Citations

Abstract Aims Heart failure (HF), a major global health challenge, affects millions worldwide and poses substantial healthcare and economic burdens. It is estimated that a large proportion of those with early systolic dysfunction remain asymptomatic at a stage when guideline-directed medical therapies have been shown to prevent disease progression. To develop an artificial intelligence (AI) model capable of predicting abnormal left ventricular ejection fraction (EF) directly from static, non-gated, non-contrast chest computed tomography (CT) scans as a form of opportunistic screening, Methods and results Using a multi-institutional dataset of 34 058 paired non- contrast CT images and echocardiogram reports from two academic centres, we trained our model of classification for predicting left-ventricle ejection fraction (LVEF) categories: abnormal EF (EF < 50%) vs. normal on 25 948 studies. We validated the model on 8110 paired chest CT and echocardiogram results from a separate institution. The model achieved an area under the receiver operating characteristic (AUROC) curve of 0.786 on the hold-out test set and 0.762 on external validation to detect an abnormal EF (<50%). Beyond strong predictive performance, the AI model surpassed expert radiologists in both accuracy and efficiency and provided interpretable visualizations highlighting imaging features linked to reduced LVEF. Conclusion In this study, we developed and validated an AI model capable of predicting abnormal LVEF directly from static, non-gated, non-contrast chest CT scans, a novel application for an imaging modality typically used for unrelated indications as a form of opportunistic screening. This technology holds significant promise for early detection of systolic HF, reducing the diagnostic gap, and improving outcomes in asymptomatic HF patients.

Background: Artificial intelligence (AI), particularly generative and large language models, is being used in nursing education, practice, and scholarly writing. Generative AI applications have been specifically examined for their use in conducting literature reviews with evidence supporting reduced production time of scholarly work. However, there has been limited investigation of their levels of accuracy with identifying references for a literature review. Objective: The purpose of this study was to compare human-generated citations of literature reviews with AI literature-review generated citations. Methods: Using a comparative exploratory design, references from 4 human-written literature reviews, 2 published and 2 unpublished, on 4 different topics, were compared to references derived from 2 AI literature applications, Consensus and Elicit. Three prompting strategies were utilized, including prompts generated using ChatGPT-4. Agreement between the AI and human references was evaluated. Results: The percent of agreement between AI and human generated reference lists ranged from 0% to 63.6%. The Consensus application had a greater overall mean rate of match (21.3%) as compared to Elicit (3.7%). The use of a ChatGPT-4 prompt did not significantly impact results, and there were no differences based on published or unpublished literature reviews. Conclusion: The 2 literature-based applications examined in this study offered a glimpse of their potential use and limitations. The use of an AI literature review application may support but not replace human work.

ABSTRACT Background This study aimed to explore the effect of family history (FH) and polygenic risk scores (PRS) for multiple psychiatric disorders on lithium response in bipolar disorder (BD). Method The sample included patients from the Mayo Clinic BD Biobank. FH in first‐degree relatives was obtained via the patient questionnaire. Linear regression models tested the association of FH and PRS for BD, major depressive disorder (MDD), schizophrenia (SCZ), alcohol use disorder (AUD), anxiety disorder (ANX), and attention‐deficit/hyperactivity disorder (ADHD) with lithium response measured by the Alda A score adjusted for the Alda B sum score. Post hoc models additionally adjusted for clinical covariates (age at onset, rapid cycling, and BD subtype). Results 716 patients had Alda scores for lithium response (61.9% females, mean age = 43.4 years). FH‐BD ( β = −0.57, p = 0.015), AUD ( β = −0.44, p = 0.045), and ANX ( β = −0.61, p = 0.050) were associated with worse lithium response. After adjusting for clinical covariates, associations for FH‐BD and FH‐ANX were no longer significant. PRS‐BD was associated with better response ( β = 0.22, p = 0.041), while PRS‐MDD ( β = −0.28, p = 0.01) and PRS‐ADHD ( β = −0.24, p = 0.028) were associated with worse response, with effects largely unchanged after adjusting for clinical covariates. In the combined model considering all FHs simultaneously, only FH‐BD remained significantly associated with worse lithium response ( β = −0.71, p = 0.039). In the combined model for PRS, only PRS‐BD ( β = 0.31, p = 0.008; better response) and PRS‐MDD ( β = −0.29, p = 0.020; worse response) showed significant associations. Conclusions In this exploratory study, FH‐BD, AUD, and ANX were associated with poor response, though only FH‐AUD remained significant after adjusting for clinical factors. PRS‐BD predicted better response, while PRS‐MDD was associated with worse response. These findings suggest independent and potentially complementary roles of FH and PRS. Integrating both familial and genetic risk measures may improve personalized treatment strategies and outcomes for BD patients.