A Representativeness-informed Model for Research Record Selection from Electronic Medical Record Systems

Victor A Borza, Ellen Wright Clayton, Murat Kantarcioglu, Yevgeniy Vorobeychik, Bradley Malin

Scientific and clinical studies have a long history of bias in recruitment of underprivileged and minority populations. This underrepresentation leads to inaccurate, inapplicable, and non-generalizable results…

Split Learning for Distributed Collaborative Training of Deep Learning Models in Health Informatics

Li Z, Yan C, Zhang X, Gharibi G, Yin Z, Jiang X, Malin BA

Deep learning continues to rapidly evolve and is now demonstrating remarkable potential for numerous medical prediction tasks. However, realizing deep learning models that generalize across healthcare organizations is challenging…

Towards Fair Patient-Trial Matching via Patient-Criterion Level Fairness Constraint

Chang C-Y, Yuan J, Ding S, Tan Q, Zhang K, Jiang X, Hu X, Zou N

Clinical trials are indispensable in developing new treatments, but they face obstacles in patient recruitment and retention, hindering the enrollment of necessary participants. To tackle these challenges, deep learning frameworks have been created to match patients to trials…

Sensitive Data Detection with High-Throughput Machine Learning Models in Electrical Health Records

Zhang K, Jiang X

In the era of big data, there is an increasing need for healthcare providers, communities, and researchers to share data and collaborate to improve health outcomes, generate valuable insights, and advance research. The Health Insurance Portability and Accountability Act of 1996 (HIPAA) is a federal law designed to protect sensitive health information by defining regulations for protected health information (PHI). However, it does not provide efficient tools for detecting or removing PHI before data sharing…

Does Synthetic Data Generation of LLMs Help Clinical Text Mining?

Tang R, Han X, Jiang X, Hu X

Recent advancements in large language models (LLMs) have led to the development of highly potent models like OpenAI’s ChatGPT. These models have exhibited exceptional performance in a variety of tasks, such as question answering, essay composition, and code generation. However, their effectiveness in the healthcare sector remains uncertain…

NIH to Inject Health Bolus of Data to Sustain the Future for Medical Discoveries

Thomas M. Johnson and Grace C.Y. Peng 

Computational modeling and artificial intelligence (AI) are integrating into medicine and biomedical research at a dizzying pace. Practitioners are utilizing AI in all aspects of healthcare, from the staging of lung cancer nodules on MRI images to workflow management in hospitals…

When Personalization Harms: Reconsidering the Use of Group Attributes in Prediction

Suriyakumar V, Ghassemi M, Ustun B. When personalization harms performance: reconsidering the use of group attributes in prediction. Proceedings of the International Conference on Machine Learning (ICML). 2013: in press.

Machine learning models are often personalized with categorical attributes that are protected, sensitive, self-reported, or costly to acquire. In this work, we show models that are personalized with group attributes can reduce performance at a group level…

Cross-Team Collaboration and Diversity in the Bridge2AI Project

Huimin Xu, Chitrank Gupta, Zhandos Sembay, Swathi Thaker, Pamela Payne-Foster, Jake Chen, and Ying Ding. 2023. Cross-Team Collaboration and Diversity in the Bridge2AI Project. In Companion Proceedings of the ACM Web Conference 2023 (WWW ’23 Companion). Association for Computing Machinery, New York, NY, USA, 790–794.

The Bridge2AI project, funded by the National Institutes of Health, involves researchers from different disciplines and backgrounds to develop well-curated AI health data and tools…

Enhancing Fairness in Disease Prediction by Optimizing Multiple Domain Adversarial Networks

Bin Li, Xinghua Shi, Hongchang Gao, Xiaoqian Jiang, Kai Zhang, Arif O Harmanci, Bradley Malin

Predictive models in biomedicine need to ensure equitable and reliable outcomes for the populations they are applied to. Unfortunately, biases in medical predictions can lead to unfair treatment and widening disparities…

Human-Centered Design to Address Biases in Artificial Intelligence

You Chen, Ellen Wright Clayton, Laurie Lovett Novak, Shilo Anders, and Bradley Malin

Artificial intelligence (AI) promises to help health organizations deliver equitable care to their patients and optimize administrative processes. However, the complex life cycle of AI can be biased in ways that exacerbate health disparities and inequities…

Blockchain-enabled immutable, distributed, and highly available clinical research activity logging system for federated COVID-19 data analysis from multiple institutions

Tsung-Ting Kuo,  Anh Pham,  Maxim E Edelson,  Jihoon Kim,  Jason Chan,  Yash Gupta,  Lucila Ohno-Machado, The R2D2 Consortium

We aimed to develop a distributed, immutable, and highly available cross-cloud blockchain system to facilitate federated data analysis activities among multiple institutions.

