1
|
Martindale APL, Llewellyn CD, de Visser RO, Ng B, Ngai V, Kale AU, di Ruffano LF, Golub RM, Collins GS, Moher D, McCradden MD, Oakden-Rayner L, Rivera SC, Calvert M, Kelly CJ, Lee CS, Yau C, Chan AW, Keane PA, Beam AL, Denniston AK, Liu X. Concordance of randomised controlled trials for artificial intelligence interventions with the CONSORT-AI reporting guidelines. Nat Commun 2024; 15:1619. [PMID: 38388497 PMCID: PMC10883966 DOI: 10.1038/s41467-024-45355-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2023] [Accepted: 01/22/2024] [Indexed: 02/24/2024] Open
Abstract
The Consolidated Standards of Reporting Trials extension for Artificial Intelligence interventions (CONSORT-AI) was published in September 2020. Since its publication, several randomised controlled trials (RCTs) of AI interventions have been published but their completeness and transparency of reporting is unknown. This systematic review assesses the completeness of reporting of AI RCTs following publication of CONSORT-AI and provides a comprehensive summary of RCTs published in recent years. 65 RCTs were identified, mostly conducted in China (37%) and USA (18%). Median concordance with CONSORT-AI reporting was 90% (IQR 77-94%), although only 10 RCTs explicitly reported its use. Several items were consistently under-reported, including algorithm version, accessibility of the AI intervention or code, and references to a study protocol. Only 3 of 52 included journals explicitly endorsed or mandated CONSORT-AI. Despite a generally high concordance amongst recent AI RCTs, some AI-specific considerations remain systematically poorly reported. Further encouragement of CONSORT-AI adoption by journals and funders may enable more complete adoption of the full CONSORT-AI guidelines.
Collapse
Affiliation(s)
| | - Carrie D Llewellyn
- Department of Primary Care and Public Health, Brighton and Sussex Medical School, Brighton, UK
| | - Richard O de Visser
- Department of Primary Care and Public Health, Brighton and Sussex Medical School, Brighton, UK
| | - Benjamin Ng
- Birmingham and Midland Eye Centre, Sandwell and West Birmingham NHS Trust, Birmingham, UK
- Christ Church, University of Oxford, Oxford, UK
| | - Victoria Ngai
- University College London Medical School, London, UK
| | - Aditya U Kale
- Institute of Inflammation and Ageing, University of Birmingham, Birmingham, UK
- University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
- National Institute for Health and Care Research (NIHR) Birmingham Biomedical Research Centre, University of Birmingham, Birmingham, UK
| | | | - Robert M Golub
- Northwestern University Feinberg School of Medicine, Chicago, Illinois, USA
| | - Gary S Collins
- Centre for Statistics in Medicine//UK EQUATOR Centre, Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences, University of Oxford, Oxford, UK
| | - David Moher
- Centre for Journalology, Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottowa, Canada
| | - Melissa D McCradden
- Department of Bioethics, The Hospital for Sick Children, Toronto, Canada
- Genetics & Genome Biology Research Program, Peter Gilgan Centre for Research & Learning, Toronto, Canada
- Division of Clinical and Public Health, Dalla Lana School of Public Health, Toronto, Canada
| | - Lauren Oakden-Rayner
- Australian Institute for Machine Learning, University of Adelaide, Adelaide, Australia
| | - Samantha Cruz Rivera
- Birmingham Health Partners Centre for Regulatory Science and Innovation, University of Birmingham, Birmingham, UK
- Centre for Patient Reported Outcomes Research (CPROR), Institute of Applied Health Research, College of Medical and Dental Sciences, University of Birmingham, Birmingham, UK
| | - Melanie Calvert
- National Institute for Health and Care Research (NIHR) Birmingham Biomedical Research Centre, University of Birmingham, Birmingham, UK
- Birmingham Health Partners Centre for Regulatory Science and Innovation, University of Birmingham, Birmingham, UK
- Centre for Patient Reported Outcomes Research (CPROR), Institute of Applied Health Research, College of Medical and Dental Sciences, University of Birmingham, Birmingham, UK
- NIHR Applied Research Collaboration (ARC) West Midlands, University of Birmingham, Birmingham, UK
- NIHR Blood and Transplant Research Unit (BTRU) in Precision Transplant and Cellular Therapeutics, University of Birmingham, Birmingham, UK
| | | | | | - Christopher Yau
- Nuffield Department of Women's and Reproductive Health, University of Oxford, Oxford, UK
- Health Data Research UK, London, UK
| | - An-Wen Chan
- Department of Medicine, Women's College Hospital. University of Toronto, Toronto, Canada
| | - Pearse A Keane
- NIHR Biomedical Research Centre at Moorfields, Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology, London, UK
| | - Andrew L Beam
- Department of Epidemiology, Harvard. T.H. Chan School of Public Health, Boston, MA, USA
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
| | - Alastair K Denniston
- Institute of Inflammation and Ageing, University of Birmingham, Birmingham, UK
- University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
- National Institute for Health and Care Research (NIHR) Birmingham Biomedical Research Centre, University of Birmingham, Birmingham, UK
- Birmingham Health Partners Centre for Regulatory Science and Innovation, University of Birmingham, Birmingham, UK
- NIHR Biomedical Research Centre at Moorfields, Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology, London, UK
| | - Xiaoxuan Liu
- Institute of Inflammation and Ageing, University of Birmingham, Birmingham, UK.
