We develop medical decision support systems

About us

We are creating Analytics-as-a-Service solutions to aid diagnosis or therapy choices. We are primarily interested in the dual challenges of 1) earlier and more granular diagnosis and 2) improved therapy selection for individual patients.

We focus on narrowly defined situations where a clinical decision is “costly”, on account of requiring the generation, collation and processing of large volumes of complex data by highly-trained experts. Good examples for such scenarios include the diagnosis of autism based on a scripted interview or the detection of certain types of heart disease based on an echocardiogram.

For such cases we develop automated, scalable medical decision support systems that receive raw data and produce a recommendation for diagnosis or therapy. Our products are available as Analytics-as-a-Service, and regulated as medical devices.

Ultimately, our solutions help health care providers select therapies for individual patients that benefit them the most. If we do our job well, we improve patient care, increase the success rate of therapies and eliminate unnecessary cost associated with suboptimal therapy choices.

Technology

We build our Analytics-as-as-Service (AaaS) products using unique combinations of classical AI algorithms, modern deep learning approaches, computer vision, and statistical methods.

Our analytical engines are modular, based on reusable software modules, each module developed to produce or quantify some biomarker that is relevant to the decision support task at hand. We can rapidly develop new AaaS products by combining such modules to tackle a new clinical challenge.

Our analytics is embedded in an infrastructure that allows us to transmit and store medical information, and deliver results to health care providers in compliance with relevant laws, regulations and guidelines. Data never leaves our servers, as we don’t rely on third-party services, and it is always encrypted and subject to strict access control.

Our products are fully automated beyond uploading data to us. Therefore, our AaaS products are infinitely scalable and inexpensive to operate. Their output is always quantitative.

Products

We have active product development programs in neurodevelopment and neurodegenerative disorders, as well as in cardiology. We have research stage programs in dermatology and ophthalmology.

In neurodevelopmental disorders we have developed an Analytics-as-a-Service solution to comprehensively assess social and communication skills based on video and audio. We are seeking regulatory approval for this system for autism diagnosis and monitoring, while we are researching its applicability in PTSD and neurodegenerative disorders.

In cardiology, we are interested in patient selection challenges in electrophysiology, procedure planning for interventional cardiology and cardiothoracic surgery, early prediction of heart failure and other major disorders in the general population, pediatric populations and athletes. Our first product, soon to enter the regulatory approval process, uses novel digital biomarkers derived from 3D echo to predict heart failure progression.

Please, feel free to reach out for white papers, publication lists, demos, etc. We are not secretive and thrive on partnerships.

Publications

  • Regional shape, global function and mechanics in right ventricular volume and pressure overload conditions: a three‐dimensional echocardiography study

    Jurate Bidviene, Denisa Muraru, Francesco Mafessanti, Egle Ereminiene, Attila Kovács, Bálint Lakatos, Jolanta‐Justina Vaskelyte, Remigijus Zaliunas, Elena Surkova, Gianfranco Parati, Luigi P. Badano

    The International Journal of Cardiovascular Imaging

    2021

    Our aim was to assess the regional right ventricular (RV) shape changes in pressure and volume overload conditions and their relations with RV function and mechanics. The end-diastolic and end-systolic RV endocardial surfaces were analyzed with three-dimensional echocardiography (3DE)...

  • Acute changes of global and longitudinal right ventricular function: an exploratory analysis in patients undergoing open-chest mitral valve surgery, percutaneous mitral valve repair and off-pump coronary artery bypass grafting

    Marius Keller, Tim Heller, Tobias Lang, Johannes Patzelt, Juergen Schreieck, Christian Schlensak, Peter Rosenberger and Harry Magunia

    Cardiovascular Ultrasound

    2020

    Right ventricular (RV) function is an important prognostic indicator. The acute effects of cardiac interventions or cardiac surgery on global and longitudinal RV function are not entirely understood. In this study, acute changes of RV function during mitral valve surgery (MVS),...

  • The ongoing quest for improving machine learning-based risk stratification

    Márton Tokodi, Walter Richard Schwertner, Annamária Kosztin, Béla Merkely

    European Heart Journal

    2020

    This commentary refers to ‘Machine learning-based mortality prediction: how to be connected to daily clinical practice?’, by W.H. Kim and J.-T. Kim, on page 2913. We greatly appreciate the interest of Kim and Kim in our recently published work.1,2 As pointed out by them, the current version of the SEMMELWEIS-CRT score has some limitations besides its undeniable strengths...

  • Right ventricular mechanical pattern in patients undergoing mitral valve surgery: a predictor of post-operative dysfunction?

