Health

Artificial intelligence can predict breast cancer years before it shows up on a mammogram. That’s according to a ground-breaking new study from MIT. Its author Regina Barzilay was diagnosed with breast cancer in 2014 and beat it.

Artificial intelligence is already making groundbreaking changes in our society and benefiting us in ways never thought possible. One of the fields that is being heavily impacted by AI is health care. We’ve talked about how AI is being used to assist mental health studies and treatment before, and how it’s changing the fight against diabetes. Now we will focus on another huge aspect of AI in health care: cardiovascular diseases.

Mental health is among the most important aspects of health care these days — and the Covid-19 pandemic has only made it more critical.

TikTok is introducing automated captions, a feature that will add subtitles to posts in its popular video-sharing app without requiring users to enter the text themselves. The feature, which is being rolled out in the coming weeks, is the latest attempt by a social-media company to make its products more accessible and avoid shutting out large segments of the population.

The vaccine rollout, to date, has been anything but orderly. Each state sets its own parameters for eligibility and has to contend with limited supplies or limited storage. Vaccines are lost, go bad, or are administered to people in the wrong order — say, your healthy niece got one before your elderly father.

Researchers showed long ago that artificial intelligence models could identify a person’s basic psychological traits from their digital footprints in social media. A new study provides strong evidence that machine-learning models can also map a person’s mood swings and volatility from week to week. Using AI tools to analyze Facebook posts, the new machine-learning model infers both how happy or sad a person is feeling at any given time as well as how aroused or lackadaisical. Over time, this algorithm can even produce a video out of a person’s emotional ups and downs. The findings could spark new worries about privacy or the use of social media to market to people.

Among the most pressing matters cancer patients and doctors discuss is how serious the disease is and how long the patient can expect to live. These are tough conversations that affect how the patient is treated. And for most of medical history, life-expectancy predictions have mainly been educated guesses based on the physician’s knowledge and experience, among other information. Recently, however, significant improvements have been made to the accuracy of these important predictions by turning to artificial intelligence. A new algorithm could lead to greater accuracy in cancer prognosis and, ultimately and most importantly, to better care for patients.

With regards to mental health services, AI — in particular, natural language processing (NLP) tools — could improve care as well as increase access to it. For example, NLP could help researchers figure out what makes some psychotherapists more effective than others — information that could then be used to improve training for new clinicians. NLP systems could also listen in on therapy sessions to provide feedback to clinical trainees or experienced clinicians, create a first draft of necessary clinical documentation, or spot changes in a patient’s speech patterns that might be an early indicator of a worsening condition. More advanced AI might even converse with patients and be available at all hours of the day — increasing access to care.

Scientists have developed a machine-learning method that crunches massive amounts of data to help determine which existing medications could improve outcomes in diseases for which they are not prescribed. The goal of this is to speed up "drug repurposing" -- the idea of using an already developed drug to treat another symptom. Figuring out what other ailments can be treated by an existing drug is no small task, though: it takes an enormous amount of time, data, and experimentation. That's where AI comes in. AI can be used to significantly speed up the process. Drug repurposing is an attractive pursuit because it could lower the risk associated with safety testing of new medications and dramatically reduce the time it takes to get a drug into the marketplace for clinical use.

Last week, Stanford Medicine issued an apology for releasing a vaccine prioritization list that included only seven medical residents and fellows. Stanford Medicine has more than 1,300 residents on staff, many of whom are routinely asked to treat Covid-19 patients.

The idea of relying on artificial intelligence to make important medical decisions about patients can be a little scary. Can we really rely on AI to understand our health? The short answer: yes, but with oversight. The use of AI in healthcare needs to be driven by ethical standards. For instance, AI should always benefit the health and wellbeing of individuals. AI should never be left alone; it should be overseen and regulated. AI should never do harm. AI should be developed using data represented of all peoples, not only the people who program it. And lastly, the healthcare industry needs to be transparent about the ways in which it is using AI.

Google Health researchers have been using AI to help review prostate biopsies, improving the quality, efficiency, and consistency of cancer detection and grading. Researchers ran studies comparing the quality of analysis with AI and without AI; they found that not only did AI-assisted analyses have higher quality results, they also improved tumor detection, among other benefits.

The operating room is getting a lot of attention from artificial intelligence — especially in neurosurgery. In one example from recent research, an algorithm is being developed that could predict tumor treatment responses based on a patient’s genetics. If information like this became available to surgeons and clinicians, their rate of success could increase dramatically.

AI has seemingly infinite applications in the world of healthcare, and mental health is no exception. Digital mental health resources are all the rage these days, with smartphone apps that can hook you up with a therapist for convenient counseling. AI is already being used to analyze hospital admissions data to predict the likelihood that someone may take their own life. It is helping therapists increase emotional awareness for patients and clients. And it’s found in chatbots that are available 24/7, offering relevant and helpful responses.