A toolbox for surfacing health equity harms and biases in large language models.

Large language models (LLMs) hold promise to serve complex health information needs but also have the potential to introduce harm and exacerbate health disparities. Reliably evaluating equity-related model failures is a critical step toward developing systems that promote health equity. We present resources and methodologies for surfacing biases with potential to precipitate equity-related harms in long-form, LLM-generated answers to medical questions and conduct a large-scale empirical case study with the Med-PaLM 2 LLM.

Memory-efficient low-compute segmentation algorithms for bladder-monitoring smart ultrasound devices.

Post-operative urinary retention is a medical condition where patients cannot urinate despite having a full bladder. Ultrasound imaging of the bladder is used to estimate urine volume for early diagnosis and management of urine retention. Moreover, the use of bladder ultrasound can reduce the need for an indwelling urinary catheter and the risk of catheter-associated urinary tract infection.

Multicontrast Pocket Colposcopy Cervical Cancer Diagnostic Algorithm for Referral Populations.

. We use deep learning models to classify cervix images-collected with a low-cost, portable Pocket colposcope-with biopsy-confirmed high-grade precancer and cancer. We boost classification performance on a screened-positive population by using a class-balanced loss and incorporating green-light colposcopy image pairs, which come at no additional cost to the provider.

A novel speculum-free imaging strategy for visualization of the internal female lower reproductive system.

Fear of the speculum and feelings of vulnerability during the gynecologic exams are two of the biggest barriers to cervical cancer screening for women. To address these barriers, we have developed a novel, low-cost tool called the Callascope to reimagine the gynecological exam, enabling clinician and self-imaging of the cervix without the need for a speculum. The Callascope contains a 2 megapixel camera and contrast agent spray mechanism housed within a form factor designed to eliminate the need for a speculum during contrast agent administration and image capture.

Combining multiple contrasts for improving machine learning-based classification of cervical cancers with a low-cost point-of-care Pocket colposcope.

We apply feature-extraction and machine learning methods to multiple sources of contrast (acetic acid, Lugol's iodine and green light) from the white Pocket Colposcope, a low-cost point of care colposcope for cervical cancer screening. We combine features from the sources of contrast and analyze diagnostic improvements with addition of each contrast. We find that overall AUC increases with additional contrast agents compared to using only one source.

Development of Algorithms for Automated Detection of Cervical Pre-Cancers With a Low-Cost, Point-of-Care, Pocket Colposcope.

Goal: In this paper, we propose methods for (1) automatic feature extraction and classification for acetic acid and Lugol's iodine cervigrams and (2) methods for combining features/diagnosis of different contrasts in cervigrams for improved performance.

Methods: We developed algorithms to pre-process pathology-labeled cervigrams and extract simple but powerful color and textural-based features. The features were used to train a support vector machine model to classify cervigrams based on corresponding pathology for visual inspection with acetic acid, visual inspection with Lugol's iodine, and a combination of the two contrasts.

An integrated strategy for improving contrast, durability, and portability of a Pocket Colposcope for cervical cancer screening and diagnosis.

Introduction: We have previously developed a portable Pocket Colposcope for cervical cancer screening in resource-limited settings. In this manuscript we report two different strategies (cross-polarization and an integrated reflector) to improve image contrast levels achieved with the Pocket Colposcope and evaluate the merits of each strategy compared to a standard-of-care digital colposcope. The desired outcomes included reduced specular reflection (glare), increased illumination beam pattern uniformity, and reduced electrical power budget.

Design and preliminary analysis of a vaginal inserter for speculum-free cervical cancer screening.

Objective: Cervical cancer screening usually requires use of a speculum to provide a clear view of the cervix. The speculum is one potential barrier to screening due to fear of pain, discomfort and embarrassment. The aim of this paper is to present and demonstrate the feasibility of a tampon-sized inserter and the POCkeT Colposcope, a miniature pen sized-colposcope, for comfortable, speculum-free and potentially self-colposcopy.