1
|
Wang YC, Chen KW, Tsai BY, Wu MY, Hsieh PH, Wei JT, Shih ESC, Shiao YT, Hwang MJ, Chang KC. Implementation of an All-Day Artificial Intelligence-Based Triage System to Accelerate Door-to-Balloon Times. Mayo Clin Proc 2022; 97:2291-2303. [PMID: 36336511 DOI: 10.1016/j.mayocp.2022.05.014] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/22/2021] [Revised: 03/18/2022] [Accepted: 05/03/2022] [Indexed: 11/06/2022]
Abstract
OBJECTIVE To implement an all-day artificial intelligence (AI)-based system to facilitate chest pain triage in the emergency department. METHODS The AI-based triage system encompasses an AI model combining a convolutional neural network and long short-term memory to detect ST-elevation myocardial infarction (STEMI) on electrocardiography (ECG) and a clinical risk score (ASAP) to prioritize patients for ECG examination. The AI model was developed on 2907 twelve-lead ECGs: 882 STEMI and 2025 non-STEMI ECGs. RESULTS Between November 1, 2019, and October 31, 2020, we enrolled 154 consecutive patients with STEMI: 68 during the AI-based triage period and 86 during the conventional triage period. The mean ± SD door-to-balloon (D2B) time was significantly shortened from 64.5±35.3 minutes to 53.2±12.7 minutes (P=.007), with 98.5% vs 87.2% (P=.009) of D2B times being less than 90 minutes in the AI group vs the conventional group. Among patients with an ASAP score of 3 or higher, the median door-to-ECG time decreased from 30 minutes (interquartile range [IQR], 7-59 minutes) to 6 minutes (IQR, 4-30 minutes) (P<.001). The overall performances of the AI model in identifying STEMI from 21,035 ECGs assessed by accuracy, precision, recall, area under the receiver operating characteristic curve, F1 score, and specificity were 0.997, 0.802, 0.977, 0.999, 0.881, and 0.998, respectively. CONCLUSION Implementation of an all-day AI-based triage system significantly reduced the D2B time, with a corresponding increase in the percentage of D2B times less than 90 minutes in the emergency department. This system may help minimize preventable delays in D2B times for patients with STEMI undergoing primary percutaneous coronary intervention.
Collapse
Affiliation(s)
- Yu-Chen Wang
- Division of Cardiovascular Medicine, China Medical University Hospital, Taichung, Taiwan; Division of Cardiovascular Medicine, Asia University Hospital, Taichung, Taiwan; Department of Medical Laboratory Science and Biotechnology, Asia University, Taichung, Taiwan
| | - Ke-Wei Chen
- Division of Cardiovascular Medicine, China Medical University Hospital, Taichung, Taiwan
| | - Being-Yuah Tsai
- AI Center for Medical Diagnosis, China Medical University Hospital, Taichung, Taiwan
| | - Mei-Yao Wu
- Department of Chinese Medicine, China Medical University Hospital, Taichung, Taiwan; School of Post-Baccalaureate Chinese Medicine, China Medical University, Taichung, Taiwan
| | | | - Jung-Ting Wei
- Division of Cardiovascular Medicine, China Medical University Hospital, Taichung, Taiwan; School of Medicine, China Medical University, Taichung, Taiwan
| | - Edward S C Shih
- Institute of Biomedical Sciences, Academia Sinica, Taipei, Taiwan
| | - Yi-Tzone Shiao
- Center of Institutional Research and Development, Asia University, Taichung, Taiwan
| | - Ming-Jing Hwang
- Institute of Biomedical Sciences, Academia Sinica, Taipei, Taiwan
| | - Kuan-Cheng Chang
- Division of Cardiovascular Medicine, China Medical University Hospital, Taichung, Taiwan; School of Medicine, China Medical University, Taichung, Taiwan.
