AI identifies appendix removal and diet as risk for Alzheimer’s disease

AI News


summary: A large-scale interdisciplinary study has shifted the focus of Alzheimer’s disease research from the brain to the gut. Using AI to analyze data from nearly 10,000 people, researchers identified common life events, particularly appendix removal and long-term dietary patterns, to be among the strongest predictors of disease.

This study suggests that the gut microbiome acts as the brain’s main line of defense, and its disruption over decades can eventually lead to neurodegeneration.

important facts

  • Appendix connections: In a surprising finding, people who had their appendix removed had a significantly increased risk of Alzheimer’s disease. Researchers believe that the appendix acts as a “reservoir” of beneficial bacteria that replenishes the intestines after illness.
  • Microbial depletion: Alzheimer’s disease patients showed a severe reduction in bacteria that produce short-chain fatty acids, which are essential for maintaining the intestinal barrier and suppressing brain inflammation.
  • Patterns over nutrients: The AI ​​model found that overall dietary patterns (a diet high in plant protein, dairy, and omega-3s) were far more predictive of brain health than any single vitamin or supplement.
  • Predictive screening: The study leveraged machine learning on more than 120 everyday factors to create a framework for a low-cost, community-level screening tool that can identify risk before cognitive symptoms appear.

sauce: University of Technology Sydney

Alzheimer’s disease affects more than 55 million people worldwide, and that number is expected to nearly triple by 2050. Alzheimer’s disease has long been thought to occur in the brain. A slow buildup of toxic proteins, a gradual loss of neurons, and a tragedy unfolding in your mind.

However, a new joint interdisciplinary study by the University of Technology Sydney and Massachusetts General Hospital/Harvard Medical School It’s pointing to a completely different place: the intestines.

This shows the outline of a person and the bran axis.
The appendix may act as a reservoir for beneficial bacteria, and removing it can make the brain more vulnerable over time. Credit: Neuroscience News

In one of the largest multimodal machine learning studies of its kind, using artificial intelligence (AI) trained on data from around 10,000 people, the UTS research team analyzed more than 120 everyday factors, including diet, medical history, gut bacteria and lifestyle, to determine which of these were most strongly associated with Alzheimer’s risk. The results could lead to an AI framework that can be deployed as a low-cost community-level screening tool.

Discovery of a game-changing appendix

“The most unexpected result of this study was also perhaps one of the most obvious,” said project co-leader Kaveh Khalilpour, an expert in complex socio-technical systems at the UTS Visualization Institute. “People who had their appendix removed, one of the most routine surgical procedures in the world, showed a significantly increased risk of Alzheimer’s disease and emerged as one of the strongest contributors in the overall analysis.”

“We speculate that it acts as a reservoir of beneficial gut bacteria. When this is removed, the microbiome loses an important recovery mechanism: the ability to replenish healthy microbial communities after illness, infection, or antibiotic use,” he said.

Over decades, that disruption may further worsen, leading to a gradual decline in the gut’s ability to protect itself from inflammatory signals associated with neurodegeneration.

“This finding is particularly compelling because it shows that long-term brain health can be shaped by early life experiences through lasting effects on the gut microbiome,” said postdoctoral researcher Talat Jabeen.

“This reframes the way we think about Alzheimer’s disease risk, not as something that comes with age but as something that quietly accumulates over the course of a person’s life.”

Diet as a driver, not just a signal

Dietary patterns have also been found to be one of the strongest predictors of Alzheimer’s disease risk, highlighting the role of daily habits in shaping brain health.

“In this study, we found that overall dietary patterns were more beneficial than individual nutrients. Diets rich in plant protein, dairy products, omega-3 fatty acids, and whole foods were consistently associated with a lower risk of Alzheimer’s disease, whereas diets rich in processed foods, refined sugars, and saturated fats showed just the opposite direction,” said Dr. Kallipore.

“What’s remarkable is that overall dietary patterns outperformed measurements of individual nutrients, meaning it’s not a single vitamin or supplement that matters, but the cumulative daily impact of how a person eats over years or decades.”

Lactose intake has emerged as a particularly salient individual signal, with increased dairy intake associated with lower predicted risk, which may reflect gut microbiota responses to fermented and dairy-rich foods, as well as the known neuroprotective properties of calcium.

“The implications are important. If diet contributes to neurodegeneration, it could potentially also help prevent neurodegeneration,” said Ali Zomorodi, an assistant professor at Massachusetts General Hospital and Harvard Medical School and a collaborator on the ongoing project.

The gut-brain axis: where everything connects

To understand the biological mechanisms behind these associations, the research team analyzed gut microbiome data from participants in the same cohort. What they discovered was a consistent and impressive picture of microbial destruction in Alzheimer’s patients.

