Jisoo Kim

Hiba Ahsan, Denis Jered McInerney, Jisoo Kim et al. · amazon-science, salesforce

Unstructured data in Electronic Health Records (EHRs) often contains critical information -- complementary to imaging -- that could inform radiologists' diagnoses. But the large volume of notes often associated with patients together with time constraints renders manually identifying relevant evidence practically infeasible. In this work we propose and evaluate a zero-shot strategy for using LLMs as a mechanism to efficiently retrieve and summarize unstructured evidence in patient EHR relevant to a given query. Our method entails tasking an LLM to infer whether a patient has, or is at risk of, a particular condition on the basis of associated notes; if so, we ask the model to summarize the supporting evidence. Under expert evaluation, we find that this LLM-based approach provides outputs consistently preferred to a pre-LLM information retrieval baseline. Manual evaluation is expensive, so we also propose and validate a method using an LLM to evaluate (other) LLM outputs for this task, allowing us to scale up evaluation. Our findings indicate the promise of LLMs as interfaces to EHR, but also highlight the outstanding challenge posed by "hallucinations". In this setting, however, we show that model confidence in outputs strongly correlates with faithful summaries, offering a practical means to limit confabulations.

Jisoo Kim, Chu-Hsuan Lin, Alberto Ceballos-Arroyo et al.

Introduction: Deep learning (DL) models can help detect intracranial aneurysms on CTA, but high false positive (FP) rates remain a barrier to clinical translation, despite improvement in model architectures and strategies like detection threshold tuning. We employed an automated, anatomy-based, heuristic-learning hybrid artery-vein segmentation post-processing method to further reduce FPs. Methods: Two DL models, CPM-Net and a deformable 3D convolutional neural network-transformer hybrid (3D-CNN-TR), were trained with 1,186 open-source CTAs (1,373 annotated aneurysms), and evaluated with 143 held-out private CTAs (218 annotated aneurysms). Brain, artery, vein, and cavernous venous sinus (CVS) segmentation masks were applied to remove possible FPs in the DL outputs that overlapped with: (1) brain mask; (2) vein mask; (3) vein more than artery masks; (4) brain plus vein mask; (5) brain plus vein more than artery masks. Results: CPM-Net yielded 139 true-positives (TP); 79 false-negative (FN); 126 FP. 3D-CNN-TR yielded 179 TP; 39 FN; 182 FP. FPs were commonly extracranial (CPM-Net 27.3%; 3D-CNN-TR 42.3%), venous (CPM-Net 56.3%; 3D-CNN-TR 29.1%), arterial (CPM-Net 11.9%; 3D-CNN-TR 53.3%), and non-vascular (CPM-Net 25.4%; 3D-CNN-TR 9.3%) structures. Method 5 performed best, reducing CPM-Net FP by 70.6% (89/126) and 3D-CNN-TR FP by 51.6% (94/182), without reducing TP, lowering the FP/case rate from 0.88 to 0.26 for CPM-NET, and from 1.27 to 0.62 for the 3D-CNN-TR. Conclusion: Anatomy-based, interpretable post-processing can improve DL-based aneurysm detection model performance. More broadly, automated, domain-informed, hybrid heuristic-learning processing holds promise for improving the performance and clinical acceptance of aneurysm detection models.