TAGS
Miri – the person, not the organization – . There’s a lot there worth thinking about, but one part caught my eye:
I’m a little tired of being told that SSRIs “don’t work” when they’re part of the reason I didn’t try to off myself four years ago. There is compelling evidence to suggest they do not actually work and there is compelling evidence to suggest that they do actually work, so I’m comfortable saying that the jury’s still out on this one.
I think the jury is less out now than it was a couple of years ago. I think there’s at least kind of a consensus on the data, mixed with a lot of debate over how to express a very complicated reality to the public in a concise way.
And I am going to bypass that debate by just braindumping eight thousand words worth of very complicated reality on you.
The claim that “SSRIs don’t work” or “SSRIs are mostly just placebo” is most commonly associated with Irving Kirsch, a man with the awesome job title of “Associate Director Of The Program For Placebo Studies at Harvard”.
(fun fact: there’s actually no such thing as “Placebo Studies”, but Professor Kirsch’s belief that he directs a Harvard department inspires him to create much higher-quality research.)
In 1998, he published of 19 placebo-controlled drug trials that suggested that almost all of the benefits of antidepressants were due to the placebo effect. Psychiatrists denounced him, saying that you can choose pretty much whatever studies you want for a meta-analysis.
After biding his time for a decade, in 2008 he struck back with , this being one of the first papers in all of medical science to take the audacious step of demanding all the FDA’s data through the Freedom of Information Act. Since drug companies are required to report all their studies to the FDA, this theoretically provides a rare and wonderful publication-bias-free data set. Using this set, he found that, although antidepressants did seem to outperform placebo, the effect was not “clinically significant” except “at the upper end of very severe depression”.
This launched a minor war between supporters and detractors. Probably the strongest support he received was by Fournier et al, which found that
The magnitude of benefit of antidepressant medication compared with placebo increases with severity of depression symptoms and may be minimal or nonexistent, on average, in patients with mild or moderate symptoms. For patients with very severe depression, the benefit of medications over placebo is substantial.
Of course, a very large number of antidepressants are given to people with mild or moderate depression. So what now?
Let me sort the debate about antidepressants into a series of complaints:
1. Antidepressants were oversold and painted as having more biochemical backing than was really justified 2. Modern SSRI antidepressants are no better than older tricyclic and MAOI antidepressants, but are prescribed much more because of said overselling 3. There is large publication bias in the antidepressant literature 4. The effect size of antidepressants is clinically insignificant 5. And it only becomes significant in the most severe depression 6. And even the effects found are only noticed by doctors, not the patients themselves 7. And even that unsatisfying effect might be a result of “active placebo” rather than successful treatment 8. And antidepressants have much worse side effects than you have been led to believe 9. Therefore, we should give up on antidepressants (except maybe in the sickest patients) and use psychotherapy instead
1. Antidepressants were oversold and painted as having more biochemical backing than was really justified – Totally true
It is starting to become slightly better known that the standard story – depression is a deficiency of serotonin, antidepressants restore serotonin and therefore make you well again – is kind of made up.
There was never much more evidence for the serotonin hypothesis than that chemicals that increased serotonin tended to treat depression – making the argument that “antidepressants are biochemically justified because they treat the low serotonin that is causing your depression” kind of circular. Saying “Serotonin treats depression, therefore depression is, at root, a serotonin deficiency” is about as scientifically grounded as saying “Playing with puppies makes depressed people feel better, therefore depression is, at root, a puppy deficiency”.
The whole thing became less tenable with the discovery that several chemicals that didn’t increase serotonin were also effective antidepressants – not to mention one chemical, tianeptine, that decreases serotonin. Now the conventional wisdom is that depression is a very complicated disturbance in several networks and systems within the brain, and serotonin is one of the inputs and/or outputs of those systems.
Likewise, a whole bunch of early ’90s claims: that modern antidepressants have no side effects, that they produce miraculous improvements in everyone, that they make you better than well – seem kind of silly now. I don’t think anyone is arguing against the proposition that there was an embarrassing amount of hype that has now been backed away from.
