https://github.com/ceharvs/directed-reading
Repo for Directed Reading and Research course. Fall 2014
Science Score: 23.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
○codemeta.json file
-
○.zenodo.json file
-
✓DOI references
Found 4 DOI reference(s) in README -
✓Academic publication links
Links to: ncbi.nlm.nih.gov, wiley.com, ieee.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (9.4%) to scientific vocabulary
Repository
Repo for Directed Reading and Research course. Fall 2014
Basic Info
- Host: GitHub
- Owner: ceharvs
- Language: TeX
- Default Branch: master
- Size: 17.5 MB
Statistics
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Directed-Reading
Repo for Directed Reading and Research course. Fall 2014
Related Articles
Big Data's Effect on Organ Transplants
http://mashable.com/2014/07/23/big-data-organ-transplants/ Article on big data and organ transplants but in regards to donor matching. Interesting article but more related to living donor matching than exploratory data analysis.
Big Data for All: Privacy and User Control in the Age ofAnalytics
Omer Tene andJules PolonetskyBigDataforAll: Privacy and User Control in the Age ofAnalytics, 11 Nw.J. TECH. & INTELL. PROP. 239 (2013). http://scholarlycommons.1aw.northwestern.edu/njtip/voll 1/iss5/1 Article reviews the "date deluge" which leads to privacy concerns and the need for a balance between beneficial uses of data and individual privacy. Protecting privacy becomes difficult as information is multiplied and shared among multiple parties around the world. Predictive analysis can become problematic when based on sensitive categories like health, race, or sexuality. Predictive analysis may have a stifling effect on individuals and society, perpetuating old prejudices.
Lung Transplant Outcome Prediction using UNOS Data
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6691751 Analysis of lung transplant data from UNOS to develop risk prediction models for mortality within 1 year of lung transplant using data mining. Dataset has 5319 patient instances. Data mining techniques were used to build predictive models for the outcome. Results were evaluates using the c-statistic. Feature selection was also used in the model to find a smaller subset of attributes that can potentially achieve similar prediction performance but can result in a simpler model. Sixteen different classification schemes were used in the study including support vector machines, artificial neural networks, decision tables, KStar, bayesian network, and logistic regression.
Two feature selection techniques were also used for the study: Correlation Feature Selection (CFS) and Information Gain. CFS was used to find a smaller subset of attributed and then information gain was used on the reduced set of attributes to find a ranking of the attributes.
The UNOS SAR file contained data on all transplant candidates and recipients in the US since 1987. Data entry is mandated by the 1984 National Transplantation Act. There is one record per waiting list registration/transplant event. Each record includes the most recent follow-up data including patient/graft survival. The dataset has about 500 fields used to characterize the candidate/recipient.
The WEKA (http://www.cs.waikato.ac.nz/ml/weka/) toolkit was used for the implementation of data mining techniques.
2011 U.S. Organ and Tissue Transplant Cost Estimates and Discussion
http://publications.milliman.com/research/health-rr/pdfs/2011-us-organ-tissue.pdf Report on the costs of organ transplants in the US. Average costs per member per month (PMPM) of the billed charges and utilization related to the 30 days before and 180 days folowing a transplant. Interesting report given with estimated costs for everything.
Organ Donation: Is an opt-in or opt-out system better
http://www.medicalnewstoday.com/articles/282905.php Analysis of 48 countries to see if opt-out or opt-in is a better approach. They don't go into hard/soft opt out. In 2013, 28K transplants were performed. Countried with opt-out systems had a higher total number of kidneys fonated. Opt-out systems also have the greatest overall number of transplants. Opt-in systems have a higher rate of kidney donations from living donors. !! Spain seems to have the best network!!
TRANSPLANT NEPHROLOGISTS AND SURGEONS: DO MORE TO INCREASE LIVING DONATION
http://www.kidney.org/news/transplant-nephrologists-and-surgeons-do-more-increase-living-donation Transplant surgons believe there aren't enough benefits to becoming a living organ donor. These medical professionals believe that there should be full reimbursement of out-of-pocket expenses such as medical bills, and childcare costs associated with organ donation. Strategies vary around the world for rewarding living donation. Some professionals said they agreed (in principal) with limited, government regulated trial of financial incentives for living kidney donation.
Others
http://www.ncbi.nlm.nih.gov/pubmed/18336698 http://www.nejm.org/doi/full/10.1056/NEJM198502283120905 - can't access http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3644053/pdf/nihms224965.pdf http://onlinelibrary.wiley.com/doi/10.1111/j.1600-6143.2011.03902.x/pdf http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2517970/pdf/116062008Article_628.pdf http://onlinelibrary.wiley.com/doi/10.1111/j.1600-6143.2010.03211.x/pdf http://www.ncbi.nlm.nih.gov/pubmed/12807104 - can't access http://onlinelibrary.wiley.com/doi/10.1111/j.1467-8322.2011.00837.x/pdf - can't access
Owner
- Name: Christine Harvey
- Login: ceharvs
- Kind: user
- Website: itsharveytime.com
- Repositories: 19
- Profile: https://github.com/ceharvs