WO-2026094044-A1 - SYSTEM AND METHOD FOR MENTAL ILLNESS DIAGNOSIS

WO2026094044A1WO 2026094044 A1WO2026094044 A1WO 2026094044A1WO-2026094044-A1

Abstract

The presently disclosed subject matter relates to a system and method for determining whether a subject is suffering from a mental illness. The system and method comprising a processing circuitry configured to: obtain: (i) genetic and epigenetic information of said subject, and (ii) a machine learning model capable of receiving genetic and epigenetic information of a given subject and determining whether said given subject is suffering from said mental illness, wherein said machine learning model is trained based on one or more features generated by analyzing genetic and epigenetic information of a plurality of subjects suffering from said mental illness, associated with one or more corresponding genomic positions of said plurality of subjects' genomes; and, determine, using said machine learning model and said genetic and epigenetic information of said subject, whether said subject is suffering from said mental illness.

Inventors

BERTOCCHI, Uri
HADDAD, Ben Zion

Assignees

MINDOMICS LTD.

Dates

Publication Date: 20260507
Application Date: 20251030
Priority Date: 20241031

Claims (19)

1. A system for determining whether a subject is suffering from a mental illness, the system comprising a processing circuitry configured to: obtain: (i) genetic and epigenetic information of said subject, and (ii) a machine learning model capable of receiving genetic and epigenetic information of a given subject and determining whether said given subject is suffering from said mental illness, wherein said machine learning model is trained based on one or more features generated by analyzing genetic and epigenetic information of a plurality of subjects suffering from said mental illness, associated with one or more corresponding genomic positions of said plurality of subjects' genomes; and, determine, using said machine learning model and said genetic and epigenetic information of said subject, whether said subject is suffering from said mental illness.
2. The system of claim 1, wherein said mental illness is one of: depression, bipolar disorder, anxiety disorder, paranoia, post-traumatic stress disorder, psychosis, or schizophrenia.
3. The system of claim 1, wherein said system also obtains (iii) psychometrical information associated with said subject, so that said machine learning model is trained and capable of determining whether said subject is suffering from said mental illness based on said psychometrical information.
4. The system of claim 3, wherein said psychometrical information includes at least one of: medical information, physiological information, psychological information, or sociological information.
5. The system of claim 1, wherein said genetic and epigenetic information of said subject are derived from a biological specimen acquired from said subject.
6. The system of claim 5, wherein said deriving of said genetic and epigenetic information is performed by executing genetic and epigenetic sequencing on said specimen.
7. The system of claim 1, wherein said genetic information of said subject contains information regarding one or more nucleotides of said subject's genome located within said corresponding genomic positions, and wherein said epigenetic information of said subject contains information regarding presence or absence of one or more chemical groups linked to said one or more nucleotides within said corresponding genomic positions.
8. The system of claim 7, wherein said one or more chemical groups includes at least one of: methyl group, hydroxymethyl group, or acetyl group.
9. The system of claim 7, wherein said epigenetic information of said subject contains information regarding presence or absence of one or more epigenetic modifications of: Histone acetylation, Histone methylation, Histone phosphorylation, Histone ubiquitination, Histone sumoylation, Histone crotonylation, Histone citrullination, Histone ADP-ribosylation, Histone glycosylation, Histone serotonylation, RNA methylation (e.g., m6A methylation), Chromatin remodeling, or Non-coding RNA- associated gene silencing, associated with said one or more nucleotides within said corresponding genomic positions.
10. A method for determining whether a subject is suffering from a mental illness comprising: obtaining: (i) genetic and epigenetic information of said subject, and (ii) a machine learning model capable of receiving genetic and epigenetic information of a given subject and determining whether said given subject is suffering from said mental illness, wherein said machine learning model is trained based on one or more features generated by analyzing genetic and epigenetic information of a plurality of subjects suffering from said mental illness, associated with one or more corresponding genomic positions of said plurality of subjects' genomes; and, determining, using said machine learning model and said genetic and epigenetic information of said subject, whether said subject is suffering from said mental illness.
11. The method of claim 10, wherein said mental illness is one of: depression, bipolar disorder, anxiety disorder, paranoia, post-traumatic stress disorder, psychosis, or schizophrenia.
12. The method of claim 10, wherein said system also obtains (iii) psychometrical information associated with said subject, so that said machine learning model is trained and capable of determining whether said subject is suffering from said mental illness based on said psychometrical information.
13. The method of claim 12, wherein said psychometrical information includes at least one of: medical information, physiological information, psychological information, or sociological information.
14. The method of claim 10, wherein said genetic and epigenetic information of said subject are derived from a biological specimen acquired from said subject.
15. The method of claim 14, wherein said deriving of said genetic and epigenetic information is performed by executing genetic and epigenetic sequencing on said specimen.
16. The method of claim 10, wherein said genetic information of said subject contains information regarding one or more nucleotides of said subject's genome located within said corresponding genomic positions, and wherein said epigenetic information of said subject contains information regarding presence or absence of one or more chemical groups linked to said one or more nucleotides within said corresponding genomic positions.
17. The method of claim 16, wherein said one or more chemical groups includes at least one of: Methyl group, hydroxymethyl group, or acetyl group.
18. The method of claim 16, wherein said epigenetic information of said subject contains information regarding presence or absence of one or more epigenetic modifications of: Histone acetylation, Histone methylation, Histone phosphorylation, Histone ubiquitination, Histone sumoylation, Histone crotonylation, Histone citrullination, Histone ADP-ribosylation, Histone glycosylation, Histone serotonylation, RNA methylation (e.g., m6A methylation), Chromatin remodeling, or Non-coding RNA- associated gene silencing, associated with said one or more nucleotides within said corresponding genomic positions.
19. A non-transitory computer readable storage medium having computer readable program code embodied therewith, the computer readable program code, executable by at least one processor of a computer to perform a method for determining whether a subject is suffering from a mental illness, the method comprising: obtaining: (i) genetic and epigenetic information of said subject, and (ii) a machine learning model capable of receiving genetic and epigenetic information of a given subject and determining whether said given subject is suffering from said mental illness, wherein said machine learning model is trained based on one or more features generated by analyzing genetic and epigenetic information of a plurality of subjects suffering from said mental illness, associated with one or more corresponding genomic positions of said plurality of subjects' genomes; and, determining, using said machine learning model and said genetic and epigenetic information of said subject, whether said subject is suffering from said mental illness.

