Prediction of stroke thrombolysis outcome using CT brain machine learning
| Autor: | Pankaj Sharma, Paul Bentley, Daniel Rueckert, Jeban Ganesalingam, Sarah Epton, Anoma Lalani Carlton Jones, Kate Mahady, Amrish Mehta, Omid Halse, Paul Rinne |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2014 |
| Předmět: |
Male
INTRACRANIAL HEMORRHAGE Intracranial haemorrhage medicine.medical_treatment computer.software_genre Severity of Illness Index lcsh:RC346-429 Imaging Outcome Assessment Health Care ACUTE ISCHEMIC-STROKE Stroke SCALE RISK Brain Thrombolysis 3. Good health Improved performance Neurology Area Under Curve Tissue Plasminogen Activator Cohort lcsh:R858-859.7 TRIAL Female Ct brain INTRAVENOUS THROMBOLYSIS INFARCTION Life Sciences & Biomedicine Cognitive Neuroscience Neuroimaging Machine learning lcsh:Computer applications to medicine. Medical informatics Article CLASSIFICATION Outcome Assessment (Health Care) Fibrinolytic Agents Artificial Intelligence Predictive Value of Tests medicine Humans Radiology Nuclear Medicine and imaging lcsh:Neurology. Diseases of the nervous system TISSUE-PLASMINOGEN ACTIVATOR Retrospective Studies Science & Technology business.industry medicine.disease Support vector machine SYMPTOMATIC INTRACEREBRAL HEMORRHAGE Stroke thrombolysis Neurology (clinical) Artificial intelligence Neurosciences & Neurology business Prediction Tomography X-Ray Computed 1109 Neurosciences computer |
| Zdroj: | NeuroImage: Clinical, Vol 4, Iss C, Pp 635-640 (2014) NeuroImage : Clinical |
| Popis: | A critical decision-step in the emergency treatment of ischemic stroke is whether or not to administer thrombolysis — a treatment that can result in good recovery, or deterioration due to symptomatic intracranial haemorrhage (SICH). Certain imaging features based upon early computerized tomography (CT), in combination with clinical variables, have been found to predict SICH, albeit with modest accuracy. In this proof-of-concept study, we determine whether machine learning of CT images can predict which patients receiving tPA will develop SICH as opposed to showing clinical improvement with no haemorrhage. Clinical records and CT brains of 116 acute ischemic stroke patients treated with intravenous thrombolysis were collected retrospectively (including 16 who developed SICH). The sample was split into training (n = 106) and test sets (n = 10), repeatedly for 1760 different combinations. CT brain images acted as inputs into a support vector machine (SVM), along with clinical severity. Performance of the SVM was compared with established prognostication tools (SEDAN and HAT scores; original, or after adaptation to our cohort). Predictive performance, assessed as area under receiver-operating-characteristic curve (AUC), of the SVM (0.744) compared favourably with that of prognostic scores (original and adapted versions: 0.626–0.720; p Highlights • Machine learning of acute stroke CTs may predict thrombolysis-associated haemorrhage. • CT machine learning also circumvents high variability of radiologist interpretations. • Favourable performance of CT machine learning reported here warrants further research. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|