2. Modern SSRI antidepressants are no better than older tricyclic and MAOI antidepressants, but are prescribed much more because of said overselling – First part true, second part less so
Most studies find SSRI antidepressants to be no more effective in treating depression than older tricyclic and MAOI antidepressants. Most studies aren’t really powered to do this. It seems clear that there aren’t spectacular differences, and hunting for small differences has proven very hard.
If you’re a geek about these sorts of things, you know that a few studies have found non-significant advantages for Prozac and Paxil over older drugs like clomipramine, and marginally-significant advantages for Effexor over SSRIs. But conventional wisdom is that tricyclics can be even more powerful than SSRIs for certain very severe hospitalized depression cases, and a lot of people think MAOIs worked better than anything out there today.
But none of this is very important because the real reason SSRIs are so popular is the side effect profile. While it is an exaggeration to say they have no side effects (see above) they are an obvious improvement over older classes of medication in this regard.
Tricyclics had a bad habit of causing fatal arrythmias when taken at high doses. This is really really bad in depression, because depressed people tend to attempt suicide and the most popular method of suicide attempt is overdosing on your pills. So if you give depressed people a pill that is highly fatal in overdose, you’re basically enabling suicidality. This alone made the risk-benefit calculation for tricyclics unattractive in a lot of cases. Add in dry mouth, constipation, urinary problems, cognitive impairment, blurry vision, and the occasional tendency to cause heart arrythmias even when taken correctly, and you have a drug you’re not going to give people who just say they’re feeling a little down.
MAOIs have their own problems. If you’re using MAOIs and you eat cheese, beer, chocolate, beans, liver, yogurt, soy, kimchi, avocados, coconuts, et cetera, et cetera, et cetera, you have a chance of precipitating a “hypertensive crisis”, which is exactly as fun as it sounds. As a result, people who are already miserable and already starving themselves are told they can’t eat like half of food. And once again, if you tell people “Eat these foods with this drug and you die” and a week later the person wants to kill themselves and has some cheese in the house, then you’re back to enabling suicide. There are some MAOIs that get around these restrictions in various clever ways, but they tend to be less effective.
SSRIs were the first class of antidepressants that mostly avoided these problems and so were pretty well-placed to launch a prescribing explosion even apart from being pushed by Big Pharma.
3. There is large publication bias in the antidepressant literature – True, but not as important as some people think
People became more aware of publication bias a couple of years after serious research into antidepressants started, and it’s not surprising that these were a prime target. When this issue rose to scientific consciousness, several researchers tried to avoid the publication bias problem by using only FDA studies of antidepressants. The FDA mandates that its studies be pre-registered and the results reported no matter what they are. This provides a “control group” by which accusations of publication bias can be investigated. The results haven’t been good. From :
Recent reports suggest that efficacy of antidepressant medications versus placebo may be overstated, due to publication bias and less efficacy for mildly depressed patients. For example, of 74 FDA-registered randomized controlled trials (RCTs) involving 12 antidepressants in 12,564 patients, 94% of published trials were positive whereas only 51% of all FDA registered studies were positive.
express the same data a different way:
. The FDA deemed 38 of the 74 studies (51%) positive, and all but 1 of the 38 were published. The remaining 36 studies (49%) were deemed to be either negative (24 studies) or questionable (12). Of these 36 studies, 3 were published as not positive, whereas the remaining 33 either were not published (22 studies) or were published, in our opinion, as positive (11) and therefore conflicted with the FDA’s conclusion. Overall, the studies that the FDA judged as positive were approximately 12 times as likely to be published in a way that agreed with the FDA analysis as were studies with nonpositive results according to the FDA (risk ratio, 11.7; 95% confidence interval [CI], 6.2 to 22.0; P<0.001). This association of publication status with study outcome remained significant when we excluded questionable studies and when we examined publication status without regard to whether the published conclusions and the FDA conclusions were in agreement
I think a lot of this has since been taken on board, and most of the rest of the research I’ll be talking about uses FDA data rather than published data. But as you can see, the overall change in effect size – from 0.31 to 0.41 – is not that terribly large.
4. The effect size of antidepressants is clinically insignificant – Depends what you mean by “clinically insignificant”
As mentioned above, when you try to control for publication bias, the effect size of antidepressant over placebo is 0.31.
