Artificial Intelligence | News | Insights | AiThority
[bsfp-cryptocurrency style=”widget-18″ align=”marquee” columns=”6″ coins=”selected” coins-count=”6″ coins-selected=”BTC,ETH,XRP,LTC,EOS,ADA,XLM,NEO,LTC,EOS,XEM,DASH,USDT,BNB,QTUM,XVG,ONT,ZEC,STEEM” currency=”USD” title=”Cryptocurrency Widget” show_title=”0″ icon=”” scheme=”light” bs-show-desktop=”1″ bs-show-tablet=”1″ bs-show-phone=”1″ custom-css-class=”” custom-id=”” css=”.vc_custom_1523079266073{margin-bottom: 0px !important;padding-top: 0px !important;padding-bottom: 0px !important;}”]

Precipio Achieves Impressive Initial Results of AI Decision-Support Tool

Groundbreaking clinical and economic impact to be generated

Specialty diagnostics company Precipio, Inc., announced that preliminary results from its artificial intelligence (AI) initial MVP (Minimal Viable Product) model demonstrate a profound clinical value. The next phase is to develop a working platform expected to become commercial within the next 12-18 months.

Background

The diagnosis of hematopoietic diseases (via the analysis of bone marrow and peripheral blood samples) has always suffered from an inherent systemic flaw, stemming from the expectation that  oncologists provide a clinical suspicion upon submitting a biopsy for diagnosis. The clinical suspicion determines the pathway of diagnosis, and is the sole driver for the laboratory in its testing selection, intended to confirm/rule out the oncologist’s clinical suspicion. If the clinical suspicion is incorrect, the lab will embark down the wrong path, potentially resulting in a mistaken diagnosis. Numerous studies [2] indicate that in blood-related cancers, the rate of misdiagnosis is approximately 25% of patients tested.

Precipio’s solution

As part of our mission to battle misdiagnosis, Precipio took a different approach, whereby the oncologist’s clinical suspicion was one factor within the decision process, rather than the sole driving factor. Precipio developed a proprietary triaging algorithm that examines multiple patient factors (CBC tests, chemistry results, patient history, clinical symptoms and others) in order to arrive at its own clinical suspicion, which more often than not, varied from the clinician’s suspicion. We believe this process is a substantive contributor to Precipio’s >99% accuracy rate.

Recommended AI News: AiThority Interview With Adrian Leer, Managing Director – Triad Group Plc

Initial Results

Precipio’s data clearly demonstrates that overall clinicians have a low likelihood of assessing the correct clinical suspicion. Precipio’s initial AI MPV achieved accuracy results which are, in aggregate, double that of clinicians. With initial based on a limited data set, we believe that additional data will yield far better results. The machine-learning components of the iAI systems currently in development enable our model to improve with each case, and reach increasingly higher levels of accuracy..

Transition to an AI platform
Related Posts
1 of 14,598

Although the current algorithm is used internally on every case analyzed by our lab staff at Precipio, we recognized that this systematic flaw is a global problem, requiring a global solution. A computerized system that receives input factors and provides a correct clinical suspicion would serve as a decision-support tool for any physician suspecting their patient has a blood-related cancer. A SaaS-based system could effectively provide access to this solution on a worldwide scale.

Market potential

Each year, approximately 40 million people in the US undergo routine blood tests, with those test results providing precisely the factors needed for our AI system. Absent a proper assessment, many early-stage cancer patients go undetected until the patient becomes symptomatic, typically associated with disease progression. Access to the AI model may provide a groundbreaking change of the way suspected blood-related cancer patients are assessed prior to the biopsy and diagnosis stages. While it is currently early to quantify the value of this system, given the annual spend on diagnostics, and the waste related to blood-related cancers due to misdiagnosis, the market potential appears to be substantial.

Recommended AI News: Keith Block Steps Down as Salesforce Co-CEO; Marc Benioff is Chair and CEO

Beneficiaries

The potential beneficiaries from this system among the various healthcare constituents are:

  • Physicians: Higher accuracy and correlation between clinical suspicion and actual disease state.
  • Payors: Reduction or containment of unnecessary testing
  • Pharmaceuticals – assist in identifying accuracy of medication therapy, and reducing undesirable pharmacovigilance consequences.
  • Patient: early-detection

“AI appears in almost every facet of our life, helping us navigate movie decisions and the traffic while driving home from work. Why not use AI technology to navigate the complex process of diagnosing patients with terrible diseases such as blood-related cancers”, said Ori Karev, Precipio’s Chief Strategy Officer, and architect of this initiative. “The team at Precipio have developed a groundbreaking algorithm with demonstrated clinical benefit to their patients and physicians. Now we are going to transform this into a product for patients and their physicians around the world.”

Next Steps

Over the next few months, under Ori’s leadership, a team will be formed to develop this project. The team will also be working with leading payors, healthcare networks, and EMR companies to partner with Precipio in the development of this service. The company will continue to provide periodic updates as these efforts progress.

Recommended AI News: AWS Acquires a Powerful Data Exploration and Visualization to Boost Python & R Integration

Leave A Reply

Your email address will not be published.