Grayson L. Baird
YOU?
Author Swipe
View article: Accessing AI mammography reports impacts patient follow-up behaviors: the unintended consequences of including AI in patient portals
Accessing AI mammography reports impacts patient follow-up behaviors: the unintended consequences of including AI in patient portals Open
Although artificial intelligence (AI) tools are growing in breast imaging, little research has examined how to communicate AI findings in patient portals. English-speaking US women with ≥1 prior mammogram (n = 1623) were randomized to one …
View article: Diagnostic value of grayscale inversion imaging for detecting difficult cases of pulmonary nodules
Diagnostic value of grayscale inversion imaging for detecting difficult cases of pulmonary nodules Open
Gray-scale inversion imaging may not enhance sensitivity but offers potential benefits in specificity, especially for experienced radiologists. The findings suggest that gray-scale inversion could serve as a useful educational tool for imp…
View article: Individualized Interactomes from Pulmonary Arterial Hypertension Cell Biopsies Predict Therapeutic Response
Individualized Interactomes from Pulmonary Arterial Hypertension Cell Biopsies Predict Therapeutic Response Open
Pulmonary arterial hypertension (PAH) is characterized by molecular heterogeneity and variable pharmacotherapeutic responses. We used an in silico clinical trial design to test whether transcriptomic data from pulmonary artery endothelial …
View article: Transpulmonary bubble transit in patients hospitalised with COVID-19 pneumonia
Transpulmonary bubble transit in patients hospitalised with COVID-19 pneumonia Open
Background We previously demonstrated a high prevalence of transpulmonary bubble transit (TPBT) using transcranial Doppler (TCD) in patients with COVID-19 pneumonia, but these observations require confirmation. Methods Patients at two acad…
View article: Abn-BLIP: Abnormality-aligned Bootstrapping Language-Image Pre-training for pulmonary embolism diagnosis and report generation from CTPA
Abn-BLIP: Abnormality-aligned Bootstrapping Language-Image Pre-training for pulmonary embolism diagnosis and report generation from CTPA Open
Medical imaging plays a pivotal role in modern healthcare, with computed tomography pulmonary angiography (CTPA) being a critical tool for diagnosing pulmonary embolism and other thoracic conditions. However, the complexity of interpreting…
View article: Effects of Dehydroepiandrosterone in Pulmonary Hypertension (EDIPHY): A Randomized, Double-Blind, Placebo-Controlled Crossover Trial
Effects of Dehydroepiandrosterone in Pulmonary Hypertension (EDIPHY): A Randomized, Double-Blind, Placebo-Controlled Crossover Trial Open
Rationale The adrenal steroid dehydroepiandrosterone (DHEA) and its sulfated form (DHEA-S) are deficient in pulmonary arterial hypertension (PAH) and lower levels are associated with worse right ventricular (RV) function, a decisive factor…
View article: Dismantling open-label placebos and their rationales: A remote 4-arm randomized controlled trial protocol
Dismantling open-label placebos and their rationales: A remote 4-arm randomized controlled trial protocol Open
This trial will investigate how different components of OLPs impact pain among a chronic pain population. We also highlight novel ways to address limitations of prior OLP studies; namely, lack of blinding and improper controls.
View article: Is a score enough? Pitfalls and solutions for AI severity scores
Is a score enough? Pitfalls and solutions for AI severity scores Open
Severity scores, which often refer to the likelihood or probability of a pathology, are commonly provided by artificial intelligence (AI) tools in radiology. However, little attention has been given to the use of these AI scores, and there…
View article: Vision-language model for report generation and outcome prediction in CT pulmonary angiogram
Vision-language model for report generation and outcome prediction in CT pulmonary angiogram Open
Accurate and comprehensive interpretation of pulmonary embolism (PE) from Computed Tomography Pulmonary Angiography (CTPA) scans remains a clinical challenge due to the limited specificity and structure of existing AI tools. We propose an …
View article: A Unified Platform for Radiology Report Generation and Clinician-Centered AI Evaluation
A Unified Platform for Radiology Report Generation and Clinician-Centered AI Evaluation Open
Generative AI models have demonstrated strong potential in radiology report generation, but their clinical adoption depends on physician trust. In this study, we conducted a radiology-focused Turing test to evaluate how well attendings and…
View article: Radiologist-AI workflow can be modified to reduce the risk of medical malpractice claims
Radiologist-AI workflow can be modified to reduce the risk of medical malpractice claims Open
Background Artificial Intelligence (AI) is rapidly changing the legal landscape of radiology. Results from a previous experiment suggested that providing AI error rates can reduce perceived radiologist culpability, as judged by mock jury m…
View article: Is there a sonographer effect? Sonographer as a source of variability for Shear Wave Elastography
Is there a sonographer effect? Sonographer as a source of variability for Shear Wave Elastography Open
Aims: This study aims to estimate the degree of sonographers as a source of systematic variance for Shear Wave Elastography (SWE) values.Materials and methods: Two studies estimated variance in SWE measurements: 1) within-subjects and betw…
View article: Triage with AI: A Rule-out Framework Quantifying the Risks and Benefits of Screening Mammogram Automation
Triage with AI: A Rule-out Framework Quantifying the Risks and Benefits of Screening Mammogram Automation Open
Background AI has been proposed as a triage or “rule out” device to reduce radiologist workload, but it is presently unclear how an AI triage threshold should be determined. We present a framework for determining an optimal threshold. Mate…
View article: Pre-hospital LVO detection: One size does not fit all
Pre-hospital LVO detection: One size does not fit all Open
A range of techniques are being developed with the goal of leverage physiologic data to detect large vessel occlusion (LVO) in the prehospital setting. The output of most every technique is a continuous (or ordinal) variable, but a thresho…
View article: A universal translator for AI scores: Providing context using error
A universal translator for AI scores: Providing context using error Open
Artificial intelligence (AI) programs in radiology typically provide a numeric score for each case that correlates with the underlying pathology. However, these scores are not readily interpretable by themselves. To address this, we propos…
View article: An automated software algorithm for optimizing microwave ablation parameters for treatment of liver tumors
An automated software algorithm for optimizing microwave ablation parameters for treatment of liver tumors Open
Streamlining microwave liver ablation parameter selection using an automated software algorithm reduces variability and improves estimated MAM coverage of liver tumors.
