Early diagnosis of Alzheimer’s disease using artificial intelligence

According to a study published in the journal of radiology, research shows that artificial intelligence (AI) technology predict the development of Alzheimer’s disease early.

Early diagnosis of Alzheimer’s is important as treatments and interventions are more effective early in the course of the disease. However, early diagnosis has proven to be challenging. Research has linked the disease process to changes in metabolism, as shown by glucose uptake in certain regions of the brain, but these changes can be difficult to recognize.

Credit: Radiological Society of North America

“Differences in the pattern of glucose uptake in the brain are very subtle and diffuse,” said study co-author Jae Ho Sohn, M.D., from the Radiology & Biomedical Imaging Department at the University of California in San Francisco (UCSF). “People are good at finding specific biomarkers of disease, but metabolic changes represent a more global and subtle process.”

The researchers trained the deep learning algorithm on a special imaging technology known as 18-F-fluorodeoxyglucose positron emission tomography (FDG-PET). In an FDG-PET scan, FDG, a radioactive glucose compound, is injected into the blood. PET scans can then measure the uptake of FDG in brain cells, an indicator of metabolic activity.

The researchers had access to data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), a major multi-site study focused on clinical trials to improve the prevention and treatment of this disease. The ADNI dataset included more than 2,100 FDG-PET brain images from 1,002 patients. Researchers trained the deep learning algorithm on 90 percent of the dataset and then tested it on the remaining 10 percent of the dataset. Through deep learning, the algorithm was able to teach itself metabolic patterns that corresponded to Alzheimer’s disease.

Finally, the researchers tested the algorithm on an independent set of 40 imaging exams from 40 patients that it had never studied. The algorithm achieved 100 percent sensitivity at detecting the disease an average of more than six years prior to the final diagnosis.

“We were very pleased with the algorithm’s performance,” Dr. Sohn said. “It was able to predict every single case that advanced to Alzheimer’s disease.”

Although he cautioned that their independent test set was small and needs further validation with a larger multi-institutional prospective study, Dr. Sohn said that the algorithm could be a useful tool to complement the work of radiologists especially in conjunction with other biochemical and imaging tests–in providing an opportunity for early therapeutic intervention.

Future research directions include training the deep learning algorithm to look for patterns associated with the accumulation of beta-amyloid and tau proteins, abnormal protein clumps and tangles in the brain that are markers specific to Alzheimer’s disease, according to UCSF’s Youngho Seo, Ph.D., who served as one of the faculty advisors of the study.

Citation: Yiming Ding, Jae Ho Sohn, Michael G. Kawczynski, Hari Trivedi, Roy Harnish, Nathaniel W. Jenkins, Dmytro Lituiev, Timothy P. Copeland, Mariam S. Aboian, Carina Mari Aparici, Spencer C. Behr, Robert R. Flavell, Shih-Ying Huang, Kelly A. Zalocusky, Lorenzo Nardo, Youngho Seo, Randall A. Hawkins, Miguel Hernandez Pampaloni, Dexter Hadley, and Benjamin L. Franc. “A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain.” Radiology, 2018, 180958.
doi:10.1148/radiol.2018180958.

.embed-container { position: relative; padding-bottom: 56.25%; height: 0; overflow: hidden; max-width: 100%; } .embed-container iframe, .embed-container object, .embed-container embed { position: absolute; top: 0; left: 0; width: 100%; height: 100%; }

Potential treatment for Alzheimer’s dementia using cell therapy

Researchers from Gladstone Institute uncovered the therapeutic benefits of genetically improving interneurons with a voltage-gated sodium channel Nav1.1 and transplanting them into the brain of a mouse model of Alzheimer’s disease. This study is led by Jorge Palop, Ph.D., an assistant investigator at the Gladstone Institutes. The study findings are published in journal Neuron.

Inhibitory interneurons are essential for managing brain rhythms.  They regulate the oscillatory rhythms and network synchrony that are required for cognitive functions. Network dysrhythmias in Alzheimer’s disease and multiple neuropsychiatric disorders are associated with hypofunction of Nav1.1, a voltage-gated sodium channel subunit predominantly expressed in interneurons in Alzheimer’s disease (AD).

Researchers found a way to re-engineer inhibitory interneurons genetically boosted by adding protein Nav1.1 to improve their function. They showed that these enhanced interneurons, when transplanted into the abnormal brain of Alzheimer mice, can properly control the activity of excitatory cells and restore brain rhythms.

The researchers then discovered that the interneurons with enhanced function were able to overcome the toxic disease environment and restore brain function. The findings could eventually lead to the development of new treatment options for patients with Alzheimer’s disease.

In addition to examining if the cell therapy could be translated from mice to humans, researchers are working on pharmaceutical drugs to enhance the function of inhibitory interneurons.

