Lorenzo Lolli

No more endless academic paper searches! Writing a research paper used to take weeks. With tlooto AI, you can go from a rough idea to a structure draft -- in just 3 minutes.

"With [some AI bullshit] you can go from a rough idea to a structured draft — in just 3 minutes"

We're so cooked.

"[T]he scientific enterprise is now witness to widespread, organized defection from the scientific public goods game. Large swaths of players, among them many scientists, reviewers, editors and publishers, are choosing to no longer make genuine contributions to the pot."

Fantastic new paper by @reeserichardson.bsky.social et al.

An enormous amount of work showing the extent of coordinated scientific fraud and involvement of some editors.
The number of fraudulent publications grows at a rate far outpacing that of legitimate science.
www.pnas.org/doi/10.1073/...

“As the investigation proceeded, it became clear that 𝙖 𝙗𝙧𝙤𝙖𝙙 𝙖𝙣𝙙 𝙨𝙤𝙥𝙝𝙞𝙨𝙩𝙞𝙘𝙖𝙩𝙚𝙙 𝙣𝙚𝙩𝙬𝙤𝙧𝙠 of about 35 authors 𝙬𝙚𝙧𝙚 𝙥𝙤𝙩𝙚𝙣𝙩𝙞𝙖𝙡𝙡𝙮 𝙘𝙤𝙡𝙡𝙪𝙙𝙞𝙣𝙜 over a very large number of journals and published papers, a fraction of which were published by Frontiers,” @retractionwatch.com

Frontiers to retract 122 articles, links thousands in other publishers’ journals to “unethical” network The publisher Frontiers has begun retracting a batch of 122 articles across five journals after an investigation found a network of authors and editors engaged in “unethical actions” such as manipu…

Frontiers to retract 122 articles, links thousands in other publishers’ journals to “unethical” network

Journals Operating Predatory Practices Are Systematically Eroding the Science Ethos: A Gate and Code Strategy to Minimise Their Operating Space and Restore Research Best Practice Scientific research seeks to extend knowledge and understanding, an activity that perhaps more than any other advances society and humanity. In essence, it is the search for truth. But, because it se....

here’s a positive suggestion for academic publishing.
Journals need to be accredited as meeting integrity standards in order to qualify for APCs
enviromicro-journals.onlinelibrary.wiley.com/doi/full/10....

It seems like a lot of systematic-reviews/meta-analyses are analogous to money laundering. You run a load of studies that nobody actually reads, many of them "dirty", through some process. On the other end you get "clean" results that the ignorant or deceitful can easily communicate as "evidence".

Even @robcaliff.bsky.social says "real world" data is only at the "promise" stage. The only thing it seems to be "missing" is accuracy, completeness, and the ability to account for bias. Their words not mine! 😜 www.nejm.org/doi/full/10....

ht @emilymoin.com

Cover picture with blog title & subtitle, and results graph in the background

Post just up: Is multiple imputation making up information?

tldr: no.

Includes a cheeky simulation study to demonstrate the point.
open.substack.com/pub/tpmorris...

New blogpost. The shitshow that results when a publisher fails to check up on their peer reviewers, with authors caught up in a nightmare process. deevybee.blogspot.com/2025/07/trou...

Our team quantified how often clinical prediction models are evaluated or used. Spoiler alert: we found more self-reported clinical use in patient care than evidence of thorough evaluation.

www.jclinepi.com/article/S089...

Excellent review discussing different issues plaguing also sports and exercise sciences with unjustified categorisation of continuous measurements and the “blanket” linear mixed-effects modelling on log-transformed values by default compared to more appropriate methods

www.jstor.org/stable/2991772

A brief guide to statistical analysis of grouped data in preclinical research Nature Metabolism - Clustering and nesting (C&N) arise in many preclinical studies, such as when animals are group-housed or share litters, or in cell culture. Ignoring C&N...

A brief guide to statistical analysis of grouped data in preclinical research rdcu.be/er3HG

This variable was measured 5 times within each period. There's a person by time interaction in each period – even the control periods! Probably, serial effects in the repeated measurements are masquerading as individual differences in the outcome over the treatment period. This is not HTE.

We can look at our replicate crossover trials (a type of n-of-1 trial), some having repeated measurements within each period, to explore this question. We can take a variable for which there was little evidence of HTE. Between-treatment consistency is poor with no person by treatment interaction.

The question was whether repeated measurements WITHIN a single treatment period is compatible with repeated administration of treatment-control cycles – as in sets of n-of-1 trials – for informing heterogeneity of treatment effects (HTE). We think not.

