Search

Background: Ultrasound (US) imaging is characterised by high levels of operator subjectivity and variability. Recent advances in artificial intelligence (AI) have demonstrated the potential to reduce both factors. This study pilots the end-to-end automation of multiple elements of the mid-trimester obstetric screening US scan using AI-enabled tools. Methods: A single centre, prospective method comparison study was conducted. Participants had both standard manual and AI-assisted US scans performed independently by different blinded sonographers. The AI-tools automated the acquisition of standard plane images, measurement of fetal biometrics and the production of a written clinical report with saved images available for review. A feedback survey captured the sonographers’ perception of scanning with both methods. Findings: Twenty-three subjects were studied. The average time saving per scan was 7.62 min (34.7%) when using the AI-assisted method (p

ImportanceObtaining follow-up blood cultures (FUBCs) in patients with Staphylococcus aureus bloodstream infection (BSI) is standard practice, although its utility in patients with gram-negative bacterial BSI (GN-BSI) is unclear.ObjectiveTo examine whether obtaining FUBCs is associated with decreased mortality (key question [KQ] 1) and whether positive vs negative FUBCs are associated with increased mortality (KQ2).Data SourcesMEDLINE, EMBASE, Cochrane Central Register of Controlled Trials, Web of Science, and gray literature were searched from inception to March 11, 2022.Study SelectionTwo investigators used predefined eligibility criteria to independently screen titles, abstracts, and relevant full texts. Randomized clinical trials or observational studies that matched or statistically adjusted for differences in, at minimum, level of acute illness between patients in the intervention (eg, FUBCs obtained) and control (eg, FUBCs not obtained) groups were included in primary analyses. Articles published in languages other than English were excluded.Data Extraction and SynthesisData abstraction and quality assessments were performed by one investigator and verified by a second investigator. Risk of bias was assessed with the Newcastle-Ottawa Scale. Effect sizes were pooled using random-effects models. The study followed the Meta-analysis of Observational Studies in Epidemiology (MOOSE) reporting guideline.Main Outcomes and MeasuresMortality before hospital discharge or up to 30 days from the index blood culture.ResultsFrom 3495 studies, 15 were included (all nonrandomized). In the 5 studies (n = 4378 patients) that met criteria for the KQ1 primary analysis, obtaining FUBCs was associated with decreased mortality (hazard ratio, 0.56; 95% CI, 0.45-0.71). For KQ2, 2 studies met criteria for the primary analysis (ie, matched or statistically adjusted for differences in patients with positive vs negative FUBCs), so an exploratory meta-analysis of all 9 studies that investigated KQ2 (n = 3243 patients) was performed. Positive FUBCs were associated with increased mortality relative to negative blood cultures (odds ratio, 2.27; 95% CI, 1.54-3.34). Limitations of the literature included a lack of randomized studies and few patient subgroup analyses.Conclusions and RelevanceIn this systematic review and meta-analysis, obtaining FUBCs in patients with GN-BSI was associated with decreased mortality. The benefit of FUBCs may stem from identification of patients with positive FUBCs, which was a poor prognostic marker.

Fetal ultrasound screening during pregnancy plays a vital role in the early detection of fetal malformations which have potential long-term health impacts. The level of skill required to diagnose such malformations from live ultrasound during examination is high and resources for screening are often limited. We present an interpretable, atlas-learning segmentation method for automatic diagnosis of Hypo-plastic Left Heart Syndrome (HLHS) from a single `4 Chamber Heart' view image. We propose to extend the recently introduced Image-and-Spatial Transformer Networks (Atlas-ISTN) into a framework that enables sensitising atlas generation to disease. In this framework we can jointly learn image segmentation, registration, atlas construction and disease prediction while providing a maximum level of clinical interpretability compared to direct image classification methods. As a result our segmentation allows diagnoses competitive with expert-derived manual diagnosis and yields an AUC-ROC of 0.978 (1043 cases for training, 260 for validation and 325 for testing)., Comment: MICCAI'21 Main Conference

Patient-specific models of blood flow are being used clinically to diagnose and plan treatment for coronary artery disease. A remaining challenge is bridging scales from flow in arteries to the micro-circulation supplying the myocardium. Previously proposed models are descriptive rather than predictive and have not been applied to human data. The goal here is to develop a multiscale patient-specific model enabling blood flow simulation from large coronary arteries to myocardial tissue. Patient vasculatures are segmented from coronary computed tomography angiography data and extended from the image-based model down to the arteriole level using a space-filling forest of synthetic trees. Blood flow is modeled by coupling a 1D model of the coronary arteries to a single-compartment Darcy myocardium model. Simulated results on five patients with non-obstructive coronary artery disease compare overall well to [$$^{15}$$ 15 O]$$\text {H}_{{2}}$$ H 2 O PET exam data for both resting and hyperemic conditions. Results on a patient with severe obstructive disease link coronary artery narrowing with impaired myocardial blood flow, demonstrating the model’s ability to predict myocardial regions with perfusion deficit. This is the first report of a computational model for simulating blood flow from the epicardial coronary arteries to the left ventricle myocardium applied to and validated on human data.