    Márton Tokodi, Endre Németh, Bálint K. Lakatos, Erika Kispál, Zoltán Tősér, Levente Staub, Kristóf Rácz, Ádám Soltész, Szabolcs Szigeti, Tamás Varga, János Gál, Béla Merkely and Attila Kovács

    ESC Heart Failure

    2020

    The PREPARE-MVR study (PRediction of Early PostoperAtive Right vEntricular failure in Mitral Valve Replacement/Repair patients) sought to investigate the alterations of right ventricular (RV) contraction pattern in patients undergoing mitral valve replacement/repair (MVR) and to explore the associations between pre-operative RV mechanics and early post-operative RV dysfunction (RVD)...

  • Competing Approaches to Defining Right Ventricular Motion Directions in Three Dimensions: A Pressing Need for Standardization?

    Márton Tokodi, MD, Bálint Károly Lakatos, MD, Zoltán Tősér, Msc, Béla Merkely, MD, PhD, DSc, Masaaki Takeuchi, MD, PhD, FASE, Attila Kovács, MD, PhD, FASE

    Journal of the American Society of Echocardiography

    2020

    We greatly appreciate the interest and insightful comments of Duchateau et al. regarding our work. Indeed, the standardized alignment of three-dimensional (3D) models is the linchpin of all technologies aiming to evaluate right ventricular (RV) function in a directionwise manner as variations in the definition of directions might significantly affect the measured parameters...

  • Importance of Nonlongitudinal Motion Components in Right Ventricular Function: Three-Dimensional Echocardiographic Study in Healthy Volunteers

    Bálint Károly Lakatos, MD, Yosuke Nabeshima, MD, Márton Tokodi, MD, Yasufumi Nagata, MD, PhD, Zoltan Tősér, MSc, Kyoko Otani, MD, PhD, Tetsuji Kitano, MD, Alexandra Fábián, MD, Adrienn Ujvári, MD, Andras Mihály Boros, MD, PhD, Béla Merkely, MD, PhD, DSc, Attila Kovács, MD, PhD, FASE, and Masaaki Takeuchi, MD, PhD, FASE

    Journal of the American Society of Echocardiography

    2020

    Global right ventricular (RV) function is determined by the interplay of different motion compo- nents related to the myofiber architecture, and the relative importance of these components is still not thoroughly characterized. The aims of this study were to quantify the relative contributions of longitudinal, radial, and anteroposterior motion components...

  • Machine learning-based mortality prediction of patients undergoing cardiac resynchronization therapy: the SEMMELWEIS-CRT score

    Márton Tokodi, Walter Richard Schwertner, Attila Kovács, Zoltán Tősér, Levente Staub, András Sárkány, Bálint Károly Lakatos, Anett Behon, András Mihály Boros, Péter Perge, Valentina Kutyifa, Gábor Széplaki, László Gellér, Béla Merkely, and Annamária Kosztin

    European Heart Journal

    2020

    Our aim was to develop a machine learning (ML)-based risk stratification system to predict 1-, 2-, 3-, 4-, and 5- year all-cause mortality from pre-implant parameters of patients undergoing cardiac resynchronization therapy (CRT)...

  • Advancements in vision & speech analyses of ASD symptom domains

    Zoltán Tősér, Zachary Arnold, Richard Bellon, Máté Csákvári, Edith Ocampo, Allison Wainer, Mark Pollack, András Lőrincz, Latha Soorya

    INSAR - International Society for Autism Research / Annual Meeting

    2019

    The mission of Argus Cognitive is to develop a non-intrusive, fully automated system that increases accessibility, affordability and objectivity of behavioral health care for common mental health and neurological conditions...

  • Right ventricular mechanical pattern in health and disease: beyond longitudinal shortening

    Attila Kovács, Bálint Lakatos, Márton Tokodi, Béla Merkely

    Heart Failure Reviews

    2019

    Right ventricular (RV) function has proven to be a prognostic factor in heart failure with reduced and preserved ejection fraction and in pulmonary hypertension. RV function is also a cornerstone in the management of novel clinical issues, such as mechanical circulatory support devices or grown-up congenital heart disease patients...

  • Towards an automated analysis of social-communication behaviors in ASD

    Zoltán Tősér, Zachary Arnold, Máté Csákvári, András Lőrincz, Edith Ocampo, Mark Pollack, Allison Wainer, Latha Soorya

    INSAR - International Society for Autism Research / Annual Meeting

    2018

    Objective behavioral assessment is a mainstay of behavioral sciance tools. Recent advances adapting human-AI interaction technology has promise to streamline analisys of core social-communication behaviors for treatment research...

