An annotated ventricular tachycardia (VT) alarm database: Toward a uniform standard for optimizing automated VT identification in hospitalized patients
Abstract Background False ventricular tachycardia (VT) alarms are common during in‐hospital electrocardiographic (ECG) monitoring. Prior research shows that the majority of false VT can be attributed to algorithm deficiencies. Purpose The purpose of this study was: (1) to describe the creation of a...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-07-01
|
| Series: | Annals of Noninvasive Electrocardiology |
| Subjects: | |
| Online Access: | https://doi.org/10.1111/anec.13054 |
| _version_ | 1797782971597455360 |
|---|---|
| author | Michele M. Pelter Mary G. Carey Salah Al‐Zaiti Jessica Zegre‐Hemsey Claire Sommargren Lamberto Isola Priya Prasad David Mortara Fabio Badilini |
| author_facet | Michele M. Pelter Mary G. Carey Salah Al‐Zaiti Jessica Zegre‐Hemsey Claire Sommargren Lamberto Isola Priya Prasad David Mortara Fabio Badilini |
| author_sort | Michele M. Pelter |
| collection | DOAJ |
| description | Abstract Background False ventricular tachycardia (VT) alarms are common during in‐hospital electrocardiographic (ECG) monitoring. Prior research shows that the majority of false VT can be attributed to algorithm deficiencies. Purpose The purpose of this study was: (1) to describe the creation of a VT database annotated by ECG experts and (2) to determine true vs. false VT using a new VT algorithm created by our group. Methods The VT algorithm was processed in 5320 consecutive ICU patients with 572,574 h of ECG and physiologic monitoring. A search algorithm identified potential VT, defined as: heart rate >100 beats/min, QRSs > 120 ms, and change in QRS morphology in >6 consecutive beats compared to the preceding native rhythm. Seven ECG channels, SpO2, and arterial blood pressure waveforms were processed and loaded into a web‐based annotation software program. Five PhD‐prepared nurse scientists performed the annotations. Results Of the 5320 ICU patients, 858 (16.13%) had 22,325 VTs. After three levels of iterative annotations, a total of 11,970 (53.62%) were adjudicated as true, 6485 (29.05%) as false, and 3870 (17.33%) were unresolved. The unresolved VTs were concentrated in 17 patients (1.98%). Of the 3870 unresolved VTs, 85.7% (n = 3281) were confounded by ventricular paced rhythm, 10.8% (n = 414) by underlying BBB, and 3.5% (n = 133) had a combination of both. Conclusions The database described here represents the single largest human‐annotated database to date. The database includes consecutive ICU patients, with true, false, and challenging VTs (unresolved) and could serve as a gold standard database to develop and test new VT algorithms. |
| first_indexed | 2024-03-13T00:19:29Z |
| format | Article |
| id | doaj.art-8c4a1b9974664fc998589f1e4639f182 |
| institution | Directory Open Access Journal |
| issn | 1082-720X 1542-474X |
| language | English |
| last_indexed | 2024-03-13T00:19:29Z |
| publishDate | 2023-07-01 |
| publisher | Wiley |
| record_format | Article |
| series | Annals of Noninvasive Electrocardiology |
| spelling | doaj.art-8c4a1b9974664fc998589f1e4639f1822023-07-11T16:43:54ZengWileyAnnals of Noninvasive Electrocardiology1082-720X1542-474X2023-07-01284n/an/a10.1111/anec.13054An annotated ventricular tachycardia (VT) alarm database: Toward a uniform standard for optimizing automated VT identification in hospitalized patientsMichele M. Pelter0Mary G. Carey1Salah Al‐Zaiti2Jessica Zegre‐Hemsey3Claire Sommargren4Lamberto Isola5Priya Prasad6David Mortara7Fabio Badilini8Department of Physiological Nursing University of California San Francisco School of Nursing San Francisco California USASchool of Nursing University of Rochester Rochester New York USADepartment of Acute & Tertiary Care Nursing University of Pittsburgh Pittsburgh Pennsylvania USASchool of Nursing University of North Carolina at Chapel Hill Chapel Hill North Carolina USADepartment of Physiological Nursing University of California San Francisco School of Nursing San Francisco California USAAMPS‐LLC New York New York USADepartment of Medicine Division of Hospital Medicine, School of Medicine University of California San Francisco California USADepartment of Physiological Nursing University of California San Francisco School of Nursing San Francisco California USADepartment of Physiological Nursing University of California San Francisco School of Nursing San Francisco California USAAbstract Background False ventricular tachycardia (VT) alarms are common during in‐hospital electrocardiographic (ECG) monitoring. Prior research shows that the majority of false VT can be attributed to algorithm deficiencies. Purpose The purpose of this study was: (1) to describe the creation of a VT database annotated by ECG experts and (2) to determine true vs. false VT using a new VT algorithm created by our group. Methods The VT algorithm was processed in 5320 consecutive ICU patients with 572,574 h of ECG and physiologic monitoring. A search algorithm identified potential VT, defined as: heart rate >100 beats/min, QRSs > 120 ms, and change in QRS morphology in >6 consecutive beats compared to the preceding native rhythm. Seven ECG channels, SpO2, and arterial blood pressure waveforms were processed and loaded into