Machine Learning Times
Machine Learning Times
EXCLUSIVE HIGHLIGHTS
How Generative AI Helps Predictive AI
 Originally published in Forbes, August 21, 2024 This is the...
4 Ways Machine Learning Can Perpetuate Injustice and What to Do About It
 Originally published in Built In, July 12, 2024 When ML...
The Great AI Myth: These 3 Misconceptions Fuel It
 Originally published in Forbes, July 29, 2024 The hottest thing...
Where FICO Gets Its Data for Screening Two-Thirds of All Card Transactions
 Originally published in The European Business Review, March 21,...
SHARE THIS:

10 years ago
6 ways providers can employ predictive analytics

 

For more case studies in predictive healthcare, see Predictive Analytics World for Healthcare, October 6-7, 2014 in Boston.

Six use cases highlight how healthcare could harness big data to improve care and cut costs for high-risk patients, according to a new article published this month in Health Affairs.

David Bates, senior vice president for quality and safety at Boston-based Brigham and Women’s Hospital, and co-authors present the following six scenarios as offering strong opportunities for employing predictive analytics:

  1. High-cost patients
  2. Readmissions
  3. Triage
  4. Decompensation (when a patient’s condition worsens)
  5. Adverse events
  6. Finding the best treatment when a disease affects multiple organ systems

Other industries have successfully used predictive models created from their big data stores, the authors say, with Amazon’s product recommendation system cited as an example. However, despite the data being captured and stored in electronic health records, an array of challenges so far have stood in the way of using that data effectively.

Among their insights:

  • While analytics can help identify high-risk patients, those at low risk can be identified as well to make efforts to reallocate resources more effective
  • An array of new monitors can alert staff in real-time to signs that a patient’s condition is worsening; one example fits under the patient’s mattress, monitoring respiration, pulse and movement and sends alerts to an on-duty nurse’s smartphone
  • Analytics have the potential to predict which patient may suffer an adverse drug event and to detect events early, using vital signs, genomic, lab and other data

However, the authors see the greatest potential for better targeting treatment for people with diseases affecting multiple organs. They point to the National Patient-Centered Clinical Research Network (PCORnet)–the planned “network of networks”–as a means to integrate data from silos of single-disease registries.

They urge federal investment in research into analytics and big data; a clearer regulatory stance at the Food and Drug Administration in that area; a strengthening of incentives for providers to control costs; and federally defined privacy parameters for use of big data. They also point out that HIPAA doesn’t adequately address privacy of data amassed from various sources.

A recent White House report made a similar point on HIPAA, saying more protections may be needed in the electronic age.

The Federal Trade Commission also recently called for more transparency in how data brokers compile and use consumer information.

To learn more:
– read the abstract

By Susan D. Hall, writer & editor, IT Business Edge
Originally published at /www.fiercehealthit.com

Leave a Reply