In the last year, the national health services of many countries have been subject to the significant and dynamic downsizing of their resources yet, despite this, they have managed to deal with the impact of the health emergency connected with SARS-CoV-2, albeit with difficulty. This scenario has accelerated the process of innovating the healthcare system, demonstrating the importance of systematically rethinking remote healthcare assistance, particularly in the context of domestic medicine and hospital discharges.
In fact, the clinical path of the patient is complex and multi-faceted, not only involving medical consultation and diagnostic check-ups but also a series of tasks that they can carry out independently without the supervision of healthcare professionals. To this end, Exprivia is committed to creating increasingly innovative e-Health solutions suitable for the care of the patient, with a targeted and personalised approach.
Exprivia’s solutions make it possible to monitor the patient remotely from their own home using advanced technologies like smart sensors and medical devices. Indeed, the goal of eHealth is to personalise the treatment course of every patient, often termed their Clinical Pathway (CP), taking into account the biological characteristics of the illness and the clinical history and lifestyle of the patient.
Telemedicine for responding to the health emergency
Thanks to telemedicine, a necessary solution for healthcare assistance programmes, patients can be monitored remotely thanks to the supervision of a smart multi-agent system whose architecture is able to manage the specific clinical sub-pathway of the discharged patient, verifying its validation via a doctor or nurse and guaranteeing respect for the prescriptions issued.
The smart medical devices and sensors of the Internet of Medical Things (IoMT), together with environmental and interactive devices with limited processing and archiving capacities, make it possible to check that every device connected to a smart home is able to transmit useful data that can be aggregated, analysed and processed. In this way, Machine Learning (ML) algorithms can be used to provide predictive diagnostics that promote, adjust to and validate the regular activities of the patient at home.
As such, the tasks of the patient would be validated for their attached clinical pathway, which can be managed like a workflow in a Process Mining activity evaluation phase.
Exprivia’s innovative approach to strategically supporting a patient's clinical pathway
In the Paper published as part of the proceedings of the international AIxIA 2020 – Advances in Artificial Intelligence conference (19th International Conference of the Italian Artificial Intelligence Association),in the spirit of the Internet of Medical Things, Exprivia, in collaboration with Bari Polytechnic, explores the formal aspects of the performance of Process Mining activities in an Edge Computing infrastructure, in which the activity logs are collected from data deriving from mobile and interactive medical devices.
The solution focuses on the smart module known as CPAC (Clinical Pathway Adherence Checker) which helps patients follow their medical prescriptions (i.e. their treatments) and provides doctors with actions in order that they can exclude a clinical deterioration.
The study adds further context with the aim of designing and developing a Full-Edge platform architecture in which different AI modules cooperate towards one large shared goal or various smaller goals connected to the world of healthcare.
There are multiple benefits: firstly, the doctor’s workload is lightened with less critical tasks taken away from them; secondly, remote monitoring is made more economical and accessible, particularly in remote areas where medical assistance is limited; finally, the progress of medical technology is incentivised through Big Data.In a nutshell, Edge Computing will make it easier to manage and classify data in a uniform, efficient and secure way.
In addition, considering the intrinsic vulnerability of AI technologies, Exprivia proposes a module for detecting anomalies - CPAD (Clinical Pathway Anomaly Detection) - which can act as an Explainable Security system, making it possible to receive an exhaustive explanation of attack reports which can be easily interpreted also by non-experts in Machine Learning and therefore, in this case, the doctor and the patient undergoing treatment.