Can a Computer Replace a Pathologist? by Rishi Rawat
Can a Computer Replace a Pathologist? by Rishi Rawat
“This is an introductory course in machine learning (ML) that covers the basic theory, algorithms, and applications. ML is a key technology in Big Data, and in many financial, medical, commercial, and scientific applications. It enables computational systems to adaptively improve their performance with experience accumulated from the observed data. ML has become one of the hottest fields of study today, taken up by undergraduate and graduate students from 15 different majors at Caltech. This course balances theory and practice, and covers the mathematical as well as the heuristic aspects. The lectures below follow each other in a story-like fashion:
- What is learning?
- Can a machine learn?
- How to do it?
- How to do it well?
- Take-home lessons.
“The 18 lectures are about 60 minutes each plus Q&A.”
Caltech: Learning From Data Machine Learning Course by Yaser S. Abu-Mostafa
Textbook: Learning From Data by Yaser S. Abu-Mostafa and Malik Magdon-Ismail
Ronald Bayer, Ph.D., and Sandro Galea, M.D., Dr.P.H.
“The NIH’s most recent Estimates of Funding for Various Research, Condition, and Disease Categories report (www.report.nih.gov/categorical_spending.aspx) shows, for example, that total support in fiscal year 2014 for research areas including the words ‘gene,’ ‘genome,’ or ‘genetic’ was about 50% greater than funding for areas including the word ‘prevention.’…The proportion of NIH-funded projects with the words ‘public’ or ‘population’ in their title, for example, has dropped by 90% over the past 10 years, according to the NIH Reporter.”
“Without minimizing the possible gains to clinical care from greater realization of precision medicine’s promise, we worry that an unstinting focus on precision medicine by trusted spokespeople for health is a mistake — and a distraction from the goal of producing a healthier population.”
NEJM: Public Health in the Precision-Medicine Era by Ronald Bayer, Ph.D., and Sandro Galea, M.D., Dr.P.H.
“As much as 30% of the entire world’s stored data is generated in the health care industry. A single patient typically generates close to 80 megabytes each year in imaging and electronic medical record (EMR) data. This trove of data has obvious clinical, financial, and operational value for the health care industry, and the new value pathways that such data could enable have been estimated by McKinsey to be worth more than $300 billion annually in reduced costs alone…Read More”
NEJM Catalyst: Using It or Losing It? The Case for Data Scientists Inside Health Care by Marco D. Huesch, MBBS, PhD & Timothy J. Mosher, MD
Data science is blossoming as a field at the moment. Popular jargon from traditional statistics to new machine learning techniques are used colloquially in both online articles and day-to-day exchanges. One of the excellent things about data science, noted by David Venturi, is that by nature the field is computer-based. Why not learn about it all for free online then? Venturi has written several articles enumerating lists of massive open online courses (MOOC) relevant to someone interested in only a single highly-ranked data science class, or a complete masters degree in data science for the more dedicated individual. One of the benefits of these courses is they are more poignant and focus on only the knowledge relevant to applying data science skills. Another perk is the nonexistent price tag, as opposed to the tens or hundreds of thousands of dollars of student loans one could thrust themselves into while pursuing a data science masters at a formal institution. Venturi explains why he left grad school to learn about data science before finishing his first semester. If nothing else, some of these courses may be useful to supplement a graduate school education.
FreeCodeCamp.org: David Venturi
FreeCodeCamp.org: The best Data Science courses on the internet, ranked by your reviews
A population of healthy volunteers that are full-time tests subjects for clinical trials in the pharmaceutical industry
The New Yorker: Guinea-Pigging
Consumption of ultra-processed foods and cancer risk: results from NutriNet-Santé prospective cohort is a web-based survey looking at the association of cancer risk and consuming ultra-processed foods in people in France who responded to a survey. Population-based cohort studies were previously done by calling people’s landlines, asking them to fill out surveys, and requesting that they drive to the clinic for a health examination.
Perhaps further epidemiological studies will be done primarily using online surveys, as the authors did in this paper. It would make epidemiological studies much less expensive and more readily available. But the validity of the results have not yet been verified.
Using the internet selects for younger people responding to the survey. This may not be representative of the larger population. But as these generations age, using the internet for data collection may be a useful tool.
The internet is an anonymous place, and it is difficult to understand the population that is being studied when using the World Wide Web as the only data collection vehicle. This may be a worth-while sacrifice for the convenience of bypassing what has historically been the most arduous part of studying the public’s health.
A guide on learning how to type
I had no idea how to type entering medical school. My peers we’re jamming out notes on their macbook like Billy Joel after 3 bottles of red. My roommate told me about this Keybr site. It adds one letter at a time, and as you get better scores it adds more letters. It’s pretty addicting. But it doesn’t really teach you proper technique. I googled lessons, and there were a bunch of sites like How To Type that illustrates which keys to hit with which finger. So I learned and spent 30 hours in the basement of the library tapping away. This is one of the most useful skills I’ve learned in grad school. I can’t believe I went through college without learning to type. Don’t make my mistake. Be better than me.