A Clinical and Imaging Fused Deep Learning Model Matches Expert Clinician Prediction of 90-Day Stroke Outcomes.

BACKGROUND AND PURPOSE: Predicting long-term clinical outcome in acute ischemic stroke is beneficial for prognosis, clinical trial design, resource management, and patient expectations. This study used a deep learning-based predictive model (DLPD) to predict 90-day mRS outcomes and compared its predictions with those made by physicians. MATERIALS AND METHODS: A previously developed DLPD that incorporated DWI and clinical data from the acute period was used to predict 90-day mRS outcomes in 80 consecutive patients with acute ischemic stroke from a single-center registry. We assessed the predictions of the model alongside those of 5 physicians (2 stroke neurologists and 3 neuroradiologists provided with the same imaging and clinical information). The primary analysis was the agreement between the ordinal mRS predictions of the model or physician and the ground truth using the Gwet Agreement Coefficient. We also evaluated the ability to identify unfavorable outcomes (mRS >2) using the area under the curve, sensitivity, and specificity. Noninferiority analyses were undertaken using limits of 0.1 for the Gwet Agreement Coefficient and 0.05 for the area under the curve analysis. The accuracy of prediction was also assessed using the mean absolute error for prediction, percentage of predictions ±1 categories away from the ground truth (±1 accuracy [ACC]), and percentage of exact predictions (ACC). RESULTS: To predict the specific mRS score, the DLPD yielded a Gwet Agreement Coefficient score of 0.79 (95% CI, 0.71-0.86), surpassing the physicians' score of 0.76 (95% CI, 0.67-0.84), and was noninferior to the readers (P < .001). For identifying unfavorable outcome, the model achieved an area under the curve of 0.81 (95% CI, 0.72-0.89), again noninferior to the readers' area under the curve of 0.79 (95% CI, 0.69-0.87) (P < .005). The mean absolute error, ±1ACC, and ACC were 0.89, 81%, and 36% for the DLPD. CONCLUSIONS: A deep learning method using acute clinical and imaging data for long-term functional outcome prediction in patients with acute ischemic stroke, the DLPD, was noninferior to that of clinical readers.

Regional Anesthesia as an Alternative to Moderate Sedation for Perioperative Pain Control for Percutaneous Gastrostomy Tube Placement.

Percutaneous gastrostomy tube placement is typically performed under moderate sedation. However, some patients are not ideal candidates for moderate sedation because of respiratory compromise, difficult airways, or other factors. The purpose of this study was to evaluate regional anesthesia as an alternative to moderate sedation. A retrospective review of patients who underwent percutaneous gastrostomy tube placement between March 2014 and September 2020 was performed. Data on patient demographics, anesthesia type, pain scores, and opiate usage were collected. A total of 189 patients were included in the study; 35 (18.5%) received regional anesthesia and 154 received moderate sedation. Patients in the regional anesthesia group tolerated the procedure well, with lower mean immediate postprocedural and maximal pain scores of 0.7 vs 2.2 (P = .011) and 4.3 vs 6.5 (P = .003), respectively. Regional anesthesia is effective at controlling perioperative pain and is an alternative with a low complication rate for patients who cannot tolerate moderate sedation.

Progressive cavitating leukoencephalopathy associated with a homozygous POLG mutation of 264C>G (p.F88L).

Progressive cavitating leukoencephalopathy is a childhood neurodegenerative syndrome characterized by brain MR imaging findings of patchy leukoencephalopathy with cavities and vascular permeability, initially affecting the corpus callosum and centrum semiovale, and eventually coalescing into large cystic regions of white matter. We report a case of progressive cavitating leukoencephalopathy in a 2-year-old female patient presenting as intermittent motor deficits which partially resolved over several months. Whole exome sequencing revealed a homozygous c.264C>G (p.F88L) POLG variant of uncertain pathogenicity which was potentially related to this presentation. Further testing and information are needed to prove the pathogenicity of this variant, but considering other studies which report similar genotypes in association with differing phenotypes, the current case report supports a possible pathogenicity. This case could therefore represent the first reported instance of progressive cavitating leukoencephalopathy in the presence of a POLG mutation.