Disruptive Artificial Intelligence engine to facilitate rapid low cost development of specialist e-health applications for smart decision making in medical pre-diagnosis

Información del proyecto

Al-medicare

Identificador del acuerdo de subvención: 762032

DOI

10.3030/762032

Proyecto cerrado

Fecha de la firma de la CE 4 Febrero 2017

Fecha de inicio 1 Febrero 2017

Fecha de finalización 31 Mayo 2017

Financiado con arreglo a

• SOCIETAL CHALLENGES - Health, demographic change and well-being

Coste total

€ 71 429,00

Aportación de la UE

€ 50 000,00

Coordinado por

INFERMEDICA SPOLKA Z OGRANICZONA ODPOWIEDZIALNOSCIA
Poland

Periodic Reporting for period 1 - Al-medicare (Disruptive Artificial Intelligence engine to facilitate rapid low cost development of specialist e-health applications for smart decision making in medical pre-diagnosis)

Período documentado: 2017-02-01 hasta 2017-05-31

Resumen del contexto y de los objetivos generales del proyecto

The purpose of the actions defined in our Work Plan have been achieved. We are assured that our disruptive Artificial Intelligence engine can facilitate rapid low cost development of specialist e-health applications for smart decision making in medical pre-diagnosis moreover as a patient triage AI solution can help save patients from self-misdiagnosis and can optimize utilization of resources by cutting off redundancies.

Trabajo realizado desde el comienzo del proyecto hasta el final del período abarcado por el informe y los principales resultados hasta la fecha

We have conducted technical and technological feasibility study (Task 1) including elaborated Medical Conditions Listing for our Medical knowledge base which is one of the most important component of Infermedica’s platform, technical assessment of the solution including: interface engine; Probabilistic modelling, Machine learning based on real patient diagnoses, Bayesian adjustment of condition prevalence model based on real patient diagnoses that includes: Variational inference in Bayesian Network, Combined Bayesian and classification models The objective was to outline the Automatic verification of the medical content process and we described it. We have accelerated partnership relations with potential partners and customers and prepared a work plan which defines the actions that we are going to undertake in SME Instrument phase 2 project either from technical and business perspective.

Moreover, we have conducted market and commercial study (Task 2) including deep market study, Innovation Management Strategy/IPR study and actions focused on market demonstration and market uptake.

Based on the results and information gathered we have updated our initial business. Now we are ready to bring the product into the market considering all costs associated and profitability.

Avances que van más allá del estado de la técnica e impacto potencial esperado (incluida la repercusión socioeconómica y las implicaciones sociales más amplias del proyecto hasta la fecha)

Phase 1 execution proved that our innovative project is feasible and has a commercial value. The solution will help save patients from self-misdiagnosis and will optimize utilization of resources by cutting off redundancies Patient triage AI can contribute to achieving universal health coverage as well as divert into educational function. Due to technological development, people are still keen on self-diagnosing themselves online. Being unsupervised by the specialist makes the whole activity less predictable and puts them in position to hurt themselves or generate unnecessary physician office visits. Shortage of doctors, especially in the US, is going to deepen by 2030. Physicians would have to choose to either work long hours or limit number of treated patients. At the same time, digital health market growth will be positively influenced by population aging, patient empowerment, more common access to new media and healthcare privatization. Legal factors and people habits will inhibit the progres Currently the competitors can be divided into two distinct groups: big data analyzers and triage-communication based solutions. Main customers for the solution would include health insurers, health providers and software developers. In OECD countries, 280 private insurance companies, 2400 private for profit hospitals and 1400 healthtech startups might be early adopters of AI-based technology

Value proposition