Top

Published in:

01-01-2020 | Subarachnoid Hemorrhage | Original Article - Vascular Neurosurgery - Aneurysm

Meteorological factors for subarachnoid hemorrhage in the greater Düsseldorf area revisited: a machine learning approach to predict the probability of admission of patients with subarachnoid hemorrhage

Authors: Hans-Jakob Steiger, Athanasios K. Petridis, Angelo Tortora, Hendrik-Jan Mijderwijk, Kerim Beseoglu, Jasper H. van Lieshout, Marcel A. Kamp, Igor Fischer

Published in: Acta Neurochirurgica | Issue 1/2020

Abstract

Background

Reported data regarding the relation between the incidence of spontaneous subarachnoid hemorrhage (SAH) and weather conditions are conflicting and do so far not allow prognostic models.

Methods

Admissions for spontaneous SAH (ICD I60.*) 2009–2018 were retrieved form our hospital data base. Historical meteorological data for the nearest meteorological station, Düsseldorf Airport, was retrieved from the archive of the Deutsche Wetterdienst (DWD). Airport is in the center of our catchment area with a diameter of approximately 100 km. Pearson correlation matrix between mean daily meteorological variables and the daily admissions of one or more patients with subarachnoid hemorrhage was calculated and further analysis was done using deep learning algorithms.

Results

For the 10-year period from January 1, 2009 until December 31, 2018, a total of 1569 patients with SAH were admitted. No SAH was admitted on 2400 days (65.7%), 1 SAH on 979 days (26.7%), 2 cases on 233 days (6.4%), 3 SAH on 37 days (1.0%), 4 in 2 days (0.05%), and 5 cases on 1 day (0.03%). Pearson correlation matrix suggested a weak positive correlation of admissions for SAH with precipitation on the previous day and weak inverse relations with the actual mean daily temperature and the temperature change from the previous days, and weak inverse correlations with barometric pressure on the index day and the day before. Clustering with admission of multiple SAH on a given day followed a Poisson distribution and was therefore coincidental. The deep learning algorithms achieved an area under curve (AUC) score of approximately 52%. The small difference from 50% appears to reflect the size of the meteorological impact.

Conclusion

Although in our data set a weak correlation of the probability to admit one or more cases of SAH with meteorological conditions was present during the analyzed time period, no helpful prognostic model could be deduced with current state machine learning methods. The meteorological influence on the admission of SAH appeared to be in the range of only a few percent compared with random or unknown factors.

Available only for authorised users

Abe T, Ohde S, Ishimatsu S, Ogata H, Hasegawa T, Nakamura T, Tokuda Y (2008) Effects of meteorological factors on the onset of subarachnoid hemorrhage: a time-series analysis. J Clin Neurosci 15(9):1005–1010. https://doi.org/10.1016/j.jocn.2007.07.081 CrossRefPubMed

Backes D, Rinkel GJ, Algra A, Vaartjes I, Donker GA, Vergouwen MD (2016) Increased incidence of subarachnoid hemorrhage during cold temperatures and influenza epidemics. J Neurosurg 125(3):737–745. https://doi.org/10.3171/2015.8.JNS151473 CrossRefPubMed

Baño-Ruiz E, Abarca-Olivas J, Duart-Clemente JM, Ballenilla-Marco F, García P, Botella-Asunción C (2010) Influence of the atmospheric pressure and other variable weather on the incidence of the subarachnoid hemorrhage. Neurocirugia (Astur) 21(1):14–21 SpanishCrossRef

Ben-Hur A, Horn D, Siegelmann HT, Vapnik V (2001) Support vector clustering. J Mach Learn Res 2:125–137

Beseoglu K, Hänggi D, Stummer W, Steiger HJ (2008) Dependence of subarachnoid hemorrhage on climate conditions: a systematic meteorological analysis from the Dusseldorf metropolitan area. Neurosurgery 62(5):1033–1038; discussion 1038-9. https://doi.org/10.1227/01.neu.0000325864.91584.c7 CrossRefPubMed

Brownlee J (2016) How to compare machine learning algorithms in Python with scikit-learn. https://machinelearningmastery.com/compare-machine-learning-algorithms-python-scikit-learn/. Accessed 30 May 2019

Cao Y, Wang X, Zheng D, Robinson T, Hong D, Richtering S, Leong TH, Salam A, Anderson C, Hackett ML (2016) Air pressure, humidity and stroke occurrence: a systematic review and meta-analysis. Int J Environ Res Public Health 5(7):13. https://doi.org/10.3390/ijerph13070675 ReviewCrossRef

Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: Synthetic Minority Over-sampling Technique. JAIR 16:321–357. https://doi.org/10.1613/jair.953 CrossRef

Chyatte D, Chen TL, Bronstein K, Brass LM (1994) Seasonal fluctuation in the incidence of intracranial aneurysm rupture and its relationship to changing climatic conditions. J Neurosurg 81(4):525–530CrossRef

10.

