Machine learning is a type of artificial intelligence that allows computer programs to learn when exposed to new data without being programmed. Now, researchers in The Netherlands have coupled machine learning methods with a special MRI technique that measures the perfusion, or tissue absorption rate, of blood throughout the brain to detect early forms of dementia, such as mild cognitive impairment (MCI), Radiology.
‘MRI can help with the diagnosis of Alzheimer’s disease,’ said principal investigator Alle Meije Wink, Ph.D., from the VU University Medical Centre in Amsterdam. ‘However, the early diagnosis of Alzheimer’s disease is problematic.’

Scientists have long known that Alzheimer’s disease is a gradual process and that the brain undergoes functional changes before the structural changes associated with the disease show up on imaging results. Physicians have no definitive way of identifying who has early dementia or which cases of mild cognitive impairment will progress to Alzheimer’s disease.

‘With standard diagnostic MRI, we can see advanced Alzheimer’s disease, such as atrophy of the hippocampus,’ Dr. Meije Wink said. ‘But at that point, the brain tissue is gone and there’s no way to restore it. It would be helpful to detect and diagnose the disease before it’s too late.’

For the new study, the researchers applied machine learning methods to special type of MRI called arterial spin labelling (ASL) imaging. ASL MRI is used to create images called perfusion maps, which show how much blood is delivered to various regions of the brain.

The automated machine learning program is taught to recognize patterns in these maps to distinguish among patients with varying levels of cognitive impairment and predict the stage of Alzheimer’s disease in new (unseen) cases.
The study included 260 of 311 participants from the Alzheimer Center of the VU University Medical Center dementia cohort who underwent ASL MRI between October 2010 and November 2012.

The study group included 100 patients diagnosed with probable Alzheimer’s disease, 60 patients with mild cognitive impairment (MCI) and 100 patients with subjective cognitive decline (SCD), and 26 healthy controls.
SCD and MCI are considered to be early stages of the dementia process and are diagnosed based on the severity of cognitive symptoms, including memory loss and thought- and decision-making problems.

The automated system was able to distinguish effectively among participants with Alzheimer’s disease, MCI and SCD. Using classifiers based on the automated machine learning training, the researchers were then able to predict the Alzheimer’s diagnosis or progression of single patients with a high degree of accuracy, ranging from 82 percent to 90 percent.
‘ASL is a promising alternative functional biomarker for the early diagnosis of Alzheimer’s disease,’ Dr. Meije Wink said.

Radiological Society of North Americawww2.rsna.org/timssnet/media/pressreleases/14_pr_target.cfm?ID=1890

A study led by investigators from the Ragon Institute of MGH, MIT and Harvard finds evidence that antibody protection may help control infection with the bacteria that causes tuberculosis (TB). In their study the research team describes finding consistent differences in both the structure and function of antibodies targeting the TB bacteria between individuals with active TB disease and those with latent TB, which neither produces symptoms nor can be transmitted. The findings may lead to better ways of distinguishing between active and latent disease and to a more effective vaccine against a disease that kills more than 1.5 million people each year.

‘Ending tuberculosis by 2030 is one of the targets of the World Health Organization’s newly adopted Sustainable Developmental Goals,’ says Lenette Lu, MD, PhD, of the Ragon Institute and the Massachusetts General Hospital (MGH) Department of Medicine. ‘A more effective vaccine against TB could substantially contribute towards that goal, impacting the nearly one in three people worldwide who are infected and addressing the leading killer of individuals infected with HIV.’

The only currently available preventive against infection with the TB bacteria – the BCG vaccine – has been available since the 1920s; but its effectiveness against pulmonary TB, the most common form of the disease, has always been uncertain. BCG is believed to work by stimulating cellular immunity, which is carried out by specialized immune cells including T cells and the macrophages that are directly infected by TB bacteria. Previous investigations into a possible role for antibodies in the immune response to TB have had conflicting results, but the Ragon team – led by Galit Alter, PhD, of MGH Department of Medicine and Sarah Fortune, MD, of the Harvard T.H. Chan School of Public Health – used a novel approach.

