Impact of automatic acquisition of key clinical information on the accuracy of electrocardiogram interpretation: a cross-sectional study
Abstract Background The accuracy of electrocardiogram (ECG) interpretation by doctors are affected by the available clinical information. However, having a complete set of clinical details before making a diagnosis is very difficult in the clinical setting especially in the early stages of the admis...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-12-01
|
| Series: | BMC Medical Education |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12909-023-04907-9 |
| _version_ | 1797397979841167360 |
|---|---|
| author | Shaohua Guo Bufan Zhang Yuanyuan Feng Yajie Wang Gary Tse Tong Liu Kang-Yin Chen |
| author_facet | Shaohua Guo Bufan Zhang Yuanyuan Feng Yajie Wang Gary Tse Tong Liu Kang-Yin Chen |
| author_sort | Shaohua Guo |
| collection | DOAJ |
| description | Abstract Background The accuracy of electrocardiogram (ECG) interpretation by doctors are affected by the available clinical information. However, having a complete set of clinical details before making a diagnosis is very difficult in the clinical setting especially in the early stages of the admission process. Therefore, we developed an artificial intelligence-assisted ECG diagnostic system (AI-ECG) using natural language processing to provide screened key clinical information during ECG interpretation. Methods Doctors with varying levels of training were asked to make diagnoses from 50 ECGs using a common ECG diagnosis system that does not contain clinical information. After a two-week-blanking period, the same set of ECGs was reinterpreted by the same doctors with AI-ECG containing clinical information. Two cardiologists independently provided diagnostic criteria for 50 ECGs, and discrepancies were resolved by consensus or, if necessary, by a third cardiologist. The accuracy of ECG interpretation was assessed, with each response scored as correct/partially correct = 1 or incorrect = 0. Results The mean accuracy of ECG interpretation was 30.2% and 36.2% with the common ECG system and AI-ECG system, respectively. Compared to the unaided ECG system, the accuracy of interpretation was significantly improved with the AI-ECG system (P for paired t-test = 0.002). For senior doctors, no improvement was found in ECG interpretation accuracy, while an AI-ECG system was associated with 27% higher mean scores (24.3 ± 9.4% vs. 30.9 ± 10.6%, P = 0.005) for junior doctors. Conclusion Intelligently screened key clinical information could improve the accuracy of ECG interpretation by doctors, especially for junior doctors. |
| first_indexed | 2024-03-09T01:18:05Z |
| format | Article |
| id | doaj.art-e84d5f07ec804060aef8b9b9ba21420c |
| institution | Directory Open Access Journal |
| issn | 1472-6920 |
| language | English |
| last_indexed | 2024-03-09T01:18:05Z |
| publishDate | 2023-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Education |
| spelling | doaj.art-e84d5f07ec804060aef8b9b9ba21420c2023-12-10T12:22:34ZengBMCBMC Medical Education1472-69202023-12-0123111010.1186/s12909-023-04907-9Impact of automatic acquisition of key clinical information on the accuracy of electrocardiogram interpretation: a cross-sectional studyShaohua Guo0Bufan Zhang1Yuanyuan Feng2Yajie Wang3Gary Tse4Tong Liu5Kang-Yin Chen6Tianjin Key Laboratory of Ionic-Molecular Function of Cardiovascular disease, Department of Cardiology, Tianjin Institute of Cardiology, The Second Hospital of Tianjin Medical UniversityDepartment of Cardiovascular Surgery, Tianjin Medical University General HospitalTianjin Key Laboratory of Ionic-Molecular Function of Cardiovascular disease, Department of Cardiology, Tianjin Institute of Cardiology, The Second Hospital of Tianjin Medical UniversityDepartment of Cardiology, TEDA International Cardiovascular Hospital, Cardiovascular Clinical College of Tianjin Medical UniversityTianjin Key Laboratory of Ionic-Molecular Function of Cardiovascular disease, Department of Cardiology, Tianjin Institute of Cardiology, The Second Hospital of Tianjin Medical UniversityTianjin Key Laboratory of Ionic-Molecular Function of Cardiovascular disease, Department of Cardiology, Tianjin Institute of Cardiology, The Second Hospital of Tianjin Medical UniversityTianjin Key Laboratory of Ionic-Molecular Function