Sign in

Rudolf J

@rudolfjs.id.au
291 followers 1.6K following 6 posts

Digital Health Researcher. Industry Fellow at UQ. Associate Fellow Australasian Institute of Digital Health.

PostsRepliesMedia
Reposted by Rudolf J
Open Access Tracking Project @oatp.fediscience.org.ap.brid.gy · 09/07/2026
Toward Collaborative Reproducible Manuscripts www.cos.io/blog/toward-collaborativ…
cos.io
Toward Collaborative Reproducible Manuscripts
COS Principal Research Scientist Noah Haber shares how the SCORE project developed a collaborative reproducible manuscript workflow, walks through two different approaches, and introduces an open-source R package created from that work.
141
Reposted by Rudolf J
UQ Research Computing Centre @uq-rcc.bsky.social · 14/05/2026
We will take over operational responsibility for the Queensland Node of the ARDC Nectar Research Cloud from QCIF Digital Research from 1 July 2026. This transition is building on UQ/RCC's extensive experience in delivering national research services. rcc.uq.edu.au/article/2026... #UQ @ardc.edu.au
rcc.uq.edu.au
Queensland Nectar Node transition to UQ
042
Reposted by Rudolf J
Australian Research Data Commons (ARDC) @ardc.edu.au · 05/05/2026
📣Have your say: ARDC Annual Survey now open! Help improve the services we deliver to the Australian research community. Start the 5 min survey now: bit.ly/2026-ardc-su...
Card reading "A R D C Survey 2026 - Tell Us What You Think - Take the survey" against a photo of attendees at an A R D C event happily stretching
057
Rudolf J @rudolfjs.id.au · 15/04/2026
I would love to know the how the team went. We are preparing for RHEL 9.7 to RHEL 10 upgrade on our cluster.
130
Reposted by Rudolf J
Melissa McCradden @mdmccradden.bsky.social · 18/02/2026
What is a silent evaluation in #HealthAI ? And how do you do one? 👀 check out our new paper! We performed a scoping study re published practices in silent evals for AI/ML tools - everything from hospital-based prediction algos to regulatory-approved medical devices www.nature.com/articles/s44...
nature.com
A scoping review of silent trials for medical artificial intelligence - Nature Health
This scoping review examines previous experience in performing silent evaluations of clinical AI applications, collecting evidence from 75 studies on implementation features and the sociotechnical con...
111
Reposted by Rudolf J
National Computational Infrastructure @nci-australia.bsky.social · 16/01/2026
011
Reposted by Rudolf J
National Computational Infrastructure @nci-australia.bsky.social · 09/01/2026
A first for 2026 and a first for the Southern Hemisphere. Applications are now open for IHPCSS 2026, hosted by @pawseycentre.bsky.social in Perth, Australia. 📍 Perth, WA 📅 12–17 July 2026 ⏰ Apply by 31 Jan 2026 🔗 ss26.ihpcss.org/application/ #IHPCSS2026 #HPC#EarlyCareerResearchers #GlobalScience
042
Rudolf J @rudolfjs.id.au · 09/12/2025
Will newsletter notifications be in this Bluesky account or will re:Port have it’s own account?
100
Reposted by Rudolf J
Springer @springer.springernature.com · 13/09/2025
Feeling overwhelmed in your research journey? You're not alone. The ECR Hub is a free, supportive space for early career researchers to share, learn, and connect. bit.ly/3JTKzZX #ECR #ResearchPublishing
ECR Hub
A space for early career researchers from across all disciplines to connect, learn, and discover tailored opportunities
032
Reposted by Rudolf J
The New Stack @thenewstack.io · 28/05/2025
A special CNCF licensing exception helps solidify OpenTofu as a vendor-neutral, community-driven Infrastructure as Code (IaC) solution.
bit.ly
OpenTofu Joins CNCF: New Home for Open Source IaC Project
A special CNCF licensing exception helps solidify OpenTofu as a vendor-neutral, community-driven Infrastructure as Code (IaC) solution.
001
Reposted by Rudolf J
NEJM AI @ai.nejm.org · 23/04/2025
A locally deployable, open-source LLM-Anonymizer can remove personal identifiers with high accuracy, offering a scalable and accessible solution for secure medical data processing. Learn more: nejm.ai/4iFTASJ #AI #MedSky #MLSky
A visual representation of how the LLM-Anonymizer can remove personal identifiers for medical documents
062
Reposted by Rudolf J
Adam Johnson @adamj.eu · 20/04/2025
#GitHub mini tip: Use the GitHub CLI command `gh issue develop -c` to create and checkout a local branch linked to the given issue. No need to name the branch, and when you later run `gh pr create`, the pull request will be linked to the issue automatically.