| |
Collapse
|
2
|
Amoras TSG, Rodrigues TB, Menezes CR, Zaninotto CV, Tavares RDS. Door-to-balloon Time in Cardiovascular Emergency Care in a Hospital of Northern Brazil. INTERNATIONAL JOURNAL OF CARDIOVASCULAR SCIENCES 2020. [DOI: 10.36660/ijcs.20190104] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022] Open
|
3
|
Type 1 myocardial infarction rapid screening scale for emergency triage in patients with non-traumatic chest pain: A study of 1928 cases with coronary angiography. Int J Cardiol 2020; 321:1-5. [PMID: 32805329 DOI: 10.1016/j.ijcard.2020.08.008] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/16/2019] [Revised: 07/11/2020] [Accepted: 08/07/2020] [Indexed: 11/21/2022]
Abstract
INTRODUCTION The effectiveness of treatment and prognosis of patients with type 1 myocardial infarction are highly correlated with time of diagnosis. This study aimed to develop a type 1 MI rapid screening scale (T1MIrs scale) suitable for emergency pre-diagnosis. METHODS A total of 1928 patients who underwent coronary angiography were enrolled. Multivariate regression analysis was used to identify the independent risk factors of type 1 MI. And the T1MIrs scale was developed and evaluated according to the multivariate regression result. RESULTS The incidence of type 1 MI was 23.3% in the population with suspected acute coronary syndrome. After 5 adjusting for relevant factors, MEWS score (OR = 1.809, 95%CI 1.623-2.016, P < .001), typical symptoms (OR = 9.826, 95%CI 7.379-13.084, P < .001), male (OR = 2.184, 95%CI 1.602-2.979, P < .001), age (OR = 1.021, 95%CI 1.009-1.033, P = .001), history of diabetes (OR = 2.174, 95%CI 1.594-2.963, P < .001) and current smoker (OR = 2.498, 95%CI 1.550-4.026, P < .001) were the independent risk factors for type 1 MI. The T1MIrs scale is established based on risk factors, with a range of 0-8 points. The incidence of type 1 MI is ascending with the scale (0.3% vs. 3.7% vs. 14.3% vs. 34.9% vs. 57% vs. 76.4% vs. 84.2% vs. 87.5% vs. 100%, P for trend <0.001). CONCLUSIONS Type 1 MI is common in patients with suspected acute coronary syndrome in emergency department. The T1MIrs scale could act as a rapid pre-examination triage of suspected population in emergency department, which is meaningful to screen out type 1 MI patients as soon as possible.
Collapse
|
4
|
Pulia M, Salman T, O'Connell TF, Balasubramanian N, Gaines R, Shah F, Henry M, Leya F, Mathew V, Bufalino D, Steen L, Lewis B, Darki A, Cichon M, Fennessy M, Sielaff A, Haas M, Lopez JJ. Impact of Emergency Medical Services Activation of the Cardiac Catheterization Laboratory and a 24-Hour/Day In-Hospital Interventional Cardiology Team on Treatment Times (Door to Balloon and Medical Contact to Balloon) for ST-Elevation Myocardial Infarction. Am J Cardiol 2019; 124:39-43. [PMID: 31056110 DOI: 10.1016/j.amjcard.2019.03.046] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/07/2019] [Revised: 03/18/2019] [Accepted: 03/19/2019] [Indexed: 10/27/2022]
Abstract
The incremental benefit of emergency medical services (EMS) activation of the cardiac catheterization laboratory (CCL) for ST-elevation myocardial infarction (STEMI) in the setting of an established in-house interventional team (IHIT) is uncertain. We evaluated the impact of EMS activation on door-to-balloon (D2B) time and first medical contact-to-balloon (FMC2B) time for STEMI when coupled with a 24-hour/day IHIT. All patients presenting with STEMI to Loyola University Medical Center had demographic, procedural, and outcome data consecutively entered in a STEMI Data Registry. From 223 consecutive patients presenting between April 2009 and December 2015, a retrospective analysis was performed on 190 patients. Patients were divided into 2 groups depending on CCL activation mode (EMS activation or emergency department activation) and STEMI treatment process times were compared. The primary end point was D2B process times. The secondary end point was FMC2B process times in a subgroup analysis of EMS-transported patients. D2B times were shorter (37 ± 14 minutes vs 57 ± 27 minutes, p < 0.001) with EMS activation. Subgroup analysis of EMS-transported patients demonstrated shorter FMC2B times with EMS activation (52 ± 17 minutes vs 67 ± 32 minutes, p = 0.002). EMS activation was the only predictor of D2B ≤60 minutes in multivariable analysis of EMS-transported patients (odds ratio 9.4; 95% confidence interval 2.1 to 43.0; p = 0.04). In conclusion, EMS activation of the CCL in STEMI was associated with significant improvements in already excellent D2B and FMC2B times even in the setting of a 24-hour/day IHIT.
Collapse
|
5
|
Yamada T, Takahashi A, Mizuguchi Y, Hashimoto S, Taniguchi N, Nakajima S, Hata T. Impact of shorter door-to-balloon time on prognosis of patients with STEMI-single-center analysis with a large proportion of the patients treated within 30 min. Cardiovasc Interv Ther 2018; 34:97-104. [PMID: 29736670 DOI: 10.1007/s12928-018-0521-1] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2017] [Accepted: 04/03/2018] [Indexed: 12/14/2022]
Abstract
Several recent studies suggested that the door-to-balloon time (DTBT) for patients with ST-segment elevation myocardial infarction (STEMI) should be as short as possible, despite the existing guideline for STEMI. This study aimed to evaluate the clinical outcomes of the STEMI patient cohort having the highest proportion of patients treated with a DTBT of ≤ 30 min ever reported. We evaluated 527 consecutive patients with STEMI who underwent percutaneous coronary intervention between 2007 and 2015. The mean age was 68.0 ± 12.7 years, and the mean DTBT was 44.4 ± 33.1 min. The patients were classified into four groups according to the DTBT, and the relationship between the DTBT and clinical outcome was investigated. DTBTs were ≤ 30 min in 146 patients (27.7%), 31-60 min in 297 patients (56.4%), 61-90 min in 60 patients (11.4%), and > 90 min in 24 patients (4.6%). In-hospital mortality rates were 0.7, 5.0, 11.7, and 12.5% for DTBTs of ≤ 30, 31-60, 61-90, and > 90 min, respectively. In multivariate analysis, a DTBT ≤ 30 min (odds ratio [OR] 0.11, 95% confidence interval [CI] 0.01-0.91, p = 0.041), shock on arrival (OR 2.74, 95% CI 1.02-7.37, p = 0.046), and blood transfusion (OR 49.60, 95% CI 13.90-177.00, p < 0.001) were the independent predictors of in-hospital mortality. Patients with STEMI treated with a DTBT ≤ 30 min showed significantly better clinical outcomes than those treated with a DTBT > 30 min.