Quorum-based model learning on a blockchain hierarchical clinical research network using smart contracts

Tsung-Ting Kuo, Anh Pham

We aim at addressing the site availability issue on a hierarchical network by designing an immutable/transparent/source-verifiable quorum mechanism.

Evaluation of software impact designed for biomedical research: Are we measuring what’s meaningful?

Awan Afiaz, Andrey A. Ivanov, John Chamberlin, David Hanauer, Candace L. Savonen, Mary J. Goldman,Martin Morgan, Michael Reich, Alexander Getka, Aaron Holmes, Sarthak Pati, Dan Knight, Paul C. Boutros, Spyridon Bakas, J. Gregory Caporaso, Guilherme Del Fiol, Harry Hochheiser, Brian Haas, Patrick D. Schloss, James A. Eddy, Jake Albrecht, Andrey Fedorov, Levi Waldron, Ava M. Hoffman, Richard L. Bradshaw, Jeffrey T. Leek, and  Carrie Wright

Software is vital for the advancement of biology and medicine. Through analysis of usage and impact metrics of software, developers can help determine user and community engagement. These metrics can be used to justify additional funding, encourage additional use, and identify unanticipated use cases…

Correlations Between Anxiety and/or Depression Diagnoses and Dysphagia Severity

Can Doruk, Valentina Mocchetti, Hal Rives, Paul Christos, Anaïs Rameau

An increased prevalence of mood and anxiety disorders in patients with dysphagia has been noted previously, but whether dysphagia severity may be exacerbated by anxiety and depression has never been studied before…

In Response to Concurrent Validity of the IOPI and Tongueometer Orofacial Strength Measurement Devices

James A. Curtis, Valentina Mocchetti, Anaïs Rameau

Female Surgical Ergonomics in Otolaryngology: A National Survey Study

Elliot Morse, Katherine Tai, Lexa Harpel, Hayley Born, Priya Krishna, Anaïs Rameau

Ergonomics, the study of the interaction between a worker and their job environment, is receiving increased attention in the field of surgery. The occupational need for prolonged standing, prolonged holding of ergonomically suboptimal postures, use of varied equipment…

Concurrent Validity of a Low-Cost Manometer for Objective Assessments of Respiratory Muscle Strength

James A. Curtis, Valentina Mocchetti, Anaïs Rameau

This study examined the agreement in maximal expiratory (MEP) and inspiratory (MIP) pressure readings between two digital manometers: (1) the MicroRPM – the gold-standard manometer for respiratory muscle strength testing; and (2) the LDM – a low-cost, commercially available, alternative manometer…

Generative AI, Specific Moral Values: A Closer Look at ChatGPT’s New Ethical Implications for Medical AI

Gavin Victora, Jean-Christophe Bélisle-Pipon, Vardit Ravitsky

Cohen’s (Citation2023) mapping exercise of possible bioethical issues emerging from the use of ChatGPT in medicine provides an informative, useful, and thought-provoking trigger for discussions of AI ethics in health…

A deep learning pipeline for automated classification of vocal fold polyps in flexible laryngoscopy

Peter Yao, Dan Witte, Alexander German, Preethi Periyakoil , Yeo Eun Kim, Hortense Gimonet, Lucian Sulica, Hayley Born, Olivier Elemento, Josue Barnes, Anaïs Rameau

Purpose: To develop and validate a deep learning model for distinguishing healthy vocal folds (HVF) and vocal fold polyps (VFP) on laryngoscopy videos, while demonstrating the ability of a previously developed informative frame classifier in facilitating deep learning development.

Outcomes of Gender-Affirming Voice and Communication Modification Training for Non-binary Individuals: A Case Series

Keith A. Chadwick, David Liao, Isaac L. Alter, Rachel Coleman, Katerina Andreadis, Rebecca Riekki, Jack Waldman, Hal Rives, Mary Pitti, Anaïs Rameau

There is currently no research reporting solely on outcomes of voice and communication modification training (VCMT) in individuals who identify as non-binary and genderqueer (NBGQ) in the English literature…

Cough Sounds in Screening and Diagnostics: A Scoping Review

Siddhi Hegde, Shreya Sreeram, Isaac L Alter, Chaya Shor, Tulio A Valdez, Kara D Meister, Anaïs Rameau

The aim of the study was to examine applications of cough sounds towards screening tools and diagnostics in the biomedical and engineering literature, with particular focus on disease types, acoustic data collection protocols, data processing and analytics, accuracy, and limitations…

