IBM develops machine learning models for early detection of Alzheimer's

IBM

As we all know IBM is a recognized company American multinational technology and consulting company, which made the Red Hat purchase last year. Though It is also involved in machine learning models.

Of which is currently working for the early detection of diseases. If there is an area where artificial intelligence can be used for the good of society, it is probably in the medical field where artificial intelligence can provide valuable assistance to specialists.

Artificial intelligence is increasingly used in this field to assist physicians in diagnosing patients, especially in non-obvious cases that may require the analysis of a large amount of data, before making a decision.

With Watson, IBM has been one of the pioneers of artificial intelligence in the service of medicine, and the AI ​​that powers the tech giant's cognitive services has already been proven.

In one of his exploits, for example, Watson found in a patient a rare leukemia that doctors had not detected.

Using the traditional method, doctors diagnosed the 60-year-old woman with acute myeloid leukemia.

This classic method of diagnosing cases of leukemia is based on an evaluation by a team of specialist doctors who analyzed the genetic information of the patient, as well as clinical studies available for comparison.

After this success for the case of leukemia, among other diseases, IBM attacks Alzheimer's disease.

Your researchers are working to meet the challenge of detecting Alzheimer's disease years before its event through machine learning and a simple blood test.

Technology for the common good

In a study published in the scientific journal Nature, IBM says machine learning and artificial intelligence could be exploited to detect Alzheimer's disease early without resorting to invasive and expensive tests.

Instead of removing the cerebrospinal fluid to test the level of beta-amyloid it contains, A recent study has shown that the level of protein in the blood can help diagnose Alzheimer's disease in a patient 10 years earlier.

This approach has been adopted by IBM researchers who use machine learning and artificial intelligence techniques to arrive at conclusive results.

"Blood collection is systematic, minimally invasive, and inexpensive," say the IBM researchers.

In our work, we are developing a blood-based signature that can provide a cheap and minimally invasive estimate of the amyloid status of an individual's cerebrospinal fluid using a machine learning approach.

We show that a random forest model derived from plasma components can accurately predict that subjects have abnormal (low) beta-amyloid levels in cerebrospinal fluid, which is an indicator of risk for Alzheimer's disease. «

There have been hundreds of clinical trials of individuals with symptoms of Alzheimer's disease since the early 2000s.

However, there is a high failure rate due in part to trials of patients with cognitive impairment.

Important because they are already in the final stages of the disease. Being able to detect the disease earlier could lead to conclusive trials and possibly find a cure for this disease. It is in this sense that IBM's work is important.

"Although the trial is still in the early stages of research, it could potentially help improve the selection of individuals for drug trials - it has been established that people with mild cognitive impairment are"

The abnormal concentration of amyloid in your cerebrospinal fluid would be 2.5 times more likely to develop Alzheimer's disease, ”says IBM.

For now, the IBM researchers report a statistical accuracy of 77%, which is a good result, as the work is still in its infancy.

The IBM team also claims that machine learning algorithms developed for research they could be extended to model and detect other biomarkers in cerebrospinal fluid.

Source: https://www.nature.com


Be the first to comment

Leave a Comment

Your email address will not be published. Required fields are marked with *

*

*

  1. Responsible for the data: Miguel Ángel Gatón
  2. Purpose of the data: Control SPAM, comment management.
  3. Legitimation: Your consent
  4. Communication of the data: The data will not be communicated to third parties except by legal obligation.
  5. Data storage: Database hosted by Occentus Networks (EU)
  6. Rights: At any time you can limit, recover and delete your information.