Collapse
Affiliation(s)
- Takeshi Yamada
- Department of Cardiology, Sakurakai Takahashi Hospital, 5-18-1 Oikecho, Suma-ku, Kobe, Hyogo, 654-0026, Japan.
| | - Akihiko Takahashi
- Department of Cardiology, Sakurakai Takahashi Hospital, 5-18-1 Oikecho, Suma-ku, Kobe, Hyogo, 654-0026, Japan
| | - Yukio Mizuguchi
- Department of Cardiology, Sakurakai Takahashi Hospital, 5-18-1 Oikecho, Suma-ku, Kobe, Hyogo, 654-0026, Japan
| | - Sho Hashimoto
- Department of Cardiology, Sakurakai Takahashi Hospital, 5-18-1 Oikecho, Suma-ku, Kobe, Hyogo, 654-0026, Japan
| | - Norimasa Taniguchi
- Department of Cardiology, Sakurakai Takahashi Hospital, 5-18-1 Oikecho, Suma-ku, Kobe, Hyogo, 654-0026, Japan
| | - Shunsuke Nakajima
- Department of Cardiology, Sakurakai Takahashi Hospital, 5-18-1 Oikecho, Suma-ku, Kobe, Hyogo, 654-0026, Japan
| | - Tetsuya Hata
- Department of Cardiology, Sakurakai Takahashi Hospital, 5-18-1 Oikecho, Suma-ku, Kobe, Hyogo, 654-0026, Japan
| |
Collapse
|
6
|
Kohan LC, Nagarajan V, Millard MA, Loguidice MJ, Fauber NM, Keeley EC. Impact of around-the-clock in-house cardiology fellow coverage on door-to-balloon time in an academic medical center. Vasc Health Risk Manag 2017; 13:139-142. [PMID: 28458558 PMCID: PMC5403126 DOI: 10.2147/vhrm.s132405] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022] Open
Abstract
Objectives To assess if a change in our cardiology fellowship program impacted our ST elevation myocardial infarction (STEMI) program. Background Fellows covering the cardiac care unit were spending excessive hours in the hospital while on call, resulting in increased duty hours violations. A night float fellow system was started on July 1, 2012, allowing the cardiac care unit fellow to sign out to a night float fellow at 5:30 pm. The night float fellow remained in-house until the morning. Methods We performed a retrospective study assessing symptom onset to arrival, arterial access to first device, and door-to-balloon (D2B) times, in consecutive STEMI patients presenting to our emergency department before and after initiation of the night float fellow system. Results From 2009 to 2013, 208 STEMI patients presented to our emergency department and underwent primary percutaneous coronary intervention. There was no difference in symptom onset to arrival (150±102 minutes vs 154±122 minutes, p=0.758), arterial access to first device (12±8 minutes vs 11±7 minutes, p=0.230), or D2B times (50±32 minutes vs 52±34 minutes, p=0.681) during regular working hours. However, there was a significant decrease in D2B times seen during off-hours (72±33 minutes vs 49±15 minutes, p=0.007). There was no difference in in-hospital mortality (11% vs 8%, p=0.484) or need for intra-aortic balloon pump placement (7% vs 8%, p=0.793). Conclusion In academic medical centers, in-house cardiology fellow coverage during off-hours may expedite care of STEMI patients.
Collapse
Affiliation(s)
| | | | - Michael A Millard
- Department of Medicine, University of Virginia, Charlottesville, VA, USA
| | | | | | | |
Collapse
|
7
|
Sharma R, Henry TD. Time to consider a STEMI sleepover?: measuring the "value" of an in-house STEMI team. Catheter Cardiovasc Interv 2015. [PMID: 26198060 DOI: 10.1002/ccd.26085] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
Abstract
This study demonstrates that the presence of an in-hospital STEMI team significantly reduces D2B times. PCI centers should consider the "value" (outcomes relative to cost) of an in-house STEMI team. Larger studies are required to assess the cost effectiveness and clinical effectiveness attributable to an in-house STEMI team.
Collapse
Affiliation(s)
- Rahul Sharma
- Cedars-Sinai Heart Institute, Los Angeles, California
| | | |
Collapse
|