The Impact of Machine Learning on Health Care Delivery and Quality: The Wounded Machine, a Tale of being Ill
Ontario spends more than $1.5 billion dollars a year on the treatment and management of wounds
Wounds often have a widespread etiology across multiple disease states, making wound care an orphan clinical specialty. While the delivery of wound care has attempted to evolve into a true clinical specialization over the past few decades, care is often varied and fragmented. With an aging population and increasing health challenges, such as the burgeoning diabetic epidemic, the need for innovation is greater today than ever.
Advancements in machine visioning and machine learning have created a significant opportunity for innovation in this field. Industry-best technology and algorithms can facilitate the standardisation of wound assessment and documentation, while providing insight into the delivery of quality initiatives.
This approach should be adopted to empower health care providers to implement highly compliant, best-practice wound care programs across the care-continuum, driving clinical and operational resources.
This technology-driven approach provides a means to automate and de-skill some components of wound assessment and care. This is imperative globally as healthcare systems struggle with both resource and budget limitations. Further, given the challenge in mandating wound care as a clinical specialty, the delivery of care by “less skilled” resources is essential.
The adoption of machine learning for the delivery of wound care has shown significant quality and ROI benefits for health systems across North America. Focus in this orphan clinical area has identified a significant unmet need with significant benefits for both the healthcare providers and “payors” alike. Not only will big data and machine learning provide a solution to the healthcare challenges but also an insight into the problem to allow policy to drive system-wide change moving forward.
Session address:
1 Richmond Street West
