Importance of hospital and clinical factors for early mortality in Takotsubo syndrome: Insights from the Swedish Coronary Angiography and Angioplasty Registry.
30-day mortality
Gradient boosting
Machine learning
Predictors of mortality
Swedish Coronary Angiography and Angioplasty Registry (SCAAR)
Takotsubo syndrome
Journal
BMC cardiovascular disorders
ISSN: 1471-2261
Titre abrégé: BMC Cardiovasc Disord
Pays: England
ID NLM: 100968539
Informations de publication
Date de publication:
15 Jul 2024
15 Jul 2024
Historique:
received:
16
04
2024
accepted:
01
07
2024
medline:
15
7
2024
pubmed:
15
7
2024
entrez:
14
7
2024
Statut:
epublish
Résumé
Takotsubo syndrome (TTS) is an acute heart failure syndrome with symptoms similar to acute myocardial infarction. TTS is often triggered by acute emotional or physical stress and is a significant cause of morbidity and mortality. Predictors of mortality in patients with TS are not well understood, and there is a need to identify high-risk patients and tailor treatment accordingly. This study aimed to assess the importance of various clinical factors in predicting 30-day mortality in TTS patients using a machine learning algorithm. We analyzed data from the nationwide Swedish Coronary Angiography and Angioplasty Registry (SCAAR) for all patients with TTS in Sweden between 2015 and 2022. Gradient boosting was used to assess the relative importance of variables in predicting 30-day mortality in TTS patients. Of 3,180 patients hospitalized with TTS, 76.0% were women. The median age was 71.0 years (interquartile range 62-77). The crude all-cause mortality rate was 3.2% at 30 days. Machine learning algorithms by gradient boosting identified treating hospitals as the most important predictor of 30-day mortality. This factor was followed in significance by the clinical indication for angiography, creatinine level, Killip class, and age. Other less important factors included weight, height, and certain medical conditions such as hyperlipidemia and smoking status. Using machine learning with gradient boosting, we analyzed all Swedish patients diagnosed with TTS over seven years and found that the treating hospital was the most significant predictor of 30-day mortality.
Sections du résumé
BACKGROUND
BACKGROUND
Takotsubo syndrome (TTS) is an acute heart failure syndrome with symptoms similar to acute myocardial infarction. TTS is often triggered by acute emotional or physical stress and is a significant cause of morbidity and mortality. Predictors of mortality in patients with TS are not well understood, and there is a need to identify high-risk patients and tailor treatment accordingly. This study aimed to assess the importance of various clinical factors in predicting 30-day mortality in TTS patients using a machine learning algorithm.
METHODS
METHODS
We analyzed data from the nationwide Swedish Coronary Angiography and Angioplasty Registry (SCAAR) for all patients with TTS in Sweden between 2015 and 2022. Gradient boosting was used to assess the relative importance of variables in predicting 30-day mortality in TTS patients.
RESULTS
RESULTS
Of 3,180 patients hospitalized with TTS, 76.0% were women. The median age was 71.0 years (interquartile range 62-77). The crude all-cause mortality rate was 3.2% at 30 days. Machine learning algorithms by gradient boosting identified treating hospitals as the most important predictor of 30-day mortality. This factor was followed in significance by the clinical indication for angiography, creatinine level, Killip class, and age. Other less important factors included weight, height, and certain medical conditions such as hyperlipidemia and smoking status.
CONCLUSIONS
CONCLUSIONS
Using machine learning with gradient boosting, we analyzed all Swedish patients diagnosed with TTS over seven years and found that the treating hospital was the most significant predictor of 30-day mortality.
Identifiants
pubmed: 39004698
doi: 10.1186/s12872-024-04023-6
pii: 10.1186/s12872-024-04023-6
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
359Informations de copyright
© 2024. The Author(s).
