Call for Contributions
Inform the Chair: with the Title of your Contribution
Submission URL:
https://www.iariasubmit.org/conferences/submit/newcontribution.php?event=BIOTECHNO+2017+Special
Please select Track Preference as MLPM
The common biomedical community conception is that Precision Medicine’s goals can be reached only by increasing the accuracy of wet lab measurements. The results of biological experiments enter more and more into the realm of Big Data. Big Data do not talk themselves. Data should be preprocessed and analyzed. Moreover, identifying differentially expressed genes should not be the final result of the bioinformatic analysis, being an incomplete response to a potentially significant biomedical question. This is why we will not often see studies reporting the results of a t-test or similar algorithms, for a classification problem, in other fields than biomedical research. Most of them end with a classifier, developed using machine learning techniques.
So, accurate measurements of informative classes of biomedical variables, either molecules or extracted from medical images, combined with adequate machine learning methods, could lead to Precision Medicine. These can be used to develop highly accurate, robust (generalizing well to new cases) and transparent (easy to understand) predictive models. However, biological systems are highly redundant, and this is related to their amazing robustness. The usual machine learning approach, exclusively focused on identifying the minimal subset of relevant variables, while perfectly justified, preclude redundancy understanding and exploiting. Thus, new machine learning methods or adapting the existing ones is needed.
The special session opens to everybody as well as industrial partners to make contributions in this area.
Topics for this session include but are not limited to:
Predictive models for diagnosis, prognosis and response to treatment
Biomedical image processing and analysis
Analysis of high-throughput biotechnology data
Machine learning integration with Electronic Health Records
Machine learning approaches to liquid biopsy
Machine learning approaches to redundancy understanding and exploiting
Evaluation and use of information technology in healthcare
Industrial challenges in bioinformatics
Future directions and challenges in bioinformatics
Important Datelines
- Inform the Chair: As soon as you decided and secured the financial support - Submission: February 3