| Title: |
Algorithmic versus expert human interpretation of instantaneous wave-Free Ratio (iFR) coronary pressure-wire pullback data |
| Authors: |
Cook, C; Takayuki, W; Howard, J; Keeble, TR; Iglesias, JF; Schampaert, E; Bhindi, R; Ambrosia, A; Matsuo, H; Nishina, H; Kikuta, Y; Shiono, Y; Nakayama, M; Doi, S; Takai, M; Goto, S; Yakuta, Y; Karube, K; Akashi, YJ; Clesham, GJ; Kelly, PA; Davies, JR; Karamasis, GV; Kawase, Y; Robinson, NM; Sharp, ASP; Escaned, J; Davies, J |
| Contributors: |
Wellcome Trust |
| Source: |
1324 ; 1315 |
| Publisher Information: |
Elsevier |
| Publication Year: |
2019 |
| Collection: |
Imperial College London: Spiral |
| Subject Terms: |
Science & Technology; Life Sciences & Biomedicine; Cardiac & Cardiovascular Systems; Cardiovascular System & Cardiology; artificial intelligence; coronary physiology; iFR; instantaneous wave-free ratio; percutaneous coronary intervention; INCREMENTAL PROGNOSTIC VALUE; DISEASE; RISK; REVASCULARIZATION; 1102 Cardiorespiratory Medicine and Haematology; Cardiovascular System & Hematology |
| Description: |
Background Interpretation of instantaneous wave-Free Ratio (iFR) pressure-wire pullback data can be complex and is subjective. Objectives To investigate if algorithmic interpretation (AI) of iFR pressure-wire pullback data would be non-inferior to expert human interpretation. Methods Fifteen human experts interpreted 1008 iFR pullback traces (691 unique, 317 duplicate). For each trace, experts determined the hemodynamic appropriateness for percutaneous coronary intervention (PCI), and in such cases, the optimal physiological strategy for PCI. The Heart Team (HT) interpretation was determined by consensus of the individual expert opinions. The same 1008 pullback traces were also interpreted algorithmically. The co-primary hypotheses of this study were that AI would be non-inferior to that of the median expert human in determining 1) the hemodynamic appropriateness for PCI, and 2) the physiological strategy for PCI. Results Regarding the hemodynamic appropriateness for PCI, the median expert human demonstrated 89.3% agreement with the HT in comparison to 89.4% for AI (p |
| Document Type: |
article in journal/newspaper |
| Language: |
unknown |
| Relation: |
JACC: Cardiovascular Interventions; http://hdl.handle.net/10044/1/70649; https://dx.doi.org/10.1016/j.jcin.2019.05.025; PS3162_WHCP |
| DOI: |
10.1016/j.jcin.2019.05.025 |
| Availability: |
http://hdl.handle.net/10044/1/70649; https://doi.org/10.1016/j.jcin.2019.05.025 |
| Rights: |
©2019 The Authors. Published By Elsevier on Behalf of The American College of Cardiology Foundation. This Is An Open Access Article Under The CC-BY License ( http://creativecommons.org/licenses/by/4.0/ ) |
| Accession Number: |
edsbas.B28D9B74 |
| Database: |
BASE |