This number can actually be broken down further. According to , who are working off of slightly different data and so get slightly different numbers, the effect size of placebo is 0.92 and the effect size of antidepressants is 1.24, which means antidepressants have a 0.32 SD benefit over placebo. Several different studies get similar numbers, including the Kirsch meta-analysis that started this whole debate.
Effect size is a hard statistic to work with (albeit extremely fun). The guy who invented effect size suggested that 0.2 be called “small”, 0.5 be called “medium”, and 0.8 be called “large”. NICE, a UK health research group, somewhat randomly declared that effect sizes greater than 0.5 be called “clinically significant” and effect sizes less than 0.5 be called “not clinically significant”, but their reasoning was basically that 0.5 was a nice round number, and a few years later they changed their mind and admitted they had no reason behind their decision.
Despite these somewhat haphazard standards, some people have decided that antidepressants’ effect size of 0.3 means they are “clinically insignificant”.
(please note that “clinically insignificant” is very different from “statistically insignificant” aka “has a p-value less than 0.05.” Nearly everyone agrees antidepressants have a statistically significant effect – they do something. The dispute is over whether they have a clinically significant effect – the something they do is enough to make a real difference to real people)
There have been a couple of attempts to rescue antidepressants by raising the effect size. For example, note that Kirsch incorrectly took the difference between the average effect of drugs and the average effect of placebos, rather than the average drug-placebo difference (did you follow that?) When you correct that mistake, the drug-placebo difference rises significantly to about 0.4.
They also note that Kirsch’s study lumps all antidepressants together. This isn’t necessarily wrong. But it isn’t necessarily right, either. For example, his study used both Serzone (believed to be a weak antidepressant, rarely used) and Paxil (believed to be a stronger antidepressant, commonly used). And in fact, by his study, Paxil showed an effect size of 0.47, compared to Serzone’s 0.21. But since the difference was not statistically significant, he averaged them together and said that “antidepressants are ineffective”. In fact, his study showed that Paxil was effective, but when you average it together with a very ineffective drug, the effect disappears. He can get away with this because of the arcana of statistical significance, but by the same arcana I can get away with not doing that.
So right now we have three different effect sizes. 1.2 for placebo drug, 0.5 for drug alone if we’re being statistically merciful, 0.3 for drug alone if we’re being harsh and letting the harshest critic of antidepressants pull out all his statistical tricks.
The reason effect size is extremely fun is that it allows you to compare effects in totally different domains. I will now attempt to do this in order to see if I can give you an intuitive appreciation for what it means for antidepressants.
Suppose antidepressants were in fact a weight loss pill.
An effect size of 1.2 is equivalent to the pill making you lose 32 lb.
An effect size of 0.5 is equivalent to the pill making you lose 14 lb.
An effect size of 0.3 is equivalent to the pill making you lose 8.5 lb.
Or suppose that antidepressants were a growth hormone pill taken by short people.
An effect size of 1.2 is equivalent to the pill making you grow 3.4 in.
An effect size of 0.5 is equivalent to the pill making you grow 1.4 in.
An effect size of 0.3 is equivalent to the pill making you grow 0.8 in.
Or suppose that antidepressants were a cognitive enhancer to boost IQ. gives us some context about occupations.
An effect size of 1.2 is equivalent to the pill making you gain 18 IQ points, ie from the average farm laborer to the average college professor.
An effect size of 0.5 is equivalent to the pill making you gain 7.5 IQ points, ie from the average farm laborer to the average elementary school teacher.
An effect size of 0.3 is equivalent to the pill making you gain 5 IQ points, ie from the average farm laborer to the average police officer.
To me, these kinds of comparisons are a little more revealing than NICE arbitrarily saying that anything below 0.5 doesn’t count. If you could take a pill that helps your depression as much as gaining 1.4 inches would help a self-conscious short person, would you do it? I’d say it sounds pretty good.
5. The effect of antidepressants only becomes significant in the most severe depression – Everything about this statement is terrible and everyone involved should feel bad
So we’ve already found that saying antidepressants have an “insignificant” effect size is kind of arbitrary. But what about the second part of the claim – that they only have measurable effects in “the most severe depression”?