Example of running `gh issue develop -c`.
1324
Rudolf J @rudolfjs.id.au · 18/04/2025
Thrilled to share with @andrewmallett8.bsky.social our Study Protocol in @frontiersin.bsky.social on streamlining QA/Audit & unlocking health data! We detail AQuIRE (governance) & the RDL (secure data access) - working together for responsible QI innovation 🤝 📄 Paper: doi.org/10.3389/fdgt...
doi.org
Frontiers | Development and implementation of digital solutions in healthcare: insights from the Australian tertiary hospital landscape
032
Reposted by Rudolf J
Melissa McCradden @mdmccradden.bsky.social · 28/03/2025
Health AI research, meet critical appraisal 🤯 Time to get serious about methodology! PROBAST+AI is a tool for reviewing the quality, applicability, and risk of bias in AI studies. Very pleased to have had a part in this important work! #AIEthics #Bioethics #MedTwitter www.bmj.com/content/388/...
bmj.com
PROBAST+AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods
The Prediction model Risk Of Bias ASsessment Tool (PROBAST) is used to assess the quality, risk of bias, and applicability of prediction models or algorithms and of prediction model/algorithm studies....
011
Reposted by Rudolf J
Melissa McCradden @mdmccradden.bsky.social · 03/04/2025
Our new paper touches on some of the under-represented issues in ethics & tech in paediatrics 📣environmental impact and its relationship to global equity 📣codesign with youth 📣nurses at the forefront of tech We advocate for a broader look on ethics of tech www.sciencedirect.com/science/arti...
sciencedirect.com
Harnessing technology in pediatric nursing: Balancing innovation, equity and sustainability
011
Reposted by Rudolf J
Kubernetes @kubernetes.io · 30/03/2025
Kubernetes v1.33 sneak peek-
kubernetes.io
Kubernetes v1.33 sneak peek
As the release of Kubernetes v1.33 approaches, the Kubernetes project continues to evolve. Features may be deprecated, removed, or replaced to improve the overall health of the project. This blog post...
0103
Reposted by Rudolf J
Kubernetes @kubernetes.io · 30/03/2025
NFTables mode for kube-proxy-
buff.ly
NFTables mode for kube-proxy
A new nftables mode for kube-proxy was introduced as an alpha feature in Kubernetes 1.29. Currently in beta, it is expected to be GA as of 1.33. The new mode fixes long-standing performance problems with...
0174
Reposted by Rudolf J
Towards Data Science @towardsdatascience.com · 02/01/2025
Learn how you can leverage knowledge graphs and AI to retrieve, filter, and summarize large amounts of text data — Steve Hedden unpacks the process in a detailed tutorial, focused on the example of medical journal articles.
towardsdatascience.com
How to Build a Graph RAG App
Using knowledge graphs and AI to retrieve, filter, and summarize medical journal articles
022
Reposted by Rudolf J
Melissa McCradden @mdmccradden.bsky.social · 20/12/2024
It is so exciting to see this amazing work finally released in full! @xiaoliu.bsky.social is a rockstar 😁 We use these standards in #AIEthics review to encourage reflection on data for potential bias, assess for fairness concerns & raise the bar for #HealthAI Congrats @jaldmn.bsky.social & team!
041
Reposted by Rudolf J
Maarten van Smeden @maartenvsmeden.bsky.social · 18/12/2024
Were you taught that a model with Y = a + bX + cZ + dXZ is right and with Y = a + bXZ is wrong because interaction effects MUST be accompanied by their main effects? Well... maybe it's not that simple 👇
4428
Reposted by Rudolf J
Maarten van Smeden @maartenvsmeden.bsky.social · 23/12/2024
1) Class imbalance There is class imbalance if the binary outcome (0/1) of a study does not have equal numbers of 0s and 1s. Methods to artificially correct this imbalance are popular, but in many situations may do more harm than good arxiv.org/abs/2404.19494
arxiv.org
The harms of class imbalance corrections for machine learning based prediction models: a simulation study
Risk prediction models are increasingly used in healthcare to aid in clinical decision making. In most clinical contexts, model calibration (i.e., assessing the reliability of risk estimates) is criti...
