Periodic Reporting for period 1 - MEDAS (MedAS: a Machine learning enabled Clinical Decision Support System to prevent prescription errors and improve patient safety)
Reporting period: 2017-05-01 to 2017-08-31
Medication errors are a major problem for patient’s safety, causing harm (2M lives globally) and economic burden (€4,5B-€21,8B, depending on the country). ICTs such as Clinical Decision Support Systems can help reduce them, but they lack accuracy because they are unable to identify risky situations that are not covered by their fixed alarm systems. MedAS incorporates data form different sources and uses big data analytics and machine learning algorithms to identify previously undetectable prescription errors. In order to bring MedAS to TRL9 and commercialize it in the European market, we aim to improve its accuracy and patient surveillance capacities, as well as to extend its ability to detect new types of patients and the adjustment of MedAS to the markets we aim to reach. We will launch MedAS in Q1 2020, first in those countries that have higher rates of EHR adoption (Germany, UK and Italy) and then with others that advanced in health technologies application, reaching a global market share of 6,14% by Q4 20204.
Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far
To ensure commercial feasibility, we have conducted an in-depth analysis of our market, including its dynamics, its environment and key players, our end users and customers, and our competitors. We have also conducted and FTO analysis and defined our value proposition. We have also designed a communication strategy. To analyse the financial risks of launching MedAS, we have observed different scenarios and ensure financial viability in all of them. To assess the technical feasibility, we have stablished the tasks needed to improve our accuracy, our ability to identify new patients and ensure the adaption to the markets we want to reach.
Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)
MedAS incorporates machine learning techniques and big data analytics to detect previously undetectable prescription errors. It is not based on fixed rules as its competitors and this enables it to identify more risky situations and prevent more errors. It is optimized to reduce false positive, reducing alert fatigue and minimizing disturbances to the clinical practice and facilitating the adoption of the technology by the clinician. It can be customized to the demographics and characteristics of the populations of each health care organization to improve accuracy.