UCIE | CSIC-UMH

We participate in national and international innovation programmes, with public and private funding and often with the participation of industry partners. Active projects driven from IN.Pulse are:

AGEGEROP. Search for geroprotective agents

Principal Investigators: María Domínguez and Roberto Santoro

Project start date: 2022

Call: INNVA2/2022/13

Convener: AVI

We investigate geroprotective interventions to prevent frailty in people who have suffered from age-accelerating diseases such as cancer and COVID19, using an automated drug-screening platform, and scalable through the use of artificial intelligence.

More Info

AGEGEROP. Search for geroprotective agents

INNVA2/2022/13. AVI 2022 – 2024 action line L2

Ageing is an inevitable biological phenomenon but certain diseases such as cancer or COVID19 accelerate this process by triggering a syndrome called frailty. This accelerated ageing is a state of vulnerability triggered after a stressful event, such as hospitalisation or illness, and is a consequence of cumulative deterioration in many physiological systems.

This cumulative decline means that any new minor stressful event triggers disproportionate responses in health status. To put this into perspective, there are more than 14 million cancer survivors in Europe whose frailty rates range from just under ten per cent to over eighty per cent. To this growing population, we must add the population that has experienced COVID19 , some 219 million, with almost 5 million affected in Spain, who may suffer from frailty. Frailty leads to loss of autonomy and, in the elderly, risk of social isolation.

The aim of the project is to accelerate the discovery of and research into interventions with the capacity to prevent, delay or reverse the ageing process, known as geroprotective agents. It is part of the Generalitat Valenciana’s strategy to help combat diseases of great social, emotional and economic impact, and to establish a basis based on scientific research to develop therapies that improve quality of life and the European-wide strategy EUROCARE (Survival of cancer patients in Europe).

Many of the existing geroprotectants (~ 259 compounds http://www.geroprotectors.org) have been identified in studies in the fruit fly Drosophila melanogaster and the mouse Mus musculus. Ageing accelerates many diseases, and diseases such as cancer in early life accelerate ageing. We need to bridge the gap between these two phenotypes. That is why our recent research has focused on discovering treatments that reduce the incidence of cancer in animals and also its sequelae. These compounds are new and others are known and even already used in medicine, such as trichostatin A, valproic acid, rapamycin, or Resveratrol. Reducing cancer extends lifespan and interventions that delay ageing appear to protect against cancer (funded by grant CICPF16001DOMÍ and AECC2017).

Longitudinal longevity studies and/or screening for geroprotective agents urgently demand automation of these experiments and using AI could increase the accuracy of drug response and reduce cost and time.

At IN we have developed a device for the automation of experiments in Drosophila, which has been protected by a patent. With the help of IN.pulse, this project aims to accelerate this idea/prototype, currently at TRL 4/5 level, to a marketable product. Such automation would differentiate our tests/platform from those existing worldwide.

The acceleration of this technological development emerging in the NI offers an excellent opportunity to participate in the development of knowledge to detect, prevent, and reduce frailty/ageing that can guide clinical practice.

This scalable automation and AI for a rapid and cost-effective drug screening platform could be offered as a service of the NI to provide in vivo results on the various properties of drugs of interest, e.g. their side effects, toxicity, impact on lifespan, and performance or health. This information could serve as an excellent starting point for scientists and companies trying to validate theoretical predictions or plan longevity experiments, providing results before designing pre-clinical and clinical trials.

Principal Investigators:

María Domínguez Castellano

Principal investigator of the ‘Mechanisms of growth control and cancer’ group at the NI

Roberto Santoro

Pre-doctoral researcher in the group ‘Mechanisms of growth control and cancer’ at the IN

External partners:

Funded by:

LONELYNESS. Early identification of loneliness and emotional distress

Principal Investigators: Santiago Canals and Cristina Márquez

Project start date: 2022

Call: INNVA2/2022/13

Convener: AVI

Social support networks are key to mental and emotional health, especially in the geriatric population that has been severely affected by the pandemic. The project proposes to identify subjective loneliness and emotional stress through multidimensional telemetric measures and deep learning algorithms to design personalised care activities and improve quality of life.

More Info

LONELYNESS. Early identification of loneliness and emotional distress

INNVA2/2022/13. AVI 2022 – 2024 action line L2

Support networks and social interactions are an important pillar of people’s mental health. The current pandemic has further highlighted how loneliness and social isolation can have a negative impact on emotional well-being, factors that can exacerbate other physical and cognitive health problems.

Approximately 30% of older people feel lonely, which is one of the major risks for their decline and entry into dependency. Support networks and social interactions are an important pillar in people’s mental health.

The geriatric population has been one of the sectors of the population most affected by the COVID19 pandemic, both in terms of mortality and in relation to the negative effects of social isolation. However, the lack of objective markers to identify those in vulnerable situations hinders the effectiveness of care work and hinders the application of personalised treatments at a time when health and care staff have had to adapt their routines to strict protocols to maximise safety.