During the peer-review of our paper, “Understanding treatment response heterogeneity using randomised crossover trials: A primer for exercise and nutrition scientists”, an interesting question arose which @lorenzololli.bsky.social & I are now pursuing as our next project. osf.io/preprints/os...

Statistics Notes: Units of analysis In clinical studies the focus of interest is almost always the patient. If we carry out a randomised trial to compare two treatments we are interested in comparing the outcomes of patients who receive...

Essentially, a re-conceptualisation of what should be “the unit of analysis” compared to blokes like Bland and Altman who seemingly got it wrong all along, aside from highlighting further the robustness and prognostic value of the 𝒔𝒑𝒐𝒓𝒕𝒐𝒎𝒊𝒄𝒔 from their original study 😀

www.bmj.com/content/314/...

That reply was also excellent for highlighting their “…predictive model was developed based on 894 observations derived from distributed lag models created from 14,500 daily observations spanning 2 seasons. Therefore, the effective sample size is 894, rather than being limited to just 24 players”.

Our field brought -omics to a whole new level by forging novel “𝒔𝒑𝒐𝒓𝒕𝒐𝒎𝒊𝒄𝒔” to bridge “the gap between 𝒑𝒆𝒓𝒔𝒐𝒏𝒂𝒍𝒊𝒛𝒆𝒅 𝒎𝒆𝒅𝒊𝒄𝒊𝒏𝒆 and daily clinical practice…” 👀

journals.humankinetics.com/view/journal...

The leaky pipe of clinical prediction models. by @maartenvsmeden.bsky.social‬ et al

You can have all the omni-omics data in the world and the bestest algorithms, but eventually a predicted probability is produced & it should be evaluated using well-established methods, and correctly implemented in the context of medical decision making.

statsepi.substack.com/i/140315566/...

Quality of scientific papers questioned as academics ‘overwhelmed’ by the millions published Widespread mockery of AI-generated rat with giant penis in one paper brings problem to public attention

“Volume is a bad driver,” [Sir Mark Walport] said. “The incentive should be quality, not quantity. It’s about re-engineering the system in a way that encourages good research from beginning to end.”

www.theguardian.com/science/2025...

Thanks to @lorenzololli.bsky.social here is the accepted (in IJSNEM) version of our paper, "Understanding treatment response heterogeneity using randomised crossover trials: A primer for exercise and nutrition scientists". This is prior to the proofing stage: osf.io/preprints/os...

The only problem is that the citations go to papers that don't actually exist.

Carry-over Carry-on Treatment time During the time I worked in the pharmaceutical industry, I designed and analysed many cross-over trials. The simplest such trial would compare two treatments A & B (say) by allocating p...

Balaam's design. How it works and why you shouldn't use it.
www.linkedin.com/pulse/carry-...

It's not just about "faulty" data or privacy concerns. It's about whether the information conveyed by the device can help improve decision making in a manner that leads to better outcomes. We have ways of evaluating this, but they are largely ignored, in both academia and industry.

It is baffling how many do not understand that simulation is just a (usually inferior) way of doing the calculations. It is not a way of producing evidence.

We are not going to "sell" the public on the value of universities and higher education by aping how industry promotes itself.

Springer Nature book on machine learning is full of made-up citations Would you pay $169 for an introductory ebook on machine learning with citations that appear to be made up? If not, you might want to pass on purchasing Mastering Machine Learning: From Basics to Ad…

Of course it is:

Springer Nature book on machine learning is full of made-up citations retractionwatch.com/2025/06/30/s...

Some Practical Guidelines for Effective Sample Size Determination Sample size determination is often an important step in planning a statistical study—and it is usually a difficult one. Among the important hurdles to be surpassed, one must obtain an estimate of o...

“One cannot avoid addressing the issues of effect-size elicitation (𝙞𝙣 𝙖𝙗𝙨𝙤𝙡𝙪𝙩𝙚 𝙩𝙚𝙧𝙢𝙨) and estimating the error variance, as difficult as these may be.

𝙎𝙩𝙖𝙣𝙙𝙖𝙧𝙙𝙞𝙯𝙚𝙙 𝙚𝙛𝙛𝙚𝙘𝙩𝙨 𝙙𝙤 𝙣𝙤𝙩 𝙩𝙧𝙖𝙣𝙨𝙡𝙖𝙩𝙚 𝙞𝙣𝙩𝙤 𝙝𝙤𝙣𝙚𝙨𝙩 𝙨𝙩𝙖𝙩𝙚𝙢𝙚𝙣𝙩𝙨 𝙖𝙗𝙤𝙪𝙩 𝙨𝙩𝙪𝙙𝙮 𝙜𝙤𝙖𝙡𝙨.”

www.tandfonline.com/doi/abs/10.1...