Jakub Ruszkowski

modelbased: An R package to make the most out of your statistical models through marginal means, marginal effects, and model predictions Makowski et al., (2025). modelbased: An R package to make the most out of your statistical models through marginal means, marginal effects, and model predictions. Journal of Open Source Software, 10(1...

#statstab #390 modelbased: An R package to make the most out of
your statistical models through marginal means,
marginal effects, and model predictions

Thoughts: Great package for getting predicted probabilities for your models.

#rstats #r #easystats

doi.org/10.21105/jos...

The Double-Icodextrin Dose Randomized Controlled Trial of a Double #Icodextrin Dose for #Older Patients on Incremental Continuous Ambulatory Peritoneal Dialysis #CAPD

#VisualAbstract by @md_abdulqader83

www.kireports.org/ar...

@lobbedezt.bsky.social @clemencebechade.bsky.social

The "reproducibility crisis" in science constantly makes headlines. Repro efforts are often limited. What if you could assess reproducibility of an entire field?

That's what @brunolemaitre.bsky.social et al. have done. Fly immunity is highly replicable & offers lessons for #metascience

A 🧵 1/n

[Skim] KI-Tools für die wissenschaftliche Literaturrecherche: Potenziale, Problematiken, Didaktik und Zukunftsperspektiven www.degruyterbrill.com/document/doi... - or AI Tools for Academic Literature Search: Possibilities, Problems, Didactics, and Future Prospects insanely comprehensive! (1)

Next level of cherry-picking. Lack of significance in Student's t-test? Report then F-test and interpret it as a t-test 🫣🫣🫣

(F-test compares variances, not means🤡)

Source: doi.org/10.3390/cell...

#Statistics thought of the day: Need power calculations for a 2-group comparison on an ordinal or continuous response variable Y with/without clumping at a specific value (e.g., 0) of Y, with a possibly bimodal, heavy tailed, or skewed distribution? See www.fharrell.com/post/pop/ #RStats #StatsSky

CLINICAL IMPACT:
Current CKD staging doesn't account for proximal tubular damage - a key risk factor for hypomagnesemia in CKD patients. 💊 Mg supplementation showed limited efficacy in proteinuric patients

Read more: doi.org/10.1093/ndt/...
🧵3/3

KEY FINDINGS:
🔍 Proteinuria = higher probability of hypo-Mg (OR 2.2; 95% CI 1.2–4.0), especially in non-diabetics
📈 Higher proteinuria (uPCR) → higher urinary Mg excretion (FE-Mg)
🧪 When proximal tubular markers were included in analysis, the uPCR-FEMg association weakened significantly

🧵2/3

HYPOMAGNESEMIA IN CKD - Renal Magnesium Wasting

While CKD typically causes hypermagnesemia due to ↓GFR, researchers from Osaka University found that ~15% of CKD patients paradoxically develop hypomagnesemia instead.
academic.oup.com/ndt/article/...
🧵1/3

#NephSky #Nephrology

Fecal microbiota transplantation from patients into animals to establish human microbiota-associated animal models: a scoping review Journal of Translational Medicine

A Review published in the Journal of Translational Medicine gives an overview of the current state of research using human-to-animal fecal microbiota transplantation to elucidate the role of the gut microbiota in the pathophysiology of noninfectious diseases and traits.

#MedSky

Thanks for sharing! ☺️ I have to admit, my enthusiasm faded when I kept discovering—often buried deep in the manuscript or hidden in the supplements—that their “groundbreaking” findings were based on FMT from a single donor. 🤦‍♂️ The field suffers from weak methodology and poor reporting standards.

Fecal microbiota transplantation from patients into animals to establish human microbiota-associated animal models: a scoping review - Journal of Translational Medicine Background Fecal microbiota transplantation (FMT) from humans with specific medical conditions to animal models can demonstrate causality by inducing or exacerbating pathophenotypes, linking the gut m...

This field is exploding with potential! 🚀 But we need better methods and reporting to truly understand the gut-disease connection.

Hope you find this work (~ 2 years) interesting and helpful in your research!

🔎5/5

Our recommendations for better research (short version):
1️⃣ Follow GRAFT guidelines (adapted for human→animal FMT)
2️⃣ Use multiple donors
3️⃣ Include both sexes (if possible)
4️⃣ Verify microbiota colonization
5️⃣ Comprehensive outcome assessment
6️⃣ Transparent reporting

🔎4/5

MAJOR finding: Huge methodological gaps! 📋
🔸 Many studies use single donors (big generalizability problem!)
🔸 86% of studies don't report donor medications
🔸 Methods vary wildly (fresh vs frozen samples, different volumes)
We need standardization!
🔎3/5

What we found:
🔸 IBD, IBS, obesity, colorectal cancer & depression = most studied health issues
🔸 Cancer research focuses heavily on the non-responsivness to immunotherapy
🔸 Cardiovascular and renal outcomes are surprisingly understudied! 💔
🔎2/5

Fecal microbiota transplantation from patients into animals to establish human microbiota-associated animal models: a scoping review - Journal of Translational Medicine Background Fecal microbiota transplantation (FMT) from humans with specific medical conditions to animal models can demonstrate causality by inducing or exacerbating pathophenotypes, linking the gut m...