2242
Reposted by Rudolf J
merve @merve.bsky.social · 31/12/2024
supercharge your LLM apps with smolagents 🔥 however cool your LLM is, without being agentic it can only go so far enter smolagents: a new agent library by @hf.co to make the LLM write code, do analysis and automate boring stuff! huggingface.co/blog/smolage...
thumbnail that says introducing smolagents
28516
Reposted by Rudolf J
EQUATOR Network @equatornetwork.bsky.social · 29/12/2024
2024 saw release of the CHEERS guidance for reporting economic evaluations of health technologies that use #AI www.valueinhealthjournal.com/article/S109... #artificialintelligence #reporting #transparency
057
Reposted by Rudolf J
EQUATOR Network @equatornetwork.bsky.social · 29/12/2024
2024 saw a major update of the TRIPOD reporting standards for #artificialintelligence and #machinelearning in healthcare www.bmj.com/content/385/... (guidance) www.bmj.com/content/385/... (opinion piece) #statsSky #MLSky #transparency #reportingstandards #AI
297
Reposted by Rudolf J
Elinor @elinorpd.bsky.social · 28/12/2024
i went through goodresearch.dev today and its very helpful and interesting! especially the neuroscience section "Brains & coding" about how to structure your code and thinking to minimize short term memory burden! and very practical, there's a tidbit on creating a project package for each project!
goodresearch.dev
The Good Research Code Handbook
This handbook is for grad students, postdocs and PIs who do a lot of programming as part of their research. It will teach you, in a practical manner, how to organize your code so that it is easy to...
2132
Reposted by Rudolf J
European Commission @ec.europa.eu · 28/12/2024
It’s time for THE charger. Today, the USB-C becomes officially the common standard for charging new mobile electronic devices in the EU. It means better-charging technology, reduced e-waste, and less fuss to find the chargers you need! #DigitalEU
A minimalist illustration showing a packaged charger box labeled "one Union one Charger." The box features an image of a blue charger with the European Union flag symbol and a USB-C cable. The scene is set within a holiday theme, with decorative Christmas trees, ornaments, and gift boxes surrounding the charger box. In the top right corner, there is a small EU flag symbol.
21677681643
Reposted by Rudolf J
megan peters 🧠 @meganakpeters.bsky.social · 21/12/2024
this this this 100%. a few days ago, i allowed myself to NOT look at screens & emails as soon as i woke up. instead, i lay in bed, half asleep, & thought for a while. and i worked out a solution to a problem. forget fear: EMAIL is the mind killer, the little-death that brings total obliteration.
5707
Reposted by Rudolf J
Altmetric @altmetric.com · 22/12/2024
If you or your research group/university/fellow astronauts run a blog or a site that focuses on sharing or talking about your research, DM us the link and we’ll track it for you.
media.tenor.com
a man in a suit and tie is sitting in a car and says this is totally going in my blog
Alt: a man in a suit and tie is sitting in a car and says this is totally going in my blog
27921
Reposted by Rudolf J
Anna Clemens, PhD @annaclemens.com · 21/12/2024
Sitting and looking at a blank piece of paper, thinking... 💭 "I'm gonna do something else because it's just not flowing" Conquer the blank page #AcademicSky #NewPI #Postdoc
annaclemens.com
How to Start Writing a Research Paper
Staring at a the blank page and don't know where to start? Here are 6 strategies that will help you get started to write your scientific paper and stop procrastinating.
084
Reposted by Rudolf J
GitHub @github.com · 21/12/2024
Try it out now on GitHub Models ⬇️ github.blog/changelog/20...
"Mistral Large 24.11 is now available in GitHub Models" with a purple background
0596
Reposted by Rudolf J
Jeremy Howard @howard.fm · 19/12/2024
I'll get straight to the point. We trained 2 new models. Like BERT, but modern. ModernBERT. Not some hypey GenAI thing, but a proper workhorse model, for retrieval, classification, etc. Real practical stuff. It's much faster, more accurate, longer context, and more useful. 🧵
19620147
Reposted by Rudolf J
Bluesky @bsky.app · 19/12/2024
📢 App Version 1.96 is rolling out now (1/6) In this release: a notifications Mentions tab, reserving your default username when you verify your account with a domain, and other improvements!
Bluesky 1.96. Improvements: New "Mentions" tab in notifications. Usernames on .bsky.social are now reserved when you switch to your own domain. New button to change reply ordering and visual style in threads. Visual improvements to the app. New translations: Nepali, Khmer, and Romanian.
807200772995
Reposted by Rudolf J
Fabrizio Gilardi @fgilardi.bsky.social · 18/12/2024
✨ New LLM paper ✨ > Open-source LLMs perform well in text annotation tasks > Fine-tuned open-source LLMs outperform zero-shot GPT-4 > Fine-tuning beats few-shot training with modest amount of annotated data w/ @malizadeh.bsky.social @maelkubli.bsky.social et al. link.springer.com/article/10.1...
