An executive working in the artificial intelligence (AI) space, Shourjya Sanyal, PhD, chief executive officer of Think Biosolution, said the rapid aging of the worldwide population is opening the door to the use of AI to help care for people with chronic diseases as health care delivery adapts to increased demands. In an article written for Forbes magazine, he noted the number of people aged 80 years and older will rise from the current 14.5 percent of the U.S. population (65 and older) to more than 20 percent by 2030, with similar patterns seen across most of the rest of the Western world. As a result, health care delivery pathways "need to be readjusted, keeping in mind the prevalence of chronic diseases, comorbidities and polypharmacy requirements of the elderly and geriatric patients." There are also specific diseases related to this age cohort as well, like atherosclerosis, osteoporosis, cardiovascular diseases, obesity, diabetes, dementia, and osteoarthritis that require "quick diagnosis and continuous supervision by a professional caregiver." Added to the mix is the growing shortage of physicians and caregivers, Sanyal said.
From the surgery robot in the operating theatre to the care robot that looks after you at home, robots are beginning to make their way into healthcare across the globe, and their potential to cut costs and improve results for patients means that soon they could be as much a part of hospital practice as bedpans and blood pressure cuffs. Surgeons are one of the first medical specialties to welcome their robot overlords: in the NHS, surgical robots can already be found assisting with a range of operations, including urology, colorectal, and prostate procedures. These robots -- which are made up of a set of arms wielding cameras, lights and medical instruments -- are controlled by a surgeon sitting at a console who is then able to control the actions of the robot's arms with great precision. Using robots means surgeons can make smaller incisions, reducing blood loss and pain for patients, which can mean a faster recovery time and a shorter stay in hospital. That's good news for the patients, who can get back to their normal life quicker, but also good news for the NHS, which has fewer infections and complications to deal with, and sees beds freed up faster.
It's been established for a while now that we are already living in the future. Nearly everything is automated and cars are practically driving themselves. Life isn't always a terrifying dystopian nightmare come true however. There are so many ways the advancement in technology is making our lives easier and better. Smartwatches are a great example of this.
Every day sees strides across the field of artificial intelligence, and healthcare is just one of the many industries looking to smart automation as a means to reduce burden and improve results. The last year in particular has brought a wealth of new healthcare focused software tools to the forefront, and as such has ignited debate on how these algorithms are being reviewed and regulated by the FDA. "FDA is lagging in the production of guidance to explain its approach for these newer products. This is a problem, because Commissioner Gottlieb himself in a blog post noted well over a year ago that individual decision-making by FDA is not enough for digital therapeutics to thrive," Bradley Merrill Thompson, a lawyer at Epstein Becker & Green who also leads CDS Coalition, an industry group, wrote in an email on the subject. "Industry has been asking since 2015 for better guidance on the use of software-based algorithms in connection with drug administration. The commissioner, starting in April 2018, has been promising new guidance focused on the use of software with drugs, and in fact reiterated that promise only a couple weeks ago. But the concern is that the new guidance may not be focused on the issues of greatest concern to industry. We shall have to wait to see." Thompson also noted that while the agency is relying on its 510(k) regulatory pathways in the meantime, the heterogeneity of these nontraditional tools has resulted in an ever-growing number of De Novo clearances and device classifications.
A machine learning (ML)-based risk calculator developed to assess an individual's long-term risk for atherosclerotic cardiovascular disease (ASCVD) identified 13 percent more high-risk patients and recommended unnecessary statin therapy 25 percent less often than standard risk assessment tools in initial tests, researchers reported in the Journal of the American Heart Association. First author Ioannis A. Kakadiaris, PhD, and colleagues with the Society for Heart Attack Prevention and Eradication (SHAPE) wrote in JAHA that the current gold standard for ASCVD risk assessment--the American College of Cardiology and American Heart Association's Pooled Cohort Equations Risk Calculator--is flawed in its accuracy. "Studies have demonstrated that the current U.S. guidelines based on the ACC/AHA risk calculator may underestimate risk of atherosclerotic CVD in certain high-risk individuals, therefore missing opportunities for intensive therapy and preventing CVD events," Kakadiaris and coauthors said. The existing approach to CVD risk assessment desperately needs an overhaul." According to a consensus report from SHAPE, comprehensive ASCVD risk assessment should include evaluation of plaque, blood and myocardial vulnerability factors if it's going to be anywhere near accurate.
While these bring tremendous benefits, AI also raises concerns, ranging from security, to human rights abuses. Speaking in Paris last weekend, Secretary-General Antonio Guterres praised AI but cautioned that "technology should empower not overpower us" and that the world needs to set policies that contain unintended consequences or malicious use of frontier technologies. UN News asked Eleonore Pauwels, Research Fellow on Emerging Cybertechnologies at United Nations University (UNU), about AI – what it is, how it works, and what she sees happening in the next few years. In its current form, called "deep learning", AI is a growing set of autonomous and self-learning algorithms she told us, capable of performing tasks it was commonly thought could only be done by the human brain. At its core, AI produces powerful predictive reasoning while minimizing the noise from unpredictable and complex human behaviour.
Timely prediction of clinically critical events in Intensive Care Unit (ICU) is important for improving care and survival rate. Most of the existing approaches are based on the application of various classification methods on explicitly extracted statistical features from vital signals. In this work, we propose to eliminate the high cost of engineering hand-crafted features from multivariate time-series of physiologic signals by learning their representation with a sequence-to-sequence auto-encoder. We then propose to hash the learned representations to enable signal similarity assessment for the prediction of critical events. We apply this methodological framework to predict Acute Hypotensive Episodes (AHE) on a large and diverse dataset of vital signal recordings. Experiments demonstrate the ability of the presented framework in accurately predicting an upcoming AHE.
We develop a prediction-based prescriptive model for learning optimal personalized treatments for patients based on their Electronic Health Records (EHRs). Our approach consists of: (i) predicting future outcomes under each possible therapy using a robustified nonlinear model, and (ii) adopting a randomized prescriptive policy determined by the predicted outcomes. We show theoretical results that guarantee the out-of-sample predictive power of the model, and prove the optimality of the randomized strategy in terms of the expected true future outcome. We apply the proposed methodology to develop optimal therapies for patients with type 2 diabetes or hypertension using EHRs from a major safety-net hospital in New England, and show that our algorithm leads to the most significant reduction of the HbA1c, for diabetics, or systolic blood pressure, for patients with hypertension, compared to the alternatives. We demonstrate that our approach outperforms the standard of care under the robustified nonlinear predictive model.
First, you are strapped from the chest upwards on to the table, with your feet hoisted into stirrups. The table is swung down backwards, so you are tilted, head-down, at an angle of 45 degrees. Then a machine, known by some surgeons as'the 800lb gorilla', can get to work. It sounds so medieval, but this is the most modern of surgical techniques -- robotic surgery. The extraordinary posture, known as the steep Trendelenburg, is necessary to position the patient precisely so the robot arms can reach inside them.