Sign in

Andrew Vickers

@vickersbiostats.bsky.social
1K followers 46 following 678 posts

Biostatistician at Memorial Sloan Kettering Cancer Center. Special interest in prostate cancer, risk prediction, patient-reported outcomes, decision-making.

PostsRepliesMedia
Andrew Vickers @vickersbiostats.bsky.social · 06/10/2026
mm pattern 4 on biopsy far superior predictor of prostate cancer outcome than stage, grade, PSA, cores. We show using mm criteria rather than "favorable intermediate risk" would increase the number of US men eligible for active surveillance by >50,000. pubmed.ncbi.nlm.nih.gov/42830647/
pubmed.ncbi.nlm.nih.gov
Checking your browser - reCAPTCHA
010
Andrew Vickers @vickersbiostats.bsky.social · 05/10/2026
"When we tell a patient they have prostate cancer, we mean the pathologist has looked at prostate biopsy cores under a microscope and saw areas without a basal cell layer; what the patient hears, however, is something entirely different" academic.oup.com/jnci/advance...
academic.oup.com
Helping patients make better choices by relabeling pattern 3 prostate disease as noncancerous
I have sat in consulting rooms listening to my surgeon colleagues explain to a patient their diagnosis, prognosis, and recommended management. Every time,
021
Andrew Vickers @vickersbiostats.bsky.social · 17/09/2026
Netto et al published an argument against relabeling pattern 3 prostate disease as pre-cancerous: pattern 3 but not benign shares “canonical molecular alterations” with pattern 4. A literature review shows this to be false @uroegg @dr_coops bjui-journals.onlinelibrary.wiley.com/doi/10.1111/...
bjui-journals.onlinelibrary.wiley.com
Is Gleason pattern 3 cancer? Molecular features do not distinguish pattern 3 from benign tissue
Click on the article title to read more.
000
Andrew Vickers @vickersbiostats.bsky.social · 25/08/2026
Can anyone at AMA please explain to be the rationale of insisting on two significant figures for high p values but one significant figure for lower p values? The 4 in p=0.34 tells us nothing; truncating the 4 so p=0.034 is changed to 0.03 is losing information.
111
Andrew Vickers @vickersbiostats.bsky.social · 22/08/2026
On the left, Robin meets his hero, Jimmy Mickle, at frisbee summer camp, 2018. On the right, Robin and Jimmy after Robin's team, San Francisco Revolver, defeats Jimmy's (New York Pony) in the World Ultimate Club Championship final.
020
Andrew Vickers @vickersbiostats.bsky.social · 13/08/2026
Actually, it mainly depends on how you do testing. If you test mainly old folks, have liberal biopsy criteria and treat all cancers found harm > benefit. If you test only age<70, biopsy only if positive 2ry test like MRI, and surveil low risk cancers, benefit > harm.
000
Andrew Vickers @vickersbiostats.bsky.social · 12/08/2026
Almost all high-income countries have a national policy recommending shared decision-making before PSA screening. We show: a) this recommendation never justified by evidence; b) best evidence is PSA screening not a preference-sensitive decision. journals.sagepub.com/eprint/UP9VV...
journals.sagepub.com
Should there be informed decision-making for prostate cancer screening? An analysis of preference sensitivity - Andrew Vickers, Sigrid Carlsson, 2026
Background Almost all national guidelines groups recommend that individual men make an informed personal decision about whether to be screened for prostate canc...
030
Andrew Vickers @vickersbiostats.bsky.social · 11/08/2026
We always given folks information and ask for consent (even emergency appendectomy). That is very different from current policy of shared decision making.
100
Andrew Vickers @vickersbiostats.bsky.social · 10/08/2026
We have a separate paper showing that at the individual level, PSA screening is not a preference sensitive decision. The assertion that folks requesting a PSA should be counseled and made personal decision is not evidence based.
100
Andrew Vickers @vickersbiostats.bsky.social · 10/08/2026
Perfectly reasonable position. But then the policy should be "no PSA", not "have a PSA if you want one"
110
Andrew Vickers @vickersbiostats.bsky.social · 10/08/2026
Generally assumed population-based PSA screening = increased overdiagnosis. But already lots of PS testing going on. In a modeling study, we show organized screening would reduce PSA tests, overdiagnsosis compared to current disorganized approach onlinelibrary.wiley.com/doi/10.1002/...
onlinelibrary.wiley.com
Effect of Implementing Population‐Based Prostate‐Specific Antigen Screening on Testing Rates and Prostate Cancer Overdiagnosis in England: A Statistical Modelling Study
We undertook a statistical modeling study to determine the effect of implementing population-based prostate-specific antigen (PSA) screening in England on overdiagnosis and PSA testing rates in compa...
0114
Andrew Vickers @vickersbiostats.bsky.social · 07/08/2026
Can everyone stop using the term "real world data" and just be precise about setting, participants and interventions? grandroundsinurology.com/the-reality-...
grandroundsinurology.com
2283
Andrew Vickers @vickersbiostats.bsky.social · 21/07/2026
I've long been suspicious of "regret" as an endpoint. This is principally because decisional regret is predicated on the (improbable) understanding of outcome under the counterfactual. New paper shows regret is basically explained by "I had a bad outcome". pubmed.ncbi.nlm.nih.gov/42429300/
pubmed.ncbi.nlm.nih.gov
Function drives 1-year decision regret in radical prostatectomy: a multicentre prospective study - PubMed
Surgical decision regret after RP is primarily driven by postoperative functional outcomes rather than oncological results or surgical approach. Optimising functional recovery and managing patient exp...
021
Andrew Vickers @vickersbiostats.bsky.social · 21/07/2026
Hiring right now and the surnames on our shortlist have the following origins: Jewish, Chinese, Irish, West African, East European, English, South Asian, Spanish. What a joy to live in a country where we get so many different histories and perspectives.
121
Andrew Vickers @vickersbiostats.bsky.social · 16/07/2026
Hasn’t it been amazing to see teams from the minor footballing countries doing so well at the world cup, even if they come up short? I refer to Morocco, Egypt, Cape Verde and, of course, England.
020
Andrew Vickers @vickersbiostats.bsky.social · 09/07/2026
When I report that I am doing a randomized trial, this is in distinction to a study with non-randomized or historical controls. But when a researcher claims to be analyzing "real world data", this is in distinction to what exactly?
031
Andrew Vickers @vickersbiostats.bsky.social · 23/06/2026
Looking for the best papers on the positive and negative likelihood ratio for prostate MRI. What is LR+ and LR- separately for PIRADS 3, 4 and 5? Problem is, this can only be derived from a study where everyone had a biopsy or long-term follow-up.
000
Andrew Vickers @vickersbiostats.bsky.social · 17/06/2026
Has anyone been noticing folks are starting to say "numerically superior" to describe results that are not statistically significant?
020
Andrew Vickers @vickersbiostats.bsky.social · 12/06/2026
Can someone explain to be how, in meta-analysis, leave-one-out methodology, has anything to do with exploring the sources of heterogeneity?
221
Andrew Vickers @vickersbiostats.bsky.social · 10/06/2026
One of my true heroes. She managed to find a work around to a catch-22 that male doctors had created to prevent women becoming doctors.
010
Andrew Vickers @vickersbiostats.bsky.social · 10/06/2026
I've actually challenged both him and his supporters to cite a single paper where he found something out, rather than just whine about other people's studies.
010
Andrew Vickers @vickersbiostats.bsky.social · 26/05/2026
Lots of interesting arguments against removing "cancer" label from pattern 3 prostate disease. For instance, pattern 3 involves basal cells & often has PTEN loss. Question now is whether these are a hill worth other people dying on. jamanetwork.com/journals/jam...
jamanetwork.com
Prostate Cancer Mortality After Relabeling Low-Grade Prostate Cancer as Precancerous
This decision analytical model study evaluates the effects of relabeling grade group 1 prostate cancer on prostate cancer mortality in the US.
000
Andrew Vickers @vickersbiostats.bsky.social · 04/05/2026
"Due to low sensitivity, PSMA-PET/CT without evidence of nodal disease does not obviate the need for PLND" BUT "PSMA-avid nodal disease portends ... nearly inevitable ... recurrence / progression, supporting treatment intensification." bjui-journals.onlinelibrary.wiley.com/doi/10.1111/...
bjui-journals.onlinelibrary.wiley.com
Diagnostic and prognostic utility of PSMA‐PET/CT in node‐metastatic prostate cancer
Objective To measure the sensitivity of prostate-specific membrane antigen-positron emission tomography/computed tomography (PSMA-PET/CT) for detecting lymph node involvement (LNI) in patients under.....
010
Andrew Vickers @vickersbiostats.bsky.social · 30/04/2026
Definitely not! we should also look at QoL. But mortality is also of interest, hence request for your thoughts.
000
Andrew Vickers @vickersbiostats.bsky.social · 30/04/2026
PSA screening reduces cancer-specific mortality (PCSM). Questions remain about effect on all-cause (OS). PSA could reduce PCSM not OS only with deaths from other causes, eg complications of surgery. Please reply with list of screening-induced causes of death.
000
Reposted by Andrew Vickers
Stuart McDonald @actuarybyday.bsky.social · 24/04/2026
If the UK were a US state, how would it rank? It depends entirely on what you measure! Fascinating table showing a startlingly different picture depending on the choice of metric. Source: www.linkedin.com/posts/diogo-...
19311154
Andrew Vickers @vickersbiostats.bsky.social · 22/04/2026
Analysis of the CAP randomized trials demonstrates prostate cancer overdiagnosis is highly age dependent. Opportunistic screening policies have led to most PSA tests being in older men. These policies should be revaluated. onlinelibrary.wiley.com/doi/10.1002/ijc.70492
onlinelibrary.wiley.com
Evaluating the Impact of Age on Prostate Cancer Overdiagnosis Using Long‐Term Follow‐Up From the CAP Randomised Trial
Uncertainty persists over whether the benefits of prostate-specific antigen (PSA) screening outweigh harms from overdiagnosis, a key barrier to population-wide adoption. Here, English male mortality ....
053
Andrew Vickers @vickersbiostats.bsky.social · 16/04/2026
Accrual to cancer RCTs is very poor. Keeping the product (ie the trial) the same but changing the advertising has a very small effect doi.org/10.1002/cam4.... Alternatively , change the product pubmed.ncbi.nlm.nih.gov/39410769/: it is possible to rapidly accrue to large, single-center RCTs
doi.org
Strategies for increasing accrual in cancer clinical trials: What is the evidence?
Introduction Despite the importance of clinical trial participation among cancer patients, few participate—and even fewer patients from ethnic and racial minoritized groups. It is unclear whether su.....
010
Andrew Vickers @vickersbiostats.bsky.social · 16/04/2026
Time to bring back a classic! I asked a journal editor for a date. She declined, but said I could date her sister if I paid $4,000.
000
Andrew Vickers @vickersbiostats.bsky.social · 13/04/2026
Just saw geology undergraduate final presentations @carleton.edu Way better presentational, statistical and causal reasoning skills than at typical medical conferences. Why we aren’t teaching our fellows and residents better, given that, you know, lives are at stake?
010
Andrew Vickers @vickersbiostats.bsky.social · 02/04/2026
Doing statistics well is hard. Avoiding egregious errors in analysis, reporting and interpretation isn't. Just read, understand and follow the guidelines. pubmed.ncbi.nlm.nih.gov/32451178/ pubmed.ncbi.nlm.nih.gov/37286459/ pubmed.ncbi.nlm.nih.gov/40914655/ pubmed.ncbi.nlm.nih.gov/30580902/
pubmed.ncbi.nlm.nih.gov
Guidelines for Reporting of Figures and Tables for Clinical Research in Urology - PubMed
In an effort to improve the presentation of and information within tables and figures in clinical urology research, we propose a set of appropriate guidelines. We introduce six principles: (1) include graphs only if they improve the reader's ability to understand the study findings; (2) think throug …
0116
Andrew Vickers @vickersbiostats.bsky.social · 27/03/2026
Just submitted a paper to "Diabetes & Metabolic Syndrome: Clinical Research & Reviews". Was asked by editor *before* they would peer review: my h-index ; all publications in past 12 months, along with impact factor of each journal in which they were published". #RealScience
020
Andrew Vickers @vickersbiostats.bsky.social · 11/03/2026
pubmed.ncbi.nlm.nih.gov/29404569/
pubmed.ncbi.nlm.nih.gov
Statistical Code for Clinical Research Papers in a High-Impact Specialist Medical Journal - PubMed
Statistical Code for Clinical Research Papers in a High-Impact Specialist Medical Journal
030
Andrew Vickers @vickersbiostats.bsky.social · 04/03/2026
They start with two premises I don't support. 1) you can assess heterogeneity by eyeballing the trials and deciding whether they seem similar enough, and (2) if not, random effects is the solution. Random effects does not deal with the problem of heterogeneity!!!
000
Andrew Vickers @vickersbiostats.bsky.social · 04/03/2026
I know, shocking, right?
000
Andrew Vickers @vickersbiostats.bsky.social · 03/03/2026
If only AI / ML had been around when I was training, I wouldn’t have had to learn about things like causal inference, how to evaluate prediction models or even, say, the importance of data quality. What a waste of time all that was!