View article: Abn-BLIP: Abnormality-aligned Bootstrapping Language-Image Pre-training for Pulmonary Embolism Diagnosis and Report Generation from CTPA
Abn-BLIP: Abnormality-aligned Bootstrapping Language-Image Pre-training for Pulmonary Embolism Diagnosis and Report Generation from CTPA Open
Medical imaging plays a pivotal role in modern healthcare, with computed tomography pulmonary angiography (CTPA) being a critical tool for diagnosing pulmonary embolism and other thoracic conditions. However, the complexity of interpreting…
View article: Peer-review Blinded Assay Test (P-BAT): a framework for trustless laboratory quality assurance for state-regulated cannabis markets
Peer-review Blinded Assay Test (P-BAT): a framework for trustless laboratory quality assurance for state-regulated cannabis markets Open
The purpose of laboratory testing in the cannabis industry is to ensure public safety by preventing products that exceed hazardous limits of contaminants from reaching consumers, and to provide consumers with transparent and accurate label…
View article: Accessing AI mammography reports impacts patient interest in pursuing a medical malpractice claim: The unintended consequences of including AI in patient portals
Accessing AI mammography reports impacts patient interest in pursuing a medical malpractice claim: The unintended consequences of including AI in patient portals Open
Background Artificial intelligence (AI) tools are increasingly used in breast imaging and radiology more broadly. Patients express varying levels of trust and acceptance toward the incorporation of AI tools, although no research has examin…
View article: Just because you’re paranoid doesn’t mean they won’t side with the plaintiff: Examining perceptions of liability about AI in radiology
Just because you’re paranoid doesn’t mean they won’t side with the plaintiff: Examining perceptions of liability about AI in radiology Open
Background Artificial Intelligence (AI) will have unintended consequences for radiology. When a radiologist misses an abnormality on an image, their liability may differ according to whether or not AI also missed the abnormality. Methods U…
View article: Infarcts Due to Large Vessel Occlusions Continue to Grow Despite Near-Complete Reperfusion After Endovascular Treatment
Infarcts Due to Large Vessel Occlusions Continue to Grow Despite Near-Complete Reperfusion After Endovascular Treatment Open
Background and Purpose Infarcts in acute ischemic stroke (AIS) patients may continue to grow even after reperfusion, due to mechanisms such as microvascular obstruction and reperfusion injury. We investigated whether and how much infarcts …
View article: The Epistemology behind Covariate Adjustment
The Epistemology behind Covariate Adjustment Open
It is often asserted that to control for the effects of confounders, one should include the confounding variables of concern in a statistical model as a covariate. Conversely, it is also asserted that control can only be concluded by desig…
View article: Structural Entities Extraction and Patient Indications Incorporation for Chest X-ray Report Generation
Structural Entities Extraction and Patient Indications Incorporation for Chest X-ray Report Generation Open
The automated generation of imaging reports proves invaluable in alleviating the workload of radiologists. A clinically applicable reports generation algorithm should demonstrate its effectiveness in producing reports that accurately descr…
View article: Neurocognitive Mechanism of Radiologists’ Perceptual Errors: Results of Preliminary Studies
Neurocognitive Mechanism of Radiologists’ Perceptual Errors: Results of Preliminary Studies Open
Background The most prevalent type of radiologist error is failing to detect abnormalities on images, the so-called “perceptual error.” The prevalence of this type of false-negative (FN) error remains essentially unchanged since it was fir…