Personalised Medicine in the Identification of Preclinical Cognitive Impairment. Development of a Predictive Risk Model (DENDRITE)

Personalised Medicine in the Early Identification of Preclinical Cognitive Impairment. Development of a Predictive Risk Model.

The goal of this observational study is to use the combined power of the integration of clinical, molecular, proteomic, genomic, care, social, environmental and behavioural data in patients, using advanced artificial intelligence techniques for data processing and analysis, in order to generate predictive models for the preclinical detection of CI in the population aged 55-70 years.

Study Overview

• Status: Recruiting
• Conditions: Cognitive Dysfunction

Detailed Description

The "Comprehensive Plan for Alzheimer's and other Dementias" shows that more than 50% of cases of cognitive impairment (CI) in population-based studies are undetected. The figure is particularly striking in the case of mild dementias, of which up to 90% are undiagnosed. The aim is to use the combined power of the integration of clinical, molecular, proteomic, genomic, care, social, environmental and behavioural data in patients, using advanced artificial intelligence techniques for data processing and analysis, in order to generate predictive models for the preclinical detection of CI in the population aged 55-70 years.

Multicentre, non-interventional, convergent mixed methods observational study, with a prospective observational design part and a qualitative design part. Sample recruited randomly among users of the public health system in the participating geographical locations. Data will be collected in 6 regions (Andalucia, Castilla-Mancha, Catalonia, Valencia, Madrid and the Basque Country) and their rural and urban Primary Care (PC) networks.

Non-institutionalised subjects, aged between 55 and 70 years, assigned to PC centres in the territories included in the study, with a "living history" (recorded in the last 12 months) and without an established diagnosis of CI.

A descriptive analysis of the characteristics of the population will be carried out using frequencies and percentages or measures of central tendency and dispersion, with their 95% confidence intervals. Baseline socio-demographic and clinical characteristics will be compared in order to study the homogeneity of the sample. For the comparison of qualitative variables, the Chi-square test or Fisher's exact test will be used and for the comparison of quantitative variables, the t-test or Wilcoxon test will be used. Logistic regression models are proposed to analyse health outcome factors associated with mild cognitive impairment. All models will include repeated measures for each individual. All models will adjust for different risk factors, and for those factors that may change over time, the interaction between time and that factor will be studied.

Initially, multivariate linear latent models will be used for the predictive model of cognitive impairment risk. The integration of data from multiple sources of information will be done using multivariate probabilistic models, in order to find a representation of the patient in a feature space influenced by all data sources (visits).

Web tools such as Ingenuity Pathway Analysis will allow the integration of data at different molecular levels (genetic, protein and autoantibody), while artificial intelligence tools will allow the integration of such data, data derived from electrochemical sensors and data related to clinical and behavioural data with cognitive impairment in order to obtain a predictive model of cognitive impairment, neurodegeneration and AD.

• Study Type: Observational
• Enrollment (Estimated): 1150

Contacts and Locations

• Study Contact: Name: Mayte Moreno-Casbas; Phone Number: +34 637390052; Email: mmoreno@isciii.es

Study Locations

• Spain
  • Bilbao, Spain, 48012
    • Recruiting
    • Irala Health Center
    • Contact: Mª Ángeles Cidoncha
    • Principal Investigator: Verónica Tiscar
  • Lleida, Spain, 25005
    • Recruiting
    • Onze de Setembre Health Center
    • Contact: Esther Rubinat
  • Madrid, Spain
    • Recruiting
    • San Andres Health Centre
    • Contact: Pedro Otones
  • Alicante
    • San Vicente Del Raspeig, Alicante, Spain, 03690
      • Recruiting
      • Sant Vicent I Health Center
      • Contact: María Isabel Orts
  • Barcelona
    • Sant Boi De Llobregat, Barcelona, Spain, 08830
      • Recruiting
      • Camps Blanc Health Center
      • Contact: Mª Isabel Feria
  • Castilla-La Mancha
    • Albacete, Castilla-La Mancha, Spain, 02006
      • Recruiting
      • Zone 8 Health Center
      • Contact: María Emilia Villena
  • Huelva
    • Gibraleón, Huelva, Spain, 21500
      • Recruiting
      • Gibraleón Health Center
      • Contact: Rafaela Camacho
    • Punta Umbría, Huelva, Spain, 21100
      • Recruiting
      • Punta Umbría Health Center
      • Contact: Rafaela Camacho

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Probability Sample

Study Population

The study will be carried out on non-institutionalised subjects in the study locations, aged 55 to 70 years, attached to the PC centres of the territories included in the study, with a living history (at least one record in the last 12 months). The individuals will be selected from lists of patients from the participating practices in the 7 geographical locations, each of them providing 150 patients. The sample will be obtained by stratified by age (5-year wide strata) and sex who do not include any diagnosis of mild CD in their clinical records (MMSE= 24-27 points). Any refusal to participate after screening will be replaced by the next subject on the sampling list from the same centre and stratum. Samples will be collected at baseline and at 16 months.

Description

Inclusion Criteria:

• Non-institutionalised subjects from the study locations.
• Aged between 55 and 70 years, attached to the PC centres of the territories included in the study
• Living history (at least one record in the last 12 months)
• Without an established diagnosis of CI.