A lot of depression research uses a test called the HAM-D, which scores depression from 0 (none) to 52 (max). Kirsch found that the effect size of antidepressants increased as HAM-D scores increased, meaning antidepressants become more powerful as depression gets worse. He was only able to find a “clinically significant” effect size (d > 0.5) for people with HAM-D scores greater than 28. People have come up with various different mappings of HAM-D scores to words. For example, the APA says:
Oh. That gives us some perspective, I guess. Also, make the opposite critique and say that the HAM-D can’t distinguish very well at the low end. Suppose HAM-Ds less than ten are meaningless and random. This would look a lot like antidepressants not working in mild depression.
Getting back to Ghaemi and Vohringer, they try a different tack and suggest that there is a statistical floor effect. They quite reasonably say that if someone had a HAM-D score of 30, and antidepressants solved 10% of their problem, they would lose 3 HAM-D points, which looks impressive. But if someone had a HAM-D score of 10, and antidepressants (still) solved 10% of their problem, they would only lose 1 HAM-D point, which sounds disappointing. But either way, the antidepressants are doing the same amount of work. If you adjust everything for baseline severity, it’s easy to see that antidepressants here would have the same efficacy in severe and mild depression, even though it doesn’t look that way at first.
I am confused that this works for effect sizes, because I expect effect sizes to be relative to the standard deviation in a sample. However, several important people tell me that it does, and that when you do this Kirsch’s effect size goes from 0.32 to 0.40.
(I think are saying the exact same thing, but so overly mathematically that I’ve been staring at it for an hour and I’m still not certain)
More important, Ghaemi and Vohringer say once you do this, antidepressants reach the magic 0.5 number not only in severe depression, but also in moderate depression. However, when I look at this claim closely, almost all the work is done by G&V’s adjusted scale in which Kirsch’s “very severe” corresponds to their “mild”.
(personal aside: I got an opportunity to talk to Dr. Ghaemi about this paper and clear up some of my confusion. Well, not exactly an opportunity to talk about it, per se. Actually, he was supposed to be giving me a job interview at the time. I guess we both got distracted. This may be one of several reasons I do not currently work at Tufts.)
So. In conclusion, everyone has mapped HAM-D numbers into words like “moderate” in totally contradictory ways, such that one person’s “mild” is another person’s “very severe”. Another person randomly decided that we can only call things “clinically significant” if they go above the nice round number of 0.5, then retracted this. So when people say “the effects of antidepressants are only clinically significant in severe depression”, what they mean is “the effects of antidepressants only reach a totally arbitrary number one guy made up and then retracted, in people whose HAM-D score is above whatever number I make up right now.” Depending on what number you choose and what word you make up to describe it, you can find that antidepressants are useful in moderate depression, or severe depression, or super-duper double-dog-severe depression, or whatever.
Science!
6. The beneficial effects of antidepressants are only noticed by doctors, not the patients themselves – Partly true but okay
So your HAM-D score has gone down and you’re no longer officially in super-duper double-dog severe depression anymore. What does that mean for the patient?
There are consistent gripes that antidepressant studies that use patients rating their own mood show less improvement than studies where doctors rate how they think a patient is doing, or standardized tests like the HAM-D.
Some people try to turn this into a conspiracy, where doctors who have somehow broken the double-blinding of studies try to report that patients have done better because doctors like medications and want them to succeed.
The reality is more prosaic. It has been known that people’s feelings are the last thing to improve during recovery from depression.
This might sound weird – what is depression except people’s feelings? But the answer is “quite a lot”. Depressed people often eat less, sleep more, have less energy, and of course are more likely to attempt suicide. If a patient gets treated with an antidepressant, and they start smiling more and talking more and getting out of the house and are no longer thinking about suicide, their doctor might notice – but the patient herself might still feel really down-in-the-dumps.
I am going to get angry comments from people saying I am declaring psychiatric patients too stupid to notice their own recovery or something like that, but it is a . Patients have access to internal feelings which they tend to weight much more heavily than external factors like how much they are able to get done during a day or how many crying spells they have, sometimes so much so that they completely miss these factors. Doctors (or family members, or other outside observers) who don’t see these internal feelings, are better able to notice outward signs. As a result, it is pretty universally believed that doctors spot signs of recovery in patients long before the patients themselves think they are recovering. This isn’t just imaginary – it’s found it datasets where the doctors are presumably blinded and with good inter-rater reliability.
