KR-20260065502-A - Method for providing information for predicting or diagnosing post-operative delirium using bacteria-derived extracellular vesicles

Abstract

The present invention relates to a method for predicting or diagnosing the occurrence of postoperative delirium using machine learning methods. The model for predicting or diagnosing postoperative delirium using the Random Forest of the present invention is developed based on selected taxa showing a strong correlation between postoperative delirium and bacterial-derived extracellular vesicles, and can effectively diagnose and/or predict postoperative delirium.

Inventors

• 구본녀
• 고홍
• 김정민
• 박수정

Assignees

• 연세대학교 산학협력단

Dates

Publication Date

20260508

Application Date

20250925

Priority Date

20241029

Claims (10)

1. i) A step of isolating extracellular vesicles from a sample isolated from an individual prior to surgery; ii) a step of extracting genes from the separated extracellular vesicles; iii) a step of selecting microorganisms using the extracted genes above; and iv) A step of generating a predictive model for the diagnosis of postoperative delirium using a random forest on the selected microorganisms above; A method for providing information for predicting or diagnosing postoperative delirium, including
2. A method for providing information according to claim 1, wherein the selection of microorganisms in step iii) is characterized by selecting microorganisms in which a difference in detection level occurs by comparing individuals that developed postoperative delirium with individuals that did not develop postoperative delirium among the individuals prior to surgery in step i).
3. In paragraph 1, the above information provision method is v) A step of inputting the detection level of the selected microorganisms in the sample separated before surgery from the subject suspected of postoperative delirium into the random forest model generated above; A method for providing information characterized by additionally including
4. A method of providing information according to claim 1, characterized in that the surgery is a spinal surgery.
5. A method of providing information according to claim 1, characterized in that the individual is 70 years of age or older.
6. A method for providing information according to claim 1, characterized in that the sample is one or more selected from the group consisting of urine, feces, hair, sweat, saliva, body fluids, blood, cerebrospinal fluid, cells, and tissues.
7. A method for providing information according to claim 1, characterized in that the gene in step ii) is one or more selected from the group consisting of 16S rDNA, 16S rRNA, DNA, and mRNA.
8. In claim 1, the microorganisms selected in step iv) are Moraxellaceae , Acinetobacter , Pseudomonas , Pseudomonadales , Alphaproteobacteria , Gammaproteobacteria , Bacilli , Burkholderiales , Herbaspirillum , Firmicutes , Oxalobacteraceae , Sphingomonadaceae , Sphingomonas , Sphingomonadales , Pseudomonadaceae , and Peptococcus ( A method for providing information characterized by being one or more selected from a group consisting of Peptococcales .
9. Any one or more selected from the group consisting of Moraxellaceae , Acinetobacter , Pseudomonas, Pseudomonadales , Alphaproteobacteria , Gammaproteobacteria , Bacilli , Burkholderiales , Herbaspirillum , Firmicutes , Oxalobacteraceae , Sphingomonadaceae , Sphingomonas , Sphingomonadales , Pseudomonadaceae , and Peptococcales A composition for diagnosing postoperative delirium comprising a preparation capable of detecting microorganisms.
10. A kit for diagnosing postoperative delirium comprising the composition of claim 9.

Description

Method for providing information for predicting or diagnosing post-operative delirium using bacteria-derived extracellular vesicles The present invention relates to a method for predicting or diagnosing the occurrence of postoperative delirium using bacterial-derived extracellular vesicles and machine learning methods. Postoperative delirium (POD), characterized by unpredictable progression, is a form of acute cognitive impairment. It is marked by confusion and variability in perception, orientation, memory, cognition, and behavior. Postoperative delirium is common in elderly patients following surgery, typically occurring between 2 and 52 days postoperatively. In patients aged 60 years or older, postoperative delirium occurs in 20–25% of cases. Spinal surgery accounted for 11.5% of the total prevalence of postoperative delirium and was associated with prolonged hospital stays, increased mortality within 30 days of surgery, higher economic costs, and a higher risk of requiring nursing care upon discharge. As the frequency of surgeries among elderly patients increases, so does interest in postoperative delirium. Consequently, predictive models for preoperative POD have garnered attention. However, preoperative risk factors regarding gender, inflammatory markers, preoperative cumulative markers, and chronic treatment have been reported inconsistently. This inconsistency in the literature has raised the possibility of heterogeneous study cohorts, hindering the development of predictive models. Delirium can be mistaken for depression due to a mental state characterized by inactivity or slowness. Its manifestation can vary significantly from person to person, ranging from hyperactivity to hypoactivity. The heterogeneous phenotypes of delirium, along with unclear pathophysiological mechanisms, make diagnosis, treatment, and research challenging. However, it can be prevented in approximately one-third of at-risk patients by screening individuals with risk factors and providing preoperative education. Therefore, investigating preoperative contributors to postoperative delirium is crucial for predicting clinical outcomes and improving patient care management through interventions. The gastrointestinal tract is generally a complex habitat home to numerous microorganisms, including bacteria, viruses, and fungi. This microbial community is continuously influenced and shaped by the host and the surrounding environment, while simultaneously affecting the host's function, health, and susceptibility to disease. In animal studies, the gut microbiome has been increasingly recognized as a significant contributor to postoperative delirium. Regular bowel preparation prior to surgery not only altered the gut microbial composition of gastric cancer patients but also increased the incidence of postoperative delirium. Recent research suggests that changes in the gut microbiome after surgery may play a significant role in the development of postoperative delirium. The gut-brain axis, representing communication between the gut microbiome and the brain, has recently been validated by an increasing number of studies. For example, there is a growing number of research findings indicating that gut microbial imbalances can directly influence cognitive impairments, such as Alzheimer's disease (AD), which result from an increase in neurotoxin and neuroinflammatory molecules and a decrease in tryptophan and norepinephrine-producing bacteria. Notably, the abundance of the anti-inflammatory genus Faecalibacterium was reduced in patients with cognitive impairment. It has been suggested that treatments altering the gut microbiome may help modify the neuropathology associated with AD and its progression. In contrast, the control cohort showed an abundance of Streptococcus Equinus and Blautia hominis . These findings highlight the pivotal role of the gut microbiome in the manifestations of postoperative delirium. Extracellular vesicles (EVs), enclosed by a phospholipid bilayer membrane, are particles ranging from 20 to 400 nm and can be detected in all body fluids, including plasma, saliva, cerebrospinal fluid, feces, and urine. EVs are expelled from cells after their outer membrane forms a vesicle and contain cellular proteins, lipids, bacterial DNA, and RNA. They play a crucial role in intercellular communication or the facilitation of disease development. They can enter the bloodstream and may interact with numerous host organs to regulate the immune system. Bacteria-derived extracellular vesicles (BEVs) have been identified as powerful carriers capable of crossing the blood-brain barrier and delivering signaling molecules to the central nervous system (CNS). BEVs play a role in regulating inflammation in the nervous system and assist in managing tissue damage and healing. Consequently, they influence the onset, progression, and potential recovery of various diseases affecting the CNS. These include autoimmune diseases, neurodegenerative diseas