Artificial Intelligence Governance and Otolaryngology-Head and Neck Surgery

Obinna I Nwosu, Matthew G Crowson, Anaïs Rameau

This rapid communication highlights components of artificial intelligence governance in healthcare and suggests adopting key governance approaches in otolaryngology – head and neck surgery…

Virtual Reality for Pain Management During High-Resolution Manometry: A Randomized Clinical Trial

Ilan Palte, Sarah Stewart, Hal Rives, James A Curtis, Necati Enver, Andrew Tritter, Katerina Andreadis, Valentina Mocchetti, Felice Schnoll-Sussman, Amir Soumekh, Rasa Zarnegar, Philip Katz, Anaïs Rameau

High-resolution esophageal manometry (HRM) is the gold standard for the diagnosis of esophageal motility disorders. HRM is typically performed in the office with local anesthesia only, and many patients find it unpleasant and painful…

Validation of a 3D-Printed Percutaneous Injection Laryngoplasty Simulator: A Randomized Controlled Trial

Julianna C Kostas, Andrew S Lee, Amit Arunkumar, Catherine Han, Mark Lee, Alexander N Goel, James Alrassi, Tyler Crosby, Christine M Clark, Milan Amin, Sara Abu-Ghanem, Diana Kirke, Anaïs Rameau

Simulation may be a valuable tool in training laryngology office procedures on unsedated patients. However, no studies have examined whether existing awake procedure simulators improve trainee performance in laryngology…

Concurrent Validity of the IOPI and Tongueometer Orofacial Strength Measurement Devices

James A Curtis, Valentina Mocchetti, Anaïs Rameau

 This study examined the concurrent validity of two orofacial strength manometers: (1) the Iowa Oral Performance Instrument (IOPI) – the current, gold standard orofacial manometer; and (2) the Tongueometer – a newly-available, lower cost, orofacial manometer…

Female Surgical Ergonomics in Otolaryngology: A Qualitative Study

Elliot Morse, Lexa Harpel, Hayley Born, Anaïs Rameau

In the past several decades, surgical ergonomics has received increased attention, in part due to high rates of musculoskeletal injuries reported by many surgeons. Surgery is a historically male-dominated field, and the operating room environment and instrumentation have been designed to accommodate the average male surgeon…

ADGR: Admixture-Informed Differential Gene Regulation

In-Hee Lee and Sek Won Kong

The regulatory elements in proximal and distal regions of genes are involved in the regulation of gene expression. Risk alleles in intronic and intergenic regions may alter gene expression by modifying the binding affinity and stability of diverse DNA-binding proteins implicated in gene expression regulation…

Identifying bias in models that detect vocal fold paralysis from audio recordings using explainable machine learning and clinician ratings

Daniel M. Low, Vishwanatha Rao, Gregory Randolph, Phillip C. Song, Satrajit S. Ghosh

Detecting voice disorders from voice recordings could allow for frequent, remote, and low-cost screening before costly clinical visits and a more invasive laryngoscopy examination. Our goals were to detect unilateral vocal fold paralysis (UVFP) from voice recordings…

Common Data Elements for Disorders of Consciousness: Recommendations from the Working Group on Physiology and Big Data

Erta Beqiri, Neeraj Badjatia, Ari Ercole, Brandon Foreman, Peter Hu, Xiao Hu, Kerri LaRovere, Geert Meyfroidt, Dick Moberg, Chiara Robba, Eric S Rosenthal, Peter Smielewski, Mark S Wainwright, Soojin Park; Curing Coma Campaign and its Contributing Members

 The implementation of multimodality monitoring in the clinical management of patients with disorders of consciousness (DoC) results in physiological measurements that can be collected in a continuous and regular fashion or even at waveform resolution…

Practice-Pattern Variation in Sedation of Neurotrauma Patients in the Intensive Care Unit: An International Survey

Rianne G.F. Dolmans, Brian V. Nahed, Faith C. Robertson, Wilco C. Peul, Eric S. Rosenthal, and Marike L.D. Broekman

Analgo-sedation plays an important role during intensive care management of traumatic brain injury (TBI) patients, however, limited evidence is available to guide practice. We sought to quantify practice-pattern variation in neurotrauma sedation management…

Multi-dimensional patient acuity estimation with longitudinal EHR tokenization and flexible transformer networks

Benjamin Shickel, Brandon Silva, Tezcan Ozrazgat-Baslanti, Yuanfang Ren, Kia Khezeli, Ziyuan Guan, Patrick J. Tighe, Azra Bihorac, and Parisa Rashidi

