What happened in health care technology this week, and why it’s important.
This week was a very busy news week with dozens of articles to consider. Here are the ones that I found the most interesting:
AI COULD REDUCE GAPS IN HEART ATTACK CARE FOR WOMEN
Researchers have developed a new artificial intelligence-based risk score that improves personalized care for female patients with heart attacks. The University of Zurich posted this summary of its research in Futurity online. In their study, the researchers analyzed data from 420,781 patients with the most common type of heart attack. Using a machine learning algorithm and the largest datasets in Europe, we were able to develop a novel artificial intelligence-based risk score that accounts for sex-related differences in the baseline risk profile and improves the prediction of mortality in both sexes.
“I hope the implementation of this novel score in treatment algorithms will refine current treatment strategies, reduce sex inequalities, and eventually improve the survival of patients with heart attacks—both male and female.”
Thomas F. Lüscher, professor at the Center for Molecular Cardiology, University of Zurich
Why it’s important – There are notable differences in the disease phenotype observed in females and males. Our study shows that women and men differ significantly in their risk factor profile at hospital admission,” says Lüscher. When age differences at admission and existing risk factors such as hypertension and diabetes are disregarded, female heart-attack patients have higher mortality than male patients. Lüscher and his team see huge potential in the application of artificial intelligence for the management of heart disease both in male and female patients.
Infographics of the week – Great summary from Dr. Bertalan Mesko and his team at The Medical Futurist Institute on tech companies collaborating with healthcare institutions. I always fund these extremely valuable in my teaching work. Bringing this information together in a single infographic makes having a substantive conversation much more effortless.
The second infographic this week was created by S3 Connected Health, and is a terrific look at how digital health companies can approach product development along the spectrum from tactical to strategic to increase RoI and demonstrate value to healthcare organizations.
Fingertip Sensor Measures Lithium Levels in Sweat
Researchers at UCLA have developed a fingertip sensor that can rapidly provide data on lithium levels in the body. Conn Hastings reported on this development in his Medgadget article. Used as a treatment for bipolar disorder and depression, lithium requires very accurate and sensitive dosing, with too little providing no therapeutic benefit but slightly too much potentially leading to unwanted side effects. The new electrochemical sensor incorporates a hydrogel pad that facilitates sensitive measurements, which require an aqueous environment. An ion-selective electrode detects the lithium ions present in the sweat on the fingertip, providing a result in as little as 30 seconds.
Why it’s important – At present, the most common method to assess lithium levels involves a blood draw and subsequent lab testing, which is inconvenient and cumbersome. Lithium can be a very effective treatment for bipolar disorder. Still, it is tricky to get the dose just right to maximize its therapeutic properties while reducing the risk of potentially dangerous side effects. Another issue with the drug is the potential for poor patient compliance. If a patient misses some doses and their medication does not appear to be working, a clinician typically must perform a blood draw and order a lab test to see if lithium levels are out of whack. This is time-consuming, invasive, and expensive. Through a single touch, the new device can obtain clinically useful molecular-level information about what is circulating in the body.
An ambitious stroke prevention study tests the Apple Watch’s promise in health
Currently, millions of people with an irregular heartbeat are told to take expensive blood thinners, which prevent strokes but also increase the risk of dangerous bleeding. Stat’s Mario Aguilar reports that a new study will investigate whether Apple Watches can be used as part of a strategy to minimize the use of those medications when they’re not needed. The seven-year study, expected to launch next spring, will compare strokes, bleeding, and health care cost outcomes between people who are given the standard course of blood thinners and an experimental group that will be directed to take medication only after an Apple Watch detects prolonged atrial fibrillation. Apple will donate devices to the project and is assisting in the development of the study application. As part of that work, the company is helping researchers build a custom algorithm for the study, which will check the heart rhythm of participants much more frequently than the algorithm available to the general public. Upon detecting atrial fibrillation that lasts several hours, patients will be directed by the software to take blood thinners until the highest risk of stroke has passed, rather than being left on the drugs indefinitely.
Why it’s important – If the experimental arm of the study can prevent strokes and reduce bleeding, it would be a significant advance for cardiac care. It would also be a coup for Apple, which for years has been developing — and aggressively marketing — features that detect irregular heart rhythms in individuals but have yet to show they can directly impact care and improve outcomes. An upcoming version of Apple’s iPhone software also has a feature to help users manage their medications. One key question will be how reliably and accurately the new algorithm used for the study can catch instances of A-fib. For the algorithm used in the Apple Watch available to the general public, the company’s studies show 88.6% sensitivity in detecting people who have irregular heart rhythms, according to documents published by the Food and Drug Administration. Those data are an important reminder of how the accuracy of consumer wearables can impact any intervention using them at scale.
