-
Tytuł:
-
Machine Learning to Predict Delayed Cerebral Ischemia and Outcomes in Subarachnoid Hemorrhage.
-
Autorzy:
-
Savarraj JPJ; From the Departments of Neurosurgery (J.P.J.S., G.W.H., T.C., R.S.K., A.C.), Internal Medicine (L.Z.), and Neurology (F.S.V.), McGovern Medical School, Center for Precision Health, School of Biomedical Informatics (Z.Z.), and Human Genetics Center, School of Public Health (Z.Z.), The University of Texas Health Science Center at Houston; and Department of Neurology (S.P., M.M.), Columbia University, NY.
Hergenroeder GW; From the Departments of Neurosurgery (J.P.J.S., G.W.H., T.C., R.S.K., A.C.), Internal Medicine (L.Z.), and Neurology (F.S.V.), McGovern Medical School, Center for Precision Health, School of Biomedical Informatics (Z.Z.), and Human Genetics Center, School of Public Health (Z.Z.), The University of Texas Health Science Center at Houston; and Department of Neurology (S.P., M.M.), Columbia University, NY.
Zhu L; From the Departments of Neurosurgery (J.P.J.S., G.W.H., T.C., R.S.K., A.C.), Internal Medicine (L.Z.), and Neurology (F.S.V.), McGovern Medical School, Center for Precision Health, School of Biomedical Informatics (Z.Z.), and Human Genetics Center, School of Public Health (Z.Z.), The University of Texas Health Science Center at Houston; and Department of Neurology (S.P., M.M.), Columbia University, NY.
Chang T; From the Departments of Neurosurgery (J.P.J.S., G.W.H., T.C., R.S.K., A.C.), Internal Medicine (L.Z.), and Neurology (F.S.V.), McGovern Medical School, Center for Precision Health, School of Biomedical Informatics (Z.Z.), and Human Genetics Center, School of Public Health (Z.Z.), The University of Texas Health Science Center at Houston; and Department of Neurology (S.P., M.M.), Columbia University, NY.
Park S; From the Departments of Neurosurgery (J.P.J.S., G.W.H., T.C., R.S.K., A.C.), Internal Medicine (L.Z.), and Neurology (F.S.V.), McGovern Medical School, Center for Precision Health, School of Biomedical Informatics (Z.Z.), and Human Genetics Center, School of Public Health (Z.Z.), The University of Texas Health Science Center at Houston; and Department of Neurology (S.P., M.M.), Columbia University, NY.
Megjhani M; From the Departments of Neurosurgery (J.P.J.S., G.W.H., T.C., R.S.K., A.C.), Internal Medicine (L.Z.), and Neurology (F.S.V.), McGovern Medical School, Center for Precision Health, School of Biomedical Informatics (Z.Z.), and Human Genetics Center, School of Public Health (Z.Z.), The University of Texas Health Science Center at Houston; and Department of Neurology (S.P., M.M.), Columbia University, NY.
Vahidy FS; From the Departments of Neurosurgery (J.P.J.S., G.W.H., T.C., R.S.K., A.C.), Internal Medicine (L.Z.), and Neurology (F.S.V.), McGovern Medical School, Center for Precision Health, School of Biomedical Informatics (Z.Z.), and Human Genetics Center, School of Public Health (Z.Z.), The University of Texas Health Science Center at Houston; and Department of Neurology (S.P., M.M.), Columbia University, NY.
Zhao Z; From the Departments of Neurosurgery (J.P.J.S., G.W.H., T.C., R.S.K., A.C.), Internal Medicine (L.Z.), and Neurology (F.S.V.), McGovern Medical School, Center for Precision Health, School of Biomedical Informatics (Z.Z.), and Human Genetics Center, School of Public Health (Z.Z.), The University of Texas Health Science Center at Houston; and Department of Neurology (S.P., M.M.), Columbia University, NY.
