Try a new search

Format these results:

Searched for:

person:mobees01

in-biosketch:true

Total Results:

2


Use of Artificial Intelligence-Based Software to Aid in the Identification of Ultrasound Findings Associated With Fetal Congenital Heart Defects

Lam-Rachlin, Jennifer; Punn, Rajesh; Behera, Sarina K; Geiger, Miwa; Lachaud, Matthias; David, Nadine; Garmel, Sara; Fox, Nathan S; Rebarber, Andrei; DeVore, Greggory R; Zelop, Carolyn M; Janssen, Matthew K; Sylvester-Armstrong, Kendra R; Kennedy, John; Spiegelman, Jessica; Heiligenstein, Mia; Bessis, Roger; Mobeen, Sadia; Kia, Farnaaz; Friedman, Caroline; Melka, Stephanie; Stos, Bertrand; De Boisredon, Malo; Askinazi, Eric; Thorey, Valentin; Gardella, Christophe; Levy, Marilyne; Arunamata, Alisa
OBJECTIVE:To evaluate whether artificial intelligence (AI)-based software was associated with enhanced identification of eight second-trimester fetal ultrasound findings suspicious for congenital heart defects (CHDs) among obstetrician-gynecologists (ob-gyns) and maternal-fetal medicine specialists. METHODS:A dataset of 200 fetal ultrasound examinations from 11 centers, including 100 with at least one suspicious finding, was retrospectively constituted (singleton pregnancy, 18-24 weeks of gestation, patients aged 18 years or older). Only examinations containing two-dimensional grayscale cines with interpretable four-chamber, left ventricular outflow tract, and right ventricular outflow tract standard views were included. Seven ob-gyns and seven maternal-fetal medicine specialists reviewed each examination in randomized order both with and without AI assistance and assessed the presence or absence of each finding suspicious for CHD with confidence scores. Outcomes included readers' performance in identifying the presence of any finding and each finding at the examination level, as measured by the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity. In addition, reading time and confidence were evaluated. RESULTS:The detection of any suspicious finding significantly improved for AI-aided compared with unaided readers with a significantly higher AUROC (0.974 [95% CI, 0.957-0.990] vs 0.825 [95% CI, 0.741-0.908], P=.002), sensitivity (0.935 [95% CI, 0.892-0.978] vs 0.782 [95% CI, 0.686-0.878]), and specificity (0.970 [95% CI, 0.949-0.991] vs 0.759 [95% CI, 0.630-0.887]). AI assistance also resulted in a significant decrease in clinician interpretation time and increase in clinician confidence score (226 seconds [95% CI, 218-234] vs 274 seconds [95% CI, 265-283], P<.001; 4.63 [95% CI, 4.60-4.66] vs 3.90 [95% CI, 3.85-3.95], P<.001, respectively). CONCLUSION/CONCLUSIONS:The use of AI-based software to assist clinicians was associated with enhanced identification of findings suspicious for CHD on prenatal ultrasonography.
PMID: 41100866
ISSN: 1873-233x
CID: 5955112

The COVID-19 Pandemic and Routine Prenatal Care: Use of Online Visits

Mobeen, Sadia; Fogel, Joshua; Harishankar, Krupa; Jacobs, Allan J
OBJECTIVE:To evaluate whether prenatal visits or screening/testing were fewer or occurred later during the initial phase of the COVID-19 pandemic in 2020 (CINT) as compared to the prior year (PreCINT). METHODS:A retrospective cohort study compared CINT (n = 2,195) to PreCINT (n = 2,395) at seven public hospitals in New York City. The primary outcome was total number of prenatal-care visits. Secondary outcomes were components of prenatal-care visits completion, timing of standard pregnancy screening tests, and adverse neonatal outcomes. RESULTS:CINT patients had more total prenatal-care visits (B = 1.30, 95% CI:1.04, 1.56, p < 0.001), lower odds for initiation of prenatal care which was inadequate according to widely used criteria (OR:0.39, 95% CI:0.34, 0.45, p < 0.001), and lower gestational age at initial visit (B=-4.51, 95% CI:-5.10, -3.93, p < 0.001) than PreCINT patients. In-person visits did not differ between the two groups. PreCINT patients had no televisits, while CINT patients had a median of one televisit (Median = 1, p < 0.001). CINT patients had increased odds for group B Streptococcus screening (OR:1.27, 95% CI: 1.10, 1.48, p = 0.001), quadrivalent screening (OR:1.30, 95% CI:1.15, 1.48, p < 0.001), and anatomy sonogram (OR:2.30, 95% CI:2.04, 2.59, p < 0.001) but decreased odds for glucose challenge test screening (OR:0.81, 95% CI:0.72, 0.91, p < 0.001). Adverse neonatal outcome did not differ between CINT and PreCINT pregnancies. CONCLUSIONS FOR PRACTICE/CONCLUSIONS:Despite the difficulties and perceived dangers of in-person visits during the COVID-19 pandemic, the COVID-19 pandemic had little negative impact upon the outpatient prenatal care received by patients in this hospital system.
PMID: 38270717
ISSN: 1573-6628
CID: 6072824