Optimize and Predict Antidepressant Efficacy for Patient With MDD Using Multi-omics Analysis and AI-predictive Tool

Alessio Fasano350 enrolled

Overview

OPADE is a non-profit, observational, multicenter, open-label study aimed at defining personalized treatment for Major Depressive Disorder (MDD). In particular, we will combine genetics, epigenetics, microbiome, immune response data together with anamnesis, questionnaires, electroencephalography (EEG) collected from subjects suffering MDD. Eventually, an Artificial Intelligence (AI)/Machine Learning (ML) predictive tool will be created to guide clinicians in improving MDD treatment and patient's stratification.

Three hundred and fifty patients diagnosed with MDD will be enrolled for 24 months and divided into 4 groups according to age: 14-17 years (70 pediatric patients), 18-30 years (100 adult patients), 31-39 years (90 adult patients), 40-50 years (90 adult patients). The study protocol includes 6 follow-up visits: T0 (enrollment), T1, T2, T3, T4, and T5. At each medical visit, psychometric questionnaires will be administered to the patients and contextual biological samples including blood, stool and saliva will be collected. The study will use a multi-omics approach including: metagenomic sequencing to characterize the microbiome composition; metabolomics to detect circulating metabolites; transcriptomics to quantify microRNAs; epigenomics to assess methylation variability between and within groups and immune assays to analyze the antibody immune response and inflammatory profiles (cytokines, interleukins and growth factors). Cortisol and lipoproteins will also be quantified. In parallel, cognitive assessment and emotional status will be recorded remotely by each patient via chatbot and wearable EEG devices, respectively. Specifically, the chatbot will collect patient's conversations and monitoring her/his feelings; the chat conversation will be than transformed in a machine-readable data. The EEG device is a mobile app that will also allows to associate brainwaves with patients' feelings.

Study Type

OBSERVATIONAL

Enrollment

350

Conditions

Major Depressive Disorder

Eligibility

Sex: ALLMin age: 14 YearsMax age: 50 Years

Medical Language ↔ Plain English

Inclusion Criteria: * Patients diagnosed with Major Depressive Disorder as certified by a SCID 5 (Structured Clinical Interview for DSM-5) for DSM-S for adults and K-SADS-PL-DSM 5 (Kiddie Schedule for Affective Disorders and Schizophrenia - Present and Lifetime for DSM 5) for adolescents. * Currently experiencing a major depressive episode with a HAM-D (Hamilton Depression) score of 18 or greater, or alternatively, a MADRS (Montgomery-Asberg Depression Rating Scale) score of 18 or greater. * About to start a new antidepressant. * Not concurrently starting a new psychotropic medication. * Age 14-50 years. * Able to use mobile devices (smart phone, tablet). * Willingness to provide written informed consent to participate. Exclusion Criteria: * Intellectual disability. * Neurological disease (multiple sclerosis, severe neurocognitive disorder, epilepsy). * Current psychotic disorder or mood disorder with psychotic features. * Primary diagnosis of alcohol or substance use disorder (DSM-5). * Patients who started concomitant psychotropic medications less than one week ago. * Active, ongoing inflammatory diseases (such as rheumatoid arthritis and rheumatic polymyalgia). or severe and unstable physical illness (such as recent myocardial infarction). * A history of hepatitis B or C, human immunodeficiency virus, or evidence of active tuberculosis infection or any active systemic infection within 2 weeks prior to the start of the study. * Use of antibiotics or other medications that may have affected the composition of the microbiota during the 30 days prior to baseline. * Pregnancy and lactation.

Outcomes

Primary Outcomes

Identify neuroinflammatory indices

Several inflammatory markers such as G-CSF, GM-CSF, IFN-γ IL-10, IL-12p40, IL-15, IL-1α, IL-1β, IL-2, IL-4, IL-5, IL-6, IL-8/CXCL8, MCP-1/CCL2, TNF-α, TNFβ will be analysed.

Time frame: 2 years

Microbiome analysis

Identification of bacterial and fungal components.

Time frame: 2 years

Metabolomic analysis

The metabolomic analysis will involve three different groups of metabolites: 1) Intermediate of tryptophan metabolism (tryptophan, serotonin, 5-HIAA, quinurenin, quinurenic acid and other hormones and derivatives involved in the pathway) and others related to purines (paraxanthin/xanthin ratio); 2) L-acylcarnitines (including short chain, medium long-lasting acylcarnitine), with particular emphasis on laurylcarnitine and acetylcarnitine; 3) Phenolic (and related), such as phenolic acid, mandelic acid or methoxy-hydroxyphenyl glycol.

Time frame: 2 years

Analysis of lipoprotein profile

Different forms of lipoproteins will be evaluated: Apolipoproteins A1 and A2, HDL-apolipoproteins A1 and A2,free cholesterol HDL3, HDL3-apolipoprotein A1, HDL2-apolipoprotein A2, apolipoprotein A2, IDL, HDL-apolipoprotein A2, VLDL and its subtypes, VLDL2-triglycerides, VLDL3-triglyceridestriglycerides, VLDL2- cholesterol, VLDL3 cholesterol, VLDL4 cholesterol free of VLDL4, phospholipids VLDL2, Phospholipids VLDL3, Cholesterol LDL5, Cholesterol free LDL5, Phospholipids LDL5, LDL5-apolipoprotein B, HDL3 cholesterol, HDL4 cholesterol HDL4, HDL3 cholesterol free, free cholesterol HDL4, HDL3-phospholipids, HDL4-phospholipids, HDL3-apolipoprotein A1, HDL4-apolipoprotein A1, HDL3-apolipoprotein A2 and HDL4-apolipoprotein A2.

Time frame: 2 years

Identify immune-profile linked and epigenomic signatures

Methylome analysis on genomic DNA will be performed.

Time frame: 2 years

AI-powered diagnostics predictive tool (companion diagnostic-like)

Deploy an AI-powered predictive tool (companion diagnostic-like) in clinical practice for the prescription of anti-depressants. OPADE AI-powered predictive tool will be a class C medical device under the In vitro diagnostic classification.

Time frame: 2 years

Mood assessment through brain biomarker

Validate a patient tracking tool for mood assessment using brain biomarker.

Time frame: 2 years

Patient engagement digital tool

Validate a patient engagement digital tool that can be deployed in any patient community to enhance clinical study outcomes.

Time frame: 2 years

Discovery of a new set of biomarkers

Propose new set of biomarkers that can guide the development of new antidepressants

Time frame: 2 years

Investigation of the gut-brain-axis and of the biomarkers of interest in the context of mental diseases starting with MDD

Identify indices in MDD to improve diagnostic accuracy for primary prevention and patients' stratification.

Time frame: 2 years

Optimize and Predict Antidepressant Efficacy for Patient With MDD Using Multi-omics Analysis and AI-predictive Tool

Overview

Conditions

Eligibility

Locations (1)

Outcomes

Primary Outcomes

Central Contacts