Kitagawa RS; From the Departments of Neurosurgery (J.P.J.S., G.W.H., T.C., R.S.K., A.C.), Internal Medicine (L.Z.), and Neurology (F.S.V.), McGovern Medical School, Center for Precision Health, School of Biomedical Informatics (Z.Z.), and Human Genetics Center, School of Public Health (Z.Z.), The University of Texas Health Science Center at Houston; and Department of Neurology (S.P., M.M.), Columbia University, NY.
Choi HA; From the Departments of Neurosurgery (J.P.J.S., G.W.H., T.C., R.S.K., A.C.), Internal Medicine (L.Z.), and Neurology (F.S.V.), McGovern Medical School, Center for Precision Health, School of Biomedical Informatics (Z.Z.), and Human Genetics Center, School of Public Health (Z.Z.), The University of Texas Health Science Center at Houston; and Department of Neurology (S.P., M.M.), Columbia University, NY. .
-
Źródło:
-
Neurology [Neurology] 2021 Jan 26; Vol. 96 (4), pp. e553-e562. Date of Electronic Publication: 2020 Nov 12.
-
Typ publikacji:
-
Journal Article
-
Język:
-
English
-
Imprint Name(s):
-
Publication: Hagerstown, MD : Lippincott Williams & Wilkins
Original Publication: Minneapolis.
-
MeSH Terms:
-
Brain Ischemia/*diagnosis
Brain Ischemia/*epidemiology
Machine Learning/*trends
Subarachnoid Hemorrhage/*diagnosis
Subarachnoid Hemorrhage/*epidemiology
Adult ; Aged ; Brain Ischemia/therapy ; Female ; Humans ; Male ; Middle Aged ; Predictive Value of Tests ; Prospective Studies ; Retrospective Studies ; Subarachnoid Hemorrhage/therapy ; Time Factors ; Treatment Outcome
-
References:
-
Stroke. 2010 Oct;41(10):2391-5. (PMID: 20798370)
Scand J Clin Lab Invest. 2008;68(1):77-80. (PMID: 18224558)
Stroke. 2000 Apr;31(4):901-6. (PMID: 10753996)
Neurosurgery. 2009 Aug;65(2):316-23; discussion 323-4. (PMID: 19625911)
J Neurosurg. 1968 Jan;28(1):14-20. (PMID: 5635959)
Neurosurgery. 2018 Jul 1;83(1):137-145. (PMID: 28973675)
Neurocrit Care. 2017 Jun;26(3):393-401. (PMID: 28028791)
J Neurosurg. 2009 Mar;110(3):487-91. (PMID: 19046046)
J Clin Endocrinol Metab. 2012 May;97(5):1423-33. (PMID: 22362821)
Ann Neurol. 2018 May;83(5):958-969. (PMID: 29659050)
Neurosurgery. 2019 Feb 1;84(2):397-403. (PMID: 29528448)
J Neurosurg Anesthesiol. 2006 Jan;18(1):68-72. (PMID: 16369143)
Stroke. 2000 Jan;31(1):118-22. (PMID: 10625725)
Psychol Sci. 2005 Jan;16(1):70-6. (PMID: 15660854)
Science. 2018 Feb 16;359(6377):725-726. (PMID: 29449469)
Neurology. 2003 Oct 28;61(8):1132-3. (PMID: 14581680)
J Stroke Cerebrovasc Dis. 2014 May-Jun;23(5):902-9. (PMID: 24103667)
Cytokine. 2018 Nov;111:334-341. (PMID: 30269030)
J Cereb Blood Flow Metab. 2014 Feb;34(2):200-7. (PMID: 24281744)
J Neurosurg. 2005 May;102(5):882-7. (PMID: 15926714)
Neurosurgery. 2006 Jul;59(1):21-7; discussion 21-7. (PMID: 16823296)
Neurosurgery. 2002 Apr;50(4):749-55; discussion 755-6. (PMID: 11904025)
Transl Stroke Res. 2012 Jul;3(Suppl 1):113-8. (PMID: 24323866)
Circulation. 2015 Nov 17;132(20):1920-30. (PMID: 26572668)
