Automatic PredICtion of Edema After Stroke

N/AActive Not RecruitingNCT04057690

University Hospital Tuebingen1,687 enrolled

Overview

To use machine learning for early detection of malignant brain edema in patients with MCA ischemia

Malignant cerebral edema following large ischemic strokes account for up to 10% of all ischemic strokes. Mortality rates are high and most of the survivors are left severely disabled. Although decompressive craniectomy has been shown to significantly decrease mortality, high morbidity rates among survivors are reported. The optimal timepoint when neurosurgical decompression should be performed in the individual patient varies and is a subject of debate. Early prediction of malignant brain edema to identify those patients who benefit from surgical treatment is a clinical challenge. The aim of this study is to use machine learning for comprehensive analysis of CT images as well as clinical data from 1500 patients with large ischemic MCA strokes in oder to develop a model for early prediction of malignant brain edema. In a first step algorithms automatically identify characteristic imaging features and clinical data of 1400 retrospective data sets to create a multistage model (learning phase). This is followed by a validation phase where the model is tested with 100 other retrospective data sets.

Study Type

OBSERVATIONAL

Enrollment

1,687

Conditions

Stroke, Acute Brain Edema

Eligibility

Sex: ALL

Medical Language ↔ Plain English

Inclusion Criteria: * Acute ≥ subtotal MCA infarct (M1-M2 occlusion) * with or without malignant brain swelling * with or without reperfusion therapy * with or without neurosurgical decompression * with or without death following malignant brain edema Exclusion Criteria: * Non-acute MCA infarct * \< subtotal MCA infarct

Locations (19)

St. John's Hospital

Vienna, Austria

Charité Universitätsmedizin Berlin

Berlin, Germany

Outcomes

Primary Outcomes

Number of patients with stroke-related malignant edema after recanalization treatment detected by deep learning algorithms

Deep learning algorithms will be used for automatic identification of specific image findings and specific clinical data that indicate a stroke-related malignant edema. Primary outcome measures are Sensitivity/Specificity/negative predictive value/positive predictive value of early detection of patients developing stroke-related malignant edema based on initial CT and 24 hour follow up CT and clinical parameters.

Time frame: 4/2019-3/2022

Secondary Outcomes

Number of correctly identified specific imaging findings for early detection of malignant edema

Used specific imaging findings for early detection of malignant brain edema are Collateral status, Clot Burden Score, Vein Score, Change in CSF volume. In this study the specific image findings are manually annotated and also automatically detected using deep learning algorithms. Secondary outcome measures are Sensitivity/Specificity/NPV/PPV of specific imaging findings identified by deep learning algorithms.

Time frame: 4/2019-3/2022

Data from ClinicalTrials.gov

This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.