For years, people from CEOs to novelists have taken tiny amounts of psychedelics to support well-being. New research shows that benefits for depression may be attributable to a placebo effect. Typically using psilocybin mushrooms or LSD, the archetypal microdoser sought less melting walls and open-eye kaleidoscopic visuals than boosts in mood and energy, like a gentle spring breeze blowing through the mind. Anecdotal reports pitched microdosing as a kind of psychedelic Swiss Army knife, providing everything from increased focus to a spiked libido and (perhaps most promisingly) lowered reported levels of depression. It was a miracle for many.

Systematic reviews (SR), in which experts summarize and analyze evidence across individual studies to provide insights on a specialized topic, are a cornerstone for evidence-based clinical decision-making, research, and policy. Given the exponential growth of scientific articles, there is growing interest in using large language models (LLMs) to automate SR generation. However, the ability of LLMs to critically assess evidence and reason across multiple documents to provide recommendations at the same proficiency as domain experts remains poorly characterized. We therefore ask: Can LLMs match the conclusions of systematic reviews written by clinical experts when given access to the same studies? To explore this question, we present MedEvidence, a benchmark pairing findings from 100 SRs with the studies they are based on. We benchmark 24 LLMs on MedEvidence, including reasoning, non-reasoning, medical specialist, and models across varying sizes (from 7B-700B). Through our systematic evaluation, we find that reasoning does not necessarily improve performance, larger models do not consistently yield greater gains, and knowledge-based fine-tuning degrades accuracy on MedEvidence. Instead, most models exhibit similar behavior: performance tends to degrade as token length increases, their responses show overconfidence, and, contrary to human experts, all models show a lack of scientific skepticism toward low-quality findings. These results suggest that more work is still required before LLMs can reliably match the observations from expert-conducted SRs, even though these systems are already deployed and being used by clinicians. We release our codebase and benchmark to the broader research community to further investigate LLM-based SR systems.

Modern multi-centre randomized controlled trials (MCRCTs) collect massive amounts of tabular data, and are monitored intensively for irregularities by humans. We began by empirically evaluating 6 modern machine learning-based outlier detection algorithms on the task of identifying irregular data in 838 datasets from 7 real-world MCRCTs with a total of 77,001 patients from over 44 countries. Our results reinforce key findings from prior work in the outlier detection literature on data from other domains. Existing algorithms often succeed at identifying irregularities without any supervision, with at least one algorithm exhibiting positive performance 70.6% of the time. However, performance across datasets varies substantially with no single algorithm performing consistently well, motivating new techniques for unsupervised model selection or other means of aggregating potentially discordant predictions from multiple candidate models. We propose the Meta-learned Probabilistic Ensemble (MePE), a simple algorithm for aggregating the predictions of multiple unsupervised models, and show that it performs favourably compared to recent meta-learning approaches for outlier detection model selection. While meta-learning shows promise, small ensembles outperform all forms of meta-learning on average, a negative result that may guide the application of current outlier detection approaches in healthcare and other real-world domains.

In 2018, volunteers with an interest in microdosing--regularly taking tiny amounts of psychedelic drugs such as LSD--began taking part in an unusual experiment. For four weeks, researchers at Imperial College London asked them to swap some of their drugs with empty capsules--placebos--so that when they took them, they didn't know if they were microdosing or not. They then completed online surveys and cognitive tasks at regular intervals, aimed at gauging their mental well-being and cognitive abilities. The idea: to explore if microdosing produces the benefits to mood and brain function that some people claim. This story originally appeared on WIRED UK.

Clinical trials are the basis of Evidence-Based Medicine. Trial results are reviewed by experts and consensus panels for producing meta-analyses and clinical practice guidelines. However, reviewing these results is a long and tedious task, hence the meta-analyses and guidelines are not updated each time a new trial is published. Moreover, the independence of experts may be difficult to appraise. On the contrary, in many other domains, including medical risk analysis, the advent of data science, big data and visual analytics allowed moving from expert-based to fact-based knowledge. Since 12 years, many trial results are publicly available online in trial registries. Nevertheless, data science methods have not yet been applied widely to trial data. In this paper, we present a platform for analyzing the safety events reported during clinical trials and published in trial registries. This platform is based on an ontological model including 582 trials on pain treatments, and uses semantic web technologies for querying this dataset at various levels of granularity. It also relies on a 26-dimensional flower glyph for the visualization of the Adverse Drug Events (ADE) rates in 13 categories and 2 levels of seriousness. We illustrate the interest of this platform through several use cases and we were able to find back conclusions that are known in the literature. The platform was presented to four experts in drug safety, and is publicly available online, with the ontology of pain treatment ADE.