In addition to binding to their target pathogens and marking them for destruction by the immune system, antibodies also directly stimulate pathogen-killing cells of the innate immune system by binding to a cell-surface protein called the Fc receptor. The Ragon team profiled TB-specific antibodies from 22 individuals with latent TB and 20 with active TB for 70 different features associated with Fc-mediated antibody function. They first identified nine characteristics that differentiated between antibodies of the two groups of participants, and further investigation identified the biomarker that best distinguished between them.

A key regulator of Fc-mediated immune function is the addition to antibodies of compounds called glycans, made up of sugar molecules; and distinct differences in glycosylation patterns were found to clearly distinguish latent TB antibodies from active TB antibodies. To confirm these results in the initial group of participants, who were from South Africa, the team conducted a similar analysis of antibodies from 20 individuals from Texas and Mexico – half with latent and half with active TB – and had the same results. Further experiments revealed that application of latent TB antibodies to TB-infected human macrophages not only increased the activation of several antimicrobial processes but also reduced the survival of the TB bacteria.

Co-lead author Amy Chung, PhD, now at the Peter Doherty Institute for Infection and Immunity in Melbourne, Australia – a joint venture between The University of Melbourne and The Royal Melbourne Hospital – explains, ‘This is a completely new area of immune research in tuberculosis, since these antibodies don’t just recognize the infection, they also recruit immune cells to target it. People with latent infection have inactive disease for a reason, and if antibodies are playing a role in controlling the infection, the mechanism they use could be harnessed for future vaccine development.’

Alter, an associate professor of Medicine at Harvard Medical School, adds, ‘The diagnostic potential of these findings should not be overlooked. The detection of Fc-related modifications of TB-specific antibodies could be easily translated into a rapid, inexpensive point-of-care diagnostic that could have enormous public health impact, particularly in those parts of the globe where TB is endemic.’

Massachusetts General Hospitalwww.massgeneral.org/about/pressrelease.aspx?id=1992

A new study from the Medical Research Council Lifecourse Epidemiology Unit, University of Southampton, shows lesions, which can best be seen on MRI scans, could help identify individuals who are more likely to suffer from more rapidly progressing osteoarthritis.
The SEKOIA study, a major international osteoarthritis disease-modifying trial, carried out MRI scanning on the knees of 176 men and women over 50 years old. They were then followed up for an average of three years with repeated knee X-rays. Individuals with abnormalities on their MRI scans at the first appointment were compared to those without to examine the effect on disease progression.
Individuals with bone marrow lesions (BMLs) on their MRI scan were found to have osteoarthritis that progressed more rapidly than those that did not. On average, the space within the joint is lost at a rate of 0.15mm per year however the Southampton study shows that, overall, individuals with BMLs had a loss rate that was 0.10mm per year faster than those without BMLs. This may lead to earlier need for joint replacement or other intervention.
BMLs show up on MRI as regions of bone beneath the cartilage with ill-defined high signal and represent areas of bone marrow edema, fibrosis, and necrosis. The Southampton researchers believe that therapies to target these abnormalities may slow the progression of this disabling joint disease, but further work is required to examine this.

University of Southampton http://tinyurl.com/zgoujax

It’s a Catch-22 with potentially deadly consequences: People trying to overcome addiction can’t get treatment for their pain, because the most powerful pain medicines also carry an addiction risk.
And so their pain continues to get in the way of their addiction recovery – or they seek pain relief in the same addictive substances they’re trying to avoid.

But a new study shows the potential for patients to break out of that cycle through a non-drug approach that combines behavioural therapy and social support to help them manage their pain. The low-cost approach, grounded in psychological theories of pain, could help address the nation’s epidemic of addictions to opioid painkillers and illicit drugs.

Veterans who received this pain-focused care while also being treated for addiction found that the intensity of their pain decreased, their ability to function increased, and their alcohol use went down, compared to veterans who received a less-focused approach. However, the two groups had similar rates of drug use.

Just 10 weekly sessions of the approach, called ImPAT for Improving Pain during Addiction Treatment, had an effect that lasted up to a year in 55 veterans who took part, according to the new results published by a team from the VA Ann Arbor Healthcare System’s Center for Clinical Management Research and University of Michigan Medical School’s Addiction Center.

The researchers have already launched a follow-up study in a larger group of 480 non-veterans in a residential addiction treatment program. And the study’s authors note that the ImPAT approach has the potential to be easily and inexpensively adopted by addiction treatment centers and groups worldwide, through team members trained in standard psychological techniques.

Addiction treatment programs often have patients who suffer from chronic pain, but offer few options to treat them, Ilgen says.’These results highlight the need for addiction treatment programs to offer a multifaceted approach that doesn’t only address substance use but also the other factors that might be driving substance use, including pain,’ says Mark Ilgen, Ph.D., the study’s lead author and a VA and U-M psychologist specializing in addiction research. ‘We’ve shown that it’s possible to improve pain outcomes in people with addiction, and even have some spillover effects on their substance use.’

To make matters worse, ‘Past studies of psychosocial approaches for pain have often excluded people with drug or alcohol problems, addiction treatment programs do not usually have providers trained in pain care, and many pain specialists will not treat people who also have addiction. So patients are caught in the middle.’

All 129 patients in the study, most of them men in their 40s and 50s, were receiving outpatient addiction treatment in a CBT-based, non-abstinence setting at the Ann Arbor VA. Half were randomly assigned to ImPAT sessions, the other half to support groups of peers, led by a therapist, where pain and addiction could be discussed.

ImPAT combines elements of cognitive behavioural therapy with another psychosocial approach called acceptance and commitment therapy.

While the two approaches aren’t usually used together, they are often used in pain treatment settings – but those clinics and programs don’t often accept people who also acknowledge they have addiction issues. Ilgen and his colleagues hope their results will help bring the techniques into addiction treatment settings, where the cognitive behavioural therapy approach is often used.

The ImPAT technique seeks to use integrated approaches both to help patients focus less on their pain and more on other aspects of life. This includes techniques to help people adapt to their pain, find ways to distract themselves from their pain, and think of ways to function in the face of pain.

‘We want to take the focus off pain and put it onto functioning, and finding pleasurable ways to spend time,’ Ilgen says. ‘There’s also a strong link between depression and pain. Pain is responsive to mood, and mood is responsive to social support.’

University of Michigan www.uofmhealth.org/news/archive/201607/treating-pain-without-feeding-addiction-study-shows-promise

A study that used fake patients to assess the performance of direct-to-consumer teledermatology websites suggests that incorrect diagnoses were made, treatment recommendations sometimes contradicted guidelines, and prescriptions frequently lacked disclosure about possible adverse effects and pregnancy risks, according to an article.
In the US, direct-to-consumer teledermatology (DTC) is rapidly expanding and large DTC services are contracting with major health plans to provide telecare. However, relatively little is known about the quality of these services.
Jack S. Resneck, Jr., M.D., of the University of California, San Francisco, and co-authors used study personnel posing as patients to submit six dermatologic cases with photographs, including neoplastic, inflammatory and infectious conditions, to regional and national DTC telemedicine websites and smartphone apps offering services to California residents. The photographs were mostly obtained from publicly available online image search engines. Study patients claimed to be uninsured and paid fees using Visa gift debit cards; no study personnel provided any false government-issued identification cards or numbers.
The authors received responses from 16 DTC websites for 62 clinical encounters over about a month from February to March 2016.
The authors report:
None of the websites asked for identification or raised concern about pseudonym use or falsified photographs.
During 68 percent of encounters, patients were assigned a clinician without any choice; 26 percent disclosed information about clinician licensure; and some used internationally based physicians without California licenses; 23 percent collected the name of an existing primary care physician and 10 percent offered to send records.
A diagnosis or a likely diagnosis was given in 77 percent of cases; prescriptions were ordered in 65 percent of these cases; and relevant adverse effects or pregnancy risks were disclosed in a minority of those.
The websites made several correct diagnoses in cases where photographs alone were adequate but when additional history was needed they often failed to ask simple, relevant questions.
Major diagnoses were missed including secondary syphilis, eczema herpeticum, gram-negative folliculitis and polycystic ovarian syndrome.
Treatments prescribed were sometimes at odds with guidelines.
A significant limitation to this study is that the authors were unable to assess whether clinicians seeing these patients in traditional in-person encounters would have performed any better.
The authors offer a series of recommended practices for DTC telemedicine websites, including obtaining proof of patient identity, collecting relevant medical history, seeking laboratory tests when an in-person physician would have relied on that information, having relationships with local physicians in all the areas where they treat patients, and creating quality assurance programmes.

JAMAhttp://tinyurl.com/hctx7t5