What kind of AI techniques are used in healthcare?

Healthcare organizations are using a variety of AI techniques to extract insights from structured and unstructured data. Natural language processing (NLP) and machine learning (ML) can be used to identify important pieces of information within medical text for a variety of clinical and administrative applications. Deep learning (DL) can be used to process large datasets and surface common trends across patients populations. Provider organizations are also starting to employ machine vision techniques to analyze imaging for diagnostic purposes.

What’s the difference between natural language processing (NLP) and machine learning?

Natural language processing (NLP) is a set of techniques that help computers process language the way humans do. This includes extracting meaning from written text or speech, and generating readable, grammatically correct original content. Machine learning (ML) is a type of artificial intelligence that focuses on automated knowledge acquisition. The goal of machine learning is to use algorithms to learn, recognize patterns, and solve problems without explicitly programmed instructions.

What kinds of healthcare data can AI analyze?

Artificial intelligence techniques have been largely used to analyze structured data—that is, data that is clearly labeled and tagged in a system so that a computer program can make sense of its composition. However, the vast majority of healthcare data is unstructured—such as the free-form text that makes up doctor’s notes in a clinical record, or scanned documents containing words or images that get uploaded to an EHR. Unstructured data makes up 80% of all healthcare data. While it’s more difficult to analyze with AI, it ultimately yields greater value since it contains more detail and nuance than a typical structured dataset.

Healthcare AI Platform for Risk Adjustment and Quality

The Apixio Platform

Every year, 1.2 billion clinical documents are generated in the U.S., but most of this data goes unused in the provision of healthcare. Without the right technology to transform PDF and image documents into machine-readable text, and well-trained models to mine these documents for relevant patient and clinical insights, organizations aren’t making the most of their data.

At Apixio, we recognized an opportunity for artificial intelligence to unlock unstructured text and help plans and providers use the data they already have to improve risk adjustment, quality measurement, and clinical documentation. The Apixio Platform is the foundational technology suite that allows us to surface targeted information from healthcare documents to inform operations and care delivery.

Step 1: Data Acquisition by InfoStream

We use a secure extraction process to pull and encrypt PDF, image, and EHR documents such as patient charts, medical and pharmacy claims, eligibility data, and more. These documents are then securely transmitted to our Data Loader for processing and analysis.

Step 2: Data Processing

Our ETL workflow loads, validates, and processes documents so they can be run through our proprietary machine learning models. During this stage, we use our optical character recognition (OCR) pipeline to translate the data in image files into machine-readable text.

Step 3: Data Analysis

Processed data is stored in individual Apixio Patient Object Models (APOMs), which include patient diseases, medications, procedures, biometric values, and derived information from prior analyses. We then apply proprietary data classifiers and predictive models to generate insights.

Step 4: Results Sorting

Insights from our machine learning models are sorted and sent through configurable workflows to our applications. Results are tuned per client, per project to ensure maximum relevancy.

Step 5: Application Review

Results are served up for review in our risk adjustment, quality measurement, and prospective solutions. Feedback from expert users is fed back into our machine learning algorithms to continually refine our approach and improve results.

View Next Step

Apixio Patents

At Apixio, we’ve been developing innovative approaches to addressing some of healthcare’s most challenging data problems since 2009. Our team has been issued a number of patents for the proprietary AI techniques and workflows used to deliver our industry-leading healthcare analytics solutions. These patents fall into three primary categories:

Medical Information Navigation: Systems that collect, clean, and normalize data from a variety of sources and store them in an aggregated clinical patient phenotype. These systems automatically map patient data into medical ontologies, index and rank the data, and make it accessible in search and workflow applications.
Medical Coding Systems: Risk adjustment and care quality applications that use data to optimize coding workflows, monitor coder performance, and detect overcoding. Additionally, these systems also support the creation of a coder marketplace.
Patient Data Utilization in Clinical Setting: Maintenance of longitudinal patient phenotypes and utilization of these phenotypes for clinical applications.

Issued Patents

Patent Title	U.S. Patent Number
Medical Information Analysis with De-Identification and Re-Identification	8,898,798
Event Stream Platforms Which Enable Applications	9,032,513; 9,639,662
Intent-Based Clustering of Medical Information	9,043,901
Optimizing and Routing Health Information	9,703,927
Medical Referral Analytics	10,061,894
Medical Information Navigation Engine (MINE)	10,176,541; 10,319,467
Mining Aggregated Clinical Documentation Using Concept Associations	10,453,574
Efficient Handling of Medical Documentation	10,482,999
Customized Annotation of Medical Information	10,580,520
Sorting Findings to Medical Coders	10,600,504
Determination of Patient True State for Personalized Medicine	10,629,303
Determination of Patient True State for Risk Management	10,614,915
Coding Health Records Using Weighted Belief Networks	10,614,913

Testimonial

The efficiencies Apixio brings to our reviews are just incredible. Their machine learning technology leads you to the right information you need for coding.

Andrew Bloschichak MD, MBA

Senior Medical Director, Government Programs - Capital Blue Cross

Testimonial

The coding team was wonderful to work with, and incorporated our specific coding guidelines when working on our project. When they noticed a trend in what we were rejecting, they shared a Coding Clinic we were unaware of for clarification on how to code the scenarios.

Josh Weisbrod

VP of Risk Adjustment

Testimonial

By using Apixio, we’re improving our auditing bandwidth and enhancing the ability of our coders to focus on other chart audits and other projects that we couldn’t do before.

JoAnn Hayden

Scripps Health Plan Services

Case Study