Description

SYSTEM AND METHOD FOR MENTAL ILLNESS DIAGNOSIS TECHNICAL FIELD The present invention relates to the field of mental illnesses, and more particularly, to the field of mental illness diagnosis. BACKGROUND A mental disorder, also referred to as a mental illness, a mental health condition, or a psychiatric disability, is a behavioral or mental pattern which causes significant distress or impairment of personal functioning. A mental disorder may be characterized by a clinically significant disturbance in an individual's cognition, emotional regulation, or behavior, often in a social context. Such disturbances may occur as single episodes, may be persistent, or may be relapsing-remitting. There are many different types of mental disorders, with signs and symptoms that vary widely between specific disorders. Disorders are usually diagnosed or assessed by a mental health professional, e.g., a clinical psychologist, psychiatrist, psychiatric nurse, or clinical social worker, using various methods (such as psychometric tests, and the like), but often relying on observation and questioning. Misdiagnosis in the field of mental disorders is a common phenomenon with severe consequences. There are estimates that approximately 50% of medical treatments are error-prone, leading to ineffective treatments and poor outcomes. One of the main reasons for misdiagnosis lies in the subjective assessment methods currently in use. As psychiatric diagnosis relies heavily on reports from the patient and his environment, as well as on the mental health professional's observations, these reports and observations tend to be open to subjective interpretation and bias. Moreover, mental disorders often show similar and overlapping symptoms, making it difficult to determine the patient's mental state accurately. Currently, there are still no objective tools for mental diagnosis, similar to blood tests or medical imaging used in other medical fields. Considering the above, there is a need in the art for a system and method for mental illness diagnosis. GENERAL DESCRIPTION In accordance with a first aspect of the presently disclosed subject matter, there is provided a system for determining whether a subject is suffering from a mental illness, the system comprising a processing circuitry configured to: obtain: (i) genetic and epigenetic information of said subject, and (ii) a machine learning model capable of receiving genetic and epigenetic information of a given subject and determining whether said given subject is suffering from said mental illness, wherein said machine learning model is trained based on one or more features generated by analyzing genetic and epigenetic information of a plurality of subjects suffering from said mental illness, associated with one or more corresponding genomic positions of said plurality of subjects' genomes; and, determine, using said machine learning model and said genetic and epigenetic information of said subject, whether said subject is suffering from said mental illness. In some cases, the mental illness is one of: depression, bipolar disorder, anxiety disorder, paranoia, post-traumatic stress disorder, psychosis, or schizophrenia. In some cases, the system also obtains (iii) psychometrical information associated with said subject, so that said machine learning model is trained and capable of determining whether said subject is suffering from said mental illness based on said psychometrical information. In some cases, the psychometrical information includes at least one of: medical information, physiological information, psychological information, or sociological information. In some cases, the genetic and epigenetic information of said subject are derived from a biological specimen acquired from said subject. In some cases, the deriving of said genetic and epigenetic information is performed by executing genetic and epigenetic sequencing on said specimen. In some cases, the genetic information of said subject contains information regarding one or more nucleotides of said subject's genome located within said corresponding genomic positions, and wherein said epigenetic information of said subject contains information regarding presence or absence of one or more chemical groups linked to said one or more nucleotides within said corresponding genomic positions. In some cases, the one or more chemical groups includes at least one of: Methyl group, hydroxymethyl group, or acetyl group. In some cases, the epigenetic information of the subject contains information regarding presence or absence of one or more epigenetic modifications of: Histone acetylation, Histone methylation, Histone phosphorylation, Histone ubiquitination, Histone sumoylation, Histone crotonylation, Histone citrullination, Histone ADP- ribosylation, Histone glycosylation, Histone serotonylation, RNA methylation (e.g., m6A methylation), Chromatin remodeling, or Non-coding RNA-associated gene silencing, associated with the one or more nu