People are living longer, driving the percentage of those over 65 to unprecedented highs. Today, 8.5 percent of people worldwide are aged 65 and over; this will double to nearly 17 percent by 2050.
With this coming age wave, there will not be enough resources to continue with current caregiving models. Higher costs and a declining number of caregivers threaten the quality and availability of care to this growing demographic.
However, despite the challenging demographics, technologies like the Internet of Things (IoT) and Artificial Intelligence (AI) can be applied to help enhance overall elder well-being and enable improved care at lower costs and with reduced human effort.
Data from the sensored homes, combined with that from wearable sensors, was analyzed to provide insight on an elder’s daily life—when he/she sleeps, cooks, exercises, bathes, toilets and connects with family and friends. These activities are key indicators to understanding how well an elder is aging-in-place and guides the appropriate level of required care.
Machine learning was then used to detect daily behavioral patterns and anomalies within this data, thereby providing doctors and caregivers with baseline norms and alerts when deviations occurred.
These deviations could signify merely a temporary change in behavior or emerging problems such as an increased likelihood for falling or illness.
When correlated with patient claims data, hospital readmission data, and activity patterns, new insights for risk mitigation emerged. This provided opportunities for putting preventative measures in place—taking eldercare to the next level.
Improving decision making around levels of care
As an elder’s physical and cognitive capabilities diminish, care providers, family and even the elders themselves worry about the increased risks of serious or catastrophic events. This concern often leads elders to transition to higher levels of care and each transition becomes exponentially costlier.
By monitoring daily activities and tracking changes among elderly patients, doctors and caregivers can make more informed decisions about when these transitions should take place, and what other types of measures can be implemented in the interim to help extend time living at home.
Extending care resources while enhancing care provision
The Avamere and IBM project found that insights gleaned from the data collected helped improve patient and resident quality of life, enhanced operational efficiency and contributed to lowering the cost of care.
Predictive modeling based on this data helped with early detection to prevent expensive ER visits and costlier post-acute care, as well as helped identify vulnerable patients who may have a propensity for hospital readmission.
By applying AI and IoT to eldercare systems, doctors and caregivers will be able to better provide care for and ensure the protection of our growing aging population—giving greater peace of mind to family and the elderly themselves.
See how Avamere and IBM have conducted a first of its kind project using real-time data from instrumented senior living residences and artificial intelligence to proactively monitor the health and well-being of older adults:
Slumping oil prices and increasingly difficult-to-extract oil pose a major challenge to companies in the oil and gas industry. At Kuwait Oil Company, one way that we’re pursuing cost optimization is by embracing intelligent, Internet of Things (IoT)-based enterprise asset management (EAM) technology – not just for oil extraction and drilling, but in all our […]
France has a long history as a pioneer in payment fraud prevention. It was the only nation that introduced Chip and PIN countrywide in 1992 . This action made France the first all-smartcard country. And it reduced fraud in France to almost zero overnight. For decades. But criminals became more sophisticated and fraud losses returned. […]
Machine learning and AI are all about data. We give AI-powered systems massive amounts of data to ingest and analyze, and then we trust the results. But I want to know how we can ensure the integrity of those systems, from the algorithms to the data sources. Solving the AI data-integrity issue I believe the […]