Register for free to join our community of investors and share your ideas. You will also get access to streaming quotes, interactive charts, trades, portfolio, live options flow and more tools.
Register for free to join our community of investors and share your ideas. You will also get access to streaming quotes, interactive charts, trades, portfolio, live options flow and more tools.
Reasonable...but nothing has been very reasonable with this stock Low volume today might argue against this being related to a leaked continue decision. If no continue announcement by Friday, all bets are off again (I think it is unlikely they announce a continue on a Monday or Tuesday - just bad timing). If no announcement before the CC, then the later the announcement the better in my view (I would take this as the company expecting a stop and being in no rush in order to wait as long as possible before having to lock the dataset).
I also wonder whether there is a leak that a continue announcement is coming AH today or tomorrow? Timing makes sense at the end of the week and prior to the conference call.
Raf - FWIW - I totally agree. They would have to look at INCREASED risk of stroke, death, MI in the V group as a safety concern. Also agree with Tas that no formal statistical analysis of these patterns are likely. That said, if V is reducing risk by 30%, it would be hard not to notice this in the numbers, so the DMC has probably been aware all along whether V seems to be having a big effect. That does not necessarily mean that any of this has been communicated "off the record" to the company, but certainly not impossible given human nature and the effects of body language.
In this July presentation, I find it interesting that they seem to be more cagey than in the past about patients years. They are still saying >26,000, which if I recall correctly, was the same as 3 months ago. Maybe they do not want anyone being able to calculate likely efficacy so they are providing inaccurate (or incomplete) numbers
JF - I know from boilerplate language required in our IRB forms that research patients sign that the FDA has the right to access individual patient information for safety monitoring (e.g., confidentiality does not apply), and knowing the condition they were in would seem to be necessary to determine safety issues. In our blinded drug studies, when there seems to be an individual safety issue, we are required to break the blind for that patient to determine whether the adverse event is related to the study drug. This is for academic drug studies, but I would assume the same would apply to industry funded trials as well.
HDG - All good points. I was primarily referencing company statements that an advantage of adding the 80% was additional opportunities to enhance study retention and compliance (or something to that effect).
Kiwi - Good point. The company has said this and I believe the extra patient contacts are important for study retention and compliance. I was in a meeting last week where several FDA officials were present, and a high level person at one point commented on how hard it is to keep patients actively engaged in a "long-term study," and this was referring to months not years. CV trials may be a different animal though - all of the MACE outcome trials are very long, and maybe CAD (and high risk diabetic) patients have more reason to stay in a trial as the outcomes are literally life and death.
Yo - True. If they stop at "80% IA," all events from March to the announcement of stoppage (and data lock) get included. Actually, the published paper would reflect approx a 90% IA. As stated earlier, one reason to drag it out as long as possible.
True - Not a great time of year to try to get a bunch of academics in the same room for a DMC meeting.
Hayward - Yes. Only thing that changes is the range it bounces between.
Yo - Not talking about full FDA approval process. Only a quick meeting prior to any DMC decision announcement where the DMC shows the FDA current 80% IA data, and gets the FDA to agree that "yes, this makes sense to stop early." Agree with other poster that this is not highly likely given the relatively recent reaffirmation of the SPA around the the 60% IA.
Tas - I think I recall seeing somewhere that if they are going to stop the trial early, the company has the right (after getting the DMC recommendation) to go to the FDA and discuss whether the FDA is still on board for stopping (I believe the FDA can see unblinded results even if the company cannot - I know that is the case for safety issues). If true, this would obviously be done before any announcement, and I would expect this to add a week or so delay to any announcement. I have no idea whether this would actually happen though.
Raf - There are certain internationally accepted trial standards across the US AND EUROPE. If R-iT adhered to these standards they should be able to submit for R-It approval to the European Medicines Agency without additional trials. Not sure whether they adhered to these or not.
Only if statistically tested in a pre-planned analysis using correction for multiplicity as noted by AVI. See my post of FDA guidelines last week (#109594).
