What happened in health care technology this week, and why it’s important.
Why Boston Children’s is hiring a ChatGPT super user
Gabriel Perna reports that as healthcare contemplates the use of generative artificial intelligence technology, Boston Children’s Hospital is moving from strategy to salary in his article in Digital Health Business and Technology online. The Boston-based hospital is hiring someone to use OpenAI’s generative AI application ChatGPT. Boston Children’s posted a job posting in April for an “AI prompt engineer” to work on its innovation and digital health accelerator. The person will design and develop AI prompts using large language models like ChatGPT.
“Right out of the box, I don’t think I’ve seen anything as transformational since the iPhone or Google.”
John Brownstein, MD, Chief Innovation Officer, Boston Children’s
Why it’s important – According to Brownstein, when margins are challenging and we’re in a tough economy, upskilling the workforce with these tools can be incredibly beneficial. The skill set of the next decade is going to be someone with the skills of a prompt engineer. Someone who knows how to interface with large language models. Someone who knows how to ask the right questions to get the correct detail. Someone who knows the boundaries by which these things work and that they don’t work.
Infographic of the week – Our homes and working environments will be loaded with connected appliances, virtual assistants, motion sensors, and remote monitoring tools connected to smart infrastructure. Beyond this, bioelectronic implants, smart clothing, ingestible sensors, and ultimately nanobots and smart dust will map the very surfaces and interior spaces of our bodies. The net effect of this ever-present IoMT will be to drive unprecedented growth in the quantity and quality of healthcare data available.
John Deere employees now using Comau exoskeletons
John Deere employees now have access to multiple Comau MATE-XT exoskeletons. Brianna Wessling covers the story in The Robot Report online. The MATE-XT exoskeleton, which is worn like a backpack, can accurately replicate all shoulder movements, helping employees perform their jobs comfortably by reducing muscle fatigue without limiting mobility or adding bulk. For John Deere employees, this means helping them move hundreds of packages a day to ensure parts are ready for next-day delivery.
Why it’s important – The devices aim to sustain worker well-being, alleviate physical stress and reduce ergonomic risk within its parts logistics operations. muscular balance while optimizing the energy expenditure needed to stabilize and sustain the arm’s weight. While wearing the exoskeleton, arm stability can be maintained using only 10% of the operator’s maximum capacity.
Video of the week – “The amazing AI super tutor for students and teachers” Sal Khan, the founder, and CEO of Khan Academy, thinks artificial intelligence could spark the most significant positive transformation education has ever seen. He shares the opportunities he sees for students and educators to collaborate with AI tools — including the potential of a personal AI tutor for every student and an AI teaching assistant for every teacher — and demos some exciting new features for their educational chatbot, Khanmigo.
CEDARS-SINAI TEAM DEVELOPS AI TOOL TO PREDICT HEART ATTACKS
Eric Wicklund reports that researchers say their AI algorithm can analyze clinical data and images of a patient’s heart and calculate the probability of cardiac arrest and other concerns over several years. The tool analyzes clinical data, such as age, weight, gender, heart rate, and blood pressure, alongside heart images showing blood flow to the heart muscle and expansions and contractions.
Why it’s important – Doctors and patients can use these graphs to track how risk changes over time and to identify individual risk factors. They can also interactively modify certain risk factors to see how they impact a patient’s risk. Researchers say these tools could help providers develop more personalized care plans for patients and improve patient engagement.
Biotech firm beats Elon Musk’s Neuralink, has implanted brain chips in 50 people for ailments
Mehul Reuben Das reports that while Elon Musk and the people at Neuralink are trying to get FDA approval to test their Neuralink BCIs on people and get them approved for medical uses, a biotech in Utah seems to have beaten them to the goal quite handsomely, and has already implanted brain chips in dozens of patients. Blackrock Neurotech, headquartered in Salt Lake City, aspires to cure physical disability, blindness, deafness, and depression. The NeuroPort Array chip enables individuals to control robotic limbs and wheelchairs, play video games, and even sense feelings. It uses nearly 100 microneedles that attach to the brain and read electrical signals produced by someone’s thoughts. More than three dozen people have so far received it. The device was first implanted in a human in 2004. Company leaders hope to bring it to market soon, announcing in 2021 they aimed for the following year.
“Our long-term goal is for our implants to be as widely available to persons with paralysis as pacemakers are to those with heart problems.”
Marcus Gerhardt, co-founder of Blackrock
Why it’s important – The device monitors electrical impulses created by the wearer’s thoughts after implantation. These signals are decoded by machine learning software into digital commands such as cursor movements, which may be utilized to operate prostheses and computer equipment. This can assist someone in drawing with a robotic arm, utilizing computer programs, or controlling a wheelchair or prosthetic limb. However, the company is now seeking FDA approval for devices designed for use outside of the lab, such as those used by people with paralysis at home.
