This open access book from Springer describes the results of natural language processing and machine learning methods applied to clinical text from electronic patient records.
Table of Contents
The History of the Patient Record and the Paper Record
User Needs: Clinicians, Clinical Researchers and Hospital Management
Characteristics of Patient Records and Clinical Corpora
Medical Classifications and Terminologies
Evaluation Metrics and Evaluation
Basic Building Blocks for Clinical Text Processing
Computational Methods for Text Analysis and Text Classification
Ethics and Privacy of Patient Records for Clinical Text Mining Research
Applications of Clinical Text Mining
Networks and Shared Tasks in Clinical Text Mining
Conclusions and Outlook
Many countries have introduced HPV vaccination programs without establishing the baseline for HPV prevalence. Using prevalence of vaccine versus non-vaccine HPV types from a county where we had actual baseline data we made a reconstructed baseline. Methods were validated by computing the Bhattacharyya coefficient of divergence. Protective effectiveness where baseline data was missing could then be estimated using non-vaccine HPV type data to reconstruct the baseline.
Vaccine 1 May 2018 https://doi.org/10.1016/j.vaccine.2018.04.073
I am a PhD student in the research group of Joakim Dillner, Karolinska Institutet. I am using Machine Learning approaches to identify which known and yet unknown viruses are present in the human metagenomic datasets that are most significantly related to the development of specific cancers. My background is software engineering – I have an MSc from University of Tartu.
At NIASC my job is to manage the NordScreen (nordscreen.org) project which is a publicly available, web-based application that delivers information of cancer screening programmes in the Nordic countries. The website will provide standardized, evidence-based indicators for monitoring the performance of screening programmes based on registry data from the Nordic countries and Estonia. Currently we are focusing on screening for cervical cancer. The Nordscreen is a collaborative project and other NIASC partners include Karolinska Institutet, the Cancer Registry of Norway, the Icelandic Cancer Registry and the Finnish Cancer Registry, where I’m working as a project manager and researcher.
I’m also starting my PhD studies in Public Health at University of Helsinki (Finland). My research is closely related to NordScreen project. In my research I’m developing indicators to measure the performance of cervical cancer screening programmes in the Nordic countries. I have a Master’s Degree in Health Sciences from University of Tampere and I’ve previously been working with health policy and measuring quality in health care. E-mail: firstname.lastname@example.org
I currently work as a data manager/bioinformatician at Group Palotie (Institute for Molecular Medicine Finland, FIMM). I have a background in biological sciences and I also have experience in data sciences and bioinformatics, in efforts to automate and facilitate biological data analysis. During my two post-doctoral projects, I have mainly worked with NGS data from microorganisms, focusing on de novo genome sequencing of fungi and metagenomics of environmental samples. E-mail: email@example.com
In order to prevent cervical cancer, all women in the country are called for tests every three years from the age of 23. Now research on register data shows that for many women it would be sufficient to go every nine years. Also research shows that it is possible to identify a high risk group that should come more often than today.
Read more here at the Swedish National Quality Registers web page.
The mobile application FightHPV is an educational game developed to provide information about main topics related to HPV. It was developed by researchers at the Norwegian Cancer Registry and financed by NIASC. Read more here.
FIMM is recruiting a Bioinformatician as part of the NIASC network. Please apply before May 7th 2017.
NIASC and SICS organised hands-on workshop in Hadoop/Spark/Flink. More information can be found here here.