FWIW - Maybe posted before, but thought those of us who occasionally get bent out of shape by Pyrr's postings might be interested in his stock picking success.
According to his own blog, he is Steven Giardino: https://seekingalpha.com/instablog/18578282-steven-giardino/4894925-nwbo-cldx-past-picks. He is actually quite honest about some of the bad picks he has made.
Per Tipranks (https://www.tipranks.com/bloggers/steven-giardino): He is "Ranked #2,013 out of 6,075 Bloggers on TipRanks (#4,125 out of 10,667 overall experts)." His recommendations were profitable 25% of the time, and those who have followed his recommendations over time would have had an average return of 10.1%.
So, whether he is actually paid by anyone to bash certain stocks or not, he seems to be just another bozo on the bus with no more or less insight than any of us into what will happen with AMRN or any other stock. He is just more opinionated and more negative than (most of) the rest of us here are.
To All - Below are excerpts from a draft FDA document (not formal guidelines yet) very relevant to discussions of the SEs in R-It. (I received this coincidentally this morning for something unrelated). I have bolded some key areas. After reading this, I realized that whether the DMC analyzes SEs using a strict Type I error corrected p value (which would be more stringent than the p<.022 for the PE) depends on whether they intend to go for labeling that states that V specifically reduces [death, stroke, whatever]. Are they simply trying to get it labelled as "reduces incidence of CV events"? If the latter, the text below clearly indicates they don't have to have any formal Type I error adjusted statistical criterion for interpreting the SEs, and that the label would be very cautious about any conclusions other than overall MACE events. The MACE component SEs in this case would simply be reported as % to underscore that the effects of V were not due to one single dominant outcome, but rather across all key MACE components (This seemed to be the case in JELIS). This seems to me to be the gist of the rationale they have implied for looking at the SEs ("robust and consistent"), and the statements in the past that the SEs do NOT have to be statistically significant would also support this view. On the other hand, the fact that they have bothered to pre-specify SEs in their most recent FDA SPA might hint that they DO plan to look formally at key SEs as potential labelled indications.
While it would clearly be nice to say on the label that V reduces deaths (or any specific component), I have seen nothing from the company that would suggest they are aiming that high. Anyone else know about this? It also seems from what is stated below that their SE MACE component analyses could in theory use events after the first trigger MACE event, which would mean total event numbers for MACE components would be greater than the number of MACE events (and increase statistical power).
Excerpts Below:
The focus of this guidance is control of the Type I error rate for the planned primary and secondary endpoints of a clinical trial so that the major findings are well supported and the effects of the drug have been demonstrated. Once a trial is successful (demonstrates effectiveness or “wins” on the primary endpoint(s)), there are many other attributes of a drug’s effects that may be described. Analyses that describe these other attributes of a drug can be informative and are often included in physician labeling. Examples include: the time course of treatment effects; the full distribution of responses amongst participants; treatment effects on the components of a composite endpoint;and treatment effects amongst subgroups.
Nevertheless, it is important to understand that these descriptions with respect to additional attributes are not demonstrated additional effects of a drug unless the analyses were prespecified, and appropriate multiplicity adjustments were applied. Therefore, presenting p-values from descriptive analyses (that is, from analyses that were not prespecified and for which appropriate multiplicity adjustments were not applied) is inappropriate because doing so would imply a statistically rigorous conclusion and convey a level of certainty about the effects that is not supported by that trial.
Composite Endpoints
There are some disorders for which more than one clinical outcome in a clinical trial is important, and all outcomes are expected to be affected by the treatment. Rather than using each as a separate primary endpoint (creating multiplicity) or selecting just one to be the primary endpoint and designating the others as secondary endpoints, it may be appropriate to combine those clinical outcomes into a single variable. This is called a “composite endpoint,” where an endpoint is defined as the occurrence or realization in a patient of any one of the specified components. When the components correspond to distinct events, composite endpoints are often assessed as the time to first occurrence of any one of the components, but in diseases where a patient might have more than one event, it also may be possible to analyze total endpoint events. A single statistical test is performed on the composite endpoint; consequently, no multiplicity problem occurs and no statistical adjustment is needed.