Late-Breaking Heart Research: AI More Accurate Than Technicians
A Cedars Sinai and Smidt Heart Institute Study, Presented at European Society of Cardiology Congress 2022, Shows Artificial Intelligence Can Better Assess and Diagnose Cardiac Function. Previously, researchers at the Smidt Heart Institute and Stanford University developed one of the first artificial intelligence technologies to assess cardiac function, specifically, left ventricular ejection fraction—the key heart measurement used in diagnosing cardiac function. Their research was published in the prestigious journal Nature. Building on this past research, the most recent study assessed the impact of artificial intelligence in clinical deployment as part of a prospective, blinded, and randomized controlled clinical trial.
In the study, Cedars-Sinai cardiologists evaluated 3,495 transthoracic echocardiogram studies, comparing initial assessment by artificial intelligence or by a sonographer—also known as an ultrasound technician. One of the significant findings was that cardiologists more frequently agreed with the AI initial assessment, such that they corrected only 16.8% of the initial assessments made by AI and simultaneously corrected 27.2% of the initial assessments made by the sonographers. This difference demonstrated not only non-inferiority but actually the superiority of AI.
“This trial was powered to show non-inferiority of the AI compared to sonographer tracings, and so we were pleasantly surprised when the results actually showed superiority for AI with respect to the pre-specified outcomes.”
David Ouyang, MD, Cardiologist, Department of Cardiology, Smidt Heart Institute
Why it’s important – The results have immediate translational implications for patients undergoing cardiac function imaging and broader implications for the field of cardiac imaging. When developed in the right way, artificial intelligence offers the opportunity to improve the quality of echocardiogram readings as well as increase efficiencies in the time and effort spent by busy cardiologists and sonographers alike.
How Vibrant Gastro’s vibrating pill treats chronic constipation without drugs
The swallowable, vibrating, Vibrant capsule has won FDA marketing authorization as a new treatment for chronic idiopathic constipation. Jim Hammerand reported on the development in Medical Design and Outsourcing. The drug-free capsule is indicated for adults with chronic idiopathic constipation who have not experienced relief despite using laxative therapies for at least one month. Vibrant Gastro says its technology is built on the premise that our circadian rhythm — commonly referred to as our “biological clock” — plays an essential role in our biological digestive process. The Vibrant pill’s mechanical vibration of the colon can synchronize an out-of-sync patient and improve bowel movements.
To start the treatment, a patient with a prescription places the Vibrant capsule in the accompanying multi-use activation pod device to activate the capsule, then swallows the capsule with a glass of water. The capsule passively moves through the digestive system to the colon, where it vibrates to mechanically stimulate the colon and resynchronize the biological clock to improve daily bowel movement bio-rhythm.
Why it’s important – The pivotal trial’s outcomes demonstrated superiority with respect to both the proportion of patients with at least one additional complete spontaneous bowel movement per week compared to baseline, 40.51% in the treatment arm, compared to 22.92% in the control arm, a difference of 17.6% (chi-square p-value = 0.0011) and at least two additional complete bowel movements per week, 23.42% in the treatment arm, compared to 11.81% in the control arm, a difference of 10.0%. The treatment is for chronic constipation, defined as fewer than three bowel movements per week, with symptoms persisting for weeks or months. The new device will be available in select U.S. states early next year, with gradual national expansion throughout 2023.
An international team sets out to cure genetic heart diseases with one shot
Called the CureHeart Project, the team — which includes researchers from Oxford, Harvard, Singapore’s National Heart Research Institute, and pharma multinational Bristol Myers Squibb — will develop therapies for inherited heart muscle conditions, which impact millions and can cause sudden death, including in young people. B. David Zarley posted an article on the project in Freethink online. They plan to tackle the problem using two types of targeted techniques, called base editing and prime editing. Many of the mutations seen in these patients come down to one fateful letter in their DNA code. That has raised the possibility that researchers could alter that one single letter and restore the code so that it is now making a normal gene with normal function. When the cause is a fault in one copy of a gene, which stops the healthy copy from working, they want to switch off the faulty copy; their second approach will be to edit the broken gene sequence itself to correct it. They’ve demonstrated both methods in mouse models.
“Our goals are to fix the hearts, to stabilise them where they are and perhaps to revert them back to more normal function.”
Christine Seidman, professor of medicine and genetics at Harvard Medical School and co-lead of CureHeart
Why it’s important – Inherited heart muscle diseases cause abnormalities in the heart, which are passed on through families. People of any age can fall victim to sudden heart failure and death, and there is generally a 50/50 chance of passing the problem along to their children. Many different mutations can cause them, but in total, they affect one out of every 250 people worldwide. By using prime and base editing — very precise tools for editing DNA — the team hopes to develop an injectable cure to repair faulty heart genes.
