Early detection of clinical deterioration in patients can help reduce admissions to intensive care units (ICUs), cardiac arrests, sepsis, and deaths. Deteriorations commonly manifest themselves early via very subtle changes in body signals, such as those directly generated by cardiac and respiratory functions. Accurately measuring those signals and computing clinical metrics (commonly referred to as "Early Warning Scores"), is essential in allowing healthcare professionals to identify whether a patient is at risk. Unfortunately, current methods to measure these signals, and subsequently identifying deteriorations, are suboptimal. This leads to very significant, and sometimes tragic, mistakes. It has been estimated that poor monitoring is implicated in around 31% of preventable deaths and is associated with over 80% of severe adverse events. The aim of this project is to add intelligence into the existing Acurable devices which are very small and patient friendly. This will make it possible to extract automatically physiological parameters which are important within the context of deteriorations at home. The unique physical sensing characteristics of Acurable devices will allow the extraction and interpretation of a much wider set of clinical indicators of deterioration than was ever possible with such a small device before. This will consequently eliminate the limitations of other unobtrusive methods, and minimise the risk of life-threatening deteriorations being missed or caught too late.

no public description

Acurable produces the first truly wearable medical device able to accurately diagnose sleep apnoea in a non-invasive way. Acurable's patented technology is a major engineering innovation and the product of 10 years research at Imperial College London. Our solution uses a non-invasive wearable sensor (AcuPebble) to monitor acoustic signals of the patient and then applies sophisticated signal treatment algorithms to extract from them the main parameters required for the diagnosis of sleep apnoea. Results from a preliminary clinical study in adults yielded excellent results on the efficacy of a former, suboptimal, version of the device detecting respiratory apnoea events in a clinical setting. The results were published by BMJ Open in 2014\. This project application covers the scientific and technical work required to modify the technology so that it can also be used in children. Throughout the course of this project: (1) We will conduct a clinical study to gather acoustic signals with the AcuPebble sensor from children who are also undergoing the standard sleep diagnosis method. These signals will be used to carry out research work leading to modification of the existing algorithms to optimize them to the physiological characteristics of the pediatric population; (2) Based on the same clinical study, the AcuPebble software will be modified to provide outputs that are relevant for diagnosis of the pediatric population; (3) The modified algorithms and system outputs will be validated to prove clinical efficacy; (4) Usability studies will be carried out leading to user interfaces customized for the specific needs of the pediatric user case; (5) A clinical evidence dossier as required by regulatory bodies will be created; (6) A data platform/user interface will be created, to allow the use of AcuPebble, not just for automatic diagnosis, but also as a signal collection research tool, that can be used to carry out research in a wider range of pediatric diseases.

Acurable produces the first truly wearable medical device able to accurately diagnose sleep apnoea in a non-invasive way. Acurable's patented technology is a major engineering innovation and the product of 10 years research at Imperial College London. Our solution uses a non-invasive wearable sensor (AcuPebble) to monitor acoustic signals of the patient and then applies sophisticated signal treatment algorithms to extract from them the main parameters required for the diagnosis of sleep apnoea. Results from a preliminary clinical study at yield excellent results on the efficacy of a former, suboptimal, version of the device detecting respiratory apnoea events in a clinical setting. The results were published by BMJ Open in 2014\. This project application covers the technical work required to further enhance the capabilities of the technology within the context of sleep apnea diagnosis. The project is composed of four main work streams: (1) conduct a clinical study to generate the clinical evidence required to demonstrate our technology efficacy on automatic detection of certain physiological biomarkers which are significant for the diagnosis of the condition; (2) build the clinical evidence dossier required for CE marking; (3) Carry out more research into the usability aspects of the system; (4) Develop the first version of a data platform/user interface, which allows the use of AcuPebble, not just for automatic diagnosis of sleep apnoea, but also a signal collection research tools that can be used by data and clinical scientists to carry out research in a wide range of respiratory and cardiac conditions.