Hospitals often lack an ongoing inventory. Moreover, since seasonal overloads, e.g. due to flu outbreaks or increased risk of accidents in winter, are seldom taken into account, orders and deliveries are placed that simply do not meet actual needs.
Although we have a highly efficient and recognised healthcare system, there is an epidemic data emergency almost everywhere with regard to the use of efficient data processing. With the PAIRS platform now under construction, “healthy” planning and ordering management can also be realized in the future.
With the implementation of a system for automated inventory control and the establishment of an early warning system for anomalies, epidemics or recurring waves of disease, etc., supply and demand planning can be brought into being in line with requirements. In addition, the solution developed within the PAIRS research project offers more cost-effective purchasing on a specialty data marketplace, e.g. by enabling composite orders to be placed for higher purchasing volumes.
The PAIRS platform enables early detection and crisis prevention from internal hospital data, i.e. patient and laboratory data. With the help of PAIRS, overarching insights can be gained from this data – especially when it comes to frequent abnormalities or anomalies. With the combination of AI and human intelligence, patterns can be identified from such data and early crisis prevention can be initiated.
As this is highly sensitive data, the release of which is strictly prohibited by the General Data Protection Regulation (GDPR), it requires the use of a system that allows access without violating the GDPR. The architecture of the PAIRS platform, based on emerging standards in these areas such as IDSA and GAIAX, offers the guarantee of data sovereignty and data privacy.
In addition, the use of state-of-the-art technologies such as Federated Learning or the patent-pending Trusted Data Hub is a privacy-preserving multi-party computing solution that guarantees data sovereignty and security for all participants. This makes it possible to use even confidential data without disclosing the respective raw data.