Clinical Background and Epidemiology: Worldwide, an estimated 38 million people are living with HIV infection. The classic kidney disease of HIV infection, commonly known as HIV-associated nephropathy, is a collapsing form of focal segmental glomerulosclerosis that almost exclusively affects individuals of African descent with advanced HIV disease. People living with HIV are also at risk for immune-complex kidney diseases, antiretroviral nephrotoxicity, and kidney disease due to co-infections and comorbidities. Challenges: The burden of HIV-related kidney disease is greatest in traditionally disadvantaged populations in resource-limited settings in sub-Saharan Africa and the Caribbean and among minority populations in the United States and Europe. Factors contributing to these disparities include a higher prevalence of HIV infection, limited access to optimal antiretroviral therapy, and genetic susceptibility to kidney disease. Treatment and Prevention: Current treatment guidelines recommend the initiation of life-long antiretroviral therapy in all people living with HIV to prevent AIDS and non-AIDS complications, including kidney disease. People living with HIV who progress to end-stage kidney disease despite treatment are candidates for dialysis and kidney transplant, including the possibility of accepting organs from HIV-positive donors in some settings. Although HIV prevention is currently the only definitive solution, expanding access to antiretroviral therapy, dialysis, and kidney transplantation in people living with HIV are important intermediate steps to address the global burden of HIV-related kidney disease.

Background Solid organ transplant (SOT) recipients are characterized by extensive healthcare exposure and have high rates of Staphylococcus aureus bacteremia (SAB). The clinical characteristics and outcome determinants of SAB in this population are poorly understood. We undertook a prospective cohort study compared the bacterial genotype and clinical outcomes of SAB among SOT and non-solid organ transplant (non-SOT) recipients. Methods Consecutive patients presenting to our institution with SAB between January 1, 2016 and December 31, 2019 were eligible for study inclusion. Each subject’s initial S. aureus bloodstream isolate was genotyped using spa typing and assigned to clonal complexes using Ridom StaphType software. Results A total of 32 SOT and 634 non-SOT recipients with SAB were included. Bacterial genotype did not differ significantly between SOT and non-SOT recipients (p=0.4855), including the proportion of SAB caused by USA300 (12.5% vs 16.7%, p=0.6339). Ninety-day mortality and incidence of metastatic complications did not significantly differ between SOT and non-SOT recipients (18.8% vs 30.1%, p=0.2329, and 37.5% vs 48.6%, p=0.2769, respectively). Transplant status was significantly associated with septic shock (50.0% vs 21.8%, adjusted OR 2.63, 95% CI: 1.22 to 5.66). Infection with USA300 was not associated with 90-day mortality or septic shock among SOT recipients (p=1.0000 for both). Staphylococcus aureus Genotype by Transplant Status Conclusion In conclusion, SOT recipients with SAB do not experience greater mortality than non-SOT recipients. Differences in genotype of the infecting bacteria do not appear to be a significant determinant of outcome in SOT recipients with SAB. Disclosures Vance G. Fowler, Jr., MD, MHS, Achaogen (Consultant)Advanced Liquid Logics (Grant/Research Support)Affinergy (Consultant, Grant/Research Support)Affinium (Consultant)Akagera (Consultant)Allergan (Grant/Research Support)Amphliphi Biosciences (Consultant)Aridis (Consultant)Armata (Consultant)Basilea (Consultant, Grant/Research Support)Bayer (Consultant)C3J (Consultant)Cerexa (Consultant, Other Financial or Material Support, Educational fees)Contrafect (Consultant, Grant/Research Support)Debiopharm (Consultant, Other Financial or Material Support, Educational fees)Destiny (Consultant)Durata (Consultant, Other Financial or Material Support, educational fees)Genentech (Consultant, Grant/Research Support)Green Cross (Other Financial or Material Support, Educational fees)Integrated Biotherapeutics (Consultant)Janssen (Consultant, Grant/Research Support)Karius (Grant/Research Support)Locus (Grant/Research Support)Medical Biosurfaces (Grant/Research Support)Medicines Co. (Consultant)MedImmune (Consultant, Grant/Research Support)Merck (Grant/Research Support)NIH (Grant/Research Support)Novadigm (Consultant)Novartis (Consultant, Grant/Research Support)Pfizer (Grant/Research Support)Regeneron (Consultant, Grant/Research Support)sepsis diagnostics (Other Financial or Material Support, Pending patent for host gene expression signature diagnostic for sepsis.)Tetraphase (Consultant)Theravance (Consultant, Grant/Research Support, Other Financial or Material Support, Educational fees)Trius (Consultant)UpToDate (Other Financial or Material Support, Royalties)Valanbio (Consultant, Other Financial or Material Support, Stock options)xBiotech (Consultant)