Links To Machine Learning Applied To Medicine

  1. Machine Learning Applied To Revenue Cycle Management – This article gives a good overview of how Machine Learning might be applied to the decision of how to effectively manage a list of patients that owe money. Instead of having staff call each person X number of times to get them to pay (highly inefficient when they are calling thousands of patients a month), Machine Learning helps to identify the patients with highest propensity to pay. This uses factors such as income level, education level, past payment delay, etc.
  2. Machine Learning Applied To Clinical Pathology – This company is using Machine Learning to augment the expertise of the Clinical Pathologist, who has to review many biopsies each day and make a determination of whether cancer is malignant or benign. The company provides tools around a pathologist’s workflow. Machine Learning is helping humans to do what they are best at, the real core analysis.
  3. Google’s Latest Efforts To Help Healthcare – Levi Thatcher, Director Of Machine Learning describes the benefits of how a company like Google can utilize their computing power for Machine Learning, but he also identifies the shortcomings in this article.
  4. Ayasdi – Ayasdi discusses automation in 3 areas for managing Value-Based Healthcare. Ayasdi’s suite of intelligent applications solve these mission critical challenges through intuitive, powerful applications – each drawing on powerful and differentiated AI platforms.
  5. Philips Healthcare discusses how AI helps to sift through large amounts of data to assist medical professionals, not replace them.
  6. Dr. Ed Corbett also discusses the use of machine learning as a tool to replace the need to sift through an immense amount of data while allowing the physician to focus on the art of medicine. See this article here.
  7. Inference Analytics – Despite the focus on Electronic Medical Records, unstructured narratives form a bulk of the data stored in health systems, for the most part these narratives remain untapped by care providers. Inference Analytics uses deep learning and artificial intelligence to understand and respond to these narratives.  There is unstructured data that healthcare organizations have stored away in documents, notes or even within databases. There is a tremendous opportunity to use this data to drive efficiencies that improve health outcomes and reduce risk for providers.
  8. American College Of Radiology Data Science Institute™ – The American College of Radiology Data Science Institute™ is collaborating with radiology professionals, industry leaders, government agencies, patients, and other stakeholders to facilitate the development and implementation of artificial intelligence (AI) applications that will help radiology professionals provide improved medical care.