MIDAS: Decision Grade Data

Power your AI applications with MIDAS structured data.
MIDAS turns unstructured patient data into structured data that seamlessly matches your workflows for faster, more accurate decision-making. Employing customized AI engines along with human oversight, MIDAS comes with the legacy ReleasePoint client service. All of which makes ReleasePoint the industry’s essential partner.

The latest tool for decision-makers.

With a combination of proprietary and customized AI tools validated by our experienced team, MIDAS enables you to re-imagine how you work with patient health data.
Video Player

Power your AI applications with MIDAS structured data.

MIDAS is the industry’s first platform for the extraction, curation, and delivery of structured medical information from traditional image-based medical records.

Customizable to optimize your workflows.

As with all of the ReleasePoint product suite, our implementation team will customize MIDAS to meet your process requirements.
Video Player

Data Extraction

MIDAS consistently delivers DECISION GRADE structured data from unstructured medical information at Scale.
The key to the quality of MIDAS data is cognitive review, a crucial step in which trained data specialists evaluate, contextualize and approve the data elements identified by the NLP automation, bringing depth and accuracy to the extracted medical Data.

Image Received

The PDF of the patient’s medical history is supplied, either by the customer via API, or through the ReleasePoint Record Retrieval process. A high-quality PDF is the starting point for the MIDAS process.

Data from Image

MIDAS sends the medical record image through our multi-pass OCR process, which creates a high-quality data version of the original medical document.

Cognitive Curation

Technology alone cannot solve this problem. Commercial NLP can only provide limited value because it cannot reliably decode the multitude of formats in world of image-based medical information.

Advanced AI

Following the curation process, MIDAS engages proprietary and commercial workflows, providing advanced text analysis and data augmentation through integration with Amazon Comprehend AI.

Delivery

Output is delivered through the MIDAS API in JSON format, ready for integration with automation tools, decision support platforms, medical data analytic systems, and other technology applications.

Data Gap

Many technology solutions have entered the market. However, technology cannot provide the context that makes structured data so valuable.
Data without context cannot be relied upon to support research outcomes, underwriting and claims decisions, or disability determinations.

While technology can successfully identify the medical condition “lung cancer,” it cannot reliably indicate whether the patient currently has lung cancer, had lung cancer, or had a family member with lung cancer.

While technology can successfully identify a date, it cannot reliably indicate whether that date is the most recent date of service, the date scheduled for a future appointment, or the date indicating when the image was last faxed.

While technology can identify a medical condition “diabetes” noted as a Chief Complaint, it cannot reliably indicate whether the patient currently has diabetes or is suspected of having diabetes.

MIDAS supplies data with context, delivering actionable data that can drive your organization forward through accurate, reliable structured health data.

MIDAS Lens

In addition to delivering accurate, reliable, structured medical data, MIDAS can impact data collection and review through its Data Lens technology.
The MIDAS Lens unlocks advanced information delivery, offering customized identification, location, and context for customer keywords. Benefits of MIDAS Lens:

Underwriting

Highlight and identify underwriting risk factors, assuring a complete and accurate accounting of the patient’s medical history.

Research

Highlight specific medical conditions, medications, diagnostics, and narrative content, enabling the research team to review larger amounts of medical information more accurately, and in less time.

Disability

Highlight and identify underwriting risk factors, assuring a complete and accurate accounting of the patient’s medical history.

Legal

Identify and locate key conditions, medications, and narrative content across a vast library of medical information, making it easy to clarify which patients are possible litigants.

Frequently Asked Questions

Why are humans used in data extraction and not just AI?

MIDAS is designed to produce “Decision Grade Data,” meaning the data delivered is of sufficient depth and quality that the original medical record image is no longer required to make decisions. Although AI has remarkable capabilities, the accuracy of AI-only data extraction is simply not sufficient to meet this standard. ReleasePoint engages a human review process that validates and annotates the individual data elements, delivering the depth and quality required for sophisticated decision making workflows.

How can I use the MIDAS Data?

End users can use MIDAS data through the MIDASight online web portal, which provides a real-time environment to engage with patient medical data. Users can also choose a sophisticated PDF abstract, which contains the extracted data from multiple providers in an efficient design, delivering a single document containing all relevant patient clinical data to reduce review time and improve accuracy.

Is there an API available to develop custom applications?

Yes, ReleasePoint supports a full API and developer sandbox. Users can submit records and download the extracted data and PDF abstracts, allowing for the construction of complex custom applications that take advantage of the industry’s only path to 100% data driven medical review. Underwriting workbench developers, claims automation developers and legal case management platforms can build AI enabled functionality based on the highest quality data available, ushering a new generation of automation and decision support solutions.