Références
Lyon AR, Bossone E, Schneider B, et al. Current state of knowledge on Takotsubo syndrome: a position Statement from the taskforce on Takotsubo Syndrome of the Heart Failure Association of the European Society of Cardiology. Eur J Heart Fail. 2016;18(1):8–27.
doi: 10.1002/ejhf.424
pubmed: 26548803
Lyon AR, Citro R, Schneider B, et al. Pathophysiology of Takotsubo Syndrome: JACC State-of-the-art review. J Am Coll Cardiol. 2021;77(7):902–21.
doi: 10.1016/j.jacc.2020.10.060
pubmed: 33602474
Omerovic E, Citro R, Bossone E, et al. Pathophysiology of Takotsubo syndrome – a joint scientific statement from the Heart Failure Association Takotsubo Syndrome Study Group and Myocardial Function Working Group of the European Society of Cardiology – part 1: overview and the central role for catecholamines and sympathetic nervous system. Eur J Heart Fail. 2022;24(2):257–73.
doi: 10.1002/ejhf.2400
pubmed: 34907620
Scally C, Rudd A, Mezincescu A, et al. Persistent long-term structural, functional, and metabolic changes after stress-induced (takotsubo) cardiomyopathy. Circulation. 2018;137(10):1039–48.
doi: 10.1161/CIRCULATIONAHA.117.031841
pubmed: 29128863
pmcid: 5841855
Redfors B, Jha S, Thorleifsson S et al. Short-and long-term clinical outcomes for patients with takotsubo syndrome and patients with myocardial infarction: a report from the Swedish coronary angiography and angioplasty registry. J Am Heart Assoc 2021;10(17).
Redfors B, Vedad R, Angerås O, et al. Mortality in takotsubo syndrome is similar to mortality in myocardial infarction - A report from the SWEDEHEART. Int J Cardiol. 2015;185:282–9.
doi: 10.1016/j.ijcard.2015.03.162
pubmed: 25818540
Prasad A, Madhavan M, Chareonthaitawee P. Cardiac sympathetic activity in stress-induced (Takotsubo) cardiomyopathy. Nat Rev Cardiol. 2009;6(6):430–4.
doi: 10.1038/nrcardio.2009.51
pubmed: 19471287
Ben Ali W, Pesaranghader A, Avram R, et al. Implementing machine learning in Interventional Cardiology: the benefits are worth the trouble. Front Cardiovasc Med. 2021;8:711401.
doi: 10.3389/fcvm.2021.711401
pubmed: 34957230
pmcid: 8692711
Karatzia L, Aung N, Aksentijevic D. Artificial intelligence in cardiology: hope for the future and power for the present. Front Cardiovasc Med. 2022;9:945726.
doi: 10.3389/fcvm.2022.945726
pubmed: 36312266
pmcid: 9608631
Schepart A, Burton A, Durkin L, et al. Artificial intelligence–enabled tools in cardiovascular medicine: a survey of current use, perceptions, and challenges. Cardiovasc Digit Health J. 2023;4(3):101–10.
doi: 10.1016/j.cvdhj.2023.04.003
pubmed: 37351333
pmcid: 10282011
Hessulf F, Bhatt DL, Engdahl J, et al. Predicting survival and neurological outcome in out-of-hospital cardiac arrest using machine learning: the SCARS model. EBioMedicine. 2023;89:104464.
doi: 10.1016/j.ebiom.2023.104464
pubmed: 36773348
pmcid: 9945645
Jerkeman M, Sultanian P, Lundgren P, et al. Trends in survival after cardiac arrest: a Swedish nationwide study over 30 years. Eur Heart J. 2022;43(46):4817–29.
doi: 10.1093/eurheartj/ehac414
pubmed: 35924401
pmcid: 9726448
Jerkeman M, Lundgren P, Omerovic E et al. Association between type of bystander cardiopulmonary resuscitation and survival in out-of-hospital cardiac arrest: A machine learning study. Resusc Plus [Internet]. 2022;10. https://www.scopus.com/inward/record.uri?eid=2-s2.0-85131969594&doi=10.1016%2fj.resplu.2022.100245&partnerID=40&md5=3d5c33a3c51836a7095b9a9626cc5de7
Aweimer A, Dietrich JW, Santoro F, et al. Takotsubo syndrome outcomes predicted by thyroid hormone signature: insights from cluster analysis of a multicentre registry. eBioMedicine. 2024;102:105063.
doi: 10.1016/j.ebiom.2024.105063
pubmed: 38502972
pmcid: 10963195
Redfors B, Shao Y, Lyon AR, Omerovic E. Diagnostic criteria for takotsubo syndrome: a call for consensus. Int J Cardiol. 2014;176(1):274–6.
