AI Article Synopsis
- Researchers tested an AI-enhanced ECG for detecting cardiac amyloidosis (CA) in a group of 440 diagnosed patients, compared to a control group of 6,600 who were matched by age and sex.
- The AI's performance showed an area under the curve (AUC) of 0.84, which is a decrease from an earlier study that reported an AUC of 0.91, indicating slight deterioration in accuracy.
- The AI performed well across different racial groups but struggled with Hispanic patients and conditions like left ventricular hypertrophy and left bundle branch block, highlighting the need for targeted improvements in these areas.
Article Abstract
Background: We have previously applied artificial intelligence (AI) to an electrocardiogram (ECG) to detect cardiac amyloidosis (CA).
Objectives: In this validation study, the authors observe the postdevelopment performance of the AI-enhanced ECG to detect CA with respect to multiple potential confounders.
Methods: Amyloid patients diagnosed after algorithm development (June 2019-January 2022) with a 12-lead ECG were identified (n = 440) and were required to have CA. A 15:1 age- and sex-matched control group was identified (n = 6,600). Area under the receiver operating characteristic (AUC) was determined for the cohort and subgroups.
Results: The average age was 70.4 ± 10.3 years, 25.0% were female, and most patients were White (91.3%). In this validation, the AI-ECG for amyloidosis had an AUC of 0.84 (95% CI: 0.82-0.86) for the overall cohort and between amyloid subtypes, which is a slight decrease from the original study (AUC 0.91). White, Black, and patients of "other" races had similar algorithm performance (AUC >0.81) with a decreased performance for Hispanic patients (AUC 0.66). Algorithm performance shift over time was not observed. Low ECG voltage and infarct pattern exhibited high AUC (>0.90), while left ventricular hypertrophy and left bundle branch block demonstrated lesser performance (AUC 0.75 and 0.76, respectively).
Conclusions: The AI-ECG for the detection of CA maintained an overall strong performance with respect to patient age, sex, race, and amyloid subtype. Lower performance was noted in left bundle branch block, left ventricular hypertrophy, and ethnically diverse populations emphasizing the need for subgroup-specific validation efforts.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11025724 | PMC |
| http://dx.doi.org/10.1016/j.jacadv.2023.100612 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Postdevelopment Performance and Validation of the Artificial Intelligence-Enhanced Electrocardiogram for Detection of Cardiac Amyloidosis.
JACC Adv
October 2023
Department of Cardiovascular Medicine, Mayo Clinic College of Medicine, Rochester, Minnesota, USA.
Article Synopsis
- Researchers tested an AI-enhanced ECG for detecting cardiac amyloidosis (CA) in a group of 440 diagnosed patients, compared to a control group of 6,600 who were matched by age and sex.
- The AI's performance showed an area under the curve (AUC) of 0.84, which is a decrease from an earlier study that reported an AUC of 0.91, indicating slight deterioration in accuracy.
- The AI performed well across different racial groups but struggled with Hispanic patients and conditions like left ventricular hypertrophy and left bundle branch block, highlighting the need for targeted improvements in these areas.
A closed-loop analysis approach for ensuring stormwater source control design solution to achieve the intended goals.
Water Res
December 2023
State Key Laboratory of Pollution Control and Resources Reuse, College of Environmental Science and Engineering, Tongji University, Shanghai 200092, PR China.
Stormwater source controls have been adopted worldwide to address hydrological and environmental impairments caused by the spread of impervious surfaces in cities. Current design method in China uses 30-year daily rainfall records to generate relationship of rainfall volume capture ratio (α) and daily design storm, and then uses design storm to propose design solution. However, source control performance differs from rain to rain, and hence the design solution's actual effect may deviate from α.
View Article and Find Full Text PDFThe Development and Validation of Simplified Machine Learning Algorithms to Predict Prognosis of Hospitalized Patients With COVID-19: Multicenter, Retrospective Study.
J Med Internet Res
January 2022
Amgen Inc, Digital Health & Innovation, Thousand Oaks, CA, United States.
Background: The current COVID-19 pandemic is unprecedented; under resource-constrained settings, predictive algorithms can help to stratify disease severity, alerting physicians of high-risk patients; however, there are only few risk scores derived from a substantially large electronic health record (EHR) data set, using simplified predictors as input.
Objective: The objectives of this study were to develop and validate simplified machine learning algorithms that predict COVID-19 adverse outcomes; to evaluate the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and calibration of the algorithms; and to derive clinically meaningful thresholds.
Methods: We performed machine learning model development and validation via a cohort study using multicenter, patient-level, longitudinal EHRs from the Optum COVID-19 database that provides anonymized, longitudinal EHR from across the United States.
Digitally processing an image of a shoe impression in blood.
J Forensic Sci
May 2021
Toolmark and Materials Laboratory, Division of Identification and Forensic Science, National Headquarters of the Israel Police, Jerusalem, Israel.
Shoeprints are valuable crime scene exhibits because, given a reasonable-quality impression and a suspect shoe, the forensic investigator can correlate the impression with the shoe and pin down a suspect. In similarity to bloody fingerprints, a common practice with bloody shoeprints is that the crime scene investigator photographs the impressions at a 90° angle with a scale, develops them with amido Black, and then photographs again. In most cases, the post-development prints will feature better and more details that are usually sufficient to perform a comparison between the impression found at the crime scene and suspect's shoes.
View Article and Find Full Text PDFDirect Gene Knock-out of Axolotl Spinal Cord Neural Stem Cells via Electroporation of CAS9 Protein-gRNA Complexes.
J Vis Exp
July 2019
Institute for Brain Research and Rehabilitation (IBRR), South China Normal University;
The axolotl has the unique ability to fully regenerate its spinal cord. This is largely due to the ependymal cells remaining as neural stem cells (NSCs) throughout life, which proliferate to reform the ependymal tube and differentiate into lost neurons after spinal cord injury. Deciphering how these NSCs retain pluripotency post-development and proliferate upon spinal cord injury to reform the exact pre-injury structure can provide valuable insight into how mammalian spinal cords may regenerate as well as potential treatment options.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!