Support Vector Machine with Fuzzy Decision-Making for Real-world Data Classification

Author(s):  
Boyang Li ◽  
Jinglu Hu ◽  
K. Hirasawa ◽  
Pu Sun ◽  
K. Marko ◽  
...  
2021 ◽  
Author(s):  
Peter Klimek ◽  
Dejan Baltic ◽  
Martin Brunner ◽  
Alexander Degelsegger-Marquez ◽  
Gerhard Garhöfer ◽  
...  

UNSTRUCTURED Real-world data (RWD) collected in routine healthcare processes and transformed to real-world evidence (RWE) has become increasingly interesting within research and medical communities to enhance medical research and support regulatory decision making. Despite numerous European initiatives, there is still no cross-border consensus or guideline determining which quality RWD must meet in order to be acceptable for decision making within regulatory or routine clinical decision support. An Austrian expert group led by GPMed (Gesellschaft für Pharmazeutische Medizin, Austrian Society for Pharmaceutical Medicine) reviewed drafted guidelines, published recommendations or viewpoints to derive a consensus statement on quality criteria for RWD to be used more effectively for medical research purposes beyond registry-based studies discussed in the European Medicines Agency (EMA) guideline for registry-based studies


Author(s):  
Alejandro Rodríguez-González ◽  
Ángel García-Crespo ◽  
Ricardo Colomo-Palacios ◽  
José Emilio Labra Gayo ◽  
Juan Miguel Gómez-Berbís ◽  
...  

The combination of the burgeoning interest in efficient and reliable Health Systems and the advent of the Information Age represent both a challenge and an opportunity for new paradigms and cutting-edge technologies reaching a certain degree of maturity. Hence, the use of Semantic Technologies for Automated Diagnosis could leverage the potential of current solutions by providing inference-based knowledge and support on decision-making. This paper presents the ADONIS approach, which harnesses the use of ontologies and the underlying logical mechanisms to automate diagnosis and provide significant quality results in its evaluation on real-world data scenarios.


Author(s):  
Boyang Li ◽  
◽  
Jinglu Hu ◽  
Kotaro Hirasawa

We propose an improved support vector machine (SVM) classifier by introducing a new offset, for solving the real-world unbalanced classification problem. The new offset is calculated based on the unbalanced support vectors resulting from the unbalanced training data. We developed a weighted harmonic mean (WHM) algorithm to further reduce the effects of noise on offset calculation. We apply the proposed approach to classify real-world data. Results of simulation demonstrate the effectiveness of our proposed approach.


2020 ◽  
Vol 23 ◽  
pp. 1s-47s
Author(s):  
Real World Data Workshop Group CSPS/Health Canada

Real world data (RWD) and real world evidence (RWE) are playing increasing roles in health-care decisions. Real world data are routinely employed to support reimbursement and coverage decisions for drugs and devices. More recently, clinical trials incorporating pragmatic designs and observational studies are considered to supplement traditional clinical trials (e.g., randomized clinical trials). Regulatory agencies and large co-operative groups including academia and industry are exploring whether leveraging big databases such as electronic medical records and claims databases can be used to garner clinical insights extending beyond those gained from randomized controlled studies. Whether RWE can ultimately replace or improve traditional clinical trials is the big question. The workshop held on December 3, 2019 at Health Canada included presenters from regulatory agencies, industry and academia. Health Canada, US FDA and European Medicine Agency presented current thinking, draft frameworks and guidance available in the public domain. While the three agencies might be at different stages of utilizing RWE for regulatory decision making, the consensus is not whether RWE would be used but when and how it can be incorporated into regulatory decision making while maintaining a high evidentiary bar. The complexity of data sourcing, curating databases, aligning on common data models, illustrated by high-profile work conducted as part of Sentinel, DSEN, OHDSI and Duke-Margolis initiatives, was presented and discussed during the workshop, creating great learning opportunities for the attendees. The design and analysis of RWE studies were compared and contrasted to those of RCTs. While there are gaps, they are closing quickly as novel analytical methods are employed and innovative ways of curating data, including natural language processing and artificial intelligence, are explored.   This proceeding contains summaries of information presented by the speakers, including current highlights about the use of RWE in regulatory decision making. In the world where the uptake of “big data” in everyday life is happening at unprecedented speed, we can expect RWE to be a fast-moving area and with the potential for big impact in health-care decision making in the years to come.


2011 ◽  
Vol 3 (1) ◽  
pp. 21-39 ◽  
Author(s):  
Alejandro Rodríguez-González ◽  
Ángel García-Crespo ◽  
Ricardo Colomo-Palacios ◽  
José Emilio Labra Gayo ◽  
Juan Miguel Gómez-Berbís ◽  
...  

The combination of the burgeoning interest in efficient and reliable Health Systems and the advent of the Information Age represent both a challenge and an opportunity for new paradigms and cutting-edge technologies reaching a certain degree of maturity. Hence, the use of Semantic Technologies for Automated Diagnosis could leverage the potential of current solutions by providing inference-based knowledge and support on decision-making. This paper presents the ADONIS approach, which harnesses the use of ontologies and the underlying logical mechanisms to automate diagnosis and provide significant quality results in its evaluation on real-world data scenarios.


Sign in / Sign up

Export Citation Format

Share Document