Predicting Depression Treatment Response: Machine Learning

Treatment of depression remains primarily an uninformed clinical process. Several effective drug and psychotherapy interventions are available. 

However, there is no reliable way to determine which treatment is likely to be the most effective for an individual patient.

A recent study that used machine learning techniques to address this problem has been published.

A research team from Yale University used clinical data from the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) trial in the U.S. 

I served as an investigator in the STAR*D and am happy to see this database still in use.

In the current study, the research team used machine learning with a group of 164 pre-treatment variables. From this group of variables, 25 were identified as providing predictive value of response/non-response to treatment with a standard antidepressant drug citalopram.

Clinical predictors of non-response included:

• High baseline depression severity scores
• Presence of psychomotor agitation at baseline
• Reduced energy ratings at baseline (fatigue)

Predictors of depression remission included:

• Current employment
• Higher level of education
• Lower scores on depression insight

The research team was able to build a machine learning model that showed a 63% sensitivity and 66% specificity in prediction response to citalopram. This was statistically greater than random (chance) prediction.

Addition support for their model was gained by replication in a second study of citalopram in depression.

This is an important and exciting finding that suggests low-cost symptom biomarkers may aid in the treatment selection for depression.

You can access the abstract of this important work by clicking HERE or by clicking on the PMID link in the citation below. 

Follow the author on Twitter WRY999 HERE.

Photo of sunset on Captiva Island, Florida is from my personal files. 

Chekroud AM, Zotti RJ, Shehzad Z, Gueorguieva R, Johnson MK, Trivedi MH, Cannon TD, Krystal JH, & Corlett PR (2016). Cross-trial prediction of treatment outcome in depression: a machine learning approach. The lancet. Psychiatry, 3 (3), 243-50 PMID: 26803397

Why Antidepressants Can Cause Gut Pain

Selective serotonin reuptake inhibitors frequently produce significant gastrointestinal side effects.  Nausea was reported by up to 26% of subjects and diarrhea in up to 30% of subjects in a recent review of the new antidepressant vilazodone.  Gastrointestinal side effects tend to be seen with the initiation of antidepressant drugs commonly followed by a period of improved tolerability.

The mechanism for this gastrointestinal effect is poorly understood.   The gut is known to have serotonin receptors.  Some gastrointestinal therapeutic agents target the serotonin receptor as their mechanism of action.  For example, the antinausea drug ondansetron appears to act through it's antagonism of the 5HT (serotonin) 3 receptor.  This results in inhibition of gastric activity while components of activity of the small intestine remain functional.

To better understand the effects of serotonin on GI motility, Janssen and colleagues from the University of Leuven conducted a novel experiment.  Twenty healthy subjects were studied in a GI motility study following administration of placebo and the selective serotonin reuptake inhibitor citalopram.

The authors found that administration of citalopram significant reduced the gastrointestinal transit time compared to that found at baseline and placebo (see chart).

Upper gastrointestinal transit time is composed of three separate phases known as the migrating motor complex of MMC.  Citalopram appeared to reduce the duration of phase 1 and phase 2 while the time spent in phase 3 was unchanged.

The authors attribute the change in transit time to a direct effect of citalopram on GI serotonin receptors although a central CNS effect could not be ruled out.  The speculate this effect may be potentially therapeutic in individuals with constipation predominant irritable bowel syndrome.

This study did not directly address the issue of GI side effects associated with the SSRI antidepressants.  Nevertheless, it suggests acute increased GI transit times with SSRIs may be a mechanism that contributes to GI side effects of nausea, diarrhea, cramping and pain.

Further studies of this effect are needed looking at a longer time frame.  Since most GI side effects improve with prolonged administration, it is possible a receptor compensation mechanism may be involved in changes in side effects over time.

Graph of gastrointestinal transit times is an original graph produced by the author from data in the manuscript.

Janssen P, Vos R, & Tack J (2010). The influence of citalopram on interdigestive gastrointestinal motility in man. Alimentary pharmacology & therapeutics, 32 (2), 289-95 PMID: 20456311