Toggle light / dark theme

So now, there are AI doctors.


Machine learning is taking medical diagnosis by storm. From eye disease, breast and other cancers, to more amorphous neurological disorders, AI is routinely matching physician performance, if not beating them outright.

Yet how much can we take those results at face value? When it comes to life and death decisions, when can we put our full trust in enigmatic algorithms—“black boxes” that even their creators cannot fully explain or understand? The problem gets more complex as medical AI crosses multiple disciplines and developers, including both academic and industry powerhouses such as Google, Amazon, or Apple, with disparate incentives.

This week, the two sides battled it out in a heated duel in one of the most prestigious science journals, Nature. On one side are prominent AI researchers at the Princess Margaret Cancer Centre, University of Toronto, Stanford University, Johns Hopkins, Harvard, MIT, and others. On the other side is the titan Google Health.

Restaurant owners say they have grown accustomed this year to constantly reinventing themselves to survive. Getting around Mother Nature as the U.S. heads toward winter may be their biggest challenge yet.

Sales from outdoor dining, reduced indoor dining, delivery, and takeout haven’t equaled what most restaurants expected to earn this year before the pandemic upended public life, some owners say. Adding heaters and other fixtures to draw diners to outdoor tables as the weather cools adds to the costs of sustaining a modest revenue stream.

But determined restaurant operators say they have no other choice. They say running at a loss while they have funds to do so—in the hope that the threat of the virus abates—is better than the challenges they would face after closing temporarily, such as finding reliable staff.

This includes volunteering to test the new vaccine being developed by the Israeli Institute for Biological Research in Ness Ziona. Meet some of the heroes who are doing their bit for humanity.

The research center said it will begin the clinical trials phase of its COVID-19 vaccine in November and about one hundred Israelis aged 18–55 are expected to participate by the time the trials are over. The first phase will include three brave volunteers and will take place in Sheba Medical Center in Tel HaShomer and Hadassah Medical Center in Jerusalem.

As with any other clinical trials, participants will be divided into two groups: those who will receive the real vaccine and those who will receive a fake vaccine, also known as placebo.

In a major breakthrough an international team of scientists, led by the University of Bristol, has potentially identified what makes SARS-CoV-2 highly infectious and able to spread rapidly in human cells. The findings, published in Science today [20 October] describe how the virus’s ability to infect human cells can be reduced by inhibitors that block a newly discovered interaction between virus and host, demonstrating a potential anti-viral treatment.

Using the Crispr gene-editing technique that won a recent Nobel Prize, Crispr Therapeutics cleared blood cancers in patients with off-the-shelf immune cells. These so-called CAR-T therapies previously required a patient’s own cells.

In a Wednesday morning announcement, Crispr Therapeutics (ticker: CRSP) said that its gene-editing let doctors use cells from healthy donors—opening up prospects for broadly available, less-expensive use of CAR-T treatment.

In the Phase 1 trial, the lymphoma blood cancer in four of 11 patients responded completely to infusions of T cells whose genes were altered to target the cancer and prevent transplant rejection. Standard treatments had failed all participants. In patients that got higher doses, the complete responses have lasted for months.

Our immune system’s capacity to mount a well-regulated defense against foreign substances, including toxins, weakens with age and makes vaccines less effective in people over age 65. At the same time, research has shown that immunotherapy targeting neurotoxic forms of the peptide amyloid beta (oligomeric Aβ) may halt the progression of Alzheimer’s disease, the most common age-related neurodegenerative disease.

A team led by Chuanhai Cao, Ph.D., of the University of South Florida Health (USF Health), has focused on overcoming, in those with impaired immunity, excess inflammation and other complications that interfere with development of a therapeutic Alzheimer’s vaccine.

Now, a by Dr. Cao and colleagues indicates that an antigen-presenting dendritic vaccine with a specific antibody response to oligomeric Aβ may be safer and offer clinical benefit in treating Alzheimer’s disease. The vaccine, called E22W42 DC, uses immune known as dendritic cells (DC) loaded with a modified Aβ peptide as the antigen.