AUTHOR=Mazza Orit , Shehory Onn , Lev Nirit 

TITLE=Machine Learning Techniques in Blood Pressure Management During the Acute Phase of Ischemic Stroke

JOURNAL=Frontiers in Neurology

VOLUME=Volume 12 - 2021

YEAR=2022

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2021.743728

DOI=10.3389/fneur.2021.743728

ISSN=1664-2295

ABSTRACT=Background and Purpose: 
Elevated blood pressure (BP) in acute ischemic stroke is common. Raised BP is related to mortality and disability, yet excessive BP lowering can be detrimental. The optimal BP management in acute ischemic stroke remains insufficient and relies on expert consensus statements. Permissive hypertension is recommended during the first 24-hours after stroke onset, yet there is ongoing uncertainty regarding the most appropriate blood BP management in the acute phase of ischemic stroke. This study aims to develop a decision support tool for improving the management of extremely high BP during the first 24 hours after acute ischemic stroke by using machine learning tools.
Methods:
This diagnostic accuracy study used retrospective data from MIMIC-III and eICU databases. Decision trees were constructed by a hierarchical binary recursive partitioning algorithm to predict BP lowering of 10-30 percent off the maximal value when antihypertensive treatment was given in patients with extremely high BP (above 220/110mmHg or 180/105mmHg for patients receiving thrombolysis) according to the American Heart Association/American Stroke Association (AHA/ASA) and the European Society of Cardiology and the European Society of Hypertension (ESC/ESH) guidelines. Regression trees were used to predict time-weighted average BP. Implementation of synthetic minority oversampling technique was used to balance the dataset according to different antihypertensive treatments. The model performance of the decision tree was compared to the performance of neural networks, random forest, and logistic regression models.
Results: 
7265 acute ischemic stroke patients were identified. Diastolic blood pressure (DBP) is the main variable for predicting BP reduction in the first 24 hours after a stroke. For patients receiving thrombolysis with DBP<120mmHg, Labetalol and Amlodipine are effective treatments. Above DBP of 120mmHg Amlodipine, Lisinopril and Nicardipine are the most effective treatments. However, successful treatment depends on avoiding hyponatremia and on kidney functions. 
Conclusions: 
This is the first study to address BP management in the acute phase of ischemic stroke using machine learning techniques. The results indicate that treatment choice should be adjusted to different clinical and BP parameters, thus providing a better decision-making approach.