An important reason for using a composite endpoint is that the incidence rate of each of the events may be too low to allow a study of reasonable size to have adequate power; the composite endpoint can provide a substantially higher overall event rate that allows a study with a reasonable sample size and study duration to have adequate power. Composite endpoints are often used when the goal of treatment is to prevent or delay morbid, clinically important but uncommon events (e.g., use of an anti-platelet drug in patients with coronary artery disease to prevent myocardial infarction, stroke, and death).
The choice of the components of a composite endpoint should be made carefully. Because the occurrence of any one of the individual components is considered to be an endpoint event, each of the components is of equal importance in the analysis of the composite. The treatment effect on the composite rate can be interpreted as characterizing the overall clinical effect when the individual events all have reasonably similar clinical importance. The effect on the composite endpoint, however, will not be a reasonable indicator of the effect on all of the components or an accurate description of the drug’s benefit, if the clinical importance of different components is substantially different and the drug effect is chiefly on the least important event. Furthermore, it is possible that a component with greater importance may appear to be adversely affected by the treatment, even if one or more event types of lesser importance are favorably affected, so that although the overall outcome still has a favorable statistical result, doubt may arise about the treatment’s clinical value. In this case, although the overall statistical analysis indicates the treatment is successful, careful examination of the data may call this conclusion into question. For this reason, as well as for a greater depth of understanding of the treatment’s effects, analyses of the components of the composite endpoint are important (see section III.D) and can influence interpretation of the overall study results.
For composite endpoints whose components correspond to events, an event is usually defined as the first occurrence of any of the designated component events. Such composites can be analyzed either with comparisons of proportions between study groups at the end of the study or using time-to-event analyses. The time-to-event method of analysis is the more common method when, within the study’s timeframe of observation, the duration of being event-free is clinically meaningful. Although there is an expectation that the drug will have a favorable effect on all the components of a composite endpoint, that is not a certainty. Results for each component event should therefore be individually examined and should always be included in study reports. These analyses will not alter a conclusion about the statistical significance of the composite primary endpoint and are considered descriptive analyses, not tests of hypotheses. If there is, however, an interest in analyzing one or more of the components of a composite endpoint as distinct hypotheses to demonstrate effects of the drug, the hypotheses should be part of the prospectively specified statistical analysis plan that accounts for the multiplicity this analysis will entail, as described above for mortality.
In analyzing the contribution of each component of a composite endpoint, there are two approaches that differ in how patients who experience more than one of the event-types are considered.
One approach considers only the initial event in each patient. This method displays the incidence of each type of component event only when it was the first event for a patient. The sum of the first events across all categories will equal the total events for the composite endpoint. The other approach considers the events of each type in each patient. With this method, each of the components can also be treated as a distinct endpoint, irrespective of the order of occurrence, giving the numbers of patients who ever experienced an event of each type. In this case, each patient can be included in the event counts for more than one component, and the sum of events on all component types will be greater than the total number of composite events using only the first events.
The different components of a composite endpoint are selected because they are all clinically important; however, because each one is not necessarily equally affected by the drug, it is relevant and important to examine the effects of the drug on the individual components as well as on the overall endpoint. Presenting only data on the composite might imply meaningful treatment effects on all of the individual components, when a composite effect may in fact be established with little or no evidence of effect on some of the individual components. On the other hand, showing the results of the analysis for each of the individual components may imply an effect on an individual component when an appropriate statistical analysis would not support that conclusion. Thus, it is important to present descriptive analyses of between-group differences for the components in a way that does not overstate the conclusions.
