Research Roundup: Single Scan Diagnoses Alzheimer's, Women Underrepresented in Trials

Research Roundup: Machine Learning to Diagnose Alzheimer’s with Single Scan and More

Alzheimer's disease is diagnosed with a range of cognitive and memory tests, but there's no definitive diagnostic test for the disease. But researchers have been able to use machine learning to evaluate MRI scans, diagnosing the disease in a single scan. For that and more research news, continue reading.

Scientists Diagnose Alzheimer's with Single Scan

Researchers at Imperial College London leveraged machine learning to examine structural features within the brain to diagnose Alzheimer's disease. Using this method, they also scanned parts of the brain not previously linked to Alzheimer's and was able to identify the disease at an early stage.

Currently, diagnosis is via several cognitive tests, including memory tests, cognitive tests and brain scans. The scans look for evidence of protein deposits in the brain and shrinking of the hippocampus, the brain area associated with memory. 

The new scan uses MRI and an algorithm to classify cancer tumors modified for the brain. They split the brain into 115 regions and specified 660 features, such as size, shape and texture, to evaluate each region. They then programmed the algorithm to identify where changes accurately predict the existence of Alzheimer's. Their research was published in the journal Communications Medicine.

"Currently, no other simple and widely available methods can predict Alzheimer's disease with this level of accuracy, so our research is an important step forward," Dr. Eric Aboagye, the lead researcher in the study, said. "Many patients who present with Alzheimer's at memory clinics do also have other neurological conditions, even within this group our system could pick out those patients who had Alzheimer's from those who did not."

Leveraging data from the Alzheimer's Disease Neuroimaging Initiative, the researchers tested their approach on brain scans from more than 400 patients with early and late-stage Alzheimer's and individuals with other neurological disorders, including frontotemporal dementia and Parkinson's disease.

They also evaluated data from more than 80 patients undergoing diagnostic testing at Imperial College Healthcare NHS Trust. In 98% of cases, their approach alone accurately predicted whether the patient had Alzheimer's or not. It could also distinguish between early and late-stage Alzheimer's with 79% accuracy.

Women Underrepresented in Clinical Trials for 3 Key Disease Areas

A study out of Brigham and Women's Hospital found that female participation in three specific disease areas lags behind their representation in the specific disease population. The key areas are adult cardiovascular, psychiatric, and cancer-related clinical trials.

The study authors note that the disparity was particularly significant in clinical trials for drugs and devices for psychiatric disorders; in this area, women make up 60% of the patient population but only 42% of the trial participants. They analyzed 1,433 clinical trials with 302,664 participants and found that, on average, 41.2% of participants were female. In CV diseases, 49% of the patient population is female, but only 41.9% of trial participants were female. In cancer, 51% of cancer patients are female, but only 41% of clinical trial participants were female.

Abnormal Lipid Processing May Drive Motor Neuron Diseases

Researchers at the University of Exeter identified a new gene, TMEM63C, that appears linked to a degenerative disease affecting the nervous system's upper motor neuron cells.

This supports their research into motor neuron degenerative diseases (MNDs), a large family of neurological disorders, suggesting they are the result of abnormal lipid processing in cells. Although MNDs are caused by changes in several different genes, the TMEM63C gene codes for a protein located in the region of the cell where the lipid processing pathways occur. They hypothesize that the appropriate maintenance of specific lipid processing pathways is vital to how brain cells function, and further, that abnormalities in the paths are common in motor neuron degenerative diseases.

Females More Likely Than Males to Suffer Long COVID

A new study from the Health of Women Team at the Johnson & Johnson Office of the Chief Medical Officer found that females were more likely to suffer from Long COVID and that females tended to present with different symptoms and/or disorders than males.

In their data analysis of about 1.3 million patients, females presented with a range of symptoms, including ear, nose and throat issues, mood, neurological, skin, gastrointestinal and rheumatological disorders, and fatigue. Males, on the other hand, were more likely to experience endocrine disorders like diabetes and kidney disorders.

Why this is the case isn't understood, but they suspect fundamental sex differences in the immune function may drive the differences in Long COVID. Females tend to have faster, more robust innate and adaptive immune responses that can protect them from initial infection and severity, but that may make them more vulnerable to prolonged autoimmune-related diseases. One of the problems with the study is that despite a large number of patients overall, only 35 articles of the 640,634 total articles in the literature offered sex-disaggregated data with enough details about symptoms to provide information about how the disease differed between males and females.

New Combo Treatment for Pediatric T-Acute Leukemia

Acute lymphoblastic leukemia (ALL) is the most common form of pediatric cancer, and the T-ALL type of leukemia has a poorer prognosis than B-lineage ALL. A study by Tampere University's Faculty of Medicine and Health Technology in Finland, the Massachusetts General Research Institute and the Harvard Stem Cell Institute identified a new drug combination that appears effective against T-ALL.

Tampere had earlier found that Bristol Myers Squibb's Sprycel (dasatinib), a general tyrosine kinase inhibitor, was effective in about one-third of the tested patient samples, but its efficacy faded quickly. They found that treating the patients with dasatinib and temsirolimus (Pfizer's Torisel), which inhibits a parallel signaling pathway, was more effective in eradicating leukemia cells in zebrafish and human disease than a single drug.

"This is a promising new treatment option for T-acute leukemia," Olli Lohi, M.D., Ph.D., research director at Tampere University and Tays Hospital's Cancer Centre, said. "The next step is to take the discovery into clinical practice for patients with relapsed or refractory disease via early phase clinical trials."

Back to news