Black Box Warning: Large Language Models and the Future of Infectious Diseases Consultation.

Large language models (LLMs) are artificial intelligence systems trained by deep learning algorithms to process natural language and generate text responses to user prompts. Some approach physician performance on a range of medical challenges, leading some proponents to advocate for their potential use in clinical consultation and prompting some consternation about the future of cognitive specialties. However, LLMs currently have limitations that preclude safe clinical deployment in performing specialist consultations, including frequent confabulations, lack of contextual awareness crucial for nuanced diagnostic and treatment plans, inscrutable and unexplainable training data and methods, and propensity to recapitulate biases. Nonetheless, considering the rapid improvement in this technology, growing calls for clinical integration, and healthcare systems that chronically undervalue cognitive specialties, it is critical that infectious diseases clinicians engage with LLMs to enable informed advocacy for how they should-and shouldn't-be used to augment specialist care.

The Brain Tumor Segmentation (BraTS-METS) Challenge 2023: Brain Metastasis Segmentation on Pre-treatment MRI.

Clinical monitoring of metastatic disease to the brain can be a laborious and timeconsuming process, especially in cases involving multiple metastases when the assessment is performed manually. The Response Assessment in Neuro-Oncology Brain Metastases (RANO-BM) guideline, which utilizes the unidimensional longest diameter, is commonly used in clinical and research settings to evaluate response to therapy in patients with brain metastases. However, accurate volumetric assessment of the lesion and surrounding peri-lesional edema holds significant importance in clinical decision-making and can greatly enhance outcome prediction. The unique challenge in performing segmentations of brain metastases lies in their common occurrence as small lesions. Detection and segmentation of lesions that are smaller than 10 mm in size has not demonstrated high accuracy in prior publications. The brain metastases challenge sets itself apart from previously conducted MICCAI challenges on glioma segmentation due to the significant variability in lesion size. Unlike gliomas, which tend to be larger on presentation scans, brain metastases exhibit a wide range of sizes and tend to include small lesions. We hope that the BraTS-METS dataset and challenge will advance the field of automated brain metastasis detection and segmentation.

Causes of Death in Patients With Brain Metastases.

BACKGROUND AND OBJECTIVES: Advances in targeted therapies and wider application of stereotactic radiosurgery (SRS) have redefined outcomes of patients with brain metastases. Under modern treatment paradigms, there remains limited characterization of which aspects of disease drive demise and in what frequencies. This study aims to characterize the primary causes of terminal decline and evaluate differences in underlying intracranial tumor dynamics in patients with metastatic brain cancer. These fundamental details may help guide management, patient counseling, and research priorities. METHODS: Using NYUMets-Brain-the largest, longitudinal, real-world, open data set of patients with brain metastases-patients treated at New York University Langone Health between 2012 and 2021 with SRS were evaluated. A review of electronic health records allowed for the determination of a primary cause of death in patients who died during the study period. Causes were classified in mutually exclusive, but collectively exhaustive, categories. Multilevel models evaluated for differences in dynamics of intracranial tumors, including changes in volume and number. RESULTS: Of 439 patients with end-of-life data, 73.1% died secondary to systemic disease, 10.3% died secondary to central nervous system (CNS) disease, and 16.6% died because of other causes. CNS deaths were driven by acute increases in intracranial pressure (11%), development of focal neurological deficits (18%), treatment-resistant seizures (11%), and global decline driven by increased intracranial tumor burden (60%). Rate of influx of new intracranial tumors was almost twice as high in patients who died compared with those who survived ( P < .001), but there was no difference in rates of volume change per intracranial tumor ( P = .95). CONCLUSION: Most patients with brain metastases die secondary to systemic disease progression. For patients who die because of neurological disease, tumor dynamics and cause of death mechanisms indicate that the primary driver of decline for many may be unchecked systemic disease with unrelenting spread of new tumors to the CNS rather than failure of local growth control.

RadImageNet: An Open Radiologic Deep Learning Research Dataset for Effective Transfer Learning.

Purpose: To demonstrate the value of pretraining with millions of radiologic images compared with ImageNet photographic images on downstream medical applications when using transfer learning. Materials and Methods: This retrospective study included patients who underwent a radiologic study between 2005 and 2020 at an outpatient imaging facility. Key images and associated labels from the studies were retrospectively extracted from the original study interpretation. These images were used for RadImageNet model training with random weight initiation. The RadImageNet models were compared with ImageNet models using the area under the receiver operating characteristic curve (AUC) for eight classification tasks and using Dice scores for two segmentation problems. Results: The RadImageNet database consists of 1.35 million annotated medical images in 131 872 patients who underwent CT, MRI, and US for musculoskeletal, neurologic, oncologic, gastrointestinal, endocrine, abdominal, and pulmonary pathologic conditions. For transfer learning tasks on small datasets-thyroid nodules (US), breast masses (US), anterior cruciate ligament injuries (MRI), and meniscal tears (MRI)-the RadImageNet models demonstrated a significant advantage (P < .001) to ImageNet models (9.4%, 4.0%, 4.8%, and 4.5% AUC improvements, respectively). For larger datasets-pneumonia (chest radiography), COVID-19 (CT), SARS-CoV-2 (CT), and intracranial hemorrhage (CT)-the RadImageNet models also illustrated improved AUC (P < .001) by 1.9%, 6.1%, 1.7%, and 0.9%, respectively. Additionally, lesion localizations of the RadImageNet models were improved by 64.6% and 16.4% on thyroid and breast US datasets, respectively. Conclusion: RadImageNet pretrained models demonstrated better interpretability compared with ImageNet models, especially for smaller radiologic datasets.Keywords: CT, MR Imaging, US, Head/Neck, Thorax, Brain/Brain Stem, Evidence-based Medicine, Computer Applications-General (Informatics) Supplemental material is available for this article. Published under a CC BY 4.0 license.See also the commentary by Cadrin-Chênevert in this issue.

