Digital Determinants of Health: Health data poverty amplifies existing health disparities-A scoping review.

Artificial intelligence (AI) and machine learning (ML) have an immense potential to transform healthcare as already demonstrated in various medical specialties. This scoping review focuses on the factors that influence health data poverty, by conducting a literature review, analysis, and appraisal of results. Health data poverty is often an unseen factor which leads to perpetuating or exacerbating health disparities. Improvements or failures in addressing health data poverty will directly impact the effectiveness of AI/ML systems. The potential causes are complex and may enter anywhere along the development process. The initial results highlighted studies with common themes of health disparities (72%), AL/ML bias (28%) and biases in input data (18%). To properly evaluate disparities that exist we recommend a strengthened effort to generate unbiased equitable data, improved understanding of the limitations of AI/ML tools, and rigorous regulation with continuous monitoring of the clinical outcomes of deployed tools.

Critical Bias in Critical Care Devices.

Critical care data contain information about the most physiologically fragile patients in the hospital, who require a significant level of monitoring. However, medical devices used for patient monitoring suffer from measurement biases that have been largely underreported. This article explores sources of bias in commonly used clinical devices, including pulse oximeters, thermometers, and sphygmomanometers. Further, it provides a framework for mitigating these biases and key principles to achieve more equitable health care delivery.

Brain magnetic resonance imaging in adult survivors of extracorporeal membrane oxygenation.

Despite the common occurrence of neurologic complications in patients with extracorporeal membrane oxygenation (ECMO), data on magnetic resonance imaging (MRI) findings in adult ECMO are limited. We aimed to describe the MRI findings of patients after ECMO cannulation. Records of patients who underwent ECMO from September 2017 to June 2019 were reviewed. MRI studies were performed using multiplanar sequences consisting of T1-, T2-weighted, fluid attenuated inversion recovery (FLAIR), diffusion-weighted imaging (DWI), and susceptibility weighted images (SWI). Of the 78 adult patients who underwent ECMO, 26 (33%) survived. Of 26, eight patients (31%) had MRI studies, with a median age of 47 years (interquartile range [IQR]: 25-57). The median ECMO support time was 8 days (IQR: 4-25) and the median time from decannulation to MRI was 12 days (IQR: 1-34). Five (63%) of eight patients had ischemic infarcts; 4 (50%) had cerebral microhemorrhage; 2 (25%) had intracranial hemorrhage; and 1 (13%) had thoracic cord ischemic infarct. There were no patients with normal MRI. All patients underwent transcranial Doppler (TCD). Four of 8 (50%) showed presence of microemboli with TCD; 3 of 4 (75%) had ischemic infarcts; and 1 of 4 (25%) had presence of multiple cerebral microhemorrhages on MRI. All ischemic infarcts had diffuse pattern of punctate to small lesions for ECMO survivors. The location of cerebral microhemorrhages included lobar (n = 4, 100%), deep (n = 2, 50%), and both (n = 2, 50%). Of the MRI studies, cerebrovascular related lesions were the most frequent, with punctate ischemic infarct being the most common type that may be associated with TCD microemboli. The results of the study suggest that subclinical cerebral lesions are commonly found in patients with ECMO support. Further research is needed to understand long-term effect of these cerebral lesions.