A novel machine learning-derived radiotranscriptomic signature of perivascular fat improves cardiac risk prediction using coronary CT angiography.

BACKGROUND: Coronary inflammation induces dynamic changes in the balance between water and lipid content in perivascular adipose tissue (PVAT), as captured by perivascular Fat Attenuation Index (FAI) in standard coronary CT angiography (CCTA). However, inflammation is not the only process involved in atherogenesis and we hypothesized that additional radiomic signatures of adverse fibrotic and microvascular PVAT remodelling, may further improve cardiac risk prediction. METHODS AND RESULTS: We present a new artificial intelligence-powered method to predict cardiac risk by analysing the radiomic profile of coronary PVAT, developed and validated in patient cohorts acquired in three different studies. In Study 1, adipose tissue biopsies were obtained from 167 patients undergoing cardiac surgery, and the expression of genes representing inflammation, fibrosis and vascularity was linked with the radiomic features extracted from tissue CT images. Adipose tissue wavelet-transformed mean attenuation (captured by FAI) was the most sensitive radiomic feature in describing tissue inflammation (TNFA expression), while features of radiomic texture were related to adipose tissue fibrosis (COL1A1 expression) and vascularity (CD31 expression). In Study 2, we analysed 1391 coronary PVAT radiomic features in 101 patients who experienced major adverse cardiac events (MACE) within 5 years of having a CCTA and 101 matched controls, training and validating a machine learning (random forest) algorithm (fat radiomic profile, FRP) to discriminate cases from controls (C-statistic 0.77 [95%CI: 0.62-0.93] in the external validation set). The coronary FRP signature was then tested in 1575 consecutive eligible participants in the SCOT-HEART trial, where it significantly improved MACE prediction beyond traditional risk stratification that included risk factors, coronary calcium score, coronary stenosis, and high-risk plaque features on CCTA (Δ[C-statistic] = 0.126, P < 0.001). In Study 3, FRP was significantly higher in 44 patients presenting with acute myocardial infarction compared with 44 matched controls, but unlike FAI, remained unchanged 6 months after the index event, confirming that FRP detects persistent PVAT changes not captured by FAI. CONCLUSION: The CCTA-based radiomic profiling of coronary artery PVAT detects perivascular structural remodelling associated with coronary artery disease, beyond inflammation. A new artificial intelligence (AI)-powered imaging biomarker (FRP) leads to a striking improvement of cardiac risk prediction over and above the current state-of-the-art.

First-in-man evaluation of the MOMO cobalt-chromium carbon-coated stent.

AIMS: Bare metal stents continue to be used for the interventional treatment of coronary artery disease. We report the clinical and angiographic results of a multicentre, single-arm evaluation of safety and feasibility of the MOMO stent (Japan Stent Technology Co., Ltd, Okayama Research Park Incubation Centre, Okayama, Japan). METHODS AND RESULTS: The MOMO stent is a novel thin-strut cobalt-chromium carbon-coated stent for the treatment of de novo coronary artery disease (CAD). In this prospective, non-randomised, single-arm study, 40 patients (stable and unstable angina) with single-vessel CAD were recruited into the study from three centres. Patients with lesions ≤15 mm in length and with a target vessel diameter of ≥3 mm were eligible. Angiographic follow-up was performed at six months. Quantitative coronary angiography (QCA) was used to measure acute gain and late luminal loss (LLL). Intravascular ultrasound (IVUS) was performed in 15 consecutive patients from two centres to assess the degree of neointimal proliferation within the stented segment at six-month follow-up. The MOMO stent performed well without any procedural complications with an acute procedure and technical success rate of 100%. Repeat revascularisation was performed in six patients (15%) during the six-month follow-up. Ischaemia-driven revascularisation was documented in three patients (7.5%). No myocardial infarction, stent thrombosis or cardiac death was observed. One non-cardiac death was reported secondary to lung cancer. Binary restenosis was 12.5% (n=5), and the LLL was 0.54±0.3 mm. CONCLUSIONS: This first-in-man experience demonstrates proof of concept of the safety and feasibility of the MOMO cobalt-chromium carbon-coated stent for patients with single focal de novo lesions presenting with stable and unstable CAD.

