Tools such as AI are transforming healthcare. These tools, for instance, are already helping coronavirus, or Covid-19 as it is now known
AI aids coronavirus (Covid-19) researchers
AI, as is well known, is very good at predictions. This explains why companies are putting AI to good use in healthcare.
A Toronto-based health surveillance company, BlueDot, issued a warning to its customers to avoid Wuhan (where the virus originated) on Dec. 31, 2019. It was not until Jan.9, 2020, that the World Health Organisation (WHO) sent a similar public notice.
BlueDot culls disease data from myriad online sources. It, then, uses airline flight information to make predictions about where infectious diseases may appear next — air routes, after all, are a common disease vector.
Similarly, an AI-powered simulation run by fintech firm HedgeChatter says Coronavirus could infect as many as 2.5 billion people within 45 days and kill as many as 52.9 million of them. Fortunately, however, conditions of infection and detection are changing, which in turn changes incredibly important factors that the AI isn’t aware of, according to Forbes.
John Brownstein, chief innovation officer at Boston Children’s Hospital and a professor at Harvard Medical School, told Time magazine on how they are using high-tech to address the coronavirus issue. His team built a tool called Healthmap, which scrapes information about new outbreaks from online news reports, chatrooms and more.
Healthmap, developed after SARS killed 774 people around the world in the mid-2000s, organizes disparate data and generates visualizations that show how and where communicable diseases like the coronavirus are spreading.
Healthmap’s output supplements more traditional data-gathering techniques used by organizations like the U.S. Centers for Disease Control and Prevention (CDC) and the World Health Organization (WHO). The project’s data is being used by clinicians, researchers and governments.
Companies like BenevolentAI, a UK-based start-up; Deargen, a South Korean AI drug discovery specialist; and US-based Insilico Medicine are also pitching in with their own AI-based solutions. There are hundreds of other startups that are using AI and other technologies for drug discovery.
AI, brain scans may alter how doctors treat depression
A computer can accurately predict whether an antidepressant will work based on a patient’s brain activity national trial. This was demonstrated by a study initiated by UT Southwestern Medical Centre in 2011 to better understand mood disorders.
Researchers predict that tools such as AI, brain imaging, and blood tests will revolutionize the field of psychiatry in the coming years, although implementing these approaches will take time.
“These studies have been a bigger success than anyone on our team could have imagined,” says Madhukar Trivedi, M.D., a UT Southwestern psychiatrist who oversaw the multi-site trial involving Stanford, Harvard and other institutions.
The study published in Nature Biotechnology included more than 300 participants with depression. They were randomly chosen to receive either a placebo or an SSRI (selective serotonin reuptake inhibitor) — the most common class of antidepressant.
Researchers used an electroencephalogram, or EEG, to measure electrical activity in the participants’ cortex before they began treatment. The team then developed a machine-learning algorithm to analyze and use the EEG data to predict which patients would benefit from the medication within two months. The findings were validated in three additional patient groups.
Among the next steps, researchers say, is developing an AI interface that can be widely integrated with EEGs across the country. They will also approval from the U.S. Food and Drug Administration.
Antidepressant use in the U.S. has increased nearly 65% over a decade and a half — from 7.7% in 1999-2002 to 12.7% in 2011-2014 — according to data from the National Health and Nutrition Examination Survey.
Trivedi says the expanded use of medications make it more critical to further understand the underpinnings of depression and ensure patients are prescribed an effective therapy.
Robot can extract blood samples
A Rutgers-led team has created a blood-sampling robot that performed as well or better than people, according to the first human clinical trial of an automated blood drawing and testing device.
The device provides quick results and would allow healthcare professionals to spend more time treating patients in hospitals and other settings, according to a release.
The results, published in the journal Technology, were comparable to or exceeded clinical standards — with an overall success rate of 87% for the 31 participants whose blood was drawn. The success rate was 97% for the 25 people whose veins were easy to access.
The device includes an ultrasound image-guided robot that draws blood from veins. Ambulances, emergency rooms, clinics, doctors’ offices and hospitals, could use a fully integrated device that includes a module that handles samples and a centrifuge-based blood analyzer.
Open source app helps predict brain tumor malignancy
Researchers from The Neuro (Montreal Neurological Institute-Hospital) and the Montreal Children’s Hospital of the McGill University Health Centre have trained machine learning algorithms on data from more than 62,000 patients with a meningioma.
Their goal, according to a recent study, was to find statistical associations between malignancy, survival, and a series of basic clinical variables including tumour size, tumour location, and surgical procedure.
While the study demonstrated that the models could effectively predict outcomes in individual patients, the researchers emphasised the need for further refinements using larger sets that include brain imaging and molecular data. The study was published in the journal npj Digital Medicine on Jan. 30.
The researchers have also developed an open-source smartphone app to allow clinicians and other researchers to interactively explore the predictive algorithms described in the paper.
They hope that making the app entirely free and open source could help future projects translate newly developed machine learning algorithms to real-world clinical practice. The app is available here for demonstration.
Solving AI’s need for more computing power
AI may offer promise to improve many areas of society, including healthcare systems, transportation and security. However, it can only meet its potential if computing can support it.
In this context, electrical engineers at Northwestern University and the University of Messina in Italy have developed a new magnetic memory device that could potentially support the surge of data-centric computing.
Based on antiferromagnetic (AFM) materials, the device is the smallest of its kind ever demonstrated and operates with record-low electrical current to write data.
“The rise of big data has enabled the emergence of AI in the cloud and on edge devices, and is fundamentally transforming the computing, networking and data storage industries. Our technology potentially could solve this challenge,” Northwestern’s Pedram Khalili, who led the research, said in a release. The research was published on Feb. 10 in the journal Nature Electronics.
Typically, memory devices require an electric current to retain stored data. But in AFM materials, it is the magnetically ordered spins that perform this task, so a continuously applied electric current is not needed. Khalili and his team used pillars of antiferromagnetic platinum manganese, which are 10 times smaller than earlier AFM-based memory devices.
“This brings AFM memory — and thus highly scaled and high-performance magnetic random-access memory (MRAM) — much closer to practical applications,” Khalili said. He and his team are already exploring how to further downscale these devices and improve methods to read out their magnetic state.
