30478910
Logroscino G, Hesdorffer DC, Cascino G, Annegers JF, Hauser WA. Time trends in incidence, mortality, and case-fatality after first episode of status epilepticus. Epilepsia. 2001;42(8):1031–5. https://doi.org/10.1046/j.1528-1157.2001.0420081031.x .
doi: 10.1046/j.1528-1157.2001.0420081031.x
pubmed: 11554890
Lattanzi S, Giovannini G, Brigo F, Orlandi N, Trinka E, Meletti S. Status epilepticus with prominent motor symptoms clusters into distinct electroclinical phenotypes. Eur J Neurol. 2021;28(8):2694–9. https://doi.org/10.1111/ene.14891 .
doi: 10.1111/ene.14891
pubmed: 33932068
Sutter R, Kaplan PW. The neurophysiologic types of nonconvulsive status epilepticus: EEG patterns of different phenotypes. Epilepsia. 2013;54(Suppl 6):23–7.
doi: 10.1111/epi.12269
pubmed: 24001065
Sutter R, Semmlack S, Kaplan PW. Nonconvulsive status epilepticus in adults - insights into the invisible. Nat Rev Neurol. 2016;12(5):281–93.
doi: 10.1038/nrneurol.2016.45
pubmed: 27063108
Sutter R. Are we prepared to detect subtle and nonconvulsive status epilepticus in critically Ill patients? J Clin Neurophysiol. 2016;33(1):25–31.
doi: 10.1097/WNP.0000000000000216
pubmed: 26840874
Kinney MO, Craig JJ, Kaplan PW. Hidden in plain sight: Non-convulsive status epilepticus—recognition and management. Acta Neurol Scand. 2017;136:280–92.
doi: 10.1111/ane.12732
pubmed: 28144933
Teasdale G, Jennett B. Assessment of coma and impaired consciousness A practical scale. Lancet. 1974;2(7872):81–4. https://doi.org/10.1016/s0140-6736(74)91639-0 .
doi: 10.1016/s0140-6736(74)91639-0
pubmed: 4136544
Lattanzi S, Giovannini G, Brigo F, Orlandi N, Trinka E, Meletti S. Clinical phenotypes within nonconvulsive status epilepticus. Epilepsia. 2021;62(9):e129–34. https://doi.org/10.1111/epi.16999 .
doi: 10.1111/epi.16999
pubmed: 34244997
Semmlack S, Kaplan PW, Spiegel R, et al. Illness severity scoring in status epilepticus-when STESS meets APACHE II, SAPS II, and SOFA. Epilepsia. 2019;60(2):189–200.
doi: 10.1111/epi.14623
pubmed: 30585317
Sutter R, Semmlack S, Opić P, et al. Untangling operational failures of the Status Epilepticus Severity Score (STESS). Neurology. 2019;92(17):e1948–56.
doi: 10.1212/WNL.0000000000007365
pubmed: 30918093
Yechoor N, Adeli A, Hafeez S. External validation of the epidemiology-based mortality score in status epilepticus in an American intensive care population. Epilepsy Res. 2018;148:32–6. https://doi.org/10.1016/j.eplepsyres.2018.10.001 .
doi: 10.1016/j.eplepsyres.2018.10.001
pubmed: 30342324
Huang TH, Lai MC, Chen YS, Huang CW. Status epilepticus mortality risk factors and a correlation survey with the newly modified STESS. Healthcare (Basel). 2021;9(11):1570.
doi: 10.3390/healthcare9111570
pubmed: 34828616