Prognosticating outcome using magnetic resonance imaging in patients with moderate to severe traumatic brain injury: a machine learning approach.
Over the last decade advancements in computer processing have enabled the application of machine learning (ML) to complex medical problems. Convolutional neural networks (CNN), a type of ML, have been used to interrogate medical images for variety of purposes. In this study, we aimed to investigate...
| Publicado en: | Brain Injury Vol. 36; no. 3; pp. 353 - 359 |
|---|---|
| Autores principales: | , , , , , , |
| Formato: | research tables/charts Journal Article |
| Publicado: |
Taylor & Francis Ltd
2022
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=157055795&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 157055795 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 02699052 B6W jtl: Brain Injury issn: 02699052 maglogo: Y pubinfo: dt: 2022 vid: 36 iid: 3 pid: 377 pub: Taylor & Francis Ltd place: Philadelphia, Pennsylvania artinfo: ui: 157055795 155088251 157055795 157055795 10.1080/02699052.2022.2034184 157055795 ppf: 353 ppct: 6 formats: tig: atl: Prognosticating outcome using magnetic resonance imaging in patients with moderate to severe traumatic brain injury: a machine learning approach. aug: au: Mohamed, Moumin Alamri, a Mohamed, M Khalid, N. O'Halloran, Pj Staartjes, Ve Uff, C affil: Department of Neurosurgery, Royal London Hospital, London, UK sug: subj: Magnetic Resonance Imaging Brain Injuries Prognosis Treatment Outcomes Machine Learning Methods Brain Injuries Radiography Severity of Injury Neural Networks (Computer) Nerve Fibers Injuries Retrospective Design ROC Curve Brain Stem Injuries Outcome Assessment Sensitivity and Specificity Data Analysis Software Descriptive Statistics Human Male Female Adult Adult: 19-44 years Male Female ab: Over the last decade advancements in computer processing have enabled the application of machine learning (ML) to complex medical problems. Convolutional neural networks (CNN), a type of ML, have been used to interrogate medical images for variety of purposes. In this study, we aimed to investigate the potential application of CNN in prognosticating patients with traumatic brain injury (TBI). Patients with moderate to severe TBI and evidence of diffuse axonal injury (DAI) were selected retrospectively. A CNN model was developed using a training subgroup and a holdout subgroup was used as a testing dataset. We reported the model characteristics including area under the receiver operating characteristic curve (AUC). We included a total of 38 patient, of which we generated 725 MRI sections. We developed a CNN model based on a modified AlexNet architecture that interpreted the brain stem injury to generate outcome predictions. The model was able to predict GOS outcomes with a specificity of 0.43 and a sensitivity of 0.997. It showed an AUC of 0.917. The utilization of machine learning MRI analysis for prognosticating patients with TBI is a valued method that require further investigation. This will require multicentre collaboration to generate large datasets. pubtype: Academic Journal doctype: research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|