a web‐based annotation software program. Five PhD‐prepared nurse scientists performed the annotations. Results Of the 5320 ICU patients, 858 (16.13%) had 22,325 VTs. After three levels of iterative annotations, a total of 11,970 (53.62%) were adjudicated as true, 6485 (29.05%) as false, and 3870 (17.33%) were unresolved. The unresolved VTs were concentrated in 17 patients (1.98%). Of the 3870 unresolved VTs, 85.7% (n = 3281) were confounded by ventricular paced rhythm, 10.8% (n = 414) by underlying BBB, and 3.5% (n = 133) had a combination of both. Conclusions The database described here represents the single largest human‐annotated database to date. The database includes consecutive ICU patients, with true, false, and challenging VTs (unresolved) and could serve as a gold standard database to develop and test new VT algorithms.https://doi.org/10.1111/anec.13054alarm fatiguealgorithmsannotation protocolelectrocardiographic monitoringintensive care unitventricular tachycardia |
| spellingShingle | Michele M. Pelter Mary G. Carey Salah Al‐Zaiti Jessica Zegre‐Hemsey Claire Sommargren Lamberto Isola Priya Prasad David Mortara Fabio Badilini An annotated ventricular tachycardia (VT) alarm database: Toward a uniform standard for optimizing automated VT identification in hospitalized patients Annals of Noninvasive Electrocardiology alarm fatigue algorithms annotation protocol electrocardiographic monitoring intensive care unit ventricular tachycardia |
| title | An annotated ventricular tachycardia (VT) alarm database: Toward a uniform standard for optimizing automated VT identification in hospitalized patients |
| title_full | An annotated ventricular tachycardia (VT) alarm database: Toward a uniform standard for optimizing automated VT identification in hospitalized patients |
| title_fullStr | An annotated ventricular tachycardia (VT) alarm database: Toward a uniform standard for optimizing automated VT identification in hospitalized patients |
| title_full_unstemmed | An annotated ventricular tachycardia (VT) alarm database: Toward a uniform standard for optimizing automated VT identification in hospitalized patients |
| title_short | An annotated ventricular tachycardia (VT) alarm database: Toward a uniform standard for optimizing automated VT identification in hospitalized patients |
| title_sort | annotated ventricular tachycardia vt alarm database toward a uniform standard for optimizing automated vt identification in hospitalized patients |
| topic | alarm fatigue algorithms annotation protocol electrocardiographic monitoring intensive care unit ventricular tachycardia |
| url | https://doi.org/10.1111/anec.13054 |
| work_keys_str_mv | AT michelempelter anannotatedventriculartachycardiavtalarmdatabasetowardauniformstandardforoptimizingautomatedvtidentificationinhospitalizedpatients AT marygcarey anannotatedventriculartachycardiavtalarmdatabasetowardauniformstandardforoptimizingautomatedvtidentificationinhospitalizedpatients AT salahalzaiti anannotatedventriculartachycardiavtalarmdatabasetowardauniformstandardforoptimizingautomatedvtidentificationinhospitalizedpatients AT jessicazegrehemsey anannotatedventriculartachycardiavtalarmdatabasetowardauniformstandardforoptimizingautomatedvtidentificationinhospitalizedpatients AT clairesommargren anannotatedventriculartachycardiavtalarmdatabasetowardauniformstandardforoptimizingautomatedvtidentificationinhospitalizedpatients AT lambertoisola anannotatedventriculartachycardiavtalarmdatabasetowardauniformstandardforoptimizingautomatedvtidentificationinhospitalizedpatients AT priyaprasad anannotatedventriculartachycardiavtalarmdatabasetowardauniformstandardforoptimizingautomatedvtidentificationinhospitalizedpatients AT davidmortara anannotatedventriculartachycardiavtalarmdatabasetowardauniformstandardforoptimizingautomatedvtidentificationinhospitalizedpatients AT fabiobadilini anannotatedventriculartachycardiavtalarmdatabasetowardauniformstandardforoptimizingautomatedvtidentificationinhospitalizedpatients AT michelempelter annotatedventriculartachycardiavtalarmdatabasetowardauniformstandardforoptimizingautomatedvtidentificationinhospitalizedpatients AT marygcarey annotatedventriculartachycardiavtalarmdatabasetowardauniformstandardforoptimizingautomatedvtidentificationinhospitalizedpatients AT salahalzaiti annotatedventriculartachycardiavtalarmdatabasetowardauniformstandardforoptimizingautomatedvtidentificationinhospitalizedpatients AT jessicazegrehemsey annotatedventriculartachycardiavtalarmdatabasetowardauniformstandardforoptimizingautomatedvtidentificationinhospitalizedpatients AT clairesommargren annotatedventriculartachycardiavtalarmdatabasetowardauniformstandardforoptimizingautomatedvtidentificationinhospitalizedpatients AT lambertoisola annotatedventriculartachycardiavtalarmdatabasetowardauniformstandardforoptimizingautomatedvtidentificationinhospitalizedpatients AT priyaprasad annotatedventriculartachycardiavtalarmdatabasetowardauniformstandardforoptimizingautomatedvtidentificationinhospitalizedpatients AT davidmortara annotatedventriculartachycardiavtalarmdatabasetowardauniformstandardforoptimizingautomatedvtidentificationinhospitalizedpatients AT fabiobadilini annotatedventriculartachycardiavtalarmdatabasetowardauniformstandardforoptimizingautomatedvtidentificationinhospitalizedpatients |