Descripción del proyecto
Un algoritmo de aprendizaje automático para la predicción precoz de infecciones posoperatorias
Aproximadamente el 25 % de los pacientes quirúrgicos en Europa padecen algún tipo de complicación posoperatoria en forma de infección. La empresa neerlandesa Healthplus.ai trabaja en el desarrollo de un algoritmo de aprendizaje automático avanzado para predecir infecciones posoperatorios 5 días antes del diagnóstico del equipo médico con una precisión del 80 %. El objetivo del proyecto PERISCOPE, financiado con fondos europeos, es aumentar el conjunto de datos y lograr una precisión superior al 90 % 5 días antes de la aparición de posibles síntomas de infección en el paciente. Además, el proyecto se centra en un plan y modelo de negocio sostenibles, en asociaciones y en cuestiones jurídicas y normativas.
Objetivo
Some 50M people need to undergo inpatient surgery per year in Europe Yet, despite intensive research efforts, around 25% of surgical patients will experience a complicated recovery with some type of infection on their path: pneumonia, urinary tract infections, wound infections, abdominal infections and bacteremia. Of course, the risk varies depending on the patient and the procedure, but despite efforts like biomarkers, risk scores or devices for early warning/detection, and preventive methods like ‘Enhanced Recovery After Surgery’ (ERAS), the overall risk still leaves almost one in four patients to get an infection within 30-days after surgery.
If we look beyond the personal suffering of patients and relatives, the cost of an infectious complication is estimated at around €10,000 per patient. Hence, total cost in only the Netherlands alone can be calculated at up to €3.5B per year, as approximately 350,000 Dutch patients go through an infection after surgery yearly. Total EU costs are even more shocking at an estimated €125B per year.
Healthplus.ai R&D BV is currently developing an advanced machine-learning (ML) algorithm (TRL level 4) to predict post-operative infections 5 days prior to the average medical team diagnosis, currently already achieving an accuracy of 80%. Through increasing the dataset and taking on more types of data, the ultimate goal is to ultimately achieve >90% accuracy at 5 days before the infectious symptoms on average are actually detected within the patient.
In this proposal, we seek how to go beyond the proven technical feasibility and assess channels to deliver the tool in a safe, affordable and scalable way through third-party vendors with a sustainable business model and plan with the right partnerships and intensify these relationships. Also, potential legal and regulatory issues with EU expansion will be identified, investigated and suitable measures outlined.
Ámbito científico
Programa(s)
Convocatoria de propuestas
Consulte otros proyectos de esta convocatoriaConvocatoria de subcontratación
H2020-SMEInst-2018-2020-1
Régimen de financiación
SME-1 - SME instrument phase 1Coordinador
1017 AZ AMSTERDAM
Países Bajos
Organización definida por ella misma como pequeña y mediana empresa (pyme) en el momento de la firma del acuerdo de subvención.