Discovery of a structural class of antibiotics with explainable deep learning.
One of the challenges with deep learning (neural networks) is that although they find patterns the reasoning disappears into an endless detail of numbers. In this paper the researchers built an 'explainable' AI to discover antibiotics instead of such a 'black box'. "The discovery of novel structural...
Source: nature.com
Citations show gender bias — and the reasons are surprising
Homophily is the tendency for people to stick with similar people. Could this partly explain some of the gender bias in citations? "Women still tend to build more on women’s work, and men still tend to build on men’s work more." "Gender bias in paper citations is less common among younger scientists,...
Source: nature.com
Machines may be better at assisting, not replacing us.
Journalist Kawandeep Virdee sees if he can be replaced by AI by writing some predictions for 2024. "I gave ChatGPT the last 13 years of Nieman Lab predictions ... [and asked it what I'd write about in 2024]" [ChatGPT suggested] Navigating the infodemic: Strategies for media in the era of misinformation...
Source: niemanlab.org
(We are not) using eHealth Data to Inform CPD for Medical Practitioners
"There is no formal or well-established correlation between individual performance data obtained through eHealth data analysis and CPD planning and programming for medical practitioners; in particular, the literature shows no consistency in type of eHealth data to analyze, software and tools to use,...
Source: nih.gov
Development of a statistical analysis software for determining effectiveness of a comprehensive fall risk management protocol
"This quality improvement project resulted in the development of a computer application that allows clinicians and medical professionals to conduct data analysis in an in-clinic setting without the help of external statistical teams, and with minimal prior training in coding or mathematics."
Source: bmj.com
Coding excursions
Anonymity with encryption At Outcomes Engine we are working on techniques to gather data from learners, analyse the data, and share the data whilst maintaining anonymity. I was involved in some work in my previous company (pharmaceutical) with the security of personal data - in our case it was data...
These six questions will dictate the future of generative AI
Generative AI took the world by storm in 2023. Its future—and ours—will be shaped by what we do next. TL;DR 1. Will we ever mitigate the bias problem? (Probably) 2. How will AI change the way we apply copyright? (A lot) 3. How will it change our jobs? (Maybe not as much as feared but things will...
Source: technologyreview.com
Development and validation of Simulation Scenario Quality Instrument (SSQI)
A validated scale for measuring quality of simulation scenarios in medical education. "Background Due to the unmet need for valid instruments that evaluate critical components of simulation scenarios, this research aimed to develop and validate an instrument that measures the quality of healthcare...
Source: biomedcentral.com
High Pay Centre analysis of FTSE 350 pay ratios • High Pay Centre
Pay inequalities at UK's largest companies remain constant, despite ‘cost of living’ crisis. "The companies with lowest-paid UK employees (based on pay at the 25th percentile) were retailer JD Sports, where the lower quartile threshold was £11,240, pub chain Mitchells & Butlers (£15,161) and...
Source: highpaycentre.org
Cornwall: Nearly £5m awarded to tackle health inequalities
The aim of the work is to enable "more research on issues that affect people in Cornwall".
Source: bbc.com
Artificial intelligence for healthcare and medical education: a systematic review
"After searching and reading a large amount of literature, we were surprised to find that most of the literature related to “AI+medical/medical education” was of low quality... This suggests us to conduct new research or improve the quality of research related to AI and medical/medical education....
Source: nih.gov
Embracing Authenticity: Why Non-Algorithmic Social Media Platforms Are More Social Than Instagram, Tumblr, or Threads
The fallacy shared both by social media services and educational services is one of trying to engineer the perfect mix of content for their clients. What we find, I think, in both education and online media is that authentic content - that is, content based in a person's actual life and relations with...
Source: downes.ca
QR codes to become less convenient?
A sticker with a fraudulent QR code pasted over a legitimate one can lead the unwary to websites that can capture your personal data. Thornaby: Woman targeted in £13k train station QR code scam. Rail firm TransPennine Express has since removed QR codes from all of its station car parks. Is the root...
Source: bbc.com
AI cuts treatment time for cancer radiotherapy
The technology will be offered at cost price to all NHS trusts in England, following successful pilot studies.
Source: bbc.com
Microsoft: Chinese hackers hit key US bases on Guam
The malware hit facilities on Guam that would be critical to any US response to an invasion of Taiwan.
Source: bbc.com
AI information retrieval: A search engine researcher explains the promise and peril of letting ChatGPT and its cousins search
A new generation of artificial intelligence-based information access systems, which includes Microsoft’s Bing/ChatGPT, Google/Bard and Meta/LLaMA, is upending the traditional search engine mode of search input and output. These systems are able to take full sentences and even paragraphs as input and...
Source: ampproject.org
The effectiveness of team-based learning in nursing education: A systematic review - PubMed Nurse education today.
Overall, TBL was found to be effective in achieving undergraduate nursing students' learning outcomes, but evidence was not sufficiently strong to warrant that it is more effective than other teaching methods. The results of this review are in favour of the implementation of TBL in nursing education...
Source: nih.gov
Learning Outcomes of High-fidelity versus Table-Top Simulation in Undergraduate Emergency Medicine Education: Prospective,
The student's performance on quantitative medical-knowledge assessment was equivalent between the high-fidelity control and low-fidelity experimental simulation groups. Analysis of knowledge acquisition between the two groups also demonstrated statistical equivalence.
Source: nih.gov
Coaching for Clinician Educators
Branzetti, Jeremy. Love, Linda M.. Schulte, Elaine E. Journal of Graduate Medical Education. Clinician educators (CEs) face manifold challenges, such as teaching under increasing clinical productivity pressures, satisfying evolving accreditation requirements, and combatting trainee and faculty burnout....
Source: allenpress.com
Just a moment...
Source: nejm.org
RSS feed