Monitoring patient disability and disease severity using AI
Who is this presentation for?Data engineers, data architects, developers
In this presentation we show soft computing methodology for quantification of disease severity and patient disability. This methodology is used in the context of personalized healthcare for solving the following problems:
• Monitoring patient disability over time to analyze the progression of disease and the response to therapy
• The decision problem of the best time to start a risky therapy
• Aggregation of objectively measured impairments and subjective symptoms to quantitatively evaluate the current level of disease severity
• Improvement of medical rating scales using graded logic for score aggregation
• Development and use of software tools for self-evaluation of patient disability
Our presentation will start by discussing the limitations of medical rating scales and the benefits of applying soft computing logic to medical scoring of disease severity, medical disability, and specific patient disability. Then, we will present the LSP technique for building precise evaluation models, and show a detailed model for logic evaluation of patient disability caused by peripheral neuropathy. The presentation will also include a case study of application of this model using the LSPmed software tool (available over the Internet), and the explainability of evaluation results. Next, we will discuss the problem of optimum timing of risky therapy and show an example of solving this problem. Finally, we will discuss possible areas of applying the presented methodology, including multiple sclerosis, arthritis, a spectrum of physical injuries, as well as the personalized quantitative assessment of effects of physical therapy.
This presentation is supported by presenter’s recent monograph Soft Computing Evaluation Logic, published by J. Wiley and IEEE Press in 2018.
Prerequisite knowledgeThe prerequisites include elementary knowledge of logic, and basic understanding of building and using mathematical models. Attendees with undergraduate degree in engineering or sciences should be perfectly suitable to benefit from this presentation.
What you'll learn
San Francisco State University
JOZO DUJMOVIĆ received BSEE, MS, and ScD degrees in computer engineering from the University of Belgrade. He is a Professor of computer science and former Chair of the Computer Science Department at San Francisco State University, where he teaches and researches soft computing, decision engineering, software metrics, and computer performance evaluation. His first industrial experience was in Institute “M. Pupin,” Belgrade, followed by professorship with the School of Electrical Engineering at the University of Belgrade. Before his current position with San Francisco State University, he was the Professor of computer science with the University of Florida, Gainesville, FL, USA; the University of Texas, Dallas, TX, USA; and Worcester Polytechnic Institute, Worcester, MA, USA. He is the author of the LSP decision method, and more than 170 refereed publications. Jozo received three best paper awards, served as General Chair of IEEE and ACM conferences, and invited keynote speaker at conferences in USA and Europe. He is the founder and principal of SEAS, a San Francisco company established in 1997, specializing in soft computing, decision engineering, and software support for the LSP decision method. His latest book entitled Soft Computing Evaluation Logic was published by John Wiley and IEEE Press in 2018.
Leave a Comment or Question
Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?
Join the conversation here (requires login)
Premier Diamond Sponsors
Premier Exhibitor Plus
For conference registration information and customer service
For more information on community discounts and trade opportunities with O’Reilly conferences
For information on exhibiting or sponsoring a conference
For media/analyst press inquires