- University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK.
- Birmingham Health Partners Centre for Regulatory Science and Innovation, University of Birmingham, Birmingham, UK.
| |
Collapse
|
2
|
Senoo K, Yukawa A, Ohkura T, Iwakoshi H, Nishimura T, Shimoo S, Inoue K, Sakatani T, Kakita K, Hattori T, Kitajima H, Nakai K, Nishiuchi S, Nakata M, Teramukai S, Shiraishi H, Matoba S. The impact of home electrocardiograph measurement rate on the detection of atrial fibrillation recurrence after ablation: A prospective multicenter observational study. IJC HEART & VASCULATURE 2023; 44:101177. [PMID: 36820388 PMCID: PMC9938453 DOI: 10.1016/j.ijcha.2023.101177] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2022] [Accepted: 01/11/2023] [Indexed: 01/21/2023]
Abstract
Background This multicenter prospective observational study examined the impact of additionally using a home electrocardiograph (ECG) to detect atrial fibrillation (AF) recurrence after ablation. Methods Between May 2019 and December 2020, 128 patients undergoing ablation were enrolled in the study. After performing ablation, they were instructed to measure their ECGs at home using Complete (ECG paired with a blood pressure monitor; Omron Healthcare, Japan) every day and to visit the hospital every 3 months until after 12 months for 24-hour Holter ECG and 12-lead ECG as usual care (UC). Results After ablation, 94 patients were followed up, and AF recurrence at 12 months was detected more commonly in adjudicators-interpreted Complete (31 [33 %]) than in UC (18 [9 %]) (hazard ratio 1.95, 95 % confidence interval [95 %CI] 1.35-2.81, P < 0.001). In patients with recurrent AF found via both modalities (n = 16), the time to first AF detection by Complete was 40.9 ± 73.9 days faster than that in UC (P = 0.04). Notably, when the adherence to Complete measurement was divided by 80 %, the add-on effect of Complete on the detection of recurrent AF in UC indicated the hazard ratio (HR) of 1.71 (95 %CI 0.92-3.18, P = 0.09) for the low adherence (<80 %) group, but it was significant for the high adherence (≥80 %) group, with HR of 2.19 (95 %CI 1.43-3.36, P < 0.001). Conclusions Despite a shorter measurement time, Complete detected recurrent AF more frequently and faster compared with UC after AF ablation. A significant adherence-dependent difference of Complete was found in detecting AF recurrence.
Collapse
Affiliation(s)
- Keitaro Senoo
- Department of Cardiac Arrhythmia Research and Innovation, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan
- Department of Cardiovascular Medicine, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan
- Corresponding author at: Department of Cardiac Arrhythmia Research and Innovation, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan.