Because most antidepressant trials are short, a lot of them reach the point where doctors notice improvement but not the point where patients notice quite as much improvement.
7. The apparent benefits of antidepressant over placebo may be an “active placebo” effect rather than a drug effect – Unlikely
Active placebo is the uncomfortable idea that no study can really have a blind control group because of side effects. That is, sugar pills have no side effects, real drugs generally do, and we all know side effects are how you know that a drug is working!
(there is a counterargument that placebos very often have placebo side effects, but most likely the real drug will at least have more side effects, saving the argument)
The solution is to use active placebo, a drug that has side effects but, as far as anyone knows, doesn’t treat the experimental condition (in this case, depression). The preliminary results from this sort of study don’t look good for antidepressants:
Thomson reviewed 68 double-blind studies of tricyclics that used an inert placebo and seven that used an active placebo (44). He found drug efficacy was demonstrated in 59% of studies that employed inert placebo, but only 14% of those that used active placebo (?2=5.08, df=1, p=0.02). This appears to demonstrate that in the presence of a side-effect-inducing control condition, placebo cannot be discriminated from drug, thus affirming the null hypothesis.
Aside from the sort of side effects that you expect with any drug, there are three side effects of SSRIs that I consider especially worrisome and worthy of further discussion. These are weight gain, sexual side effects, and emotional blunting.
Weight gain is often listed as one of the most common and debilitating effects of SSRIs. But amusingly, when a placebo-controlled double-blinded study was finally run, . After a year of pill-taking, people on Prozac had gained 3.1 kg; people on placebo had gained 4.3. There is now some talk of SSRIs as a weak but statistically significant agent for weight loss.
What happened? One symptom of depression is not eating. People get put on SSRIs when they’re really depressed. Then they get better, either because the drugs worked, because of placebo, or just out of regression to the mean. When you go from not eating to eating, you gain weight. In the one-year study, almost everyone’s depression remitted (even untreated depressive episodes rarely last a whole year), so everyone went from a disease that makes them eat less, to remission from that disease, so everyone gained weight.
Sexual side effects are a less sanguine story. Here the direction was opposite: the medical community went from thinking this was a minor problem to finding it near-universal. The problem was that doctors usually just ask “any side effects?”, and off Tumblr people generally don’t volunteer information about their penis or vagina to a stranger. When they switched to the closed-ended question “Are you having any sexual side effects?”, a lot of people who denied side effects in general suddenly started talking.
Numbers I have heard for the percent of people on SSRIs with sexual side effects include 14, 24, 37, 58, 59, and 70 (several of those come from . After having read quite a bit of this research, I suspect you’ve got at least a 50-50 chance (they say men are more likely to get them, but they’re worse in women). Of people who develop sexual side effects, 40% say they caused serious distress, 35% some distress, and 25% no distress.
So I think it is fair to say that if you are sexually active, your chances with SSRIs are not great. Researchers investigating the topic suggest people worried about sexual side effects should switch to alternative sexual-side-effect-free antidepressant Serzone. You may remember that as the antidepressant that worked worst in the efficacy studies and brought the efficacy of all the other ones down with it. Also, it causes liver damage. In my opinion, a better choice would be bupropion, another antidepressant which has been found many times not to cause sexual side effects and which may even improve your sex life.
(“Bupropion lacks this side effect” is going to be a common theme throughout this section. Bupropion causes insomnia, decreased appetite, and in certain rare cases of populations at risk, seizures. It is generally a good choice for people who are worried about SSRI side effects and would prefer a totally different set of side effects.)
There is a certain feeling that, okay, these drugs may have very very common, possibly-majority-of-user sexual side effects, but depressed people probably aren’t screwing like rabbits anyway. So after you recover, you can wait the appropriate amount of time, come off the drugs (or switch to a different drug or dose for maintenance) and no harm done.
The situation no longer seems so innocuous. Despite a lack of systematic investigation, there are from researchers and clinicians – not to mention random people on the Internet – of permanent SSRI-induced sexual dysfunction that does not remit once the drug is stopped. This is definitely not the norm and as far as we know it is so rare as to be unstudyable beyond the occasional case report.
