Search

Key Points: Question: Can novice clinicians accurately estimate gestational age using a low-cost, battery-powered ultrasonography probe with integrated artificial intelligence (AI) image interpretation? Findings: This prospective study enrolled 400 pregnant individuals with due dates confirmed by first-trimester ultrasonography. At follow-up visits randomly assigned throughout gestation, novice clinicians using an AI-enabled device estimated gestational age as accurately as credentialed sonographers using traditional ultrasonography devices (difference, 0.2 days). Meaning: Obstetrical care in low-resource settings may benefit from reliable gestational age assessment using AI integration with point-of-care ultrasonography. Importance: Accurate assessment of gestational age (GA) is essential to good pregnancy care but often requires ultrasonography, which may not be available in low-resource settings. This study developed a deep learning artificial intelligence (AI) model to estimate GA from blind ultrasonography sweeps and incorporated it into the software of a low-cost, battery-powered device. Objective: To evaluate GA estimation accuracy of an AI-enabled ultrasonography tool when used by novice users with no prior training in sonography. Design, Setting, and Participants: This prospective diagnostic accuracy study enrolled 400 individuals with viable, single, nonanomalous, first-trimester pregnancies in Lusaka, Zambia, and Chapel Hill, North Carolina. Credentialed sonographers established the "ground truth" GA via transvaginal crown-rump length measurement. At random follow-up visits throughout gestation, including a primary evaluation window from 14 0/7 weeks' to 27 6/7 weeks' gestation, novice users obtained blind sweeps of the maternal abdomen using the AI-enabled device (index test) and credentialed sonographers performed fetal biometry with a high-specification machine (study standard). Main Outcomes and Measures: The primary outcome was the mean absolute error (MAE) of the index test and study standard, which was calculated by comparing each method's estimate to the previously established GA and considered equivalent if the difference fell within a prespecified margin of ±2 days. Results: In the primary evaluation window, the AI-enabled device met criteria for equivalence to the study standard, with an MAE (SE) of 3.2 (0.1) days vs 3.0 (0.1) days (difference, 0.2 days [95% CI, −0.1 to 0.5]). Additionally, the percentage of assessments within 7 days of the ground truth GA was comparable (90.7% for the index test vs 92.5% for the study standard). Performance was consistent in prespecified subgroups, including the Zambia and North Carolina cohorts and those with high body mass index. Conclusions and Relevance: Between 14 and 27 weeks' gestation, novice users with no prior training in ultrasonography estimated GA as accurately with the low-cost, point-of-care AI tool as credentialed sonographers performing standard biometry on high-specification machines. These findings have immediate implications for obstetrical care in low-resource settings, advancing the World Health Organization goal of ultrasonography estimation of GA for all pregnant people. Trial Registration: ClinicalTrials.gov Identifier: NCT05433519 This prospective diagnostic study examines the accuracy of an AI-enabled ultrasonography tool in estimating gestational age when used by those with no prior training in sonography. [ABSTRACT FROM AUTHOR]

Purpose: Acute stroke is a serious, time-sensitive condition requiring immediate medical attention. Emergency medical services (EMS) routing and direct transport of acute stroke patients to stroke centers improves timely access to care. This study aimed to describe EMS stroke routing and transports by rurality in North Carolina (NC)., Methods: We conducted a retrospective study using existing data on EMS transports of suspected stroke patients in NC in 2019. The primary study outcome was EMS bypass of the nearest hospital for transport to a nonnearest hospital, determined by geographic information systems (GIS) analysis. Incident addresses were geocoded to census tracts and classified as urban, suburban, or rural by Rural-Urban Commuting Area codes. We compared the frequency of bypass and estimated additional transport times by urban, suburban, and rural incident locations., Findings: Of 3666 patients, 1884 (51%) EMS transports bypassed the nearest hospital. Bypass occurred less often for rural EMS incidents (39%) compared to those in urban (57%) and suburban (63%) tracts. The estimated additional transport time for rural bypasses of nonendovascular-capable stroke centers for endovascular-capable stroke centers was a median of 25 min (interquartile range 13-33)., Conclusions: Using GIS analysis, we found nearly half of EMS transports of suspected stroke patients in NC bypassed the nearest hospital, including noncertified hospitals and stroke centers. Bypasses occurred less often in rural areas, though incurred significantly longer transport times, compared to urban areas. These findings are important for regional stroke system planning, especially for improving rural access to acute stroke care., (© 2024 National Rural Health Association.)