Clinical information transfer and data capture in the acute myocardial infarction pathway: an observational study.

RATIONALE, AIMS AND OBJECTIVES: Acute myocardial infarctions (MIs) or heart attacks are the result of a complete or an incomplete occlusion of the lumen of the coronary artery with a thrombus. Prompt diagnosis and early coronary intervention results in maximum myocardial salvage, hence time to treat is of the essence. Adequate, accurate and complete information is vital during the early stages of admission of an MI patient and can impact significantly on the quality and safety of patient care. This study aimed to record how clinical information between different clinical teams during the journey of a patient in the MI care pathway is captured and to review the flow of information within this care pathway. METHOD: A prospective, descriptive, structured observational study to assess (i) current clinical information systems (CIS) utilization and (ii) real-time information availability within an acute cardiac care setting was carried out. Completeness and availability of patient information capture across four key stages of the MI care pathway were assessed prospectively. RESULTS: Thirteen separate information systems were utilized during the four phases of the MI pathway. Observations revealed fragmented CIS utilization, with users accessing an average of six systems to gain a complete set of patient information. Data capture was found to vary between each pathway stage and in both patient cohort risk groupings. The highest level of information completeness (100%) was observed only in the discharge stage of the MI care pathway. The lowest level of information completeness (58%) was observed in the admission stage. CONCLUSION: The study highlights fragmentation, CIS duplication, and discrepancies in the current clinical information capture and data transfer across the MI care pathway in an acute cardiac care setting. The development of an integrated and user-friendly electronic data capture and transfer system would reduce duplication and would facilitate efficient and complete information provision at the point of care.

Techniques to aid the implementation of novel clinical information systems: a systematic review.

BACKGROUND: This systematic review identifies and evaluates techniques that aid the implementation of novel clinical information systems (CIS) within healthcare. METHODS: We searched electronic databases (MEDLINE, EMBASE, PsycINFO and HMIC Health Management Information Consortium). Desktop reviews for all potentially eligible studies were also conducted via reference lists and forward citation searches. 14,198 abstracts were identified through the initial electronic search. 63 articles were retained following title and abstract reviews, and submitted for full text evaluation. Of these, 18 papers met eligibility criteria. RESULTS: The 5 techniques that emerged from the review and that can assist CIS implementation were: system piloting, eliciting acceptance, use of simulation, training and education, and provision of incentives. These techniques were evaluated with a range of study endpoints (including system utilisation, clinical effectiveness, user satisfaction, attitudes towards system training, and attitudes towards implementation). Consideration of the clinical context in which the CIS was implemented was a consistent theme in the evidence-base. CONCLUSIONS: Although some evidence is available for the effectiveness of the 5 implementation techniques found in this review, the variable endpoints and the non-comparable study designs mean that the evidence-base needs further developing. We discuss the potential role of simulation and clinical leadership, particularly in relation to surgeons, in CIS implementation and we propose practical advice for CIS implementation and evaluation within hospital settings.

Risk profile and outcomes of aortic valve replacement in octogenarians.

AIM: To investigate the patient characteristics, relationship between the Logistic EuroSCORE (LES) and the observed outcomes in octogenarians who underwent surgical aortic valve replacement (AVR). METHODS: Two hundred and seventy three octogenarians underwent AVR between 1996 and 2008 at Bristol Royal Infirmary. Demographics, acute outcomes, length of hospital stay and mortality were obtained. The LES was calculated to characterize the predicted operative risk. Two groups were defined: LES ≥ 15 (n = 80) and LES < 15 (n = 193). RESULTS: In patients with LES ≥ 15, 30 d mortality was 14% (95% CI: 7%-23%) compared with 4% (95% CI: 2%-8%) in the LES < 15 group (P < 0.007). Despite the increase in number of operations from 1996 to 2008, the average LES did not change. Only 5% of patients had prior bypass surgery. The LES identified a low risk quartile of patients with a very low mortality (4%, n = 8, P < 0.007) at 30 d. The overall surgical results for octogenarians were excellent. The low risk group had an excellent outcome and the high risk group had a poor outcome after surgical AVR. CONCLUSION: It may be better treated with transcatheter aortic valve implantation.