19925
Rudolf J @rudolfjs.id.au · 18/12/2024
Excited to share our new paper in BMC Nephrology examining hyperkalaemia in hospital patients. Proud of working with @andrewmallett8.bsky.social and the team in advancing understanding of this important condition. Link to paper: doi.org/10.1186/s128...
doi.org
Hyperkalaemia among hospital admissions: prevalence, risk factors, treatment and impact on length of stay - BMC Nephrology
Background Hyperkalaemia is one of the common electrolyte disorders among hospital patients, affected by many risk factors including medications and medical conditions. Prompt treatment is important g...
061
Reposted by Rudolf J
Katrina Ray @heykatray.bsky.social · 18/12/2024
We are go! Follow the new #NatureReviews journals and #NatureProtocols starter pack go.bsky.app/KcxvQLp 🧪 @natureportfolio.bsky.social
67842
Reposted by Rudolf J
nixCraft @cyberciti.biz · 18/12/2024
//Did you know you can colorize and print all IP addresses and interfaces on Linux in a tabular format for better readability? ip -br -c addr show ip -br -c link show See our ip command guide www.cyberciti.biz/faq/linux-ip... pretty cool, huh? #Linux #SysAdmin #devops
613016
Reposted by Rudolf J
ACM FAccT @facct.bsky.social · 17/12/2024
Reminder: The #FAccT2025 submission deadlines are roughly one month away! Abstracts are due January 15th and full papers on January 22nd. See the full CfP here: facctconference.org/2025/cfp
facctconference.org
ACM FAccT - 2025 CFP
02612
Rudolf J @rudolfjs.id.au · 18/12/2024
Deep memory unlocked, I use to love getting these!
000
Reposted by Rudolf J
Mark Rubin @markrubin.bsky.social · 17/12/2024
"Real-life error rates are unknown and even difficult to fully conceptualize....Theoretical error rates are only as trustworthy as the assumed model of the process that generated the real-life data." New preprint by Megan Higgs and Valentin Amrhein: www.preprints.org/manuscript/2... #Methodology 🧪
Researchers often need to justify their choice of sample size, particularly in fields such as animal research, where there are obvious ethical concerns about relying on too many or too few study subjects. The common approach is still to depend on statistical power calculations, typically carried out using simple formulas and default values. Over-reliance on power, however, not only carries the baggage of statistical hypothesis tests that have been criticized for decades, but also blocks an opportunity to strengthen the research in the design phase by learning about challenges in interpretation before the study is carried out. We recommend constructing a “quantitative backdrop” in the planning stage of a study, which means explicitly connecting ranges of possible research outcomes to their expected real-life implications. Such a backdrop can then in principle serve to identify single values of interest for use in traditional power analyses; or better, inform sample size investigations based on the goal of achieving an interval width narrow enough to distinguish values deemed practically or clinically important from those not representing practically meaningful effects. The latter bases calculations on a desired precision (rather than desired power) and relies on meaningful context rather than estimates obtained from previous research. Sample size justification should not be seen as an automatic math exercise with a right answer, but as a nuanced a priori investigation of measurement, design, analysis, and interpretation challenges.
14010
Reposted by Rudolf J
nixCraft @cyberciti.biz · 18/12/2024
I guess I am the IT department. 🥹
918218
Reposted by Rudolf J
Altmetric @altmetric.com · 17/12/2024
NEW The @digital-science.com Dimensions service now features "Share to Bluesky" buttons when you hit the Share icon. Nice positioning too. Items shared using Dimensions pages like this are tracked by Altmetric too btw. app.dimensions.ai/details/publ...
A Dimensions page with the Sharing pane open. Bluesky is the first option available. 

From: https://app.dimensions.ai/details/publication/pub.1182565350?search_mode=content&search_text=a%20place%20of%20joy&search_type=kws&search_field=text_search&order=altmetric
1426
Reposted by Rudolf J
Scott McGrath @smcgrath.phd · 16/12/2024
🧪 Nearly 63% of US adults value being notified of AI use in healthcare, with women and older adults most concerned. Transparent practices tailored to diverse needs can build trust. 🩺💻 #MLSky
jamanetwork.com
Public Attitudes Toward Notification of Use of AI in Health Care
This survey study examines public expectations related to notification about the use of artificial intelligence (AI) in health care.
0248
Reposted by Rudolf J
Altmetric @altmetric.com · 17/12/2024
A neat project released on Zenodo: "Standing out of the crowd – How can researchers be more visible?" An altmetrics comic by the team at @univie.ac.at doi.org/10.5281/zeno...
Front page for "Standing Out of the Crowd" on Zenodo. A webcomic about altmetrics by the bibliometric team at University of Vienna. It shows a book case, flasks and test tubes and a desk with a book open on it. The book contains the text "A comic by Andreas Ferus, Christian Gumpenberger, Lothar Hölbling, Lisa Schilhan
2237