Strategies for creation of data reserve and stress testing of medical AI products.

With the fast development of artificial intelligence (AI) and its applications in medicine, it is often said that the time for intelligent medicine is arriving, if not already have arrived. While there is no doubt that AI-centred intelligent medicine will transform current healthcare, it is necessary to test and re-test medical AI (MAI) products before they are implemented in the real world. From the perspective of ensuring safety, accuracy and efficiency, it is imperative that MAIs undergo stress tests in a systematic and comprehensive manner where stress tests subject MAIs to workloads and environments beyond tests carried out by their developers.

Towards Reducing Diagnostic Errors with Interpretable Risk Prediction.

Many diagnostic errors occur because clinicians cannot easily access relevant information in patient Electronic Health Records (EHRs). In this work we propose a method to use LLMs to identify pieces of evidence in patient EHR data that indicate increased or decreased risk of specific diagnoses; our ultimate aim is to increase access to evidence and reduce diagnostic errors. In particular, we propose a Neural Additive Model to make predictions backed by evidence with individualized risk estimates at time-points where clinicians are still uncertain, aiming to specifically mitigate delays in diagnosis and errors stemming from an incomplete differential.

U.S. Medical School Graduates' Placement in Graduate Medical Education: A National Study.

Purpose: This study describes graduate medical education (GME) placement outcomes for recent U.S. medical school graduates and examines racial and ethnic differences in GME placement among these graduates.

Retrieving Evidence from EHRs with LLMs: Possibilities and Challenges.

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.

Auto-segmentation of Adult-Type Diffuse Gliomas: Comparison of Transfer Learning-Based Convolutional Neural Network Model vs. Radiologists.

Segmentation of glioma is crucial for quantitative brain tumor assessment, to guide therapeutic research and clinical management, but very time-consuming. Fully automated tools for the segmentation of multi-sequence MRI are needed. We developed and pretrained a deep learning (DL) model using publicly available datasets A (n = 210) and B (n = 369) containing FLAIR, T2WI, and contrast-enhanced (CE)-T1WI.

Oncologic Safety of Close Margins in Patients With Low- to Intermediate-Grade Major Salivary Gland Carcinoma.

Importance: Postoperative radiation therapy for close surgical margins in low- to intermediate-grade salivary carcinomas lacks multi-institutional supportive evidence.

Objective: To evaluate the oncologic outcomes for low- and intermediate-grade salivary carcinomas with close and positive margins.

Design, Setting, And Participants: The American Head and Neck Society Salivary Gland Section conducted a retrospective cohort study from 2010 to 2019 at 41 centers.

The impact of COVID-19 on patients diagnosed with melanoma, breast, and colorectal cancer.

Background: The COVID-19 pandemic impacted healthcare resource allocation and utilization of preventative medical services. It is unknown if there is resultant stage migration of melanoma, breast, and colorectal cancer when comparing extended time periods before and after the pandemic onset.

Methods: A retrospective cohort study of melanoma, breast, and colorectal cancer patients was completed.

Association Between a Medical School Applicant's Community College Attendance and the Likelihood of Application Acceptance: An Investigation of Select Medical School Characteristics.

Purpose: One-third of medical school applicants attend a community college (CC), and they represent a diverse group of applicants. However, they have a lower likelihood of being accepted to medical school. Using application-level data, this study examines how an applicant's CC attendance impacts the likelihood of application acceptance and how 3 medical school characteristics moderate this association.

Neuroimaging of COVID-19.

We review the wide variety of common neuroimaging manifestations related to coronavirus disease 2019 (COVID-19) and COVID therapies, grouping the entities by likely pathophysiology, recognizing that the etiology of many entities remains uncertain. Direct viral invasion likely contributes to olfactory bulb abnormalities. COVID meningoencephalitis may represent direct viral infection and/or autoimmune inflammation.

Increasing the Representation of Black Men in Medicine by Addressing Systems Factors.

In 2015, data released by the Association of American Medical Colleges (AAMC) showed that there were more Black men applying and matriculating to medical school in 1978 than 2014. The representation of Black men in medicine is a troubling workforce issue that was identified by the National Academies of Sciences, Engineering, and Medicine as a national crisis. While premedical pathway programs have contributed to increased workforce diversity, alone they are insufficient to accelerate change.

Toward More Accessible Fully Automated 3D Volumetric MRI Decision Trees for the Differential Diagnosis of Multiple System Atrophy, Related Disorders, and Age-Matched Healthy Subjects.