of Cardiovascular disease, Department of Cardiology, Tianjin Institute of Cardiology, The Second Hospital of Tianjin Medical UniversityAbstract Background The accuracy of electrocardiogram (ECG) interpretation by doctors are affected by the available clinical information. However, having a complete set of clinical details before making a diagnosis is very difficult in the clinical setting especially in the early stages of the admission process. Therefore, we developed an artificial intelligence-assisted ECG diagnostic system (AI-ECG) using natural language processing to provide screened key clinical information during ECG interpretation. Methods Doctors with varying levels of training were asked to make diagnoses from 50 ECGs using a common ECG diagnosis system that does not contain clinical information. After a two-week-blanking period, the same set of ECGs was reinterpreted by the same doctors with AI-ECG containing clinical information. Two cardiologists independently provided diagnostic criteria for 50 ECGs, and discrepancies were resolved by consensus or, if necessary, by a third cardiologist. The accuracy of ECG interpretation was assessed, with each response scored as correct/partially correct = 1 or incorrect = 0. Results The mean accuracy of ECG interpretation was 30.2% and 36.2% with the common ECG system and AI-ECG system, respectively. Compared to the unaided ECG system, the accuracy of interpretation was significantly improved with the AI-ECG system (P for paired t-test = 0.002). For senior doctors, no improvement was found in ECG interpretation accuracy, while an AI-ECG system was associated with 27% higher mean scores (24.3 ± 9.4% vs. 30.9 ± 10.6%, P = 0.005) for junior doctors. Conclusion Intelligently screened key clinical information could improve the accuracy of ECG interpretation by doctors, especially for junior doctors.https://doi.org/10.1186/s12909-023-04907-9Artificial intelligenceElectrocardiogram interpretationKey clinical information |
| spellingShingle | Shaohua Guo Bufan Zhang Yuanyuan Feng Yajie Wang Gary Tse Tong Liu Kang-Yin Chen Impact of automatic acquisition of key clinical information on the accuracy of electrocardiogram interpretation: a cross-sectional study BMC Medical Education Artificial intelligence Electrocardiogram interpretation Key clinical information |
| title | Impact of automatic acquisition of key clinical information on the accuracy of electrocardiogram interpretation: a cross-sectional study |
| title_full | Impact of automatic acquisition of key clinical information on the accuracy of electrocardiogram interpretation: a cross-sectional study |
| title_fullStr | Impact of automatic acquisition of key clinical information on the accuracy of electrocardiogram interpretation: a cross-sectional study |
| title_full_unstemmed | Impact of automatic acquisition of key clinical information on the accuracy of electrocardiogram interpretation: a cross-sectional study |
| title_short | Impact of automatic acquisition of key clinical information on the accuracy of electrocardiogram interpretation: a cross-sectional study |
| title_sort | impact of automatic acquisition of key clinical information on the accuracy of electrocardiogram interpretation a cross sectional study |
| topic | Artificial intelligence Electrocardiogram interpretation Key clinical information |
| url | https://doi.org/10.1186/s12909-023-04907-9 |
| work_keys_str_mv | AT shaohuaguo impactofautomaticacquisitionofkeyclinicalinformationontheaccuracyofelectrocardiograminterpretationacrosssectionalstudy AT bufanzhang impactofautomaticacquisitionofkeyclinicalinformationontheaccuracyofelectrocardiograminterpretationacrosssectionalstudy AT yuanyuanfeng impactofautomaticacquisitionofkeyclinicalinformationontheaccuracyofelectrocardiograminterpretationacrosssectionalstudy AT yajiewang impactofautomaticacquisitionofkeyclinicalinformationontheaccuracyofelectrocardiograminterpretationacrosssectionalstudy AT garytse impactofautomaticacquisitionofkeyclinicalinformationontheaccuracyofelectrocardiograminterpretationacrosssectionalstudy AT tongliu impactofautomaticacquisitionofkeyclinicalinformationontheaccuracyofelectrocardiograminterpretationacrosssectionalstudy AT kangyinchen impactofautomaticacquisitionofkeyclinicalinformationontheaccuracyofelectrocardiograminterpretationacrosssectionalstudy |