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

BACKGROUND AND PURPOSE: Elevated blood pressure (BP) in acute ischemic stroke is common. A 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-h 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 h after acute ischemic stroke by using machine learning (ML) 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 the BP-lowering of 10-30% off the maximal value when antihypertensive treatment was given in patients with an extremely high BP (above 220/110 or 180/105 mmHg for patients receiving thrombolysis), according to the American Heart Association/American Stroke Association (AHA/ASA), the European Society of Cardiology, and the European Society of Hypertension (ESC/ESH) guidelines. Regression trees were used to predict the 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: In total, 7,265 acute ischemic stroke patients were identified. Diastolic BP (DBP) is the main variable for predicting BP reduction in the first 24 h after a stroke. For patients receiving thrombolysis with DBP <120 mmHg, Labetalol and Amlodipine are effective treatments. Above DBP of 120 mmHg, Amlodipine, Lisinopril, and Nicardipine are the most effective treatments. However, successful treatment depends on avoiding hyponatremia and on kidney functions. CONCLUSION: This is the first study to address BP management in the acute phase of ischemic stroke using ML techniques. The results indicate that the treatment choice should be adjusted to different clinical and BP parameters, thus, providing a better decision-making approach.

Intravitreal Trimethoprim and Sulfamethoxazole Toxicity to the Retina of Albino Rabbits.

PURPOSE: To evaluate retinal toxicity of intravitreal trimethoprim-sulfamethoxazole (TMP-SMX) in an albino rabbit model. METHODS: Albino rabbits (N = 10) were treated in the right eye with the maximum intravitreal dose of TMP-SMX mixture (1600 µg/8000 µg /0.1 mL), while 0.1 mL saline was injected into the vitreous of the left eye. Clinical examination and electrophysiological (electroretinogram [ERG] and visual evoked potentials [VEPs]) testing were conducted before injection, 3 days, 1, 2, and 4 weeks postinjection. Retinal structure and expression of glial fibrillary acidic protein (GFAP) were assessed from histology and immunocytochemistry respectively at the end of the follow-up period. RESULTS: Clinical examination was normal throughout the follow-up period. ERG responses from the experimental eyes were similar to those recorded from the control eyes, but the sum of oscillatory potentials decreased in the experimental eyes at 2 weeks postinjection. The VEP responses, elicited by stimulation of the experimental eyes, were abnormal having reduced amplitude and prolonged implicit time. Histological damage in the experimental eyes was expressed by thickness reduction of whole, outer, and inner nuclear layers. GFAP was expressed in retinal Müller cells of all experimental eyes, but none of control eyes. CONCLUSIONS: A single intravitreal injection of TMP-SMX mixture (1600 µg/8000 µg, respectively) causes functional and structural damage to the inner retina and retinal output. Signs of retinal stress were also evident by GFAP expression in retinal Müller cells of all experimental eyes. Therefore, the use of TMP-SMX via intravitreal administration should be done with caution. TRANSLATIONAL RELEVANCE: These findings highlight the risk of retinal toxicity after intravitreal injection of trimethoprim-sulfamethoxazole and emphasize that this treatment should be carefully considered.

Safety of intravitreal clindamycin in albino rabbit eyes.

PURPOSE: To study the potential toxic effects of intravitreal clindamycin on the retina of albino rabbits, by assessing functional and morphological retinal changes. METHODS: Eight albino rabbits were included in the study. In each rabbit, 1 mg/0.1 ml clindamycin was injected into the vitreous of the right (experimental) eye, and 0.1 ml saline was injected into the vitreous of the left (control) eye. The electroretinogram (ERG) was recorded before injection, 3 days, 1, 2, and 4 weeks post-injection. The visual evoked potential (VEP) was recorded 4 weeks post-injection. Clinical examination was conducted at all time points. The eyes were enucleated at the termination of the follow-up period in order to prepare the retinas for histology in order to assess retinal structure. RESULTS: ERG and VEP responses that were recorded from the experimental eye at different times following intravitreal clindamycin injection were very similar to the corresponding responses that were recorded from the control eyes. Clinical examination was normal in all eyes, and no histological damage was observed. CONCLUSIONS: Intravitreal injection of 1 mg clindamycin does not cause functional or morphological signs of retinal toxicity in albino rabbits, during a period of 4 weeks post-injection. These findings support the clinical use of 1 mg intravitreal clindamycin.