Exclusion Criteria:

• Participants with significant difficulties in completing self-reported questionnaires
• Those in whom genetic or biological testing may be affected by an underlying genetic or health condition.
• Underlying genetic or health condition.
• Patients who are hospitalised or institutionalised during follow-up will be excluded.

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Cognitive level	Evaluated with Minimental State Examination (min 0 - max 30, higher scores mean a better outcome) and Montreal Cognitive Assessment (min 0 - max 30, higher scores mean a better outcome)	16 months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
multi-omics biomarkers	this will be performed with the Illumina Infinium Global Screening array, which allows direct analysis of 750,000 SNPs with a design aimed at Personalised Medicine. These data will be used to estimate the polygenic risk score for cognitive impairment, which is a single quantitative value of the genetic load for CD for each sample/individual.	16 months
personalised behavioural patterns.	sing mobile applications that allow continuous and passive collection of a person's behavioural data such as daily patterns of steps, distance travelled, time spent using apps, sleep and presence at home. The aim will be to use such a monitoring tool in the cohort of patients under study, using artificial intelligence methods for the extraction of personalised behavioural patterns that can be combined with other sources of information.	16 months
Gait speed	the time it takes the person to walk a given distance, usually 4 m, expressed in metres/second.	16 months
The fluency and content of speech	two algorithms are proposed: a) paralinguistic system based on acoustic processing of the recordings with different versions depending on whether the audio comes from the recording of a memory test, or from a description of an image presented to the patient, b) analysis of speech content (obtained through an automatic speech recognition system) using natural language processing algorithms that extract the most relevant feature vector, as well as the calculation of statistics related to the hit/fail ratio of the memory tests.	16 months
Social support network.	The investigators will use the Arizona Social Support Interview Schedule (Barrera 1980) which elicits networks related to material help, physical assistance, intimate interaction, guidance, feedback and positive social interactions.	16 months
social interactions	The investigators will use several game-theoretic scenarios (prisoner's dilemma, trust game, investor game, risk aversion and dictator game, Cigarini et al 2018) to elicit how participants interact with each other when there may be different interaction outcomes depending on each other's behaviour. This, on the one hand, relates to the stability of social connections and, on the other hand, to their formation.	16 months

Collaborators and Investigators

• Sponsor: Instituto de Salud Carlos III
• Collaborators: Universidad Complutense de Madrid; Instituto de Investigación Biomédica de Salamanca; Carlos III Health Institute; University of Vigo; Biomedical Research Networking Centre on Frailty and Healthy Ageing; Biomedical Research Networking Centre on Mental Health; Institute of Biomedical Research of Lleida; Institute of Health and Biomedical Research of Alicante; Carlos III University of Madrid; Foundation for Biosanitary Research and Innovation in Primary Health Care; Biomedical Research Networking Centre on Epidemiology and Public Health; Research Network on Chronicity, Primary Care and Health Prevention and Promotion
• Investigators: Principal Investigator: Angeles Almeida, PhD, Consejo Superior de Investigaciones Científicas (CSIC); Principal Investigator: Rodrigo Barderas, PhD, Instituto de Salud Carlos III; Principal Investigator: MARIA TERESA MORENO-CASBAS, PhD, Nursing and Healthcare Research Unit (Investén-isciii). Instituto de Salud Carlos III. Madrid

Study record dates

Study Major Dates

• Study Start (Actual): November 1, 2023
• Primary Completion (Estimated): July 1, 2025
• Study Completion (Estimated): July 1, 2025

Study Registration Dates

• First Submitted: October 11, 2023
• First Submitted That Met QC Criteria: October 27, 2023
• First Posted (Actual): November 2, 2023

Study Record Updates

• Last Update Posted (Estimated): January 11, 2024
• Last Update Submitted That Met QC Criteria: January 10, 2024
• Last Verified: January 1, 2024

More Information

Terms related to this study

• Keywords: Primary Health Care; Biomarkers; Artificial Intelligence; Care; Precision Medicine; Cognitive Dysfunction; Early Diagnosis
• Additional Relevant MeSH Terms: Mental Disorders; Neurocognitive Disorders; Cognition Disorders; Cognitive Dysfunction
• Other Study ID Numbers: PMP22/00084

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES

IPD Plan Description

All data files generated by the project studies, if they can be k-anonymised, may be distributed in open access, accompanied by a "Readme" file in free text format containing the metadata (title, project and funding information, contact information, date of collection, geographical contact information, date of collection, geographical information, keywords, data information, licence, associated Handles/DOIs, method of generation, method of method, method of processing and analysis, list of variables included (definition, description (definition, description, units of measurement)).

The metadata contained in the Readme file shall use a standardised language, using W3C/ISO 8601 date and time formats; taxonomy and nomenclature accepted by the scientific community (CIE10, CIAP2, etc.) and including keywords with MeSH/DeCS terminology.

In addition, publications and datasets that are deposited in repositories. https://zenodo.org/record/8379825

• IPD Sharing Time Frame: During 2026
• IPD Sharing Access Criteria: They will be published on the Rapisalud platform (https://repisalud.isciii.es).
• IPD Sharing Supporting Information Type: STUDY_PROTOCOL; SAP; ICF; CSR

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No