  • Exercise-induced shift in right ventricular contraction pattern: novel marker of athlete’s heart?

    Bálint Károly Lakatos, Orsolya Kiss, Márton Tokodi, Zoltán Tősér, Nóra Sydó, Gergő Merkely, Máté Babity, Mónika Szilágyi, Zsuzsanna Komócsin, Csaba Bognár, Attila Kovács, and Béla Merkely

    American Journal of Physiology-Heart and Circulatory Physiology

    2018

    Regular vigorous physical exercise results in significant changes in cardiac morphology and function, commonly referred as the athlete’s heart. According to different sport disciplines, training regime, level of competition, age, sex, and even genetic factors, the athlete’s heart represents a broad spectrum of physiological cardiac alterations...

  • Response to Ivey-Miranda and Farrero-Torres “Is there dominance of free wall radial motion in global right ventricular function in heart transplant recipients or in all heart surgery patients?”

    Attila Kovács, Bálint Lakatos, Endre Németh, Béla Merkely

    Clinical Transplantation

    2018

    In our original article — recently published in Clinical Transplantation — we concluded that after orthotopic heart transplantation, the radial motion of right ventricular free wall compensates for the decreased longitudinal shortening to maintain ejection fraction. The editorial from Ivey-Miranda and Farrero-Torres questioned...

  • Dominance of free wall radial motion in global right ventricular function of heart transplant recipients

    Bálint Károly Lakatos, Márton Tokodi, Alexandra Assabiny, Zoltán Tősér, Annamária Kosztin, Alexandra Doronina, Kristóf Rácz, Kinga Bianka Koritsánszky, Viktor Berzsenyi, Endre Németh, Balázs Sax, Attila Kovács, Béla Merkely

    Clinical Transplantation

    2018

    Assessment of right ventricular (RV) function using conventional echocardiography might be inadequate as the radial motion of the RV free wall is often neglected. Our aim was to quantify the longitudinal and the radial components of RV function using three-dimensional (3D) echocardiography in heart transplant (HTX) recipients...

  • Quantification of the relative contribution of the different right ventricular wall motion components to right ventricular ejection fraction: the ReVISION method

    Bálint Lakatos, Zoltán Tősér, Márton Tokodi, Alexandra Doronina, Annamária Kosztin, Denisa Muraru, Luigi P. Badano, Attila Kovács and Béla Merkely

    Cardiovascular Ultrasound

    2017

    Three major mechanisms contribute to right ventricular (RV) pump function: (i) shortening of the longitudinal axis with traction of the tricuspid annulus towards the apex; (ii) inward movement of the RV free wall; (iii) bulging of the interventricular septum into the RV and stretching the free wall over the septum...

Team

Argus Cognitive was founded in 2016 by computer scientists, psychologists and a medical device entrepreneur.

  • Zoltan Toser (CEO) and Andras Lorincz (CSO) are computer scientists, specializing in machine learning.

  • Mark Pollack, MD and Latha Soorya, PhD are a practicing psychiatrist and a clinical psychologist.

  • Attila Meretei, MD has been developing medical devices for almost 20 years.

Our product development team is located in Budapest, Hungary.

We maintain a symbiotic relationship with the Neural Information Processing Group at Eotvos Lorand University, Budapest, Hungary, where we can test new technologies before including them in our development pipeline.

In cardiology we closely collaborate with various researchers in the US and Europe.

We are hiring

We are always on the lookout for talented people to join our team. We have openings in the following positions:

  • computer scientist with a machine learning background

  • software engineer (our technology stack is mostly built around Scala, Python, and Typescript)

  • sales engineer (USA)

  • system administrator

Our team is geographically dispersed, present in four continents, so provided you have excellent communication skills, remote work is feasible. Needless to say, good English is a must.

If all this sounds interesting, or you would like more info, don't hesitate to reach out to us at info@arguscognitive.com.

Contact

We have a lot more to say about the company and the team, the unmet need, the market, our technology and products, clinical results and regulatory plans and opportunities in other fields of medicine. If you are interested in a dialogue, collaboration or joining our team, please reach out to us. Thank you!

Zoltan Toser

CEO, Argus Cognitive, Inc.

zoltan@arguscognitive.com

+36 70 572 3135

Attila Meretei, MD

President, Argus Cognitive, Inc.

attila@arguscognitive.com

+1 603 400 2440

Dartmouth Regional Technical Center, 16 Cavendish Court, Lebanon, NH 03766