Search

Transport authorities rely on pavement characteristics to determine a pavement condition rating index. However, manually computing ratings can be a tedious, subjective, time-consuming, and training-intensive process. This paper presents a deep-learning framework for automatically rating the condition of rural road pavements using digital images captured from a dashboard-mounted camera. The framework includes pavement segmentation, data cleaning, image cropping and resizing, and pavement condition rating classification. A dataset of images, captured from diverse roads in Ireland and rated by two expert raters using the pavement surface condition index (PSCI) scale, was created. Deep-learning models were developed to perform pavement segmentation and condition rating classification. The automated PSCI rating achieved an average Cohen Kappa score and F1-score of 0.9 and 0.85, respectively, across 1–10 rating classes on an independent test set. The incorporation of unique image augmentation during training enabled the models to exhibit increased robustness against variations in background and clutter. • A deep-learning framework for automatic pavement condition rating for roads is presented. • Our proposed framework consists of segmentation, cleaning, resizing and classification. • A large open dataset of real-world images captured from regional and local roads in Ireland. • Images are labelled by expert data analysts using PSCI rating scale used in Ireland. • The unique augmentation enabled the models to be more robust to changes in background. [ABSTRACT FROM AUTHOR]

Objective: Advancement in healthcare provision has led to increasing octogenarian ST elevation myocardial infarction (STEMI) presentation to hospital for early revascularisation therapies. Limited literature to date exists to suggest octogenarian STEMI population; with majority of trials excluding these age group patients. Due to an ageing population, we expect increasing rates of STEMI in the octogenarian and nonagenarian population in the future. This study seeks to identify the outcomes of patients over the age of 80 presenting with STEMI and determine the factors associated with better or worse outcome., Patients and Methods: This study is a single-centre retrospective observational study involving patients' age 80 or older presenting with STEMI between January 2014 and December 2019. Patient data were collected by chart review and analysis of the local STEMI database. Standard Bayesian statistics were employed for analysis., Results: 1301 patients presented with STEMI during this period. 159/1301 (12.2%) were 80 years or older that fulfilled STEMI criteria, 35/159 (22.1%) were medically managed. 107/124 (86.29%) had angiographic evidence of acute total or partial thrombotic occlusion, and 97/107 were treated with primary percutaneous coronary intervention (PPCI). The activation ECG most commonly exhibited an anterior STEMI, while inferior STEMI ECGs had the strongest positive predictive value. PPCI group had a 30-day mortality rate of 20% (p=0.07) and 1-year mortality was 22.4%. Highest mortality was observed with cardiogenic shock, low ejection fraction, higher high sensitivity cardiac troponin T and creatinine at presentation. Conservatively managed patients had significant higher mortality rate (48% vs 22.4%, p=0.005) at 1 year., Conclusion: Patients over the age of 80 who present with STEMI and undergo PPCI have a significantly lower mortality rate at 1 year. These patients have a 77.6% survival at 1 year, with 92.4% likelihood of discharge to home (without need for long-term nursing home care). Cardiogenic shock in this group was associated with a 1-year mortality of 87.5%. Despite the advanced age, we suggest favourable outcomes described in the absence of patients presenting with cardiogenic shock., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2021. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)