AI Identifies Appendix Removal and Diet as Alzheimer’s Risks

Summary: A massive transdisciplinary study has shifted the focus of Alzheimer’s research from the brain to the gut. Using AI to analyze data from nearly 10,000 people, researchers identified that common life events, specifically appendix removal and long-term dietary patterns, are among the strongest predictors of the disease.

The study suggests that the gut microbiome acts as a primary line of defense for the brain, and its disruption over decades may be what ultimately triggers neurodegeneration.

Key Facts

  • The Appendix Connection: In a surprising finding, people who had their appendix removed showed significantly elevated Alzheimer’s risk. Researchers believe the appendix acts as a “reservoir” for beneficial bacteria that replenish the gut after illness.
  • Microbial Depletion: Alzheimer’s patients showed a severe depletion of bacteria that produce short-chain fatty acids, which are essential for maintaining the gut barrier and suppressing brain inflammation.
  • Patterns Over Nutrients: The AI model found that overall dietary patterns (diets 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 utilized machine learning on over 120 everyday factors to create a framework for a low-cost, community-level screening tool that can identify risk before cognitive symptoms appear.

Source: University of Technology Sydney

Alzheimer’s disease affects more than 55 million people worldwide, and that number is projected to nearly triple by 2050. It has long been thought of as something that happens in the brain: a slow accumulation of toxic proteins, a gradual loss of neurons, a tragedy that unfolds in the mind.

But a new collaborative transdisciplinary study by the University of Technology Sydney and Massachusetts General Hospital/Harvard Medical School is pointing somewhere else entirely: the gut.

This shows the outline of a person and the gut-bran axis.
The appendix may function as a reservoir of beneficial bacteria, and its removal could leave the brain vulnerable over time. Credit: Neuroscience News

In one of the largest multi-modal machine learning studies of its kind using artificial intelligence (AI) trained on data from nearly 10,000 people, a team of UTS researchers analysed more than 120 everyday factors, including diet, medical history, gut bacteria, and lifestyle, to identify which of them are most strongly associated with Alzheimer’s risk. The outcome could lead to an AI framework that could be deployed as a low-cost, community-level screening tool.

The appendix finding that changes the picture

“The most unexpected result in the study was perhaps also among the most revealing,” said Associate Professor Kaveh Khalilpour, co-lead of the project and a specialist in complex socio-technical systems at the UTS Visualisation Institute “People who had their appendix removed – one of the most routine surgical procedures in the world – showed substantially elevated Alzheimer’s risk, emerging as one of the strongest contributors in the entire analysis.

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

 Over decades, that disruption may compound, leaving the gut progressively less able to protect the brain from the inflammatory signals linked to neurodegeneration.

“This finding is particularly compelling, as it indicates that long-term brain health may be shaped by earlier life experiences through their enduring effects on the gut microbiome,” said PhD researcher Tallat Jabeen.

“It reframes how we think about Alzheimer’s risk, not as something that arrives with old age, but as something quietly accumulating across a lifetime.”

Diet as a driver, not just a signal

Dietary patterns also emerged as one of the strongest predictors of Alzheimer’s risk, highlighting the role of everyday habits in shaping brain health.

“Rather than individual nutrients, the study found that overall eating patterns were more informative,” said Khalilpour “Diets rich in plant protein, dairy, omega-3 fatty acids, and whole foods were consistently associated with lower Alzheimer’s risk. Whereas diets dominated by processed food, refined sugars, and saturated fats pointed sharply in the other direction.

“Notably, overall dietary patterns outperformed individual nutrient measurements, meaning it is not a single vitamin or supplement that matters, but the cumulative, daily effect of how a person eats across years and decades.”

Lactose intake emerged as a particularly striking individual signal, with higher dairy consumption associated with lower predicted risk, that may reflect the gut microbiome’s response to fermented and dairy-rich foods, as well as calcium’s known neuroprotective properties.

“The implication is significant: if diet contributes to neurodegeneration, it can also, potentially, help prevent it.”, said Ali Zomorrodi, Assistant Professor at Massachusetts General Hospital & Harvard Medical School, and a collaborator of this ongoing project.

The gut-brain axis: where it all connects

To understand the biological mechanism behind these associations, the team analysed gut microbiome data from participants in the same cohort. What they found was a consistent and striking picture of microbial disruption in those with Alzheimer’s disease.

