Donald Doherty's blog

Category: Brain Science

  • Brain Research Using Online Data Repositories: Predicting Alzheimer’s Disease IV

    Predict Alzheimer’s disease with a “100 percent accurate” test? That’s what an New York Times article reported on August 9, 2010.

    We’ll now look into the basis of the claim as I promised in my “Brain Research Using Online Data Repositories: Predicting Alzheimer’s Disease II” blog post.

    What does the original research article actually say?

    The paper “Diagnosis-Independent Alzheimer Disease Biomarker Signature in Cognitively Normal Elderly People” by Geert De Meyer and colleagues was published in the August 2010 Archives of Neurology.

    There are two exciting methods behind this paper. First, is the use of an online research data repository that brings together a mass of Alzheimer’s disease related clinical data from a number of labs known as the Alzheimer’s Disease Neuroimaging Initiative (ADNI) data repository.

    The second is the use of what the authors’ call a “mixture modeling approach.” The approach boils down to associating each kind of protein measured in the cerebrospinal fluid of patients with a dimension in a clustering algorithm.

    They clustered Amyloid beta (2 components of 1 biomarker) or Amyloid beta and tau (2 biomarkers) using an unsupervised learning method. Only after this was done were the clinical diagnoses looked at to see if data clusters were associated with normal, mild cognitive impairment, or Alzheimer’s disease. In all cases, two clusters emerged. One associated with healthy cognitive function and the other with Alzheimer’s disease.

    Using the mixed modeling approach, the cerebrospinal fluid level of the two biomarkers in 57 patients with Mild Cognitive Impairment (MCI) predicted with 100% accuracy the individuals that would progress to Alzheimer’s disease (clinically measured) over the next 5 years. This is the data cited by the New York Times.

    All of the patients in the population showing 100% predictability already had noticeable problems with memory and other cognitive abilities when the measurements were taken. The same mixed modeling approach showed a 94% accuracy when applied to a group of autopsy confirmed Alzheimer’s disease patients.

    Also in the current paper the authors showed a 93% accuracy at predicting Alzheimer’s disease using just Amyloid beta as the biomarker (autopsy confirmed Alzheimer’s disease) which is essentially the same as the number obtained when using two biomarkers (94% above). Finally, previous papers have shown comparable numbers using other methods (Oskar Hansson et al., 2006; Sebastiaan Engelborghs et al., 2008).

    In sum, it seems clear that this paper did not set out to demonstrate a more accurate method for the early prediction of Alzheimer’s disease. What the paper does seem to demonstrate is an unbiased way to parse data into clusters that may be shown to correlate with disease related outcomes.

    Other related blog posts:

    Brain Research Using Online Data Repositories: Predicting Alzheimer’s Disease

    Brain Research Using Online Data Repositories: Predicting Alzheimer’s Disease II

    Brain Research Using Online Data Repositories: Predicting Alzheimer’s Disease III

  • Distributed Thinking: Multiplayer Game Advances Protein Structure Prediction

    The collaborative and interactive multiplayer game Foldit leverages a distributed network of human users in conjunction with computer algorithms to solve protein folding problems.

    Computer algorithms are currently limited in their ability to solve the notoriously difficult problem of how strings of amino acids fold into three dimensional proteins. Humans are particularly adept at visual problem solving and tend to be more flexible at planning and carrying out strategies than computer programs. Distributed thinking applications like Foldit are human-machine hybrid systems that attempt to leverage the best of each.

    Distributed thinking is the next logical step in F. W. Taylor’s project to improve industrial efficiency. Frederick Winslow Taylor (1856-1915) sought to improve industrial efficiency (increase production to cost ratio) and established the practice of scientific management, which is often referred to as Taylorism.

    In practice Taylorism lead to workers positioned at machines along assembly lines. Each worker carried out physical actions that worked with the actions of the machines to produce something. The placement and actions were choreographed for maximum output at minimum cost (minimum number of people for a minimum number of hours).

    Machines have advanced so that they now extend some of our brain-based capabilities in addition to our muscle-based abilities. Machines first enabled us to increase efficiency in manual labor jobs so that today, for example, steel companies produce far more steel per steel worker.

    During the late twentieth century machine-based increases in efficiency moved into jobs that typically required a significant amount of education like the pharmacist’s job. Distributed computer software began to enable retail companies to optimize the number of pharmacists they needed across their businesses (sometimes thousands of stores) to fulfill prescriptions.

    Today distributed thinking takes the human-machine relationship in human enterprise to the next level. Scientific discovery itself may be made more efficient. And imagine the uses that leveraging distributed intellectual and creative power may be put.

  • Wrong Idea for Cause of Alzheimer’s Disease?

    The recent failure of an Eli Lilly clinical trial to test a promising drug highlights our lack of understanding about the cause of Alzheimer’s disease (see New York Times article).

    The Amyloid beta hypothesis, which is the prevalent idea today, states in its simplest form that the accumulation of Amyloid beta protein in the brain causes brain cells to die and, therefore, leads to symptoms of Alzheimer’s disease.

    The Amyloid beta hypothesis is based on the observation that an extraordinary accumulation of Amyloid beta protein is seen in the brains of known Alzheimer’s disease patients. The problem is that this is a correlation and does not necessarily point to a cause.

    There are a number of other possible interpretations for Amyloid beta accumulation including possibly a response by the body to protect the brain from the ravages of Alzheimer’s disease.

    Perhaps Amyloid beta accumulation in the brain is similar to the scab that forms after we scrape our skin? The scab doesn’t cause the skin damage but is formed by the body to help repair and protect the skin.

    Amyloid beta may or may not be important in the cause of Alzheimer’s disease but we must keep in mind that at this time we only know correlations. We do not know the cause.