Population scale latent space cohort matching for the improved use and exploration of observational trial data.

A significant amount of clinical research is observational by nature and derived from medical records, clinical trials, and large-scale registries. While there is no substitute for randomized, controlled experimentation, such experiments or trials are often costly, time consuming, and even ethically or practically impossible to execute. Combining classical regression and structural equation modeling with matching techniques can leverage the value of observational data. Nevertheless, identifying variables of greatest interest in high-dimensional data is frequently challenging, even with application of classical dimensionality reduction and/or propensity scoring techniques. Here, we demonstrate that projecting high-dimensional medical data onto a lower-dimensional manifold using deep autoencoders and post-hoc generation of treatment/control cohorts based on proximity in the lower-dimensional space results in better matching of confounding variables compared to classical propensity score matching (PSM) in the original high-dimensional space (P<0.0001) and performs similarly to PSM models constructed by experts with prior knowledge of the underlying pathology when evaluated on predicting risk ratios from real-world clinical data. Thus, in cases when the underlying problem is poorly understood and the data is high-dimensional in nature, matching in the autoencoder latent space might be of particular benefit.

Remote Patient Monitoring Identifies the Need for Triage in Patients with Acute COVID-19 Infection.

Introduction: Telehealth was frequently used in the provision of care and remote patient monitoring (RPM) during the COVID-19 pandemic. The Precision Recovery Program (PRP) remotely monitored and supported patients with COVID-19 in their home environment. Materials and Methods: This was a single-center retrospective cohort study reviewing data acquired from the PRP clinical initiative. Results: Of the 679 patients enrolled in the PRP, 156 patients were screened by a clinician following a deterioration in symptoms and vital signs on a total of 240 occasions, and included in the analyses. Of these 240 occasions, 162 (67%) were escalated to the PRP physician. Thirty-six patients were referred to emergency department, with 12 (7%) admitted to the hospital. The most common risk factors coinciding with hospital admissions were cardiac (67%), age >65 (42%), obesity (25%), and pulmonary (17%). The most common symptoms reported that triggered a screening event were dyspnea/tachypnea (27%), chest pain (14%), and gastrointestinal issues (8%). Vital signs that commonly triggered a screening event were pulse oximetry (15%), heart rate (11%), and temperature (9%). Discussion: Common factors (risk factors, vital signs, and symptoms) among patients requiring screening, triage, and hospitalization were identified, providing clinicians with further information to support decision making when utilizing RPM in this cohort. Conclusion: A clinician-led RPM program for patients with acute COVID-19 infection provided supportive care and screening for deterioration. Similar models should be considered for implementation in COVID-19 cohorts and other conditions at risk of rapid clinical deterioration in the home setting.

Integrated Morphoelectric and Transcriptomic Classification of Cortical GABAergic Cells.

Neurons are frequently classified into distinct types on the basis of structural, physiological, or genetic attributes. To better constrain the definition of neuronal cell types, we characterized the transcriptomes and intrinsic physiological properties of over 4,200 mouse visual cortical GABAergic interneurons and reconstructed the local morphologies of 517 of those neurons. We find that most transcriptomic types (t-types) occupy specific laminar positions within visual cortex, and, for most types, the cells mapping to a t-type exhibit consistent electrophysiological and morphological properties. These properties display both discrete and continuous variation among t-types. Through multimodal integrated analysis, we define 28 met-types that have congruent morphological, electrophysiological, and transcriptomic properties and robust mutual predictability. We identify layer-specific axon innervation pattern as a defining feature distinguishing different met-types. These met-types represent a unified definition of cortical GABAergic interneuron types, providing a systematic framework to capture existing knowledge and bridge future analyses across different modalities.

The Neural Basis of Approach-Avoidance Conflict: A Model Based Analysis.

Approach-avoidance conflict arises when the drives to pursue reward and avoid harm are incompatible. Previous neuroimaging studies of approach-avoidance conflict have shown large variability in reported neuroanatomical correlates. These prior studies have generally neglected to account for potential sources of variability, such as individual differences in choice preferences and modeling of hemodynamic response during conflict. In the present study, we controlled for these limitations using a hierarchical Bayesian model (HBM). This enabled us to measure participant-specific per-trial estimates of conflict during an approach-avoidance task. We also employed a variable epoch method to identify brain structures specifically sensitive to conflict. In a sample of 28 human participants, we found that only a limited set of brain structures [inferior frontal gyrus (IFG), right dorsolateral prefrontal cortex (dlPFC), and right pre-supplementary motor area (pre-SMA)] are specifically correlated with approach-avoidance conflict. These findings suggest that controlling for previous sources of variability increases the specificity of the neuroanatomical correlates of approach-avoidance conflict.