J R Soc Interface. 2018 Apr;15(141):. (PMID: 29618526)
Lancet Respir Med. 2018 Nov;6(11):801. (PMID: 30343029)
Stroke Vasc Neurol. 2017 Jun 21;2(4):230-243. (PMID: 29507784)
J Neurosurg. 2003 Jun;98(6):1222-6. (PMID: 12816268)
Transl Stroke Res. 2012 Jun;3(2):296-304. (PMID: 23626658)
Biom J. 2008 Jun;50(3):419-30. (PMID: 18435502)
Neurocrit Care. 2018 Apr;28(2):203-211. (PMID: 29043545)
Surg Neurol. 2001 Apr;55(4):197-203. (PMID: 11358585)
J Clin Monit Comput. 2019 Feb;33(1):95-105. (PMID: 29556884)
Brain. 1974 Mar;97(1):79-86. (PMID: 4434173)
J Gen Intern Med. 2004 Nov;19(11):1154-9. (PMID: 15566446)
Crit Care Med. 2005 Jul;33(7):1603-9; quiz 1623. (PMID: 16003069)
Cerebrovasc Dis. 2010;29(6):576-83. (PMID: 20375501)
J Crit Care. 2017 Feb;37:126-129. (PMID: 27718411)
Neurocrit Care. 2016 Aug;25(1):64-70. (PMID: 26703130)
Neurocrit Care. 2014 Dec;21(3):444-50. (PMID: 24715326)
Ann Surg. 1979 Jan;189(1):96-100. (PMID: 365113)
Biometrics. 1988 Sep;44(3):837-45. (PMID: 3203132)
Surg Neurol. 1987 Mar;27(3):253-8. (PMID: 3810457)
-
Grant Information:
-
K01 ES026833 United States ES NIEHS NIH HHS
-
Entry Date(s):
-
Date Created: 20201113 Date Completed: 20210209 Latest Revision: 20240403
-
Update Code:
-
20240403
-
PubMed Central ID:
-
PMC7905786
-
DOI:
-
10.1212/WNL.0000000000011211
-
PMID:
-
33184232
-
Objective: To determine whether machine learning (ML) algorithms can improve the prediction of delayed cerebral ischemia (DCI) and functional outcomes after subarachnoid hemorrhage (SAH).
Methods: ML models and standard models (SMs) were trained to predict DCI and functional outcomes with data collected within 3 days of admission. Functional outcomes at discharge and at 3 months were quantified using the modified Rankin Scale (mRS) for neurologic disability (dichotomized as good [mRS ≤ 3] vs poor [mRS ≥ 4] outcomes). Concurrently, clinicians prospectively prognosticated 3-month outcomes of patients. The performance of ML, SMs, and clinicians were retrospectively compared.
Results: DCI status, discharge, and 3-month outcomes were available for 399, 393, and 240 participants, respectively. Prospective clinician (an attending, a fellow, and a nurse) prognostication of 3-month outcomes was available for 90 participants. ML models yielded predictions with the following area under the receiver operating characteristic curve (AUC) scores: 0.75 ± 0.07 (95% confidence interval [CI] 0.64-0.84) for DCI, 0.85 ± 0.05 (95% CI 0.75-0.92) for discharge outcome, and 0.89 ± 0.03 (95% CI 0.81-0.94) for 3-month outcome. ML outperformed SMs, improving AUC by 0.20 (95% CI -0.02 to 0.4) for DCI, by 0.07 ± 0.03 (95% CI -0.0018 to 0.14) for discharge outcomes, and by 0.14 (95% CI 0.03-0.24) for 3-month outcomes and matched physician's performance in predicting 3-month outcomes.
Conclusion: ML models significantly outperform SMs in predicting DCI and functional outcomes and has the potential to improve SAH management.
(© 2020 American Academy of Neurology.)