The perception of loneliness is by definition subjective. Each person perceives social isolation differently, and the effect of certain daily activities on their mental health is also highly subjective. Nursing home workers are adept at intuitively identifying the state of mind of their elderly, but these practices would greatly benefit from objective measurements that can inform the state of each individual person.

One of the impediments to the objective identification of changes in emotional state, as well as the selection of those daily activities that especially benefit people, particularly in the case of the geriatric population, is the phenomenon described as social desirability. It is common that when asked how they feel, grandparents respond with what they think the interlocutor intends to hear. The impossibility of identifying emotional states is even more difficult in people with dementia or a high degree of dependency.

The aim of the project is the early identification of moments of subjective loneliness and emotional distress that can alert care staff or relatives, in order to design and implement care activities. To this end, multidimensional telemetric measurements of different physiological records will be used, accompanied by measures of social distance and subjective reports of emotional well-being. Deep Learning algorithms will be used to identify marker networks indicative of episodes of subjective loneliness perceived by the geriatric population.

Principal Investigator:

SANTIAGO CANALS RAMONEDA

Principal investigator of the ‘Plasticity of Neural Networks’ group of the IN

cristina márzquez

Center for Neuroscience and Cell Biology. University of Coimbra. Portugal

CExternal partners:

Funded by:

APPZHEIMER. Development of an application for early detection of Alzheimer’s diseas

Principal Investigator: Encarni Marcos Sanmartín

Project start date: 2022

Call: INNVA2/2022/13

Convener: AVI

AppZheimer, a software tool for early detection of Alzheimer’s disease that reduces economic expenditure and decongests the healthcare system, thus anticipating cognitive and pharmacological therapies, and improving the quality of life of patients and their environment.

More Info

APPZHEIMER. Development of an application for early detection of Alzheimer’s disease

Alzheimer’s disease is a type of dementia that causes problems in memory, behavior and thinking, even affecting everyday tasks. It currently affects about 50 million people worldwide and more than 1.2 million in Spain. It usually appears after the age of 65, with aging being the major risk factor for the disease.

It is believed that the number of cases of Alzheimer’s disease will increase substantially in the coming years due to population aging, with the consequent economic impact on both families and the healthcare system. To improve the quality of life of patients, early detection of the disease is essential to slow its progression.

The objective is the creation of a software tool, AppZheimer, that can be used by anyone, at home or in specialized centers, and that sends processed results to the health professional to help in medical decision making by aiding in the early detection of Alzheimer’s, thus anticipating cognitive and pharmacological therapies.

This project will solve a threefold problem:

It will reduce the economic expense in the diagnosis of Alzheimer’s, through a behavioral test that can be performed outside the medical center and that helps in a first screening of the population at risk of suffering from the disease.
The healthcare system will be substantially decongested, since the doctor will be able to prescribe/advise the use of AppZheimer’s over the phone, considerably reducing consultation time.
It will aid in the early detection of Alzheimer’s disease and thus enable early intervention of the disease in a significantly higher percentage of cases.

The software tool developed is expected to have a high impact on healthcare and the population, taking on special importance in this time of the COVID-19 pandemic where the increased occupation of the healthcare system has delayed the diagnosis of Alzheimer’s cases in the Valencian Community by up to 6 months (https://www.informacion.es/alicante/2021/09/20/sanidad-tarda-seis-meses-diagnosticar-57498508.html). Early detection of Alzheimer’s disease is essential to avoid possible accidents due, for example, to the use of motor vehicles when it should not be, and for the appropriate medical treatment to delay the symptoms of the disease, with a clear impact on the quality of life of the sick person and the people around him/her.

Principal Investigator:

Encarni marcos sanmartín

Doctor Investigator of the ‘Plasticity of Brain Networks’ group of the IN

External partners:

Funded by:

MREASI. Development of a Deep Learning algorithm to obtain advanced MRI images in a clinical environment

Principal Investigators: Silvia de Santis and Antonio Pertusa

Project start date: 2022

Call: INNVA2/2022/13

Convener: AVI

This project aims to translate advanced magnetic resonance imaging to the clinical environment through artificial intelligence to increase the resolution of the images and thus detect morphological and microstructural alterations in greater detail.

More Info

MREASI. Development of a Deep Learning algorithm to obtain advanced MRI images in a clinical environment

Non-invasive diagnosis by magnetic resonance imaging has advanced greatly in recent years. However, the translation of new methodologies to the clinic remains difficult and, indeed, clinical diagnosis in the daily practice of radiology services is still performed with very basic techniques.

While the usefulness of resonance approaches to detect morphological and microstructural alterations has been demonstrated, these advanced maps are usually obtained using very advanced technology, which is not currently within the reach of all hospitals. However, thanks to artificial intelligence, it is possible to increase the resolution of any image, obtaining brain maps with more detail than the input ones.

The aim of this project is to transfer advanced imaging to the clinical environment through artificial intelligence. To this end, synthetic MRI data will be generated and the necessary machine learning environment will be developed to increase the resolution of the images, so that advanced imaging is possible in a clinical context. This algorithm will be tested in a pilot study with images obtained in radiology services in our environment.

Principal Investigator: