Predicting Who Should Get Ketamine vs ECT: New Study From the Harvard Group

Individual Prediction of Optimal Treatment Allocation Between Electroconvulsive Therapy or Ketamine using the Personalized Advantage Index.

Wade B, Pindale R, Camprodon J, Luccarelli J, Li S, Meisner R, Seiner S, Henry M.Res Sq. 2023 Nov 30:rs.3.rs-3682009. doi: 10.21203/rs.3.rs-3682009/v1. Preprint.PMID: 38077094

The abstract is copied below:

Introduction: Electroconvulsive therapy (ECT) and ketamine are two effective treatments for depression with similar efficacy; however, individual patient outcomes may be improved by models that predict optimal treatment assignment. Here, we adapt the Personalized Advantage Index (PAI) algorithm using machine learning to predict optimal treatment assignment between ECT and ketamine using medical record data from a large, naturalistic patient cohort. We hypothesized that patients who received a treatment predicted to be optimal would have significantly better outcomes following treatment compared to those who received a non-optimal treatment. Methods: Data on 2526 ECT and 235 mixed IV ketamine and esketamine patients from McLean Hospital was aggregated. Depressive symptoms were measured using the Quick Inventory of Depressive Symptomatology (QIDS) before and during acute treatment. Patients were matched between treatments on pretreatment QIDS, age, inpatient status, and psychotic symptoms using a 1:1 ratio yielding a sample of 470 patients (n=235 per treatment). Random forest models were trained and predicted differential patientwise minimum QIDS scores achieved during acute treatment (min-QIDS) scores for ECT and ketamine using pretreatment patient measures. Analysis of Shapley Additive exPlanations (SHAP) values identified predictors of differential outcomes between treatments. Results: Twenty-seven percent of patients with the largest PAI scores who received a treatment predicted optimal had significantly lower min-QIDS scores compared to those who received a non-optimal treatment (mean difference=1.6, t=2.38, q<0.05, Cohen's D=0.36). Analysis of SHAP values identified prescriptive pretreatment measures. Conclusions: Patients assigned to a treatment predicted to be optimal had significantly better treatment outcomes. Our model identified pretreatment patient factors captured in medical records that can provide interpretable and actionable guidelines treatment selection.

The article is here.

And from the text:

Conclusions Predicting which antidepressant treatment will elicit the most robust response from an individual patient is of the utmost importance. In this study, we adapted the PAI method to predict optimal treatment allocation between two equally effective rapidly acting treatments for TRD: ECT and ketamine. As hypothesized, patients who received a treatment predicted optimal had signi cantly better treatment outcomes re ecting small to medium effect size differences. Importantly, these models were constructed using commonly acquired and inexpensive demographic and medical record data. Precision medicine methods such as this have the potential to provide actionable predictions for both patients and clinicians in the selection of treatments and their use should be expanded to include additional treatment modalities.

This is the second time I have found something on PubMed from "Research Square" that is a preprint prior to peer review. 

There are some very laudable goals here (precision medicine) and remarkably sophisticated statistics. But is this really a better way than clinical judgment? And starting with the premise that ECT and ketamine are equally effective? 

The ketamine story is still evolving, and the recent tragic death of a famous TV actor may just slow the out-of-control express train a bit...In the meantime, let us remember that ECT has a long track record of safety and efficacy and an undisputed role in the treatment of severe depressive and psychotic illness.