In this paper, we investigate the classification of cardiomegaly using multimodal data, combining imaging data from chest radiography with routinely collected Intensive Care Unit (ICU) data comprising vital sign values, laboratory measurements, and admission metadata. In practice a clinician would assess for the presence of cardiomegaly using a synthesis of multiple sources of data, however, prior machine learning approaches to this task have focused on chest radiographs only. We show that non-imaging ICU data can be used for cardiomegaly classification and propose a novel multimodal network trained simultaneously on both chest radiographs and ICU data. We compare the predictive power of both single-mode approaches with the joint network. We use a subset of data from the publicly available MIMIC-CXR and MIMIC-IV datasets, which contain both chest radiographs and non-imaging ICU data for the same patients. The approach from non-imaging ICU data alone achieves an AUC of 0.684 and the standard chest radiography approach an AUC of 0.840. Our joint model achieves an AUC of 0.880. We conclude that non-imaging ICU data have predictive value for cardiomegaly, and that combining chest radiographs with non-imaging ICU data has the potential to improve model performance for the same subset of patients, with further work required to demonstrate a significant improvement.

Clinical experience of perampanel overdoses is markedly limited and the relevant literature is sparse. Perampanel is a novel antiepileptic drug (an amino-3-hydroxy-5-methyl-4-isoxazlepropionic acid glutamate receptor antagonist) with a long half-life, which is used for the adjunctive treatment of epilepsy. The literature available identifies a potential for prolonged unconsciousness in overdose. We report a case of prolonged unconsciousness for 14 days following a perampanel overdose of 3.5 times the maximum daily dose, requiring protracted intubation and ventilation on intensive care, with eventual complete neurological recovery. This represents the longest known period of unconsciousness with full recovery and the first reported in a perampanel naïve patient. This case helps to inform decision-making in critical care, particularly the early consideration of admission and intubation. It highlights that while perampanel overdose may not initially cause systemic effects such as cardiac toxicity, it can cause protracted altered consciousness with secondary compromise requiring prolonged intensive care management.

Describes Novotel’s “Back to the Future” programme, introduced in 1993 with the aim of revisiting the customer‐focused philosophy that gave rise to the company’s success in the 1960s and 1970s. Novotel’s commitment to change transformed its image, structure and day‐to‐day approach to customers. Emphasis was placed on widespread empowerment of employees and a commitment to ensure decision makers were placed as close as possible to clients. Together with a massive investment in overhauling all older hotels, a new approach to managing the Group was adopted which called for a flatter organization and unprecedented autonomy for the general manager of every hotel. Novotel has today reassumed its position as leader and innovator in the European hotel industry.

SE in patients with LBBB demonstrated high feasibility and the combination of LV systolic function and myocardial ischaemia provided important prognostic information. Contrast-enhanced SE improved the prediction of outcome.

unknown. We hypothesised that information of ischemia and atherosclerosis which can be achieved simultaneously by ultrasound (SE and carotid ultrasound) can provide incremental prognostic information in these patients. Methods Consecutive patients with no previous history of CAD investigated with SE for suspected angina underwent a simultaneous carotid ultrasound. Carotid plaque burden was assessed. Patients were followed up for combined major adverse cardiac events (MACE) of all-cause mortality, non-fatal myocardial infarction and unplanned coronary revascularization. Results Of the 591 patients, (269 male (46%), mean age 59 ± 11 years), 67 (11%) demonstrated myocardial ischemia by SE. Prevalence of carotid plaque disease was higher (59%) but similar in normal and abnormal SE patients (58% vs. 66%, p = 0.22). At a mean of 37 months, 580 (98%) could be followed up during which 40 MACE occurred. In the multivariable model pre-test probability of CAD (p = 0.001), abnormal SE (p < 0.0001) and plaque burden (p < 0.0001) predicted MACE after adjusting for age, gender, cardiac risk factors and baseline drug therapy. MACE rate/year increased from 0.9% vs. 1.95% vs. 4.23% vs. 9.58% (p < 0.0001) in patients with no plaque and normal SE vs. presence of plaque and normal SE vs. no plaque and abnormal SE vs. plaque and abnormal SE, respectively. Figure demonstrates the prognostic value of simultaneous carotid plaque assessment and SE. When prognosis was assessed in a hierarchical manner as done clinically (pre-test probability of CAD followed by SE and carotid ultrasound), it showed significant increment in global chi square from 22.1 to 48.9 to 78.5 (p < 0.0001). Conclusion In patients with suspected stable angina but without known CAD simultaneous SE (for ischemia) and carotid ultrasound (for atherosclerosis) provided synergistic prognostic value. This study supports simultaneous carotid ultrasound in such patients investigated by SE and has implications in primary prevention treatment.