Transformer model architectures have revolutionized the natural language processing (NLP) domain and continue to produce state-of-the-art results in text-based applications. Prior to the emergence of transformers, traditional NLP models such as recurrent and convolutional neural networks…

Continuous ECG monitoring should be the heart of bedside AI-based predictive analytics monitoring for early detection of clinical deterioration

Oliver J. Monfredi, Christopher C. Moore, Brynne A. Sullivan, Jessica Keim-Malpass, Karen D. Fairchild, Tyler J. Loftus, Azra Bihorac, Katherine N. Krahn, Artur Dubrawski, Douglas E. Lake, J. Randall Moorman, and Gilles Clermon

The idea that we can detect subacute potentially catastrophic illness earlier by using statistical models trained on clinical data is now well-established. We review evidence that supports the role of continuous cardiorespiratory monitoring in these predictive analytics monitoring tools

Artificial intelligence for OCTA-based disease activity prediction in age-related macular degeneration

Anna Heinke, Haochen Zhang, Daniel Deussen, Carlo Miguel B Galang, Alexandra Warter, Fritz Gerald Paguiligan Kalaw, Dirk-Uwe G Bartsch, Lingyun Cheng, Cheolhong An, Truong Nguyen, William R Freeman

We hypothesize that OCTA-visualized vascular morphology may be a predictor of CNV status in AMD. We thus evaluated the use of AI to predict different stages of AMD disease based on OCTA en-face 2D projections scans…

Developing a Continuous Severity Scale for Macular Telangiectasia Type 2 Using Deep Learning and Implications for Disease Grading

Yue Wu, Catherine Egan, Abraham Olvera-Barrios, Lea Scheppke, Tunde Peto, Peter Charbel Issa, Tjebo F C Heeren, Irene Leung, Anand E Rajesh, Adnan Tufail, Cecilia S Lee, Emily Y Chew, Martin Friedlander, Aaron Y Lee

Deep learning (DL) models have achieved state-of-the-art medical diagnosis classification accuracy. Current models are limited by discrete diagnosis labels, but could yield more information with diagnosis in a continuous scale…

Trends and practices following the 2016 hydroxychloroquine screening guidelines

Fritz Gerald P. Kalaw, Justin Arnett, Sally L. Baxter, Evan Walker, Brian Pedersen & Shyamanga Borooah

This study aimed to understand the profile of hydroxychloroquine-treated patients, referral patterns, and dosing and to assess the adherence of eye care providers to the latest 2016 screening guidelines provided by the American Academy of Ophthalmology…

Artificial Intelligence and Diabetic Retinopathy: AI Framework, Prospective Studies, Head-to-head Validation, and Cost-effectiveness

Anand E. Rajesh, Oliver Q. Davidson, Cecilia S. Lee, & Aaron Y. Lee

Current guidelines recommend that individuals with diabetes receive yearly eye exams for detection of referable diabetic retinopathy (DR), one of the leading causes of new-onset blindness. For addressing the immense screening burden, artificial intelligence (AI) algorithms…

Microperimetry Findings in Pentosan Polysulfate Maculopathy

Jesse Most, Fritz Gerald P Kalaw, Evan Walker, Juan D Arias, Jason Charng, Sally L Baxter, Eric Nudleman, Henry Ferreyra, William R Freeman, Fred K Chen, Shyamanga Borooah

Pentosan polysulfate maculopathy is a toxic maculopathy associated with the use of pentosan polysulfate sodium (PPS). With few alternative treatments for interstitial cystitis (IC), early detection and monitoring for maculopathy during treatment…

Evaluating Access to Laser Eye Surgery by Driving Times Using Medicare Data and Geographical Mapping

Jamie Shaffer, Anand Rajesh, Michael W Stewart, Aaron Y Lee, Darby D Miller, Cecilia S Lee, Courtney E Francis

Recently, several states have granted optometrists privileges to perform select laser procedures (laser peripheral iridotomy, selective laser trabeculoplasty, and YAG laser capsulotomy) with the aim of increasing access…

Ethnicity is not biology: retinal pigment score to evaluate biological variability from ophthalmic imaging using machine learning

Anand E Rajesh, Abraham Olvera-Barrios, Alasdair N. Warwick, Yue Wu, Kelsey V. Stuart, Mahantesh Biradar, Chuin Ying Ung, Anthony P. Khawaja, Robert Luben, Paul J. Foster, Cecilia S. Lee, Adnan Tufail, Aaron Y. Lee, Catherine Egan, EPIC Norfolk, UK Biobank Eye and Vision Consortium

