Medial EarlySign develops decision-support tools based on machine learning that expose the hidden layer of information in standard medical data. These tools enable personal and outcome-based interpretation of medical data, yielding individualized predictions and treatment options for each patient, as well as early prediction of life-threatening conditions.

Medial EarlySign develops machine learning based decision support tools that expose the hidden layer of information in standard medical data. These new insights enable personal and outcome-based interpretation of medical data, yielding individualized predictions and treatment options for each patient, as well as early prediction of life-threatening conditions. Our cutting edge tools are designed to offer healthcare organizations a new way of looking at their data, empowering them with proactive, personalized and predictive care management capabilities.  

Medial EarlySign built and refined a unique algorithmic platform designed to handle large medical data and billions of medical data elements.  Our validated algo-medical platform creates thousands of parameters based on existing medical data, analyzing trends and interrelationships over time. This enables setting personalized risk levels for mass populations in moments, and identifying individuals who may require further intervention.

Our solutions go through rigorous clinical validation.  The company is currently conducting clinical trials in 14 leading research institutions around the world totaling more than 5 million patients.

Horizon Ventures

aMoon Fund

Horizons Ventures

Marius Nacht

Nir Kalkstein

Medial EarlySign

Efforts to deploy advanced, proactive approaches leveraging #EarlySign’s AI predictive models can play a significant role in identifying prediabetic patients at a higher risk of progressing to diabetes in the near term, when prevention efforts can have the most effect. Check out this recent blog post from Lucem Health as they provide perspective data around the growing burden of prediabetes and how the benefits of #earlydetection can impact screening resource allocation and potentially reduce the human and financial cost of diabetes.
https://lnkd.in/gdfb5UzB

EarlySign is pleased to announce the US general availability of LungFlag™, an AI based solution that identifies patients who may be or are at risk for certain respiratory illnesses, including cancers of the lung or trachea, by analyzing routine clinical data. Working together with Geisinger, this launch builds upon numerous published research papers which validate LungFlag results in the clinical environment. We are grateful for our ongoing collaboration with Geisinger to build on a shared commitment for innovation geared to improve care.

EarlySign designed the LungFlag to enhance the effectiveness with which health systems can screen for cancer, allowing for the identification and targeting of high-risk patients and enabling the right care to be delivered to those who need it the most.  LungFlag is the latest addition to EarlySign’s expanding platform of validated clinical solutions impacting the early diagnosis of serious diseases.
https://lnkd.in/gG6Etiix

Early detection of serious disease in various sub-populations represents a significant opportunity for pharmaceutical companies to impact personalized, proactive treatments.  We are pleased to continue our ongoing collaboration with Roche as they continue important research to help impact the early detection of lung cancer, especially in younger populations.
#earlydetectionsaveslives 
https://lnkd.in/gPySxr9A

Geisinger and EarlySign are pleased to announce the acceptance of a joint submission by the EASTERN VASCULAR SOCIETY (EVS). Presented at the EVS Annual Meeting in Washington, DC, the submission was entitled: “Development and Validation of a Machine Learning Prediction Model to Improve Abdominal Aortic Aneurysm Screening.”
https://lnkd.in/d2_CdE6W

Despite recommendations by the U.S. Preventive Services Task Force, adoption of screening for abdominal aortic aneurysms (AAA) remains low. This study sought to demonstrate that by utilizing a machine-learning model, a novel algorithm could detect patients who are at high risk for AAA. By selecting individuals at greatest risk for targeted screening, this EarlySign developed algorithm resulted in a more than 150% increase in the detection of AAA, when compared with standard screening guidelines. 

We would like to thank the following individuals for their dedication and contributions to this important research.

Department of Vascular and Endovascular Surgery, Geisinger
James R. Elmore, MD
Evan J. Ryer, MD 
Gregory G. Salzler, MD
Robert W. Abdu, DO

Business Intelligence Advance Analytics - Steele Institute, Geisinger, Danville, PA 
Abdul Tariq 
Jim Urick 
Elliot Mitchell 
Rebecca Maff
Grant DeLong 

STAIR Program, Geisinger, Danville, PA
Stacey L. Shriner

Medial EarlySign, Hod Hasharon, Israel 
Tal Sagiv 
Alon Lanyado 
Eran Choman 

COM:EARLYSIGN

Medial EarlySign

Analysis Not Available