On the other hand, I have this. I took SSRIs for about five to ten years as a kid, and now I have approximately the pattern of sexual dysfunction associated with SSRIs and consider myself asexual. Because I started the SSRIs too early to observe my sexuality without them, I can’t officially blame the drugs. But I am very suspicious. I feel like this provides moderate anthropic evidence that it is not as rare as everyone thinks.
The last side effect worth looking at is emotional blunting. A lot of people say they have trouble feeling intense emotions (sometimes: any emotions at all) when on SSRIs. Sansone and Sansone (2010) :
As for prevalence rates, according to a study by Bolling and Kohlenberg, approximately 20 percent of 161 patients who were prescribed an SSRI reported apathy and 16.1 percent described a loss of ambition. In a study by Fava et al, which consisted of participants in both the United States and Italy, nearly one-third on any antidepressant reported apathy, with 7.7 percent describing moderate-to-severe impairment, and nearly 40 percent acknowledged the loss of motivation, with 12.0 percent describing moderate-to-severe impairment.
A practicing clinician working off observation about the same numbers:
The sort of emotional “flattening” I have described with SSRIs may occur, in my experience, in perhaps 10-20% of patients who take these medications…I do want to emphasize that most patients who take antidepressant medication under careful medical supervision do not wind up feeling “flat” or unable to experience life’s normal ups and downs. Rather, they find that–in contrast to their periods of severe depression–they are able to enjoy life again, with all its joys and sorrows.
Many patients who experience this side effect note that when you’re depressed, “experiencing all your emotions fully and intensely” is not very high on your list of priorities, since your emotions tend to be terrible. There is a subgroup of depressed patients whose depression takes the form of not being able to feel anything at all, and I worry this effect would exacerbate their problem, but I have never heard this from anyone and SSRIs do not seem less effective in that subgroup, so these might be two different things that only sound alike. A couple of people discussing this issue have talked about how decreased emotions help them navigate interpersonal relationships that otherwise might involve angry fights or horrible loss – which sounds plausible but also really sad.
According to , “this adverse effect has been noted to be dose-dependent and reversible” – in other words, it will get better if you cut your dose, and go away completely when you stop taking the medication. I have not been able to find any case studies or testimonials by people who say this effect has been permanent.
My own experience was that I did notice this (even before I knew it was an official side effect) that it did go away after a while when I stopped the medications, and that since my period of antidepressant use corresponded with an important period of childhood socialization I ended out completely unprepared for having normal emotions and having to do a delicate social balancing act while I figured out how to cope with them. Your results may vary.
There is also a large research on suicidality as a potential side effect of SSRIs, but this looks like it would require another ten thousand words just on its own, so let’s agree it’s a risk and leave it for another day.
9. Therefore, we should give up on medication and use psychotherapy instead – Makes sense right up until you run placebo-controlled trials of psychotherapy
The conclusion of these studies that claim antidepressants don’t outperform placebo is usually that we should repudiate Big Pharma, toss the pills, and go back to using psychotherapy.
The implication is that doctors use pills because they think they’re much more effective than therapy. But that’s not really true. The conventional wisdom in psychiatry is that antidepressants and psychotherapy are about equally effective.
SSRIs get used more than psychotherapy for the same reason they get used more than tricyclics and MAOIs – not because they’re better but because they have fewer problems. The problem with psychotherapy is you’ve got to get severely mentally ill people to go to a place and talk to a person several times a week. Depressed people are not generally known for their boundless enthusiasm for performing difficult tasks consistently. Also, Prozac costs like 50 cents a pill. Guess how much an hour of a highly educated professional’s time costs? More than 50c, that’s for sure. If they are about equal in effectiveness, you probably don’t want to pay extra and your insurance definitely doesn’t want to pay extra.
Contrary to popular wisdom, it is almost never the doctor pushing pills on a patient who would prefer therapy. If anything it’s more likely to be the opposite.
However, given that we’re acknowledging antidepressants have an effect size of only about 0.3 to 0.5, is it time to give psychotherapy a second look?