Few metrics exist to describe phenotypic diversity within ophthalmic imaging datasets, with researchers often using ethnicity as an inappropriate marker for biological variability…

Race, Ethnicity, Insurance, and Population Density Associations with Pediatric Strabismus and Strabismic Amblyopia in the IRIS Registry

Anand E Rajesh, Oliver Davidson, Megan Lacy, Arthika Chandramohan, Aaron Y Lee, Cecilia S Lee, Kristina Tarczy-Hornoch; IRIS® Registry Analytic Center Consortium

Strabismus, misalignment of the eyes, is a commonly diagnosed disorder in children, with approximately 2% to 3% of children aged < 6 years diagnosed in the United States. If untreated, strabismus can lead to impaired depth perception or amblyopia…

Diabetic Retinopathy and Dementia Association, Beyond Diabetes Severity

Cecilia S Lee, Chloe Krakauer, Yu-Ru Su, Rod L Walker, Marian Blazes, Susan M McCurry, James D Bowen, Wayne C McCormick Aaron Y Lee, Edward J Boyko, Ann M O’Hare, Eric B Larson, Paul K Crane

Purpose: To investigate whether associations between diabetic retinopathy (DR) and dementia and Alzheimer’s disease (AD) remain significant after controlling for several measures of diabetes severity…

Training Deep Learning Models to Work on Multiple Devices by Cross-Domain Learning with No Additional Annotations

Yue Wu, Abraham Olvera-Barrios, Ryan Yanagihara, Timothy-Paul H Kung, Randy Lu, Irene Leung, Amit V Mishra, Hanan Nussinovitch, Gabriela Grimaldi, Marian Blazes, Cecilia S Lee, Catherine Egan, Adnan Tufail, Aaron Y Lee

Purpose: To create an unsupervised cross-domain segmentation algorithm for segmenting intraretinal fluid and retinal layers on normal and pathologic macular OCT images from different manufacturers…

Evaluation of large language models for discovery of gene set function

Mengzhou Hu, Sahar Alkhairy, Ingoo Lee, Rudolf T. Pillich, Robin Bachelder, Trey Ideker,1 and Dexter Pratt

Gene set analysis is a mainstay of functional genomics, but it relies on manually curated databases of gene functions that are incomplete and unaware of biological context. Here we evaluate the ability of OpenAI’s GPT-4, a Large Language Model (LLM)…

Investigating the Influence of Artificial Intelligence on Adolescent Health: An Urgent Call to Action

Julien Brisson, Jean-Christophe Bélisle-Pipon, Vardit Ravitsky

A multi-scale map of protein assemblies in the DNA damage response

Anton Kratz, Minkyu Kim, Marcus R. Kelly, Fan Zheng, Christopher A. Koczor, Jianfeng Li, Keiichiro Ono, Yue Qin, Christopher Churas, Jing Chen, Rudolf T. Pillich, Jisoo Park, Maya Modak, Rachel Collier, Kate Licon, Dexter Pratt, Robert W. Sobol, Nevan J. Krogan, Trey Ideker

The DNA damage response (DDR) ensures error-free DNA replication and transcription and is disrupted in numerous diseases. An ongoing challenge is to determine the proteins orchestrating DDR and their organization into complexes…

Multimodal perturbation analyses of cyclin-dependent kinases reveal a network of synthetic lethalities associated with cell-cycle regulation and transcriptional regulation

Kyle Ford, Brenton P. Munson, Samson H. Fong, Rebecca Panwala, Wai Keung Chu, Joseph Rainaldi, Nongluk Plongthongkum, Vinayagam Arunachalam, Jarek Kostrowicki, Dario Meluzzi, Jason F. Kreisberg, Kristen Jensen-Pergakes, Todd VanArsdale, Thomas Paul, Pablo Tamayo, Kun Zhang, Jadwiga Bienkowska, Prashant Mali, and Trey Ideker

Cell-cycle control is accomplished by cyclin-dependent kinases (CDKs), motivating extensive research into CDK targeting small-molecule drugs as cancer therapeutics. Here we use combinatorial CRISPR/Cas9 perturbations…

RNA editing: Expanding the potential of RNA therapeutics

Brian J. Booth, Sami Nourreddine, Dhruva Katrekar, Yiannis Savva, Debojit Bose, Thomas J. Long, David J. Huss, and Prashant Mali

RNA therapeutics have had a tremendous impact on medicine, recently exemplified by the rapid development and deployment of mRNA vaccines to combat the COVID-19 pandemic. In addition, RNA-targeting drugs have been developed for diseases…