RESUMEN
PURPOSE: Dyssynchrony may cause lung injury and is associated with worse outcomes in mechanically ventilated patients. Reverse triggering (RT) is a common type of dyssynchrony presenting with several phenotypes which may directly cause lung injury and be difficult to identify. Due to these challenges, automated software to assist in identification is needed. MATERIALS AND METHODS: This was a prospective observational study using a training set of 15 patients and a validation dataset of 13 patients. RT events were manually identified and compared with "rules-based" programs (with and without esophageal manometry and reverse triggering with breath stacking), and were used to train a neural network artificial intelligence (AI) program. RT phenotypes were identified using previously defined rules. Performance of the programs was compared via sensitivity, specificity, positive predictive value (PPV) and F1 score. RESULTS: 33,244 breaths were manually analyzed, with 8718 manually identified as reverse-triggers. The rules-based and AI programs yielded excellent specificity (>95% in all programs) and F1 score (>75% in all programs). RT with breath stacking (24.4%) and mid-cycle RT (37.8%) were the most common phenotypes. CONCLUSIONS: Automated detection of RT demonstrated good performance, with the potential application of these programs for research and clinical care.
Asunto(s)
Lesión Pulmonar , Síndrome de Dificultad Respiratoria , Humanos , Inteligencia Artificial , Estudios Prospectivos , Redes Neurales de la Computación , Síndrome de Dificultad Respiratoria/diagnóstico , Síndrome de Dificultad Respiratoria/terapia , Síndrome de Dificultad Respiratoria/etiología , Respiración Artificial/efectos adversosRESUMEN
Introduction: The COVID-19 pandemic has put increased stress on medical systems, infrastructure, and the public in expected and unexpected ways. This case report summarises an unexpected case of methanol poisoning from hand sanitiser ingestion due to changes in industry regulations, increased demand for cleaning products and severe psychosocial stressors brought on by the pandemic. Severe methanol toxicity results in profound metabolic disturbances, damage to the retina and optic nerves, and potentially death. Case Presentation: The patient was a 26-year-old male with alcohol use disorder who presented with one day of nausea, vomiting, and abdominal pain after consuming hand sanitiser. Within a few hours, the patient had suffered multiple seizures, cardiac arrests and required admission to the ICU for emergent management of methanol poisoning. EEG and brain perfusion imaging were performed to confirm brain death, given concerns about the cranial nerve exam after methanol poisoning. Conclusions: While rare, methanol toxicity remains a potentially fatal poisoning in the United States and worldwide. When healthcare and public resources are strained, healthcare professionals must consider particularly abnormal presentations. In patients suspected of brain death from methanol toxicity, cranial nerve examination may be unreliable. Therefore, additional testing is necessary to confirm brain death.