We just published the largest scoping review on fecal microbiota transplantation (FMT) from human patients to animals! Our team analyzed 489 studies that tried to go beyond showing CORRELATIONS between gut bacteria and disease, and focused on FMT from patients to animals to prove causality! 🔬

🔎1/5

#statstab #363 p-checker The one-for-all p-value analyzer

Thoughts: Easy way to check for publication bias using some current tools.

#shiny #pvalue #phacking #QRPs #zcurve #bias #pcurve #rindex

shinyapps.org/apps/p-check...

When should a Nephrologist suspect a mitochondrial disease? | Nefrología Mitochondrial diseases, taking into account those that affect the processes of the respiratory

"Maternally inherited diabetes and deafness is one of the most common mitochondrial diseases. (...) In all three cases, the symptoms were similar: diabetic patient, with hearing loss and renal involvement, non-nephrotic proteinuria and sediment without microhaematuria."

While slowing eGFR decline would be a major win, I'm struggling to see a pathophysiological basis for an increase in eGFR. Sclerosed glomeruli will not resume function. Seems we must rule out either decreased creatinine production or hyperfiltration as confounders before calling it remission.

BakRep – a searchable large-scale web repository for bacterial genomes, characterizations and metadata www.microbiologyresearch.org/content/jour... 🧬🖥️ Nextflow code: github.com/ag-computati...

Recovery of Tenofovir-induced Nephrotoxicity following Switch from Tenofovir Disoproxil Fumarate to Tenofovir Alafenamide in Human Immunodeficiency Virus-Positive Patients - PubMed Tenofovir-induced nephrotoxicity in HIV-positive patients receiving TDF was mostly reversible after changing to TAF. Thus, TAF-containing regimens can be administered safely to HIV-positive patients w...

Tenofovir-induced tubulopathy can be avoided by using tenofovir alafenamide instead of tenofovir disoproxil fumarate. I would gladly offer it to my patients with chronic hepatitis B, but unfortunately, in Poland, this formulation is available only in combination with other drugs for HIV.

Hearing loss and renal syndromes - Pediatric Nephrology The association between ear and kidney abnormalities has long been recognized; however, the connection between these two disparate organs is not always straightforward. Although Alport syndrome is the...

Alport-like syndrome with thrombocytopenia? Think about MYH9-related disorders (Epstein syndrome, Fechtner syndrome, May–Hegglin anomaly, and Sebastian syndrome). MYH9 is the gene encoding nonmuscle myosin IIA.

link.springer.com/article/10.1...

Frontiers | Commentary: Efficacy of probiotics/synbiotics supplementation in patients with chronic kidney disease: a systematic review and meta-analysis of randomized controlled trials The article "Efficacy of probiotics/synbiotics supplementation in patients with chronic kidney disease: a systematic review and meta-analysis of randomi...

Probiotics have strain-specific effects: some may be helpful, and some may do harm. Most systematic reviews on probiotics in CKD are poor quality. I raised methodological concerns about the latest one (doi.org/10.3389/fnut...), but the authors didn’t respond, and it continues to be cited...

Pathophysiology of various MGRS lesions:
By Dr. Nasr at @glomcon.org

In WoS, PubMed, and Scopus, the number can be interpreted as the number of words between two terms. In PMID 33560326, there are 3 words between "replacement" and "hip". I don't get the logic behind n+1, but I will remember this rule for my future searches.

In case you missed it, we recently updated some of our packages, including many new features (again) in the #rstats #easystats {modelbased} package:
easystats.github.io/modelbased/n...
The last weeks we were working a lot on improving support and performance for Bayesian models and especially

#statstab #343 Interpreting Log Transformations in a Linear Model

Thoughts: Not always a good idea to transform data, but if you do you need to know what it means.

#log #transformation #datatype #data #model #nonlinear #r #guide

library.virginia.edu/data/article...

a close up of a woman 's face with the words oh my god what is that ALT: a close up of a woman 's face with the words oh my god what is that

ME:

Embase NEAR/2 gives the same results as NEAR/1, W/1, or :~1 in other places 🫣 I noticed the difference when using a new version of Embase "Query translator" and checked it manually.