Development of a Complication- and Treatment-Aware Prediction Model for Favorable Functional Outcome in Aneurysmal Subarachnoid Hemorrhage Based on Machine Learning.

Maldaner, Nicolai; Zeitlberger, Anna M; Sosnova, Marketa; Goldberg, Johannes; Fung, Christian; Bervini, David; May, Adrien; Bijlenga, Philippe; Schaller, Karl; Roethlisberger, Michel; Rychen, Jonathan; Zumofen, Daniel W; D'Alonzo, Donato; Marbacher, Serge; Fandino, Javier; Daniel, Roy Thomas; Burkhardt, Jan-Karl; Chiappini, Alessio; Robert, Thomas; Schatlo, Bawarjan; ... (2021). Development of a Complication- and Treatment-Aware Prediction Model for Favorable Functional Outcome in Aneurysmal Subarachnoid Hemorrhage Based on Machine Learning. Neurosurgery, 88(2), E150-E157. Oxford University Press 10.1093/neuros/nyaa401

[img] Text
nyaa401.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (396kB) | Request a copy

BACKGROUND

Current prognostic tools in aneurysmal subarachnoid hemorrhage (aSAH) are constrained by being primarily based on patient and disease characteristics on admission.

OBJECTIVE

To develop and validate a complication- and treatment-aware outcome prediction tool in aSAH.

METHODS

This cohort study included data from an ongoing prospective nationwide multicenter registry on all aSAH patients in Switzerland (Swiss SOS [Swiss Study on aSAH]; 2009-2015). We trained supervised machine learning algorithms to predict a binary outcome at discharge (modified Rankin scale [mRS] ≤ 3: favorable; mRS 4-6: unfavorable). Clinical and radiological variables on admission ("Early" Model) as well as additional variables regarding secondary complications and disease management ("Late" Model) were used. Performance of both models was assessed by classification performance metrics on an out-of-sample test dataset.

RESULTS

Favorable functional outcome at discharge was observed in 1156 (62.0%) of 1866 patients. Both models scored a high accuracy of 75% to 76% on the test set. The "Late" outcome model outperformed the "Early" model with an area under the receiver operator characteristics curve (AUC) of 0.85 vs 0.79, corresponding to a specificity of 0.81 vs 0.70 and a sensitivity of 0.71 vs 0.79, respectively.

CONCLUSION

Both machine learning models show good discrimination and calibration confirmed on application to an internal test dataset of patients with a wide range of disease severity treated in different institutions within a nationwide registry. Our study indicates that the inclusion of variables reflecting the clinical course of the patient may lead to outcome predictions with superior predictive power compared to a model based on admission data only.

Item Type:

Journal Article (Original Article)

Division/Institute:

04 Faculty of Medicine > Department of Head Organs and Neurology (DKNS) > Clinic of Neurosurgery

UniBE Contributor:

Goldberg, Johannes; Fung, Christian and Bervini, David

Subjects:

600 Technology > 610 Medicine & health

ISSN:

0148-396X

Publisher:

Oxford University Press

Language:

English

Submitter:

Nicole Söll

Date Deposited:

12 Oct 2020 16:31

Last Modified:

15 Jan 2021 01:32

Publisher DOI:

10.1093/neuros/nyaa401

PubMed ID:

33017031

Uncontrolled Keywords:

Aneurysmal subarachnoid hemorrhage Complication- and treatment-aware Machine learning Outcome prediction

BORIS DOI:

10.7892/boris.146936

URI:

https://boris.unibe.ch/id/eprint/146936

Actions (login required)

Edit item Edit item
Provide Feedback