BERKELEY, Calif., November 18, 2020 (Newswire.com) - In 2019, the U.S. spent more than $3 trillion on healthcare, 95% of which was dispersed through an insurance company, where every dollar must be codified. To respond to that fundamental - and still very inefficient - element of our healthcare system, Diagnoss today announced the first AI-based medical coding assistant that augments, not just automates, the medical coding process. The Artificial Intelligence Engine delivers providers and billing teams alike with real-time feedback on their documentation and coding, constantly learning to improve each clinic's system's accuracy.
Beyond the inefficiencies in pre-COVID-19 times, the pandemic has caused unprecedented and unforeseeable economic disruptions to U.S. healthcare providers. For example, one-third of providers say their organizations are operating below 60% capacity, and roughly one-quarter see a risk of their organization closing in one year or less if COVID-19 continues to disrupt care and cause revenue losses.
This added financial strain means medical coding errors that impact reimbursement revenue can have severe consequences on a practice's bottom line.
"Healthcare providers are burnt out and worried about keeping their doors open," said Abboud Chaballout, founder and CEO of Diagnoss. "For every patient encounter, a physician spends an average of 16 minutes on administration, which adds up to several hours every single day. In addition, codes entered are often wrong - up to a 30% error rate - resulting in missed or delayed reimbursements. We believe that, with the great progress we've seen with artificial intelligence and machine learning, we can finally address some of these inefficiencies that are leading to physician burnout and financial strain."
How It Works
Diagnoss built its natural language processing engine from the ground up to assess doctors' notes, either as they're typing them or after they've uploaded them into the Electronic Health Record (EHR), and serves the user with actionable information in real time.
Among the actionable information Diagnoss delivers to users:
· E/M Level Meter: provides real-time feedback to users about the evaluation and management code applicable to the current patient encounter;
· Clinical Documentation Improvement Suggestions: scans the doctor's notes for missing information relevant to the current patient evaluation;
· ICD-10 Diagnosis Code and CPT Procedure Code Predictions: serves users with predictions as to which diagnosis and procedure codes could apply to a note, allowing the user to make a decision and submit those codes directly into the EHR with one click.
Diagnoss's augmentation technology is differentiated from systems that simply automate the coding process in that:
(a) users receive real-time feedback regarding the types of codes that can be billed based on the doctor's documentation, as the doctor is charting; and
(b) Diagnoss's AI actively learns and adapts with each use to continuously increase code accuracy and reduce errors.
Machine-coded charts = 50% greater accuracy
Diagnoss recently conducted a study on more than 39,000 de-identified EHR charts; the goal was to assess the clinical viability of deep learning techniques for predicting medical codes in the presence of subjectivity. The result: Compared to human coders, the machine coded charts with more than 50% greater accuracy.
Chaballout continued: "To date, AI has not been used to meaningfully improve the coding process, the focus has been on merely automating it in areas where human intervention can be eliminated - send out records and have a computer enter the codes. We are taking that a step further by helping doctors and coders on the front lines of the coding process. Imagine an expert medical coder with over 30 years of experience standing over the shoulder of a doctor or a junior coder, reading patient notes and whispering the correct codes into their ears, so they don't have to expend any more energy or time. We seek to make the medical coding process that simple for every single provider, coder, and biller."
The company previously announced a partnership with mobile EHR vendor, DrChrono. The partnership gives physician practices using DrChrono's mobile EHR platform access to Diagnoss's Artificial Intelligence Engine, which reads a doctor's note, and suggests accurate medical codes and clinical documentation improvement points.
Diagnoss' artificial intelligence technology helps medical establishments improve their collections while reducing their risk of audit. Diagnoss augments the work of clinical and billing teams by driving pertinent (1) medical code suggestions and (2) clinical documentation improvement suggestions to its users, before they make a mistake. Diagnoss' core technology includes a machine learning engine capable of deriving high impact inferences from unstructured medical data and delivering actionable information to healthcare teams. For more information about Diagnoss, visit www.diagnoss.com.