Cowperthwaite MC, Burnett MG (2011) The association between weather and spontaneous subarachnoid hemorrhage: an analysis of 155 US hospitals. Neurosurgery 68(1):132–138; discussion 138-9. https://doi.org/10.1227/NEU.0b013e3181fe23a1 CrossRefPubMed

11.

Gill RS, Hambridge HL, Schneider EB, Hanff T, Tamargo RJ, Nyquist P (2013) Falling temperature and colder weather are associated with an increased risk of aneurysmal subarachnoid hemorrhage. World Neurosurg 79(1):136–142. https://doi.org/10.1016/j.wneu.2012.06.020 CrossRefPubMed

12.

Grandi A (2018) Machine Learning: Pima Indians Diabetes. https://www.andreagrandi.it/2018/04/14/machine-learning-pima-indians-diabetes/. Accessed 30 May 2019

13.

Han MH, Kim J, Choi KS, Kim CH, Kim JM, Cheong JH, Yi HJ, Lee SH (2017) Monthly variations in aneurysmal subarachnoid hemorrhage incidence and mortality: correlation with weather and pollution. PLoS One 12(10):e0186973. https://doi.org/10.1371/journal.pone.0186973 eCollection 2017CrossRefPubMedPubMedCentral

14.

Hakan T, Kizilkilic O, Adaletli I, Karabagli H, Kocer N, Islak C (2003) Is there any seasonal influence in spontaneous bleeding of intracranial aneurysm and and/or AVM in Istanbul? Swiss Med Wkly 133(17-18):267–272PubMed

15.

Herten A, Jabbarli R, Dammann P , Hütter BO, Sure U, Wrede K (2016) Epidemiology of aneurysmal subarachnoid hemorrhage with special focus on seasonal and circaseptan influences as well as the relation with short-term weather changes: a long-term study of 821 bleeding events. Abstracts of the 67th Annual Meeting of the German Society of Neurosurgery (DGNC). https://www.egms.de/static/en/meetings/dgnc2016/16dgnc003.shtml. Accessed 30 May 2019

16.

Izumihara A (2012) Epidemiology of subarachnoid hemorrhage in the Yaeyama Islands, an isolated subtropical region of Japan most frequently affected by typhoons: a population-based study. Clin Neurol Neurosurg 114(9):1226–1231. https://doi.org/10.1016/j.clineuro.2012.03.001 CrossRefPubMed

17.

Jehle D, Moscati R, Frye J, Reich N (1994) The incidence of spontaneous subarachnoid hemorrhage with change in barometric pressure. Am J Emerg Med 12(1):90–91CrossRef

18.

Kellogg M, Petrov D, Agarwal N, Patel NV, Hansberry DR, Agarwal P, Brimacombe M, Gandhi CD, Prestigiacomo C (2017) Effects of meteorological variables on the incidence of rupture of intracranial aneurysms in Central New Jersey. J Neurol Surg A Cent Eur Neurosurg 78(3):238–244. https://doi.org/10.1055/s-0036-1594308 CrossRefPubMed

19.

Lai PM, Dasenbrock H, Du R (2014) The association between meteorological parameters and aneurysmal subarachnoid hemorrhage: a nationwide analysis. PLoS One 9(11):e112961. https://doi.org/10.1371/journal.pone.0112961 eCollection 2014CrossRefPubMedPubMedCentral

20.

Landers AT, Narotam PK, Govender ST, van Dellen JR (1997) The effect of changes in barometric pressure on the risk of rupture of intracranial aneurysms. Br J Neurosurg 11(3):191–195CrossRef

21.

Law HY, Wong GK, Chan DT, Wong L, Poon WS (2009) Meteorological factors and aneurysmal subarachnoid haemorrhage in Hong Kong. Hong Kong Med J 15(2):85–89PubMed

22.

Lee S, Guth M (2017) Associations between temperature and hospital admissions for subarachnoid hemorrhage in Korea. Int J Environ Res Public Health 14(4). https://doi.org/10.3390/ijerph14040449 CrossRef

23.

Lejeune JP, Vinchon M, Amouyel P, Escartin T, Escartin D, Christiaens JL (1994) Association of occurrence of aneurysmal bleeding with meteorologic variations in the north of France. Stroke 25(2):338–341CrossRef

24.

McDonald RJ, McDonald JS, Bida JP, Kallmes DF, Cloft HJ (2012) Subarachnoid hemorrhage incidence in the United States does not vary with season or temperature. AJNR Am J Neuroradiol 33(9):1663–1668. https://doi.org/10.3174/ajnr.A3059 CrossRefPubMed

25.

Muroi C, Yonekawa Y, Khan N, Rousson V, Keller E (2004) Seasonal variations in hospital admissions due to aneurysmal subarachnoid haemorrhage in the state of Zurich, Switzerland. Acta Neurochir 146(7):659–665CrossRef

26.

Neidert MC, Sprenger M, Wernli H, Burkhardt J-K, Krayenbühl N, Bozinov O, Regli L, Woernle CM (2013) Meteorological influences on the incidence of aneurysmal subarachnoid hemorrhage - a single center study of 511 patients. PLoS One 8:e81621. https://doi.org/10.1371/journal.pone.0081621 CrossRefPubMedPubMedCentral

27.

