SUMMARY

Our team of multi-disciplinary experts features 30 years of cutting-edge research and innovative applications in wide range of complex systems (in physics, biomedicine, engineering, finance and others fields). Using such multi-disciplinary expertise, we always stay several steps ahead of major new developments in complex systems modeling and early identification of novel or emerging multi-disciplinary techniques that could be adopted in personalized medicine and other challenging biomedical applications.

Modern machine learning (ML) and AI algorithms (including deep learning) demonstrated excellent performance in image classification and natural language processing (NLP). However, straightforward application of these techniques for personalized medicine, rare states identification and early detection of emerging abnormalities or treatment effects often results in unstable performance and inability to discover acceptable solutions.

Our first-hand understanding of pro and cons of quantitative models and modern ML algorithms allowed us to create a unique hybrid system capable of discovery of unique solutions to many challenging complex systems problems including biomedical applications. Our system optimally combines best features of many cutting-edge analytical and ML methods as well as efficiently incorporates existing expert knowledge. Our framework constantly evolves by adding complementary value of promising novel approaches discovered by our team and other researchers around the world.

While personal biomedical solutions discovered by our framework can be used in different ways, our focus is helping our clients to solve the most difficult problems associated with rare states identification and early detection of emerging abnormalities and treatment effects that are very challenging or simply impossible to detect by other means. Our solutions include but not limited to the following:

  • AI-Driven Framework for Discovery of Multi-Expert Personalized Biomedical Models & Indicators.
  • High-Capacity Engine for Multi-Factor Simulation and Multi-Objective Optimization of Treatment, Wellness & Rehabilitation Strategies.
  • 24/7 Automated Personalization, Monitoring & Decision Support.
  • Optimal Combination of All Available Biomedical Resources, Novel Research Results & Personal Data to Solve Your Current Problems.
  • Clear Explanation & Interpretation of the Discovered Personalized Treatment and Wellness Strategies.
  • Early Detection of the Emerging Medical Abnormalities, Health-Critical & Acute Events, Overtraining and Psychological Conditions.
  • Predictive Indications of Personalized Zones of Optimal Performance in Sport and Other Competitive Fields
  • Identification and forecasting of personalized weather and geomagnetic patterns critical to wellness and performance.

OUR TEAM

Valeriy Gavrishchaka

Valeriy V. Gavrishchaka received his MS and PhD degrees in computational and theoretical physics from Moscow Institute of Physics and Technology (Moscow, Russian Federation) and from West Virginia University (Morgantown, West Virginia, USA), respectively. He has 30 years of overall experience in complex systems research and applications including almost 20 years in financial industry. He worked as multi-disciplinary research scientist and consultant at Science Applications International Corporation (McLean, Virginia) on a wide range of problems in plasma / space physics and space weather forecasting using physics-based models / simulations and wide range of machine learning approaches (1997-2002).

From 2002 to 2010 he worked for several multi-billion New York based hedge funds as head of quantitative research and quantitative strategist for multi-frequency algorithmic trading. He also has multi-year experience in developing and implementing quantitative models as well as machine learning and AI frameworks for market and credit risk analytics including structured credit products. His main research interests include development and applications of novel multi-disciplinary approaches and integrated frameworks for applied quantitative modeling of complex systems in physics, finance, econometrics, medicine, and other scientific and business fields. He also develops and applies analytical models and multi-scale simulations to study fundamental processes in different physical, engineering, biological, and other systems. He is an author of more than 70 publications in mainstream scientific journals and referred conference proceedings that are frequently cited as summarized in his Google Scholar and Research Gate profiles.

Xuliang Miao

Xuliang Miao has MS degree of Financial Mathematics from Johns Hopkins University and BS degree of Applied Mathematics and Computer Science from University of California, San Diego. She has more than 5 year experience in financial industry focusing on the risk management, quantitative analysis and machine learning. For the recent five years, she has applied her advanced programing and analytical skills in several fields including biostatistics, high performance computing and credit risk. Her current passion is development and applications of novel machine learning algorithms (including various ensemble-based and deep learning frameworks combined with analytical models and expert knowledge) to challenging problems in biomedicine and quantitative finance. She has several recent publications on the novel hybrid approaches in machine learning and AI.

Andrey Makeyev

Andrey Makeyev received his BS and MS degrees in mathematics from Moscow State University (Moscow, Russian Federation). He has 30 years of overall experience in AI, Neural Nets, Machine Learning and development of complex algorithms and large-scale simulation frameworks in research and mission-critical production environments. This includes almost 20 years experience in the financial industry. He was leading a team of scientists in the nuclear physics research department at the Federal Nuclear Center (Russian Federation). He worked as head of quantitative research and quantitative strategist in a commercial bank actively using Neural Nets and other Machine Learning algorithms.

He led a full research, development and implementation cycle of biological algorithms to recognize a human genome. He is an author of several publications and presentation in the scientific conferences.

Zhenyi Yang

Zhenyi Yang received his BS and MS degrees in Financial Mathematics from University of Michigan Ann Arbor and The Johns Hopkins University in 2011 and 2013. Currently, Zhenyi works as financial engineer in a major financial company. He is an all-round data scientist and computer science expert. His current research interest includes development and real-life applications of ensemble-based models, deep learning neural networks and other machine learning algorithms. He successfully applies novel machine learning frameworks to challenging problems in biomedicine and quantitative finance.

Marina Orlova

Marina Orlova received her MS degree in biophysics from Moscow State University in 2017. She is an expert in mathematical and statistical modeling, bioinformatics and backend python development with 6+ years of experience in biomedical and IT industries.

External Multi-Disciplinary Collaborators

We actively collaborate with experts and practitioners in different fields. These include “Applied Quantitative Solutions for Complex Systems” multi-disciplinary research group (www.aqscs.com) as well as many individual experts in hard sciences, molecular biology, bioinformatics, machine learning and AI as well as medical professionals around the globe.

© 2019 Medpobs. Powered by VOOV.