Differentiating multiple system atrophy (MSA) from related neurodegenerative movement disorders (NMD) is challenging. MRI is widely available and automated decision-tree analysis is simple, transparent, and resistant to overfitting. Using a retrospective cohort of heterogeneous clinical MRIs broadly sourced from a tertiary hospital system, we aimed to develop readily translatable and fully automated volumetric diagnostic decision-trees to facilitate early and accurate differential diagnosis of NMDs.

Submandibular gland transfer for the prevention of radiation-induced xerostomia in oropharyngeal cancer: Dosimetric impact in the intensity modulated radiotherapy era.

Background: Submandibular gland (SMG) transfer decreased radiation-associated xerostomia in the 2/3-dimensional radiotherapy era. We evaluated the dosimetric implications of SMG transfer on modern intensity modulated radiotherapy (IMRT) plans.

Methods: Eighteen oropharynx cancer patients underwent SMG transfer followed by IMRT; reoptimized plans using the baseline SMG location were generated.

Clinical 7T MRI for epilepsy care: Value, patient selection, technical issues, and outlook.

Ultra-high-field 7.0 Tesla (T) MRI offers substantial gains in signal-to-noise ratio (SNR) over 3T and 1.5T, but for over two decades has remained a research tool, while 3T scanners have achieved widespread clinical use.

7T versus 3T MRI in the presurgical evaluation of patients with drug-resistant epilepsy.

Background And Purpose: MRI has a crucial role in presurgical evaluation of drug-resistant focal epilepsy patients. Whether and how much 7T MRI further improves presurgical diagnosis compared to standard of care 3T MRI remains to be established. We investigate the added value 7T MRI offers in surgical candidates with remaining clinical uncertainty after 3T MRI.

A New Framework of Designing Iterative Techniques for Image Deblurring.

In this work we present a framework of designing iterative techniques for image deblurring in inverse problem. The new framework is based on two observations about existing methods. We used Landweber method as the basis to develop and present the new framework but note that the framework is applicable to other iterative techniques.

Identification of α1,2-fucosylated signaling and adhesion molecules in head and neck squamous cell carcinoma.

Head and neck cancer is the seventh most common cancer in the world, and most cases manifest as head and neck squamous cell carcinoma. Despite the prominent role of fucosylated carbohydrate antigens in tumor cell adhesion and metastasis, little is known about the functional role of fucose-modified glycoproteins in head and neck cancer pathobiology. Inactivating polymorphisms of the fut2 gene, encoding for the α1,2-fucosyltransferase FUT2, are associated with an increased incidence of head and neck cancer among tobacco users.

Myeloid Cells Are Enriched in Tonsillar Crypts, Providing Insight into the Viral Tropism of Human Papillomavirus.

Viruses are the second leading cause of cancer worldwide, and human papillomavirus (HPV)-associated head and neck cancers are increasing in incidence in the United States. HPV preferentially infects the crypts of the tonsils rather than the surface epithelium. The present study sought to characterize the unique microenvironment within the crypts to better understand the viral tropism of HPV to a lymphoid-rich organ.

A Comparative Retrospective Study of Immunotherapy RANO Standard RANO Criteria in Glioblastoma Patients Receiving Immune Checkpoint Inhibitor Therapy.

Objectives: Real-time assessment of treatment response in glioblastoma (GBM) patients on immune checkpoint blockade (ICB) remains challenging because inflammatory effects of therapy may mimic progressive disease, and the temporal evolution of these inflammatory findings is poorly understood. We compare GBM patient response during ICB as assessed with the Immunotherapy Response Assessment in Neuro-Oncology (iRANO) and the standard Response Assessment in Neuro-Oncology (RANO) radiological criteria.

Methods: 49 GBM patients (seven newly diagnosed and 42 recurrent) treated with ICBs at a single institution were identified.

Triggers of thyroid cancer diagnosis: a systematic review and meta-analysis.

Purpose: Understanding the method of thyroid cancer detection has potential implications on interpreting incidence rates, the diagnosis and management of thyroid cancer. We conducted a systematic review of studies reporting methods of thyroid cancer detection to estimate the frequency of incidentally found cancers and classify triggers of incidental thyroid cancer diagnosis.

Methods: We searched multiple bibliographic databases from inception to June 2020.

Deep-Learning Detection of Cancer Metastases to the Brain on MRI.

Background: Approximately one-fourth of all cancer metastases are found in the brain. MRI is the primary technique for detection of brain metastasis, planning of radiotherapy, and the monitoring of treatment response. Progress in tumor treatment now requires detection of new or growing metastases at the small subcentimeter size, when these therapies are most effective.