| | - Arito Yukawa
- Department of Cardiac Arrhythmia Research and Innovation, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan
| | - Takashi Ohkura
- Department of Cardiovascular Medicine, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan
| | - Hibiki Iwakoshi
- Department of Cardiovascular Medicine, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan
| | - Tetsuro Nishimura
- Department of Cardiovascular Medicine, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan
| | - Satoshi Shimoo
- Department of Cardiovascular Medicine, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan
| | - Keiji Inoue
- Department of Cardiology, Kyoto Second Red Cross Hospital, Kyoto, Japan
| | - Tomohiko Sakatani
- Department of Cardiology, Kyoto Second Red Cross Hospital, Kyoto, Japan
| | - Ken Kakita
- Arrhythmia Care Center, Koseikai Takeda Hospital, Kyoto, Japan
| | | | - Hiroki Kitajima
- Department of Cardiovascular Medicine, Kyoto Okamoto Memorial Hospital, Kyoto, Japan
| | - Kentaro Nakai
- Department of Cardiovascular Medicine, Uji-Tokusyukai Medical Center, Kyoto, Japan
| | | | - Mitsuko Nakata
- Departments of Biostatistics, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan
| | - Satoshi Teramukai
- Departments of Biostatistics, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan
| | - Hirokazu Shiraishi
- Department of Cardiac Arrhythmia Research and Innovation, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan
- Department of Cardiovascular Medicine, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan
| | - Satoaki Matoba
- Department of Cardiac Arrhythmia Research and Innovation, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan
- Department of Cardiovascular Medicine, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan
| |
Collapse
|
3
|
Haraguchi Y, Nakamura K, Inoue M, Sasaki T, Minami K, Yoshimura S, Naito S. Antiphospholipid Syndrome Diagnosed as a Result of the Occurrence of an Ischemic Stroke After a Successful Catheter Ablation of Atrial Fibrillation and Continuous Direct Oral Anticoagulants. Int Heart J 2022; 63:153-158. [DOI: 10.1536/ihj.21-475] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Affiliation(s)
| | - Kohki Nakamura
- Division of Cardiology, Gunma Prefectural Cardiovascular Center
| | - Mitsuho Inoue
- Division of Cardiology, Gunma Prefectural Cardiovascular Center
| | - Takehito Sasaki
- Division of Cardiology, Gunma Prefectural Cardiovascular Center
| | - Kentaro Minami
- Division of Cardiology, Gunma Prefectural Cardiovascular Center
| | | | - Shigeto Naito
- Division of Cardiology, Gunma Prefectural Cardiovascular Center
| |
Collapse
|
4
|
Suzuki N, Kaneko S, Fujita M, Shinoda M, Kubota R, Ohashi T, Tatami Y, Suzuki J, Hori H, Adachi K, Ito R, Shirai Y, Yanagisawa S, Inden Y, Murohara T. Comparison of the empirical linear ablation and low voltage area-guided ablation in addition to pulmonary vein isolation in patients with persistent atrial fibrillation: a propensity score-matched analysis. BMC Cardiovasc Disord 2022; 22:13. [PMID: 35065605 PMCID: PMC8783511 DOI: 10.1186/s12872-022-02460-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2021] [Accepted: 01/11/2022] [Indexed: 11/15/2022] Open
Abstract
Background The efficacy of pulmonary vein isolation (PVI) alone is not guaranteed for persistent atrial fibrillation (PeAF), and it is unclear which type of ablation approach should be applied in addition to PVI. This study aimed to compare outcomes and prognosis between empirical linear ablation and low-voltage area (LVA) ablation after PVI for PeAF. Methods We enrolled 128 patients with PeAF who were assigned to the linear ablation group (n = 64) and the LVA ablation group (n = 64) using a propensity score-matched model. After PVI and cardioversion, the patients underwent either empirical linear ablation or LVA ablation during sinus rhythm. All patients in the linear ablation group underwent both roof line and mitral valve isthmus (MVI) ablations. An electrical-guided ablation targeting LVA (< 0.5 mV) was performed in the LVA group. When there was no LVA in the LVA group, only PVI was applied. We compared the procedural outcomes and recurrence after ablation between the two groups. Results The baseline characteristics were well-balanced between the two groups. Fifty patients had LVA (22 and 28 patients in the linear and LVA groups). The roof and MVI lines were completed in 100% and 96.9% of the patients. During the mean follow-up of 279.5 ± 161.3 days, the LVA group had significantly lower recurrence than the linear group (15 patients [23%] vs. 29 patients [45%], p = 0.014). Thirty-five patients were prescribed antiarrhythmic drugs during the follow-up period (linear group, n = 17; LVA group, n = 18); amiodarone and bepridil were administered to most of the patients (15 and 17 patients, respectively). The difference in the prognosis was relevant among the patients with LVA, while this trend was not observed in those without LVA. The LVA ablation group demonstrated significantly lower radiofrequency energy and shorter procedural time compared to the linear ablation group. The recurrence of atrial flutter was more likely to occur in the linear group than in the LVA group (14 [22%] vs. 6 [9.4%], p = 0.052). Conclusion The electrophysiological-guided LVA ablation is more effective than empirical linear ablation in PeAF patients with LVA. Unnecessary empirical linear ablation might have a risk of iatrogenic gap and atrial flutter recurrence. Supplementary Information The online version contains supplementary material available at 10.1186/s12872-022-02460-9.
Collapse
|