Part 2: Machine Learning Making Waves in Healthcare
As the complexity and amount of data rise in healthcare, payers, providers, and life science companies are increasingly employing artificial intelligence (AI) to provide quality care to patients. This is because computers and algorithms can scrub colossal amounts of data much faster and more accurately than human scientists or medical professionals, unearthing patterns and predictions that enhance disease diagnosis, inform treatment plans, and enhance public health and safety.
This is a crucial time for AI and machine learning adoption in healthcare. The Covid-19 pandemic has strained healthcare systems with rising demands for care, an unprecedented number of hospitalizations, and staffing and supply shortages — exposing how fragile our healthcare system truly is. In light of this, AI and machine learning present great potential to relieve some of the burdens on healthcare workers and healthcare systems at large.
Some healthcare and technology innovators are already collaborating to experiment with AI and machine learning. In part one of this series, we talked about how AI and machine learning technology are being tapped to improve clinical trial safety and efficacy, epilepsy care, and smoking cessation solutions. In this blog, we’ll explore how mobile devices, robotic surgeries, and wearables are all utilizing machine learning to advance healthcare delivery.
Crowdsourced Medical Data-Based Applications
There’s a clear rush to source data from a range of mobile devices in recent years for a range of healthcare applications. This race for consumer data collection is ultimately likely to provide researchers and other healthcare industry stakeholders with access to an ever-expanding arsenal of information and knowledge that can potentially help combat severe diseases and other conditions.
IBM Watson, for one, is placing great focus on grasping as much health data as possible. In 2016, IBM purchased Truven Health Analytics, which had data on the cost of treatment for over 200 patients, for a lump sum of $2.6 billion. Using this patient data with Watson’s artificial intelligence software, Watson Health aims to work as a specialized digital assistant to physicians and health administrators to improve care and curb costs. In 2018, IBM teamed up with Medtronic to develop a digital solution called Sugar.IQ to help patients makes sense of their diabetes and insulin data in real-time.
A similar effort can be witnessed in Apple’s ResearchKit, which has its sights set on helping treat Parkinson’s disease and autism via interactive apps that assess the users’ condition over prolonged periods of time.
Robotic Surgery
The da Vinci Surgical System has understandably gained plenty of attention for its ability to support surgeons in skillfully manipulating robotic limbs in surgeries performed in tight spaces and offering a lighter yet more steady hand than humans would normally be able to maintain on their own.
Robotic surgery solutions not only employ machine learning but also machine learning-assisted computer vision, which is necessary for the accurate determination of specific body parts and distances. Machine learning is also at times utilized to continuously steady the motion of robotic limbs that are directed by human operators.
Personal Genetics
AI and machine learning are also critical to the understanding of how our DNA affects our lives. While the human genome has been completely sequenced and can now be properly read and edited, our comprehension of the majority of what the genome can tell us remains lacking.
Machine learning algorithms, such as those embedded in such systems as Google’s Deep Mind, can help overcome this gap with their unparalleled ability to detect the finest patterns and variations. These algorithms make it possible to effectively process and apply patterning cognition to nearly unfathomable volumes of data, including patient records, treatment regimes, diagnostic imagery, and clinical notes — a task beyond the capabilities of unaided human researchers.
Deep Genomics for one is making significant headway in developing a system that allows the interpretation of DNA. By predicting the molecular effects of genetic variation, Deep Genomics, and the data they’re accumulating can determine how hundreds of millions of genetic variations can impact genetic code.
The day we achieve an improved comprehension of human DNA is the day in which we’ll be able to deliver personalized insights based on individual biological dispositions and personalized medicine. This capability will usher in an age of personalized genetics allowing people to achieve greater control of their health via greater information on their bodies than ever before possible.
AI-Powered Wearables
Recent advances in mobile health technology have transformed how physicians, hospitals, and nursing home facilities capture and analyze data. Ordinary accessories like watches and glasses have acquired new utility in the 21st century with the rise of machine learning. By applying machine learning algorithms to wearable devices, remote patient monitoring (RPM) technologies empower and aid healthcare professionals in providing quality care in a way unlike ever before.
Not only can providers now unearth health trends (e.g., deteriorating health) from massive quantities of data, but they can now utilize the real-time data to predict health conditions and improve their diagnoses and treatment plans. Somatix’s patented gesture detection technology is one example where wearables have combined with AI and machine learning to produce powerful predictive analytics, clinical insights, and critical alerts and reminders for health interventions.
Somatix’s Safebeingᵀᴹ algorithms remotely and passively detect physical and emotional indicators to generate insights on risk factors for adverse events, activity levels, sleep quality, poor medication compliance, falls, dehydration, irregularities, and more. SafeBeingᵀᴹ’s insights and predictions are then presented to providers through a dashboard that allows them to manage all their patients on one platform.
Powerful integrated digital health tools like SafeBeingᵀᴹ allow seniors, caregivers, and healthcare professionals to identify changes in activity and wellbeing before a loved one’s health condition deteriorates. In a study conducted by Accenture✎ EditSign, researchers found that eight out of ten physicians see RPM as highly effective, particularly in the process of earlier detection.
With some like Accenture asserting that RPM will be the third pillar of the therapeutic structure✎ EditSign in the future, it is no surprise that major healthcare players are increasing their investments in the wearable and connected device markets. For example, Best Buy spent nearly $400 million to acquire Current Health and Google acquired Fitbit for $2.1 billion. Only time will tell how quickly wearables are fully integrated into the healthcare sector, but in the meantime, the algorithms will just keep learning.