Citation: Martinez-Losa, Magdalena, Tara E. Tracy, Keran Ma, Laure Verret, Alexandra Clemente-Perez, Abdullah S. Khan, Inma Cobos, Kaitlyn Ho, Li Gan, Lennart Mucke, Manuel Alvarez-Dolado, and Jorge J. Palop. “Nav1.1-Overexpressing Interneuron Transplants Restore Brain Rhythms and Cognition in a Mouse Model of Alzheimer’s Disease.” Neuron, 2018. doi:10.1016/j.neuron.2018.02.029.

Research funding: National Institutes of Health, Alzheimer’s Association; S.D. Bechtel, Jr. Foundation.

Adapted from press release by Gladstone Institutes.

Cost of care for falls in elderly population

Researchers estimated medical costs attributable to both fatal and nonfatal falls in the elderly population and found that approximately 50 billion dollars were spent in 2015. These findings are published in the Journal of the American Geriatrics Society.

Researchers utilized population data from the National Vital Statistics System (NVSS) and cost estimates from the Web-based Injury Statistics Query and Reporting System (WISQARS) for fatal falls, quasi-experimental regression analysis of data from the Medicare Current Beneficiaries Survey (MCBS) for nonfatal falls.

For nonfatal falls in adults aged 65 and older, Medicare paid approximately $28.9 billion, Medicaid $8.7 billion and private and other payers $12.0 billion. Overall medical spending for fatal falls was estimated to be $754 million.

Study authors felt that”Preventive strategies that reduce falls among older adults could lead to a substantial reduction in health care spending.”

Citation: Florence, Curtis S., Gwen Bergen, Adam Atherly, Elizabeth Burns, Judy Stevens, and Cynthia Drake. “Medical Costs of Fatal and Nonfatal Falls in Older Adults.” Journal of the American Geriatrics Society, 2018. doi:10.1111/jgs.15304.

Research funding: CDC

Adapted from press release by Wiley publications.

New research shows relationship between activity levels and mortality in elderly

Doing just a few minutes at a time of any level of physical activity, is linked to a lower risk of death in older men according to a new study published online in the British Journal of Sports Medicine. Providing the recommended 150 minute weekly tally of moderate physical activity is reached, total volume, rather than activity in 10 minute bouts, as current guidelines suggest, might be key, the findings indicate.

This lower level of intensity is also likely to be a better fit for older men, most of whose daily physical activity is of light intensity, say the researchers. Current exercise guidelines recommend accumulating at least 150 minutes a week of moderate to vigorous physical activity in bouts lasting 10 or more minutes. But such a pattern is not always easy for older adults to achieve, say the researchers.

To find out if other patterns of activity might still contribute to lowering the risk of death, the researchers drew on data from the British Regional Heart Study. This involved 7735 participants from 24 British towns, who were aged between 40 and 59 when the study stated in 1978-80.

In 2010-12, the 3137 survivors were invited for a check-up, which included a physical examination, and questions about their lifestyle, sleeping patterns, and whether they had ever been diagnosed with heart disease.

They were also asked to wear an accelerometer, a portable gadget that continuously tracks the volume and intensity of physical activity–during waking hours for 7 days. Their health was then tracked until death or June 2016, whichever came first.

In all, 1566 (50%) men agreed to wear the device, but after excluding those with pre-existing heart disease and those who hadn’t worn their accelerometer enough during the 7 days, the final analysis was based on 1181 men, whose average age was 78. During the monitoring period, which averaged around 5 years, 194 of the men died. The accelerometer findings indicated that total volume of physical activity, from light intensity upwards, was associated with a lower risk of death from any cause.

Each additional 30 minutes a day of light intensity activity, such as gentle gardening or taking the dog for a walk, for example, was associated with a 17 percent reduction in the risk of death. This association persisted even after taking account of potentially influential lifestyle factors, such as sedentary time.

Whilst the equivalent reduction in the risk of death was around 33 percent for each additional 30 minutes of moderate to vigorous intensity physical activity a day, the benefits of light intensity activity were large enough to mean that this too might prolong life.

And there was no evidence to suggest that clocking up moderate to vigorous activity in bouts of 10 minutes or more was better than accumulating it in shorter bouts. Sporadic bouts of activity were associated with a 41 percent lower risk of death; bouts lasting 10 or more minutes were associated with a 42 percent lower risk.

Sporadic bouts seemed easier to achieve as two thirds (66%) of the men achieved their weekly total of moderate to vigorous physical activity in this way while only 16% managed to do so in bouts of 10 or more minutes. Finally, there was no evidence to suggest that breaking up sitting time was associated with a lower risk of death.

This is an observational study so no firm conclusions can be drawn about cause and effect. And those who wore the accelerometer tended to be younger and have healthier lifestyles than those who didn’t, so this might have skewed the results, say the researchers. Nor is it clear if the findings would be equally applicable to younger age groups or older women. Nevertheless, the results could be used to refine current physical activity guidelines and make them more achievable for older adults, suggest the researchers.

Future guidance might emphasise that all physical activity, however modest, is worthwhile for extending the lifespan–something that is particularly important to recognise, given how physical activity levels tail off rapidly as people age, they point out.

“the results suggest that all activities, however modest, are beneficial. The finding that low intensity physical activity is associated with lower risk of mortality is especially important among older men, as most of their daily physical activity is of light intensity,” write the researchers.

“Furthermore, the pattern of accumulation of physical activity did not appear to alter the associations with mortality, suggesting that it would be beneficial to encourage older men to be active irrespective of bouts,” they add.

Citation: Jefferis, Barbara J., Tessa J. Parsons, Claudio Sartini, Sarah Ash, Lucy T. Lennon, Olia Papacosta, Richard W. Morris, S. Goya Wannamethee, I. -Min Lee, and Peter H. Whincup. “Objectively measured physical activity, sedentary behaviour and all-cause mortality in older men: does volume of activity matter more than pattern of accumulation?” British Journal of Sports Medicine, 2018. doi:10.1136/bjsports-2017-098733.

Adapted from press release by BMJ Publications.

Research shows rise in global life expectancy by 2030

The study, led by scientists from Imperial College London in collaboration with the World Health Organization, analyzed long-term data on mortality and longevity trends to predict how life expectancy will change in 35 industrialized countries by 2030. Nations in the study included both high-income countries, such as the USA, Canada, UK, Germany, Australia, and emerging economies such as Poland, Mexico, and the Czech Republic. The researchers chose countries in the study as they all had reliable data on deaths since at least 1985.

Posterior distribution of projected change in life expectancy at birth from 2010 to 2030.
Posterior distribution of projected change in life expectancy at birth from 2010 to 2030.
Credit: The Lancet.

The study, published in The Lancet and funded by the UK Medical Research Council, revealed all nations in the study can expect to see an increase in life expectancy by 2030. The results also found that South Koreans may have the highest life expectancy in the world in 2030. The UK’s average life expectancy at birth for women will be 85.3 years in 2030.

Professor Ezzati, lead researcher from the School of Public Health at Imperial explained that South Korea’s high life expectancy may be due to a number of factors including good nutrition in childhood, low blood pressure, low levels of smoking, good access to healthcare, and uptake of new medical knowledge and technologies.

French women and Swiss men were predicted to have the highest life expectancies at birth in Europe in 2030, with an average life expectancy of 88.6 years for French women and nearly 84 years for Swiss men.

The results also revealed that the USA is likely to have the lowest life expectancy at birth in 2030 among high-income countries. The nation’s average life expectancy at birth of men and women in 2030 (79.5 years and 83.3 years), will be similar to that of middle-income countries like Croatia and Mexico. The research team thinks this may be due to a number of factors including a lack of universal healthcare, as well as the highest child and maternal mortality rate, homicide rate and obesity among high-income countries.

Along with the US, other countries who may see only small increases in life expectancy by 2030 included Japan, Sweden, and Greece, while Macedonia and Serbia were projected to have the lowest life expectancies at birth for women and men respectively in 2030.

The UK’s average life expectancy at birth for women will be 85.3 years in 2030. This places them at 21st in the table of 35 countries. The average life expectancy of a UK man meanwhile will be 82.5 years in 2030. This places them at 14th in the table of 35 countries.

The research also suggested the gap in life expectancy between women and men is closing. Professor Ezzati explained: “Men traditionally had unhealthier lifestyles and so shorter life expectancies. They smoked and drank more, and had more road traffic accidents and homicides. However as lifestyles become more similar between men and women, so does their longevity.”

Professor Colin Mathers, co-author from the World Health Organization explained: “The increase in average life expectancy in high-income countries is due to the over-65s living longer than ever before. In middle-income countries, the number of premature deaths – i.e. people dying in their forties and fifties, will also decline by 2030.” The team developed a new method to predict longevity, similar to the methods used for weather forecasting, which takes into account numerous different models for forecasting mortality and life expectancy.

Life expectancy is calculated by assessing the age at which people die across the whole population. For instance, if a country has high childhood mortality rate, this will make average national life expectancy much lower, as would a country in which many young people die of injuries and violence. The team developed a new method to predict longevity, similar to the methods used for weather forecasting, which takes into account numerous different models for forecasting mortality and life expectancy. All the predictions in the study come with some uncertainty range.

Professor Ezzati added that these results suggest we need to be thinking carefully about the needs of an ageing population: “The fact that we will continue to live longer means we need to think about strengthening the health and social care systems to support an ageing population with multiple health needs. This is the opposite of what is being done in the era of austerity. We also need to think about whether current pension systems will support us, or if we need to consider working into later life.”

Citation: Kontis, Vasilis, James E Bennett, Colin D Mathers, Guangquan Li, Kyle Foreman, and Majid Ezzati. 2017. “Future Life Expectancy in 35 Industrialised Countries: Projections with a Bayesian Model Ensemble.” The Lancet, February. Elsevier.
doi:10.1016/S0140-6736(16)32381-9.
Research funding: UK Medical Research Council, US Environmental Protection Agency.
Adapted from press release by Imperial College London.