Patrice T, Rozec B, Desal H, Blanloeil Y (2017) Oceanic meteorological conditions influence incidence of aneurysmal subarachnoid hemorrhage. J Stroke Cerebrovasc Dis 26(7):1573–1581. https://doi.org/10.1016/j.jstrokecerebrovasdis.2017.02.031 CrossRefPubMed

28.

Rivera-Lara L, Kowalski RG, Schneider EB, Tamargo RJ, Nyquist P (2015) Elevated relative risk of aneurysmal subarachnoid hemorrhage with colder weather in the mid-Atlantic region. J Clin Neurosci 22(10):1582–1587. https://doi.org/10.1016/j.jocn.2015.03.033 CrossRefPubMed

29.

Roberts SJ (1997) Parametric and non-parametric unsupervised cluster analysis. Pattern Recogn 30(2):261–272CrossRef

30.

Rosenørn J, Rønde F, Eskesen V, Schmidt K (1988) Seasonal variation of aneurysmal subarachnoid haemorrhage. Acta Neurochir 93(1-2):24–27CrossRef

31.

Rué M, Camiade E, Jecko V, Bauduer F, Vignes JR (2014) The relationship between aneurysmal subarachnoid hemorrhage and meteorological parameters based on a series of 236 French patients. Neurochirurgie 60(5):222–226. https://doi.org/10.1016/j.neuchi.2014.02.010 FrenchCrossRefPubMed

32.

Setzer M, Beck J, Hermann E, Raabe A, Seifert V, Vatter H, Marquardt G (2007) The influence of barometric pressure changes and standard meteorological variables on the occurrence and clinical features of subarachnoid hemorrhage. Surg Neurol 67(3):264–272 discussion 272CrossRef

33.

Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958

34.

Staartjes VE, Schröder ML (2018) Class imbalance in machine learning for neurosurgical outcome prediction: are our models valid? J Neurosurg Spine 29:611–612. https://doi.org/10.3171/2018.5.SPINE18543 CrossRefPubMed

35.

Tarnoki AD, Turker A, Tarnoki DL, Iyisoy MS, Szilagyi BK, Duong H, Miskolczi L (2017) Relationship between weather conditions and admissions for ischemic stroke and subarachnoid hemorrhage. Croat Med J 58(1):56–62CrossRef

36.

van Donkelaar CE, Potgieser ARE, Groen H, Foumani M, Abdulrahman H, Sluijter R, van Dijk JMC, Groen RJM (2018) Atmospheric pressure variation is a delayed trigger for aneurysmal subarachnoid hemorrhage. World Neurosurg 112:e783–e790. https://doi.org/10.1016/j.wneu.2018.01.155 CrossRefPubMed

37.

Zheng Y, Wang X, Liu J, Zhao F, Zhang J, Feng H (2016) A community-based study of the correlation of hemorrhagic stroke occurrence with meteorologic factors. J Stroke Cerebrovasc Dis 25(10):2323–2330. https://doi.org/10.1016/j.jstrokecerebrovasdis.2014.12.028 CrossRefPubMed

Title: Meteorological factors for subarachnoid hemorrhage in the greater Düsseldorf area revisited: a machine learning approach to predict the probability of admission of patients with subarachnoid hemorrhage
Authors: Hans-Jakob Steiger
Athanasios K. Petridis
Angelo Tortora
Hendrik-Jan Mijderwijk
Kerim Beseoglu
Jasper H. van Lieshout
Marcel A. Kamp
Igor Fischer
Publication date: 01-01-2020
Publisher: Springer Vienna
Keywords: Subarachnoid Hemorrhage
Subarachnoid Hemorrhage
Published in: Acta Neurochirurgica / Issue 1/2020
Print ISSN: 0001-6268
Electronic ISSN: 0942-0940
DOI: https://doi.org/10.1007/s00701-019-04128-4

At a glance: The STEP trials

Springer Medicine

Meteorological factors for subarachnoid hemorrhage in the greater Düsseldorf area revisited: a machine learning approach to predict the probability of admission of patients with subarachnoid hemorrhage

Abstract

Background

Methods

Results

Conclusion

At a glance: The STEP trials

Springer Medicine

Abstract

Background

Methods

Results

Conclusion

Please log in to get access to this content

Other articles of this Issue 1/2020

Feasibility of the new sutureless excimer laser-assisted non-occlusive anastomosis clip in a rabbit model

Individual variations of the superior petrosal vein complex and their microsurgical relevance in 50 cases of trigeminal microvascular decompression

Flow-regulated versus differential pressure valves for idiopathic normal pressure hydrocephalus: comparison of overdrainage rates and neurological outcome

Correction to: Editorial re: Facial nerve function and hearing after microsurgical removal of sporadic vestibular schwannomas in a population-based cohort by Ismail Taha et al.

Lower subscapular nerve transfer for axillary nerve repair in upper brachial plexus palsy

Ventriculoperitoneal shunt in treating of idiopathic normal pressure hydrocephalus—single-center study