The Patient Status Engine collects real-time vital sign data to enable healthcare providers to know the status of their patients now, and processes this data to predict the status of the patients in the future.
The platform generates, analyses and aggregates real-time physiological data. With AI capabilities and digital apps the PSE is the prime example of a new class of networked medical devices that uses data to alert care teams to signs of deterioration in patients, both in hospital and at home. The "data-driven" intelligence in the system can predict with high specificity, and hours before the event, which patients are likely to develop complications and need further intervention in order to prevent the adverse event from occuring at all.
This data provides insights for all clinical AI and decision support:
Helps doctors and nurses make informed and timely decisions confidently
Allows clinicians to compare real-time patient data and gain insights into their care needs
Enables clinicians to detect deterioraton earlier so they can respond faster
Threshold based, weighted aggregate Early Warning Scoring systems such as MEWS and NEWS are clinically well validated and have had a significant impact in reducing the number of adverse events and avoidable deaths in those hospitals that have adopted them.
However, outstanding challenges remain for such EWS systems: the data is sparse and tends to be backward looking, and they are time consuming for nurses, even when the scores are electronically calculated from the input observational data. The PSE overcomes these challenges by automating the entire EWS process including data capture and calculation, and the vastly richer data provides real-time trend information and highly accurate Early Warning Scores.
The PSE includes real-time NEWS as the default EWS, along with four other user selectable scores in a simple to use and highly visual presentation.
Threshold based Early Warning Scores rely on population averages to determine the normal range for each vital sign. However, at the level of the individual, and at differernt points in a patient's condition, these average "normals" may not be appropriate.
The RAPID (Real-time Adaptive and Predictive Indicator of Deterioration) Index is a new algorithmic score that uses AI methods to characterise a patient specific "phenotype" and then alerts when adverse changes are detected by comparing and continually updating the phenotypes.
The RAPID Index was developed at the Birminhgam Children's Hospital in England using a training set of over 100,000 hours of physiological data collected by the Patient Status Engine from 1400 young patients. Early indications are that the RAPID Index detects deteriorations with greater specificity and sensitivity than standard PEWS. The RAPID Index is expected to be offered as an option in the PSE in late 2019.
Get in Touch
Get in Touch