“Beneficial bacteria responsible for producing short-chain fatty acids, compounds that maintain the gut’s protective barrier and actively suppress neuroinflammation, were significantly depleted,” said Dr Faezeh Karimi, the project lead and a Senior Lecturer at UTS School of Computer Science.

“Microbial diversity was reduced. In their place, a more inflammatory microbial environment had taken hold, one that appears capable of sending damaging signals through the gut-brain axis directly to the brain.”

This is the biological thread that ties the study’s findings together. Diet shapes the gut microbiome. The microbiome communicates continuously with the brain via the gut-brain axis.

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

A new way of thinking about prevention

What makes this research particularly significant is what it implies for prevention.

Karimi notes that unlike genetic risk factors, the drivers identified in the study are diet, gut health, cardiovascular conditions, and surgical history that exist on a timeline that can be intervened upon.

“Identifying individuals at elevated risk early, before any cognitive symptom has appeared, creates a window for action: dietary change, microbiome-targeted therapy, and better cardiovascular management. That window narrows sharply once Alzheimer’s has already announced itself,” she said.

“To illustrate the real-world application: imagine an older adult who had their appendix removed following appendicitis, has eaten a low-dairy, high-sugar diet for much of their life and has no memory complaints today.

“When their routine questionnaire is entered into the AI model, these factors will show an elevated Alzheimer’s risk. Simple dietary shift, more plant protein, more fish, less sugar could begin to restore the gut balance their brain depends on.

“Further validation through long-term studies is the essential next step. But the direction of the evidence is clear: Alzheimer’s may not begin in the brain at all. It may begin quietly and years earlier, in the gut shaped by the food we eat, the bacteria we carry, and the medical history we accumulate across a lifetime.”

Key Questions Answered:

Q: Should I be worried if I’ve had my appendix removed?

A: Having an appendectomy is a risk factor, not a guarantee of disease. The study suggests that losing the appendix removes a “backup” for your gut health. You can compensate by being more intentional about your diet and gut microbiome to maintain the healthy bacteria your appendix would have otherwise stored.

Q: Why does the study highlight dairy and lactose specifically?

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

Q: How does a gut problem turn into a brain problem?

A: It is called the gut-brain axis. When the gut loses its “good” bacteria, the protective barrier weakens. This allows inflammatory signals to travel from the gut directly to the brain, where they gradually cause the loss of neurons over several decades.

Editorial Notes:

  • This article was edited by a Neuroscience News editor.
  • Journal paper reviewed in full.
  • Additional context added by our staff.

About this Alzheimer’s disease research news

Author: Jen Mansell
Source: University of Technology Sydney
Contact: Jen Mansell – University of Technology Sydney
Image: The image is credited to Neuroscience News

Original Research: Open access.
Multi-modal machine learning and gut microbiome pathway analysis for Alzheimer’s risk prediction” by Tallat Jabeen, Faezeh Karimi, Ali R. Zomorrodi, Kaveh Khalilpour. Alzheimer s & Dementia: Diagnosis, Assessment & Disease Monitoring
DOI:10.1002/dad2.70340


Abstract

Multi-modal machine learning and gut microbiome pathway analysis for Alzheimer’s risk prediction

Introduction

Early Alzheimer’s disease (AD) risk assessment requires accessible alternatives to invasive biomarkers. We developed a multi-modal machine learning framework using questionnaire metadata from participants with concurrent microbiome sequencing data.

Methods

We analyzed 9832 participants with 120 metadata features across five categories (demographic, dietary, lifestyle, nutritional, medical). Features were selected via Pearson correlation and chi-squared tests. Four algorithms were trained using 10-fold cross-validation with synthetic minority oversampling technique (SMOTE), validated on 1967 samples. The 16S rRNA sequencing data from the same cohort with 2000 samples enabled microbiome composition analysis.

Results

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

Discussion

These findings support non-invasive, multi-modal screening combining medical and dietary evaluation for AD risk stratification, with preliminary microbiome evidence suggesting gut–brain axis dysbiosis as a mechanistic pathway warranting validation in larger cohorts.

Join our Newsletter
I agree to have my personal information transferred to AWeber for Neuroscience Newsletter ( more information )
Sign up to receive our recent neuroscience headlines and summaries sent to your email once a day, totally free.
We hate spam and only use your email to contact you about newsletters. You can cancel your subscription any time.