Wearable devices may be able to capture well-being through effortless data collection using AI
Applying machine learning models, a type of artificial intelligence (AI), to data collected passively from wearable devices can identify a patient’s degree of resilience and well-being, according to investigators at the Icahn School of Medicine at Mount Sinai in New York. The findings, reported in the May 2 issue of JAMIA Open, support wearable devices, such as the Apple Watch, as a way to monitor and assess psychological states remotely without requiring the completion of mental health questionnaires.
Why it’s important – Subjects wore an Apple Watch Series 4 or 5 for the duration of their participation, measuring heart rate variability and resting heart rate throughout the follow-up period. Surveys were collected measuring resilience, optimism, and emotional support at baseline. The metrics collected were found to be predictive in identifying resilience or well-being states. Despite the Warrior Watch Study not being designed to evaluate this endpoint, the findings support the further assessment of psychological characteristics from passively collected wearable data.
Brain Activity Decoder Can Reveal Stories in People’s Minds
A new artificial intelligence system called a semantic decoder can translate a person’s brain activity — while listening to a story or silently imagining telling a story — into a continuous stream of text. The system developed by researchers at The University of Texas at Austin might help people who are mentally conscious yet unable to speak physically, such as those debilitated by strokes, to communicate intelligibly again. The study, published in the journal Nature Neuroscience, was led by Jerry Tang, a doctoral student in computer science, and Alex Huth, an assistant professor of neuroscience and computer science at UT Austin. The work partially relies on a transformer model similar to the ones that power Open AI’s ChatGPT and Google’s Bard.
Why it’s important – Unlike other language decoding systems in development, this system does not require subjects to have surgical implants, making the process noninvasive. Participants also do not need to use only words from a prescribed list. Brain activity is measured using an fMRI scanner after extensive training of the decoder, in which the individual listens to hours of podcasts in the scanner. Later, provided that the participant is open to having their thoughts decoded, listening to a new story or imagining telling a story allows the machine to generate corresponding text from brain activity alone. The system currently is not practical for use outside of the laboratory because of its reliance on the time need for an fMRI machine. But the researchers think this work could transfer to other, more portable brain-imaging systems, such as functional near-infrared spectroscopy (fNIRS).
Breakthrough for sweat: health monitoring device from UH researchers
Researchers at the University of Hawaiʻi at Mānoa College of Engineering have taken a giant leap forward in sweat analysis with an innovative 3D-printed wearable sweat sensor called the “sweatainer.” Harnessing the power of additive manufacturing (3D-printing), the researchers have developed a new type of wearable sweat sensor that expands the capability of wearable sweat devices. The sweatainer is a small, wearable device similar in size to a child’s sticker that collects and analyzes sweat, offering a glimpse into the future of health monitoring. By incorporating various sensors, the sweatainer can analyze sweat in a mode similar to previous wearable sweat-sensing systems. The findings were published in Sciences Advances on May 3.
Why it’s important – Sweat is more than just a sign of a good workout. It holds vital information about our health, providing clues to dehydration, fatigue, blood sugar levels, and even serious conditions such as cystic fibrosis, diabetes, and heart failure. Traditional approaches for sweat collection use absorbent pads or microbore (very narrow) tubes pressed against the epidermis (surface layer of the skin) using bands or straps to capture sweat as it emerges from the skin. These techniques require trained personnel, special handling, and costly laboratory equipment. One unique feature of the sweatainer is its “multi-draw” sweat collection method, which allows for collecting multiple, separate sweat samples for analysis either directly on the device or sent to a lab. Inspired by the vacutainer used in clinical blood sampling, this advancement not only makes sweat collection more efficient but also opens up new possibilities for at-home testing, storing samples for future research, and integrating with existing health monitoring methods.
How AI Can Be Used To Cut a $1 Trillion Healthcare Problem
While clinicians and other medical experts continue to debate ML’s effectiveness for treating patients, they’re neglecting a much more dependable and equally impactful use case: administrative work. ML has tremendous potential to streamline tedious administrative tasks and free up valuable time for clinicians, ultimately leading to better patient outcomes. Chris Riopelle, CEO and co-founder of Strive Health, highlights the opportunities in his Fast Company article online*.
One potential use case involves AI-powered scribing solutions, which several startups are beginning to roll out. These solutions take detailed notes of a patient and provider’s conversation, which helps streamline and better capture the visit, allowing for a more productive appointment.
Another trending use case is prior authorizations, or PAs. PAs occur when a healthcare payor requires a provider to secure approval to carry out a specific procedure or prescribe a medication. Physicians and their staff spend almost two full business days each week on PAs, and they can be a major source of contention between payors and providers. ML can quickly compile relevant patient information from EHRs and provide data-backed recommendations about the benefits of various treatment options. While providers still review the information and make the final call, ML can help reduce the time required to complete each PA.
Why it’s important – The U.S. spends nearly $4 trillion on healthcare annually, and administrative costs account for a quarter of this figure. For those not in the medical field, it can be challenging to grasp how much time clinicians spend daily on administrative work. ML has significant potential for helping providers streamline their administrative responsibilities and, as a result, foster better and more fulfilling patient experiences.