John R. Zech
YOU?
Author Swipe
View article: Evaluating the Performance and Bias of Natural Language Processing Tools in Labeling Chest Radiograph Reports
Evaluating the Performance and Bias of Natural Language Processing Tools in Labeling Chest Radiograph Reports Open
Natural language processing tools for chest radiograph report annotation show high overall accuracy but exhibit age-related bias, with poorer performance in older patients.
View article: Clinical Applications, Challenges, and Recommendations for Artificial Intelligence in Musculoskeletal and Soft-Tissue Ultrasound: <i>AJR</i> Expert Panel Narrative Review
Clinical Applications, Challenges, and Recommendations for Artificial Intelligence in Musculoskeletal and Soft-Tissue Ultrasound: <i>AJR</i> Expert Panel Narrative Review Open
Artificial intelligence (AI) is increasingly used in clinical practice for musculoskeletal imaging tasks, such as disease diagnosis and image reconstruction. AI applications in musculoskeletal imaging have focused primarily on radiography,…
View article: Visceral Adiposity Independently Predicts Time to Flare in Inflammatory Bowel Disease but Body Mass Index Does Not
Visceral Adiposity Independently Predicts Time to Flare in Inflammatory Bowel Disease but Body Mass Index Does Not Open
Background Obesity is associated with progression of inflammatory bowel disease (IBD). Visceral adiposity may be a more meaningful measure of obesity compared with traditional measures such as body mass index (BMI). This study compared vis…
View article: P835 Visceral adiposity independently predicts time to flare in inflammatory bowel disease, but BMI does not
P835 Visceral adiposity independently predicts time to flare in inflammatory bowel disease, but BMI does not Open
Background Obesity is rising globally and has been associated with increased IBD disease severity, prolonged hospital stay and increased development of extra-intestinal manifestations. Measuring “visceral adiposity” by CT scan may be a mor…
View article: Risk stratification for hydronephrosis in the evaluation of acute kidney injury: a cross-sectional analysis
Risk stratification for hydronephrosis in the evaluation of acute kidney injury: a cross-sectional analysis Open
Objective To validate an existing clinical decision support tool to risk-stratify patients with acute kidney injury (AKI) for hydronephrosis and compare the risk stratification framework with nephrology consultant recommendations. Setting …
View article: Risk Stratification for Hydronephrosis in the Evaluation of Acute Kidney Injury
Risk Stratification for Hydronephrosis in the Evaluation of Acute Kidney Injury Open
Background: Renal ultrasounds (RUS) are commonly ordered in hospitalized patients with acute kidney injury (AKI). Clinical decision support tools could be used to inform which patients may benefit from RUS to rule out hydronephrosis, howev…
View article: Individual predictions matter: Assessing the effect of data ordering in training fine-tuned CNNs for medical imaging
Individual predictions matter: Assessing the effect of data ordering in training fine-tuned CNNs for medical imaging Open
We reproduced the results of CheXNet with fixed hyperparameters and 50 different random seeds to identify 14 finding in chest radiographs (x-rays). Because CheXNet fine-tunes a pre-trained DenseNet, the random seed affects the ordering of …
View article: Risk Stratification for Renal Ultrasonography in the Evaluation of Acute Kidney Injury
Risk Stratification for Renal Ultrasonography in the Evaluation of Acute Kidney Injury Open
Abstract Background Renal ultrasounds (RUS) are commonly ordered in hospitalized patients with acute kidney injury (AKI), however clinical risk prediction could be used to inform which patients require imaging to rule out hydronephrosis. W…
View article: Detecting insertion, substitution, and deletion errors in radiology reports using neural sequence-to-sequence models
Detecting insertion, substitution, and deletion errors in radiology reports using neural sequence-to-sequence models Open
Seq2seq models can be highly effective at detecting erroneous insertions, deletions, and substitutions of words in radiology reports. To achieve high performance, these models require site- and modality-specific training examples. Incorpor…
View article: An attention based deep learning model of clinical events in the intensive care unit
An attention based deep learning model of clinical events in the intensive care unit Open
This study trained long short-term memory (LSTM) recurrent neural networks (RNNs) incorporating an attention mechanism to predict daily sepsis, myocardial infarction (MI), and vancomycin antibiotic administration over two week patient ICU …
View article: Combination of Active Transfer Learning and Natural Language Processing to Improve Liver Volumetry Using Surrogate Metrics with Deep Learning
Combination of Active Transfer Learning and Natural Language Processing to Improve Liver Volumetry Using Surrogate Metrics with Deep Learning Open
Active transfer learning using surrogate metrics facilitated deployment of deep learning models for clinically meaningful liver segmentation at a major liver transplant center.© RSNA, 2019Supplemental material is available for this article.
View article: Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study
Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study Open
Pneumonia-screening CNNs achieved better internal than external performance in 3 out of 5 natural comparisons. When models were trained on pooled data from sites with different pneumonia prevalence, they performed better on new pooled data…
View article: CANDI: an R package and Shiny app for annotating radiographs and evaluating computer-aided diagnosis
CANDI: an R package and Shiny app for annotating radiographs and evaluating computer-aided diagnosis Open
Motivation Radiologists have used algorithms for Computer-Aided Diagnosis (CAD) for decades. These algorithms use machine learning with engineered features, and there have been mixed findings on whether they improve radiologists’ interpret…
View article: Measuring the Degree of Unmatched Patient Records in a Health Information Exchange Using Exact Matching
Measuring the Degree of Unmatched Patient Records in a Health Information Exchange Using Exact Matching Open
Summary Health information exchange (HIE) facilitates the exchange of patient information across different healthcare organizations. To match patient records across sites, HIEs usually rely on a master patient index (MPI), a database respo…
View article: Identifying homelessness using health information exchange data
Identifying homelessness using health information exchange data Open
Background Homeless patients experience poor health outcomes and consume a disproportionate amount of health care resources compared with domiciled patients. There is increasing interest in the federal government in providing care coordina…