“The beneficial bacteria responsible for producing short-chain fatty acids, compounds that maintain the protective barrier of the intestine and actively suppress neuroinflammation, were significantly reduced,” said project leader Dr. Faezeh Karimi, senior lecturer at UTS School of Computer Science.

“Microbial diversity has decreased. In its place, a more inflammatory microbial environment appears to have taken hold and can send harmful signals directly to the brain via the gut-brain axis.”

This is the biological thread that ties together the research findings. Diet shapes the gut microbiome. The microbiome is in continuous communication with the brain via the gut-brain axis.

And when that microbial community is disrupted by decades of poor diet, appendix loss, and other medical events, the brain can lose one of its most important lines of defense against neurodegeneration.

A new way of thinking about prevention

What’s especially important about this study is what it means for prevention.

Karimi points out that, unlike genetic risk factors, the factors identified in the study – diet, gut health, cardiovascular status, and surgical history – exist on a timeline where intervention is possible.

“Early identification of people at high risk, before cognitive symptoms appear, opens up room for action, including dietary changes, microbiome-targeted treatments, and improved cardiovascular management. Once Alzheimer’s disease has already developed, the window of opportunity narrows rapidly,” she said.

“To illustrate a real-world application, imagine an elderly person who had their appendix removed after appendicitis, has been eating a low-dairy, high-sugar diet for most of their life, and now has no memory loss.

“When their regular questionnaires are fed into an AI model, these factors will indicate an increased risk of Alzheimer’s disease. Simple dietary changes, more plant protein, more fish, and less sugar, could begin to restore the balance in their guts that their brains depend on.”

“Further validation through long-term studies is the next important step. But the direction of the evidence is clear: Alzheimer’s disease may not start in the brain. It may begin silently and years ago in the gut, where the disease is shaped by the food we eat, the bacteria we carry, and the medical history we accumulate over a lifetime.”

Answers to key questions:

Q: Do I need to worry if I have my appendix removed?

answer: Having an appendectomy is a risk factor and does not guarantee the disease. This study suggests that when you lose your appendix, you lose your “backup” of gut health. You can compensate by being more conscious about your diet and your gut microbiome and maintaining the healthy bacteria stored in your appendix.

Q: Why is this study specifically focused on dairy products and lactose?

answer: High dairy intake emerged as a strong protective signal. Researchers believe this is due to a combination of calcium’s neuroprotective properties and how the gut microbiome responds to fermented and dairy-rich foods.

Q: How do gut problems turn into brain problems?

answer: It’s called the gut-brain axis. Loss of “good bacteria” in the gut weakens the protective barrier. This transmits inflammatory signals from the gut directly to the brain, causing gradual neuron loss over decades.

Editorial note:

  • This article was edited by the editors of Neuroscience News.
  • Journal articles were reviewed in full text.
  • Additional context added by staff.

About this Alzheimer’s disease research news

author: Jen Mansell
sauce: University of Technology Sydney
contact: Jen Mansell – University of Technology Sydney
image: Image credited to Neuroscience News

Original research: Open access.
“Multimodal Machine Learning and Gut Microbiome Pathway Analysis for Alzheimer’s Disease Risk Prediction” by Tallat Jabeen, Faezeh Karmi, Ali R. Zomorrodi, and Kaveh Khalilpour. Alzheimer’s disease and dementia: diagnosis, evaluation, and disease monitoring
DOI:10.1002/Dad2.70340


abstract

Multimodal machine learning and gut microbiome pathway analysis for Alzheimer’s disease risk prediction

introduction

Early Alzheimer’s disease (AD) risk assessment requires available alternatives to invasive biomarkers. We developed a multimodal machine learning framework using survey metadata and concurrent microbiome sequence data from participants.

method

We analyzed 9,832 participants with 120 metadata features across five categories: demographics, diet, lifestyle, nutrition, and medical care. Features were selected by Pearson correlation and chi-square test. The four algorithms were trained using 10-fold cross-validation with synthetic minority oversampling technique (SMOTE) and validated on the 1967 sample. 16S rRNA sequence data from the same cohort of 2000 samples enabled microbiome composition analysis.

result

Medical history (area under the curve) [AUC] = 0.871) and dietary patterns (AUC = 0.874) achieved the best performance, outperforming the demographic (0.795), lifestyle (0.660), and nutrition (0.569) domains (p < 0.001). Microbiome analysis reveals dysbiosis markers (Prevotella/Bacteroides ratio: 1.921) linking dietary factors and potential neuroinflammatory pathways.

discussion

These findings support a non-invasive, multimodal screening that combines medical and dietary assessments for AD risk stratification, and there is also preliminary microbiome evidence suggesting gut-brain axis dysbiosis as a mechanistic pathway that warrants validation in larger cohorts.



Source link