It is common for one component of a composite endpoint to overly influence the treatment effect, but even if that is not so, and all components contribute, the inclusion of a particular component in a composite does not usually support an independent conclusion of efficacy on that component. FDA’s guidance for industry Clinical Studies Section of Labeling for Human Prescription Drug and Biological Products — Content and Format calls for presentation in labeling of the components of a composite endpoint but without a statistical analysis of the separate components unless the components were prespecified as separate endpoints and assessed with a prospectively defined hypothesis and statistical analysis plan. In such a case, the statistical analysis will usually consider all events of each type, not just first-occurring events. Only findings on prespecified endpoints that are statistically significant, with adjustment for multiplicity, are considered demonstrated effects of a drug. All other findings are considered descriptive and would require further study to demonstrate that they are true effects of the drug.
To demonstrate an effect on a specific component or components of a composite endpoint, the component or components should be included prospectively as a secondary endpoint for the study or possibly as an additional primary endpoint (see section III.C.5), with appropriate Type I error rate control. If control of the Type I error rate is ensured with respect to the individual component or components, in addition to control for the composite, a trial will be potentially able to support conclusions regarding drug effects on the individual component or components as well as the composite.
AVI - Thanks for these guidelines. While I realize this may be the way the world works, this focus on differences in actual p value frankly doesn't make much sense. As you noted previously, if RRR for V was 12%, then that is about p<.02, which according to these guidelines would only be "some evidence." If we show exactly the same RRR (12%) but with 12,00 people instead of 8,000, suddenly exactly the same result becomes "overwhelming" (p<.001). The only difference in this example is sample size - the effect size is the same (I realize this is due to shrinking CIs). Just my opinion, but once you get into samples as large as R-It, I think the focus should be more on the actual effect size rather than the p value. I agree that 12% RRR would be underwhelming, but any RRR that beats the Fourier trial (e.g., 19%) would seem to be pretty overwhelming in my book. No idea whether the DMC would agree though.
HDG - Bingo!
'behavior':
- increased inventory
- ASM 2 months earlier (more importantly ... not in July)
- increased marketing effort
Raf -
My only conclusion is that the stopping rule is much more difficult to obtain than we are led to believe.
Raf - I am inclined to interpret the language the company has frequently used ("base case is that the study runs to completion...") as indicating that the study was designed to detect a 15% RRR at the end of the trial (full number of events) because that was how it was powered. If RRR is larger, it could stop early. I am in the camp that thinks that if there is no stop, then we are probably looking at an RRR at the final readout somewhere close to the planned 15%, rather than the larger numbers that have been thrown around.
Raf - Cannot recall dates, but believe it was in a CC transcript, and was discussed on this board at the time. It was very clear that all key SEs did NOT need to be significant, just "robust." To me, robust means consistent with each other and the overall PE result. If you look at the JELIS SEs compared to the PE, the % risk reduction was fairly similar across the board for the components, but not significant due to smaller numbers of events. Since R-It does not include the soft angina definition used in JELIS, a much higher proportion of events in R-It will have to be the hard MACE outcomes that comprise the PE. No idea whether the numbers of each will be high enough to reach significance, but I certainly would expect some to be significant if the RRR is in the 20%+ range.
Kiwi - Interesting. Argues against going to the end to be bulletproof if results are solid.
Isaeed - Yes agreed - all about trajectories now.
Isaeed - They had to clean 60% of the data last time, but only 20% this time.
Raf - But, the company has specifically said in the past that the SEs do not have to be statistically significant to be considered robust.
Raf - That works for me but no idea whether that would be acceptable in business negotiations (if there are any). I don't so much care about a buyout, but just want to see high BP interest and rumors of BO to drive up the PPS.
HD - You may be right about the company blinding maintained until all results scrubbed and finalized. I still think that the company will know the "final results" long before they are actually published or presented officially. They will not be in any BO discussions, even if they occur fairly quickly, without knowing what they have.
CBB - When you say "the final analysis is out," you are referring to publication of the final results. The company and its stats people will know the "final results" shortly after the DMC decision. They could analyze all of the subgroups etc. in a couple of days. So, the company will know the value of what they have even if it has not been announced officially.