NeuraLight is making neurological diagnostics more precise
Hillel Fuld in Fast Company brings us this article on NeuraLight, a VC-backed startup that aims to digitize neurological evaluation and care. Cofounded by former Chorus.ai president Micha Breakstone, NeuraLight’s AI-driven platform integrates multiple digital markers to accelerate and improve drug development, monitoring, and precision care for patients with neurological disorders. The idea is that if you improve the diagnosis process, you can intervene earlier, improving prognosis, and often, as in the case of relapsing-remitting MS, even changing the course of the disease. NeuraLight recently launched a trial in collaboration with a publicly traded pharma company, NeuroSense. The trial aims to establish whether NeuraLight can predict the progression of ALS using their platform.
“After watching two of my grandparents battle with Alzheimer’s and Dementia, I began studying these diseases in depth, and it soon became clear to me that cures for these diseases are extremely hard to discover because they lack robust objective and sensitive measures.”
Micha Breakstone, Co-founder, NeuraLight
Why it’s important – Research spanning several decades and published in hundreds of peer-reviewed papers has established that oculometric markers—that is, biomarkers extracted from measuring micro-movements of the eye—can be used to diagnose and predict the progression of a wide range of neurological disorders. These digital markers serve as a reliable proxy for currently used clinical endpoints. They will provide an accurate snapshot of a person’s neurological status, enabling pharmaceutical companies to introduce smart phenotyping, reduce misdiagnosis, and accurately and sensitively measure disease progression.
AI could help deliver greater success at birth
With machine learning, Mayo Clinic researchers found it is possible to predict how patterns of changes in pregnant patients who are in labor can help identify whether a vaginal delivery will occur with good outcomes for mom and baby. Andrea Fox reports on the research in her article in Healthcare IT News. According to the published study, of the 228,438 delivery episodes in the database, there were 779 antepartum, intrapartum, and postpartum variables. The algorithms analyzed data known at the time of admission in labor – patient baseline characteristics, the patient’s most recent clinical assessment, and labor progress from admission. Researchers used 66,586 records in the prediction models, where 14,439 deliveries (21.68%) reported poor labor outcomes.
Why it’s important – The ability to change the shape of and open the birth canal to make way for a baby to be born varies from patient to patient. When obstetricians analyze contractions, as well as fetal heartbeats, they assess the progress of labor and make recommendations on levels of care for the medically risky delivery process of birth. The use of the models could result in more individualized clinical decisions using the baseline characteristics of each patient, and they could also be a tool to help remote physicians and midwives transfer rural or remote patients to the appropriate level of care.
Study trains AI to predict optimal anti-seizure meds for new epilepsy patients
In other news on the AI front, Adam Ang brings us this article in MobiHealthNews. An international study led by Monash University has done what could be the world’s first demonstration of an AI model that can predict the optimal anti-seizure medication for newly diagnosed epilepsy patients. The research team has trained a deep-learning prediction model using clinical information from around 1,800 patients in five health care centers in Australia, Malaysia, China, and the United Kingdom. The model is designed by the Monash Medical AI Group and is trained using Monash’s MASSIVE computing facility. Findings from the study, which was published in the journal JAMA Neurology, showed that the AI model has a “modest” 65% accuracy in predicting the best anti-seizure medication.
Why it’s important – About 70 million people worldwide have epilepsy. Until now, there has been a lot of guesswork and experimentation by doctors on which anti-seizure drugs their patients will respond to. Currently, the predictive model is intended for adults with new-onset epilepsy who are about to begin their medication. The AI model still has a modest prediction accuracy and is slated for a wider clinical trial soon.
Walgreens finalizes CareCentrix majority stake acquisition
Walgreens Boots Alliance has completed its majority share acquisition of CareCentrix, a home-centered platform that coordinates care to the home for health plans, patients, and providers. Jeff Lagasse provides the details in his article in Healthcare Finance. The partnership was pursued primarily because of the belief that it would better address the needs of people with complex or chronic conditions as they transition out of the hospital. CareCentrix touted its analytics capabilities, emphasizing the transition to home-based care that could potentially reduce hospital readmissions and improve patient satisfaction and outcomes.
Why it’s important – Healthcare services delivered after discharge, including care delivered in the home, are one of the fastest-growing segments in healthcare today. Caring for patients from the hospital to the home represents more than $75 billion in annual healthcare costs for payers, providers, and patients, according to Walgreens. This is the latest example of retail pharmacy and big tech companies moving more aggressively into primary care and home health. After Labor Day, we should hear which company has been successful in its bid to purchase Signify Health. The three bidders in the mix are CVS, Amazon, and United Healthcare. It will be interesting to see who emerges as the top choice.
Top 10 Research Topics To Pursue In Digital Health
Finally, this article from Dr. Bertalan Mesko and his team at The Medical Futurist Institute offers some insights to anyone who is willing to dive deep into digital health but is unsure about the best direction to take. They’ve compiled a list of ten research topics we believe are promising for anyone wishing to find their calling in digital health research.
Why it’s important – I always find these posts interesting and thought-provoking. The topics suggested all fit well into the evolving digital health landscape and would benefit from additional research.