| 1. |
|
|
| 2. |
- Attia, Zachi I., et al.
(författare)
-
Rapid Exclusion of COVID Infection With the Artificial Intelligence Electrocardiogram
- 2021
-
Ingår i: Mayo Clinic proceedings. - : ELSEVIER SCIENCE INC. - 0025-6196 .- 1942-5546. ; 96:8, s. 2081-2094
-
Tidskriftsartikel (refereegranskat)abstract
- Objective: To rapidly exclude severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection using artificial intelligence applied to the electrocardiogram (ECG). Methods: A global, volunteer consortium from 4 continents identified patients with ECGs obtained around the time of polymerase chain reaction-confirmed COVID-19 diagnosis and age- and sex-matched controls from the same sites. Clinical characteristics, polymerase chain reaction results, and raw electrocardiographic data were collected. A convolutional neural network was trained using 26,153 ECGs (33.2% COVID positive), validated with 3826 ECGs (33.3% positive), and tested on 7870 ECGs not included in other sets (32.7% positive). Performance under different prevalence values was tested by adding control ECGs from a single high-volume site. Results: The area under the curve for detection of acute COVID-19 infection in the test group was 0.767 (95% CI, 0.756 to 0.778; sensitivity, 98%; specificity, 10%; positive predictive value, 37%; negative predictive value, 91%). To more accurately reflect a real-world population, 50,905 normal controls were added to adjust the COVID prevalence to approximately 5% (2657/58,555), resulting in an area under the curve of 0.780 (95% CI, 0.771 to 0.790) with a specificity of 12.1% and a negative predictive value of 99.2%. Conclusion: Infection with SARS-CoV-2 results in electrocardiographic changes that permit the artificial intelligence-enhanced ECG to be used as a rapid screening test with a high negative predictive value (99.2%). This may permit the development of electrocardiography-based tools to rapidly screen individuals for pandemic control. (C) 2021 Mayo Foundation Medical Education and Research
|
|
| 3. |
- Economou Lundeberg, Johan, et al.
(författare)
-
Ventricular tachycardia risk prediction with an abbreviated duration mobile cardiac telemetry
- 2023
-
Ingår i: Heart Rhythm O2. - 2666-5018. ; 4:8, s. 500-505
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Ventricular tachycardia (VT) occurs intermittently, unpredictably, and has potentially lethal consequences. Objective: Our aim was to derive a risk prediction model for VT episodes ≥10 beats detected on 30-day mobile cardiac telemetry based on the first 24 hours of the recording. Methods: We included patients who were monitored for 2 to 30 days in the United States using full-disclosure mobile cardiac telemetry, without any VT episode ≥10 beats on the first full recording day. An elastic net prediction model was derived for the outcome of VT ≥10 beats on monitoring days 2 to 30. Potential predictors included age, sex, and electrocardiographic data from the first 24 hours: heart rate; premature atrial and ventricular complexes occurring as singlets, couplets, triplets, and runs; and the fastest rate for each event. The population was randomly split into training (70%) and testing (30%) samples. Results: In a population of 19,781 patients (mean age 65.3 ± 17.1 years, 43.5% men), with a median recording time of 18.6 ± 9.6 days, 1510 patients had at least 1 VT ≥10 beats. The prediction model had good discrimination in the testing sample (area under the receiver-operating characteristic curve 0.7584, 95% confidence interval 0.7340–0.7829). A model excluding age and sex had an equally good discrimination (area under the receiver-operating characteristic curve 0.7579, 95% confidence interval 0.7332–0.7825). In the top quintile of the score, more than 1 in 5 patients had a VT ≥10 beats, while the bottom quintile had a 98.2% negative predictive value. Conclusion: Our model can predict risk of VT ≥10 beats in the near term using variables derived from 24-hour electrocardiography, and could be used to triage patients to extended monitoring.
|
|
| 4. |
- Sridhar, Arun R., et al.
(författare)
-
Identifying Risk of Adverse Outcomes in COVID-19 Patients via Artificial Intelligence-Powered Analysis of 12-Lead Intake Electrocardiogram.
- 2022
-
Ingår i: Cardiovascular digital health journal. - : Elsevier. - 2666-6936. ; 3:2, s. 62-74
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Adverse events in COVID-19 are difficult to predict. Risk stratification is encumbered by the need to protect healthcare workers. We hypothesize that AI can help identify subtle signs of myocardial involvement in the 12-lead electrocardiogram (ECG), which could help predict complications.Objective: Use intake ECGs from COVID-19 patients to train AI models to predict risk of mortality or major adverse cardiovascular events (MACE).Methods: We studied intake ECGs from 1448 COVID-19 patients (60.5% male, 63.4±16.9 years). Records were labeled by mortality (death vs. discharge) or MACE (no events vs. arrhythmic, heart failure [HF], or thromboembolic [TE] events), then used to train AI models; these were compared to conventional regression models developed using demographic and comorbidity data.Results: 245 (17.7%) patients died (67.3% male, 74.5±14.4 years); 352 (24.4%) experienced at least one MACE (119 arrhythmic; 107 HF; 130 TE). AI models predicted mortality and MACE with area under the curve (AUC) values of 0.60±0.05 and 0.55±0.07, respectively; these were comparable to AUC values for conventional models (0.73±0.07 and 0.65±0.10). There were no prominent temporal trends in mortality rate or MACE incidence in our cohort; holdout testing with data from after a cutoff date (June 9, 2020) did not degrade model performance.Conclusion: Using intake ECGs alone, our AI models had limited ability to predict hospitalized COVID-19 patients' risk of mortality or MACE. Our models' accuracy was comparable to that of conventional models built using more in-depth information, but translation to clinical use would require higher sensitivity and positive predictive value. In the future, we hope that mixed-input AI models utilizing both ECG and clinical data may be developed to enhance predictive accuracy.
|
|
| 5. |
- Srikanth Sridhar, Arun, et al.
(författare)
-
Wetting of native and acetylated cellulose by water and organic liquids from atomistic simulations
- 2023
-
Ingår i: Cellulose. - : Springer Nature. - 0969-0239 .- 1572-882X. ; 30:13, s. 8089-8106
-
Tidskriftsartikel (refereegranskat)abstract
- Wetting of cellulose by different liquids is interesting from the point of view of the processing of cellulose-based nanomaterials. Here, the contact angles formed by water and several organic liquids on both native and acetylated cellulose were calculated from molecular dynamics simulations. It was found that liquid surface tension was crucial for their wetting behavior. Acetylation decreases the work of adhesion to most liquids investigated, even non-polar ones, while others are not affected. Water has the highest affinity to cellulose, both native and acetylated. The results have implications for liquid infiltration of nanocellulose networks and the interaction of cellulose with different liquids in general.
|
|