Raf - I wasn't making fun of you. Just sharing my solipsistic delusions about predicting an announcement. I agree that a Monday (or early in the week) makes the most sense for a stop announcement, whereas a Friday probably is best for a continue. I cannot see them announcing over the holiday week, and they would probably have trouble getting the DMC to meet over the holidays anyway.
Thanks STS. I thought there was some rule but could not recall the time limit.
Raf - My guess is July 11 - 14. July 11 because I keep looking at clocks and they frequently (by coincidence? say 7:11, and the rest of that week because I am traveling and I frequently get big news when I travel (maybe a watched pot never boils effect?). Obviously all superstitious and half in jest, but if it is announced that week, I will take credit for predicting it!
Funny - The only reason I own AMRN is a Motley Fool article last June. I was not looking at investing in anything and accidentally ended up on a MF article (I cannot recall how I even got there). They spoke very highly of the stock as a high potential upside with low potential downside. AMRN PPS was at about 2.30 and it was so cheap with such high potential I started looking into it more. The more I read, the more I accumulated over time. Hope the idiots at MF didn't mislead me
Anyone know about any rules on when DMC results have to be reported publicly once the decision is in? For the sake of argument, say that they already met and have made a recommendation. If they recommended a stop, it would seem to be bad timing for AMRN to announce around a holiday weekend - since many traders would be gone, seems like the impact of the announcement on PPS would be reduced. On the other hand, they might want to time a continue recommendation to coincide with when many traders are gone to diminish immediate negative impact. Would the company have the flexibility to hold the info until a more opportune time if it were a stop decision?
Talley - I didn't know that term, but I also wondered whether this might account for some of the huge volume and volatility yesterday.
FWIW - At the 60% IA, PPS went from low on Sept 1 of 2.79 to a high of 3.35 on Sept 8 when continuation was announced. Over 7 days, there was a 20% increase. As of right now, we are going from a recent low of 2.93 before the run-up on June 16 to a high of 3.70 today (June 27). Over 11 days, an increase of 26%. Not sure if this implies an announcement will be coming soon, but we are clearly seeing a little larger and longer run-up than last time.
New coverage would increase action, but this is not new coverage (fairly certain Cantor had release AMRN reports previously). Just an update. Don't think this update or the Motley Fool note today (one of many at regular intervals) has anything to do with it. Doubt its an actual data leak but you never know. Maybe they are going to announce something related to China, middle east, or other partners in the near future, and this is what has leaked?
JL - Not really arguing with you. I agree that JELIS secondary prevention subgroup results suggest very high V efficacy, and I agree that the angina issue is sort of a red herring, distracting from the important results regarding the hard MACE outcomes. However, in science, there often tends to be regression towards the mean, and results that seem too good to be true are often weaker on replication. Not saying it will happen but it could. It is unclear to me exactly how closely JELIS results in an all Japanese population, mostly female, will generalize to the more diverse R-It population. I base my conservative numbers not on what the placebo rate actually is (who knows), but what it could be (and likely might be). I think you have in the past estimated a high placebo rate (in the 5.9% range), and if you are correct, this would correspond with an RRR of 35%. What I have seen in aggregate suggests it might be more around 5.4%, which still would be an overwhelming success in my book (20% RRR) and merit an expanded indication without argument. I would be happy to be wrong in my more conservative opinion though
JL - Just trying to be cautious ("At least 15% RRR"). My guess is somewhere around 20% RRR (what we would see with a 5.4-5.5% placebo event rate), but would love for it to be higher
Raf - Totally agree. If placebo rate is 5.3 or higher, PE will meet the target of 15% RRR. If not, I believe there is simply too much accumulated evidence for EPA and O3s from trials, meta-analyses, lab studies, etc. for V not to show at least 15% RRR in some key subgroups (metabolic syndrome, diabetics, high trigs) or for specific MACE outcomes.
Raf - No holes except that if you are correct on placebo rate assumptions, RRR will be slightly higher than you noted given what we know of timing of 80% IA and the number of patient years.