Since the COVID-19 pandemic, machine learning (ML) has been thrust into the spotlight. From streamlining operations to driving research and development amidst a volatile and uncertain work environment, organizations turned to ML to remain competitive and gain an advantage. In the healthcare industry, it has enabled hospitals and health systems to cope with a number of unique challenges, an unprecedented surge in contact tracing and syndromic surveillance efforts.
According to a recent IDC study, 50 percent of hospitals already have an artificial intelligence (AI) framework in place, with the remaining respondents indicating they will adopt one within 24 months. Despite the rising rate of adoption of ML, experts continue to speculate whether we have reached the full potential of the science in healthcare or if its benefits have been exaggerated. ML made progress in some areas but didn’t quite meet expectations in others.
While many have traditionally believed ML to be a ‘black box’, the technology has become increasingly explainable, leading to greater credibility for directly helping patients. This year will see ML continue to make advancements across different areas of healthcare, including triage and administration.
In the year to come, we expect to see the use of ML tools in triage practices grow. ML will increasingly be used in different aspects of the patient’s chart, to help make better decisions. Since the pandemic emerged, smarter decision-making and personalized care have jumped to the forefront of healthcare priorities. As an example, Epic developed an ML model to scan health records, identify patient deterioration and alert doctors automatically before patients need an ICU admission in order to better serve patients with life-threatening problems. The use of ML tools in triage can more accurately deliver quality care to patients by improving the work of providers.
At the onset of COVID-19, healthcare organizations also had to adapt to a remote environment. Between March and May 2020, three million online health consultations took place in Belgium. As an excellent pattern recognition tool, ML functions will also be used to make healthcare administrative tasks smarter as we continue on past the pandemic, with new practices in place and lessons learned.
Data: The Gas That Makes ML Go
Every ML project suffers from the same problem: the lack of quality data. It will be essential to prioritize healthcare data interoperability and data cleansing in 2021, so that it’s truly useful in ML projects. With the use of HL7 FHIR®-based APIs, data sharing can be made easier, allowing for greater speed of innovation and more actionable insights from data sets. One of the ways that ML can successfully overcome the hype in healthcare is to make data healthy, so that ML algorithms can deliver high quality results.
Expectations for ML have grown over the years, and in 2021, we should expect to see the gap between expectations and reality shrink. From ML-based triage to administration, clean data is helping organizations meet their goals for innovation.
About the author
Jan has 37 years of experience in IT infrastructure, IT security and successfully selling complex solutions and data platforms. Today, his main focus as a trained IT analyst is to guide companies to ‘Healthy Data’.