Search Results - "McDermott, Matthew B. A."

Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations by Seyyed-Kalantari, Laleh, Zhang, Haoran, McDermott, Matthew B. A., Chen, Irene Y., Ghassemi, Marzyeh

“…Artificial intelligence (AI) systems have increasingly achieved expert-level performance in medical imaging applications. However, there is growing concern…”
Get full text

Reply to: ‘Potential sources of dataset bias complicate investigation of underdiagnosis by machine learning algorithms’ and ‘Confounding factors need to be accounted for in assessing bias by machine learning algorithms’ by Seyyed-Kalantari, Laleh, Zhang, Haoran, McDermott, Matthew B. A., Chen, Irene Y., Ghassemi, Marzyeh

Get full text

Computational Bounds for Doing Harmonic Analysis on Permutation Modules of Finite Groups by Hansen, Michael, Koyama, Masanori, McDermott, Matthew B. A., Orrison, Michael E., Wolff, Sarah

“…We develop an approach to finding upper bounds for the number of arithmetic operations necessary for doing harmonic analysis on permutation modules of finite…”
Get full text

Deep Learning Benchmarks on L1000 Gene Expression Data by McDermott, Matthew B.A., Wang, Jennifer, Zhao, Wen-Ning, Sheridan, Steven D., Szolovits, Peter, Kohane, Isaac, Haggarty, Stephen J., Perlis, Roy H.

“…Gene expression data can offer deep, physiological insights beyond the static coding of the genome alone. We believe that realizing this potential requires…”
Get full text

Clinical Artificial Intelligence: Design Principles and Fallacies by McDermott, Matthew B A, Nestor, Bret, Szolovits, Peter

“…Clinical artificial intelligence (AI)/machine learning (ML) is anticipated to offer new abilities in clinical decision support, diagnostic reasoning, precision…”
Get full text

Structure-inducing pre-training by McDermott, Matthew B. A., Yap, Brendan, Szolovits, Peter, Zitnik, Marinka

“…Language model pre-training and the derived general-purpose methods have reshaped machine learning research. However, there remains considerable uncertainty…”
Get full text

Stronger net posterior cortical forces and asymmetric microtubule arrays produce simultaneous centration and rotation of the pronuclear complex in the early Caenorhabditis elegans embryo by Coffman, Valerie C, McDermott, Matthew B A, Shtylla, Blerta, Dawes, Adriana T

“…Positioning of microtubule-organizing centers (MTOCs) incorporates biochemical and mechanical cues for proper alignment of the mitotic spindle and cell…”
Get full text

APPRAISE-AI Tool for Quantitative Evaluation of AI Studies for Clinical Decision Support by Kwong, Jethro C C, Khondker, Adree, Lajkosz, Katherine, McDermott, Matthew B A, Frigola, Xavier Borrat, McCradden, Melissa D, Mamdani, Muhammad, Kulkarni, Girish S, Johnson, Alistair E W

“…Artificial intelligence (AI) has gained considerable attention in health care, yet concerns have been raised around appropriate methods and fairness. Current…”
Get full text

Cross-modal representation alignment of molecular structure and perturbation-induced transcriptional profiles by Finlayson, Samuel G, McDermott, Matthew B A, Pickering, Alex V, Lipnick, Scott L, Kohane, Isaac S

“…Modeling the relationship between chemical structure and molecular activity is a key goal in drug development. Many benchmark tasks have been proposed for…”
Get more information

Modeling the role of negative cooperativity in metabolic regulation and homeostasis by Bush, Eliot C, Clark, Anne E, DeBoever, Chris M, Haynes, Lillian E, Hussain, Sidra, Ma, Singer, McDermott, Matthew B A, McDermott, Matthew M, Novak, Adam M, Wentworth, John S

“…A significant proportion of enzymes display cooperativity in binding ligand molecules, and such effects have an important impact on metabolic regulation. This…”
Get full text

MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-III by Wang, Shirly, McDermott, Matthew B. A, Chauhan, Geeticka, Hughes, Michael C, Naumann, Tristan, Ghassemi, Marzyeh

“…Robust machine learning relies on access to data that can be used with standardized frameworks in important tasks and the ability to develop models whose…”
Get full text

REflex: Flexible Framework for Relation Extraction in Multiple Domains by Chauhan, Geeticka, McDermott, Matthew B. A, Szolovits, Peter

“…Systematic comparison of methods for relation extraction (RE) is difficult because many experiments in the field are not described precisely enough to be…”
Get full text

Event Stream GPT: A Data Pre-processing and Modeling Library for Generative, Pre-trained Transformers over Continuous-time Sequences of Complex Events by McDermott, Matthew B. A, Nestor, Bret, Argaw, Peniel, Kohane, Isaac

“…Generative, pre-trained transformers (GPTs, a.k.a. "Foundation Models") have reshaped natural language processing (NLP) through their versatility in diverse…”
Get full text

meds_reader: A fast and efficient EHR processing library by Steinberg, Ethan, Wornow, Michael, Bedi, Suhana, Fries, Jason Alan, McDermott, Matthew B. A, Shah, Nigam H

“…The growing demand for machine learning in healthcare requires processing increasingly large electronic health record (EHR) datasets, but existing pipelines…”
Get full text

ACES: Automatic Cohort Extraction System for Event-Stream Datasets by Xu, Justin, Gallifant, Jack, Johnson, Alistair E. W, McDermott, Matthew B. A

“…Reproducibility remains a significant challenge in machine learning (ML) for healthcare. Datasets, model pipelines, and even task/cohort definitions are often…”
Get full text

A Closer Look at AUROC and AUPRC under Class Imbalance by McDermott, Matthew B. A, Hansen, Lasse Hyldig, Zhang, Haoran, Angelotti, Giovanni, Gallifant, Jack

“…In machine learning (ML), a widespread adage is that the area under the precision-recall curve (AUPRC) is a superior metric for model comparison to the area…”
Get full text

MEDS-Tab: Automated tabularization and baseline methods for MEDS datasets by Oufattole, Nassim, Bergamaschi, Teya, Kolo, Aleksia, Jeong, Hyewon, Gaggin, Hanna, Stultz, Collin M, McDermott, Matthew B. A

“…Effective, reliable, and scalable development of machine learning (ML) solutions for structured electronic health record (EHR) data requires the ability to…”
Get full text

Structure Inducing Pre-Training by McDermott, Matthew B. A, Yap, Brendan, Szolovits, Peter, Zitnik, Marinka

“…Language model pre-training and derived methods are incredibly impactful in machine learning. However, there remains considerable uncertainty on exactly why…”
Get full text

Adversarial Contrastive Pre-training for Protein Sequences by McDermott, Matthew B. A, Yap, Brendan, Hsu, Harry, Jin, Di, Szolovits, Peter

“…Recent developments in Natural Language Processing (NLP) demonstrate that large-scale, self-supervised pre-training can be extremely beneficial for downstream…”
Get full text

ML4H Abstract Track 2020 by Alsentzer, Emily, McDermott, Matthew B. A, Falck, Fabian, Sarkar, Suproteem K, Roy, Subhrajit, Hyland, Stephanie L

“…A collection of the accepted abstracts for the Machine Learning for Health (ML4H) workshop at NeurIPS 2020. This index is not complete, as some accepted…”
Get full text