Infraestructura de Medicina de Precisión asociada a la Ciencia y la Tecnología
Myelodysplastic syndromes (MDS) are a heterogeneous group of myeloid hematologic neoplasms. The incorporation of genomic studies has allowed significant advances in their understanding. These genomic techniques not only identify diagnostic groups and confirm clonality, but also improve prognostic stratification and guide therapeutic decisions. Despite these advances, MDS continue to present challenges in terms of diagnosis, prognostic stratification, and effective treatment. The preleukemic nature of MDS and their majority representation among germline genetic predisposition diseases make them an ideal model for the development of the IMPACT pillars: genomics, prevention and data science.
The UMBRELLA (PI20/00970) and UMBRELLA-SUMMA (PI2023/01103) projects were developed within the Spanish SMD Group (GESMD). Its main objective is to facilitate next-generation sequencing (NGS) studies for patients with MDS in all the centers of the Spanish group. Our consortium will follow the foundations established by UMBRELLA to develop a coordinated strategy that integrates the clinical, genetic and molecular data of patients with MDS into the Spanish MDS registry (RESMD), previously established by the GESMD. Our proposal also seeks to add value by incorporating the evaluation of patient-perceived outcomes (PROMs) and patient-reported experience (PREMs) into the RESMD. Artificial intelligence (AI) models are presented as promising tools for the management of MDS, allowing the analysis of large volumes of data and the identification of complex patterns for personalized treatments. In addition, actions will be implemented to improve patient diagnosis, including the validation of new tools such as optical genome mapping (OGM) and the digitization of bone marrow images, and progress will be made in predictive and prognostic strategies in patients with MDS of special interest, including: patients with TP53 mutation, therapy-related neoplasms and patients with germline predisposition.
This comprehensive and multidisciplinary approach not only seeks to transform the research and treatment of myelodysplastic syndromes, but also aspires to offer patients an improvement in quality of life and a brighter future, where science and innovation come together to provide personalized and effective solutions in their fight against the disease.
1. To develop a coordinated strategy that integrates the clinical, genetic and molecular data of patients diagnosed with Myelodysplastic Syndrome (MDS) at the national level within the National Health System (SNS).
1.1. Incorporation of data from the Spanish Registry
1.2. Creation of a biobank of specific samples for MDS
1.3. Integration of Patient-Reported Outcome Measures (PROMs) and Patient-Reported Experience Measures (PREMs)
2. To validate new diagnostic tools in patients with MDS, through:
2.1. Optical Mapping of the Genome
2.2. Bone Marrow Image Digitization
3. To evaluate the value of genomic, transcriptomic and/or protein analysis as a predictive strategy in patients with MDS and clonal hematopoiesis (CH) under special conditions, by:
3.1. Study of patients with MDS/CH and TP53
mutations 3.2. Patients with Therapy-Related Neoplasms (TNCT)
3.3. Identification and characterization of patients with germline predisposition
4. Develop interoperable Artificial Intelligence (AI) tools that efficiently integrate clinical, molecular, and morphological information from patients with myelodysplastic syndromes, to create advanced algorithms that optimize diagnosis, prognosis, and personalized treatment.
5. To promote training, dissemination and dissemination of knowledge through the organisation of working groups aimed at health professionals and patients.
The ultimate goal is to improve the well-being and prognosis of patients. The project aims to incorporate the perception and experience of the patient during the care process into omics and artificial intelligence data. The development of this project will therefore benefit healthcare management by optimising treatments, reducing the costs and toxicities of inappropriate drugs, and improving the prediction of response by combining all this with patient satisfaction.
The use of Artificial Intelligence (AI) for personalized risk prediction and the selection of patients with a higher probability of responding to certain therapies will allow optimal management of them, both in terms of response to the pathology and in the use of therapeutic resources of the health system, by limiting non-optimal treatments with little impact on survival.
The group’s preliminary experience reveals that, with a relatively limited amount of clinical data, it is possible to assign a risk stratum different from that of the IPSS-R to 60% of patients, which can be correlated with significant changes in clinical practice.
It is foreseeable that the implementation of strategies based on the combination of clinical data with molecular results will allow us not only to refine the risk stratification model, but also to predict the response to drugs, which are associated with variable rates of efficacy and remarkable toxicity.
In this way, the results of this study will also contribute to optimizing the resources of the National Health System.