No. Using very similar methodology, a team involving Mind The Brain blogger James Coyne found that psychotherapy decreases HAM-D scores by about 2.66, very similar to the 2.7 number obtained by re-analysis of Kirsch’s data on antidepressants. It concludes:
If a patient has the time, money, and motivation for psychotherapy, it may be a good option – though I would only be comfortable using it as a monotherapy if the depression was relatively mild.
The Kirsch meta-analysis looked only at studies carried out before 1999. The much-publicized Fournier study examined a total of 6 antidepressant trials (n=718) using just 2 antidepressants, paroxetine and imipramine. Two of the imipramine studies used doses that were either subtherapeutic (100 mg/day) or less than optimal (100 to 200 mg/day)
What if we’ve forgotten the most important part? Antidepressants are used not only to treat acute episodes of depression, but to prevent them from coming back (maintenance therapy). This they apparently do very well, and I have seen very few studies that attempt to call this effect into question. Although it is always possible that someone will find the same kind of ambiguity around maintenance antidepressant treatment as now clouds acute antidepressant treatment, so far as far as I know this has not happened.
What if we don’t understand what’s going on with the placebo effect in our studies? Placebo effect has consistently gotten stronger over the past few decades, such that the difference between certain early tricyclic studies (which often found strong advantages for the medication) and modern SSRI studies (which often find only weak advantages for the medication) is not weaker medication effect, but stronger placebo effect (that is, if medication always has an effect of 10, but placebo goes from 0 to 9, apparent drug-placebo difference gets much lower). Wired . Theories range from the good – drug company advertising and increasing prestige and awareness of psychiatry have raised people’s expectations of psychiatric drugs – to the bad – increasing scientific competence and awareness have improved blinding and other facets of trial design – to the ugly – modern studies recruit paid participants with advertisements, so some unscrupulous people may be entering studies and then claiming toget better, hoping that this sounds sufficiently like the outcome the researchers want that everyone will be happy and they’ll get their money on schedule.
If placebos are genuinely getting better because of raised expectations, that’s good news for doctors and patients but bad news for researchers and drug companies. The patient will be happy because they get better no matter how terrible a prescribing decision the doctor makes; the doctor will be happy because they get credit. But for researchers and drug companies, it means it’s harder to prove a difference between drug and placebo in a study. You can invent an excellent new drug and still have it fail to outperform placebo by very much if everyone in the placebo group improves dramatically.
Conclusion
An important point I want to start the conclusion section with: no matter what else you believe, antidepressants are not literally ineffective. Even the most critical study – Kirsch 2008 – finds antidepressants to outperform placebo with p < .0001 significance. An equally important point: everyone except those two Scandinavian guys with the long names agree that, if you count the placebo effect, antidepressants are extremely impressive. The difference between a person who gets an antidepressant and a person who gets no treatment at all is like night and day. The debate takes place within the bounds set by those two statements. Antidepressants give a very modest benefit over placebo. Whether this benefit is so modest as to not be worth talking about depends on what level of benefits you consider so modest as to not be worth talking about. If you are as depressed as the average person who participates in studies of antidepressants, you can expect an antidepressant to have anover-placebo-benefit with an effect size of 0.3 to 0.5. That's the equivalent of a diet pill that gives you an average weight loss of 9 to 14 pounds, or a growth hormone that makes you grow on average 0.8 to 1.4 inches. You may be able to get more than that if you focus on the antidepressants, like paroxetine and venlafaxine, that perform best in studies, but we don't have the statistical power to say that officially. It may be the case that most people who get antidepressants do much better than that but a few people who have paradoxical negative responses bring down the average, but right now this result has not been replicated. This sounds moderately helpful and probably well worth it if the pills are cheap (which generic versions almost always are) and you are not worried about side effects. Unfortunately, SSRIs do have some serious side effects. Some of the supposed side effects, like weight gain, seem to be mostly mythical. Others, like sexual dysfunction, seem to be very commonand legitimately very worrying. You can avoid most of these side effects by taking other antidepressants like bupropion, but even these are not totally side-effect free. Overall I think antidepressants come out of this definitely not looking like perfectly safe miracle drugs, but as a reasonable option for many people with moderate (aka "mild", aka "extremely super severe") depression, especially if they understand the side effects and prepare for them.
.