doi: 10.1016/j.ijcard.2014.06.094
pubmed: 25043217
Omerovic E. How to think about stress-induced cardiomyopathy? – think out of the box! Scandinavian Cardiovasc J. 2011;45(2):67–71.
doi: 10.3109/14017431.2011.565794
Stekhoven DJ, Bühlmann P. MissForest—non-parametric missing value imputation for mixed-type data. Bioinformatics. 2012;28(1):112–8.
doi: 10.1093/bioinformatics/btr597
pubmed: 22039212
Friedman JH. Greedy function approximation: A gradient boosting machine. Ann Statist [Internet] 2001 [cited 2023 Jun 27];29(5). https://projecteuclid.org/journals/annals-of-statistics/volume-29/issue-5/Greedy-function-approximation-A-gradient-boosting-machine/10.1214/aos/1013203451.full .
Mayer M, missRanger. Fast Imputation of Missing Values [Internet]. 2023; https://github.com/mayer79/missRanger .
van der Laan MJ. Statistical Inference for Variable Importance. The International Journal of Biostatistics [Internet] 2006 [cited 2023 Dec 27];2(1). https://www.degruyter.com/document/doi/ https://doi.org/10.2202/1557-4679.1008/html .
Vazirani R, Delia MA, Blanco-Ponce E, et al. Renal impairment and outcome in Takotsubo syndrome: insights from a national multicentric cohort. Int J Cardiol. 2024;405:131971.
doi: 10.1016/j.ijcard.2024.131971
pubmed: 38490270
Camblor-Blasco A, Nuñez‐Gil IJ, Duran Cambra A, et al. Prognostic Utility of Society for Cardiovascular Angiography and interventions Shock Stage Approach for classifying cardiogenic shock severity in Takotsubo Syndrome. JAHA. 2024;13(6):e032951.
doi: 10.1161/JAHA.123.032951
pubmed: 38471832
pmcid: 11010033
Napp LC, Westenfeld R, Møller JE, et al. Impella Mechanical Circulatory support for Takotsubo Syndrome with shock: a Retrospective Multicenter Analysis. Cardiovasc Revascularization Med. 2022;40:113–9.
doi: 10.1016/j.carrev.2021.11.018
Redfors B, Shao Y, Omerovic E. Stress-induced cardiomyopathy in a patient with chronic spinal cord transection at the level of C5: endocrinologically mediated catecholamine toxicity. Int J Cardiol. 2012;159(3):e61–2.
doi: 10.1016/j.ijcard.2011.12.025
pubmed: 22240764
Omerovic E. Takotsubo Syndrome—Scientific basis for current treatment strategies. Heart Fail Clin. 2016;12(4):577–86.
doi: 10.1016/j.hfc.2016.06.008
pubmed: 27638027
Ansari U, El-Battrawy I, Fastner C et al. Clinical outcomes associated with catecholamine use in patients diagnosed with Takotsubo cardiomyopathy. BMC Cardiovasc Disord 2018;18(1).
Omerovic E, James S, Erlinge D, et al. Rationale and design of BROKEN-SWEDEHEART: a registry-based, randomized, parallel, open-label multicenter trial to test pharmacological treatments for broken heart (takotsubo) syndrome. Am Heart J. 2023;257:33–40.
doi: 10.1016/j.ahj.2022.11.010
pubmed: 36435233
Lu X, Li P, Teng C, et al. Prognostic factors of Takotsubo cardiomyopathy: a systematic review. ESC Heart Fail. 2021;8(5):3663–89.
doi: 10.1002/ehf2.13531
pubmed: 34374223
pmcid: 8497208
Uribarri A, Núñez-Gil IJ, Conty DA et al. Short‐ and Long‐Term Prognosis of Patients With Takotsubo Syndrome Based on Different Triggers: Importance of the Physical Nature. JAHA. 2019;8(24):e013701.
McDonagh TA, Metra M, Adamo M, et al. 2021 ESC guidelines for the diagnosis and treatment of acute and chronic heart failure. Eur Heart J. 2021;42(36):3599–726.
doi: 10.1093/eurheartj/ehab368
pubmed: 34447992