The appearance of a new dangerous and contagious disease requires the development of a drug therapy faster than what is foreseen by usual mechanisms. Many drug therapy developments consist in investigating through different clinical trials the effects of different specific drug combinations by delivering it into a test group of ill patients, meanwhile a placebo treatment is delivered to the remaining ill patients, known as the control group. We compare the above technique to a new technique in which all patients receive a different and reasonable combination of drugs and use this outcome to feed a Neural Network. By averaging out fluctuations and recognizing different patient features, the Neural Network learns the pattern that connects the patients initial state to the outcome of the treatments and therefore can predict the best drug therapy better than the above method. In contrast to many available works, we do not study any detail of drugs composition nor interaction, but instead pose and solve the problem from a phenomenological point of view, which allows us to compare both methods. Although the conclusion is reached through mathematical modeling and is stable upon any reasonable model, this is a proof-of-concept that should be studied within other expertises before confronting a real scenario. All calculations, tools and scripts have been made open source for the community to test, modify or expand it. Finally it should be mentioned that, although the results presented here are in the context of a new disease in medical sciences, these are useful for any field that requires a experimental technique with a control group.

This paper describes Simpson's paradox, and explains its serious implications for randomised control trials. In particular, we show that for any number of variables we can simulate the result of a controlled trial which uniformly point s to one conclusion ( such as'drug is effective') for every possible combination of the variable states, but when a previously unobserved confounding variable is included every possible combination of the variables state points to the opposite conclusion ('drug is not effectiv e'). In other words no matter how many variables are considered, and no matter how'conclusive' the result, one cannot conclude the result is truly'valid' since there is theoretically an unobserved confounding variable that could completely reverse the re sult.

Higher expression of nine genes may help identify people with systemic lupus erythematosus (SLE) who will respond to treatment with Stelara (ustekinumab) -- an approved therapy in inflammatory disorders but not in SLE. At the 2019 American College of Rheumatology (ACR)/Association for Rheumatology Health Professionals (ARHP) Annual Meeting, being held in Atlanta Nov. 8-13, Janssen is presenting evidence of reduced SLE disease activity with Stelara, as well as a tool to predict benefits in clinical trials. Stelara works by blocking interleukin (IL)-12 and IL-23, two pro-inflammatory molecules. It is approved in the U.S. for the treatment of psoriasis and psoriatic arthritis, as well as Crohn's disease and ulcerative colitis, which are two forms of inflammatory bowel disease. Results from a Phase 2 trial (NCT02349061) showed that Stelara reduced SLE disease activity and severe flares, among other benefits, compared with a placebo.

It may be possible to spot if your relative, friend or colleague is ill just by looking at them, research suggests. Scientists injected volunteers with either E.coli or a placebo before asking others how sick they looked two hours later. The infected patients were judged to look'significantly worse', with people noticing their drooping eyelids and mouths. They also showed more negative facial expressions, which may be brought on by inflammation as the immune system fights off the infection. Researchers believe humans may have evolved the ability to pick up on subtle cues that suggest someone is contagious to avoid getting ill.

Schizophrenia, a mental disorder that is characterized by abnormal social behavior and failure to distinguish one's own thoughts and ideas from reality, has been associated with structural abnormalities in the architecture of functional brain networks. Using various methods from network analysis, we examine the effect of two classical therapeutic antipsychotics --- Aripiprazole and Sulpiride --- on the structure of functional brain networks of healthy controls and patients who have been diagnosed with schizophrenia. We compare the community structures of functional brain networks of different individuals using mesoscopic response functions, which measure how community structure changes across different scales of a network. We are able to do a reasonably good job of distinguishing patients from controls, and we are most successful at this task on people who have been treated with Aripiprazole. We demonstrate that this increased separation between patients and controls is related only to a change in the control group, as the functional brain networks of the patient group appear to be predominantly unaffected by this drug. This suggests that Aripiprazole has a significant and measurable effect on community structure in healthy individuals but not in individuals who are diagnosed with schizophrenia. In contrast, we find for individuals are given the drug Sulpiride that it is more difficult to separate the networks of patients from those of controls. Overall, we observe differences in the effects of the drugs (and a placebo) on community structure in patients and controls and also that this effect differs across groups. We thereby demonstrate that different types of antipsychotic drugs selectively affect mesoscale structures of brain networks, providing support that mesoscale structures such as communities are meaningful functional units in the brain.