151
Andrew Vickers @vickersbiostats.bsky.social · 28/02/2026
Any suggestions as to great resources (lectures on YouTube, short didactic papers etc), to teach novice researchers about RCTs? Design, endpoints, consent, eligibility criteria, IRB etc etc any and all of it.
123
Andrew Vickers @vickersbiostats.bsky.social · 25/02/2026
Is this a great argument for most statisticians to use Stata?
230
Andrew Vickers @vickersbiostats.bsky.social · 24/02/2026
see pubmed.ncbi.nlm.nih.gov/40914655/. In brief, a random effects meta analysis requires that we estimate the random effects variance, and we can't do that if we have only a few trials. Imagine you had measured a marker on 4 patients and someone asked you what the standard deviation was.
pubmed.ncbi.nlm.nih.gov
Guidelines for Meta-analyses and Systematic Reviews in Urology - PubMed
Our guideline comprises points addressing the conduct and interpretation of systematic reviews and meta-analyses in urology. Application of the guideline would lead to a more considered interpretation of a smaller number of systematic reviews and meta-analyses, and could thus help in translating evi …
120
Andrew Vickers @vickersbiostats.bsky.social · 24/02/2026
Revman and the idea of standardizing meta-analysis was brilliant in the 1990s. That is no longer the case.
031
Andrew Vickers @vickersbiostats.bsky.social · 23/02/2026
Yes, we mention that here.https://pubmed.ncbi.nlm.nih.gov/40914655/. The post was really directed at the 99% of meta-analyses that use standard software and don't even include a statistician
121
Andrew Vickers @vickersbiostats.bsky.social · 23/02/2026
Email me!
100
Andrew Vickers @vickersbiostats.bsky.social · 21/02/2026
COULD EVERYONE PLEASE STOP USING RANDOM EFFECTS META-ANALYSIS WHEN COMBINING 3 OR 4 TRIALS? AND COULD REVIEWERS STOP DEMANDING IT?
352
Andrew Vickers @vickersbiostats.bsky.social · 11/02/2026
Great take! calibration is critical for decision making (see Ben Van Calster on this point)
010
Andrew Vickers @vickersbiostats.bsky.social · 10/02/2026
today.yougov.com/politics/art...
today.yougov.com
​​From millionaires to Muslims, small subgroups of the population seem much larger to many Americans | YouGov
When it comes to estimating the size of demographic groups, Americans rarely get it right. In two recent YouGov polls, we asked respondents to guess the percentage (ranging from 0% to 100%) of America...
110
Andrew Vickers @vickersbiostats.bsky.social · 10/02/2026
www.auajournals.org/doi/10.1097/... Lymph node dissection (LND) for radical prostatectomy: controversy about RCT, complication rate. Decision analysis puts numerical estimates on benefit, harm, uncertainty. Expected utility of LND was higher vs. no PLND across broad range of scenarios.
auajournals.org
Decision Analysis of Pelvic Lymph Node Dissection During Radical Prostatectomy | Journal of Urology
Purpose:There is controversy about the decision of whether to perform a pelvic lymph node dissection (PLND) during radical prostatectomy for prostate cancer. While a recent randomized trial reported a...
110
Andrew Vickers @vickersbiostats.bsky.social · 27/01/2026
we have shown several times that once you know PSA, PRS is non-predictive (i can send references if you like)
040
Andrew Vickers @vickersbiostats.bsky.social · 27/01/2026
Yet again, PRS do not differentially distinguish aggressive from indolent cancer. & BARCODE RCT showed poor results compared to MRI etc. Yet the authors give a thumbs up to genomics in prostate cancer screening. When is the PRS fever going to break? www.nature.com/articles/s43...
nature.com
Genomic risk model to implement precision prostate cancer screening in clinical care: the ProGRESS study - Nature Cancer
Vassy, Dornisch and colleagues developed a genomics-based prostate cancer risk model to support a randomized clinical trial of precision screening in a national healthcare system.
120
Andrew Vickers @vickersbiostats.bsky.social · 26/01/2026
Too many meta-analyses have findings equivalent to: “If you average the cost of a loaf of bread, car insurance for a year and a movie ticket, you get $752.36”
25411
Andrew Vickers @vickersbiostats.bsky.social · 22/01/2026
pmc.ncbi.nlm.nih.gov/articles/PMC...
pmc.ncbi.nlm.nih.gov
Guidelines for Reporting of Statistics for Clinical Research in Urology
In an effort to improve the quality of statistics in the clinical urology literature, statisticians at European Urology, The Journal of Urology, Urology, and BJUI came together to develop a set of guidelines to address common errors of statistical ...
110