Development and Validation of a Machine Learning Individualized Treatment Rule in First-Episode Schizophrenia

Abstract

IMPORTANCE Little guidance exists to date on how to select antipsychotic medications for patients with first-episode schizophrenia. OBJECTIVE To develop a preliminary individualized treatment rule (ITR) for patients with firstepisode schizophrenia. DESIGN, SETTING, AND PARTICIPANTS This prognostic study obtained data from Taiwan's National Health Insurance Research Database on patients with prescribed antipsychotic medications, ambulatory claims, or discharge diagnoses of a schizophrenic disorder between January 1, 2005, and December 31, 2011. An ITR was developed by applying a targeted minimum loss-based ensemble machine learning method to predict treatment success from baseline clinical and demographic data in a 70% training sample. The model was validated in the remaining 30% of the sample. The probability of treatment success was estimated for each medication for each patient under the model. The analysis was conducted between July 16, 2018, and July 15, 2019. EXPOSURES Fifteen different antipsychotic medications. MAIN OUTCOMES AND MEASURES Treatment success was defined as not switching medication and not being hospitalized for 12 months. RESULTS Among the 32 277 patients in the analysis, the mean (SD) age was 36.7 (14.3) years, and 15 752 (48.8%) were male. In the validation sample, the treatment success rate (SE) was 51.7% (1.0%) under the ITR and was 44.5% (0.5%) in the observed population (Z = 7.1; P < .001). The estimated treatment success if all patients were given a prescription for 1 medication was significantly lower for each of the 13 medications than under the ITR (Z = 4.2-16.8; all P < .001). Aripiprazole (3088 [31.9%]) and amisulpride (2920 [30.2%]) were the medications most often recommended by the ITR. Only 1054 patients (10.9%) received ITR-recommended medications. Observed treatment success, although lower than the success under the ITR, was nonetheless significantly higher than if medications had been randomized (44.5% [SE, 0.55%] vs 41.3% [SE, 0.4%]; Z = 6.9; P < .001), although only marginally higher than if medications had been randomized in their observed population proportions (44.5% [SE, 0.5%] vs 43.5% [SE, 0.4%]; Z = 2.2; P = .03]). CONCLUSIONS AND RELEVANCE These results suggest that an ITR may be associatded with an increase in the treatment success rate among patients with first-episode schizophrenia, but experimental evaluation is needed to confirm this possibility. If confirmed, model refinement that investigates biomarkers, clinical observations, and patient reports as additional predictors in iterative pragmatic trials would be needed before clinical implementation.

The promise of machine learning in predicting treatment outcomes in psychiatry

“…Recent studies have tested the potential of EHR data to predict treatment outcomes in psychiatry, with the bulk of efforts to date focused on depression, though examples exist for bipolar disorder 98 and schizophrenia 99 . Machine learning‐based efforts using EHR data have sought to identify those individuals who are likely to drop out after initiating antidepressants 100 , those who will show a stable treatment response to antidepressants 101 , and those who may transition to a bipolar diagnosis after starting antidepressants for depression 102 .…”

Using Administrative Data to Predict Suicide After Psychiatric Hospitalization in the Veterans Health Administration System

“…Or the predicted values from a model like the one developed here could be provided to clinicians as input to their clinical decision-making. But the critical distinction between the type of model developed in the current paper and precision treatment models is that the latter focus on interactions between patient characteristics and specific treatment alternatives with the goal of developing an individualized treatment rule (ITR) that predicts which treatment option is likely to be best for which patients (70,125,126). We plan to develop such a model as part of a pragmatic trial for intensive case management after psychiatric hospital discharge focused on the 60% of patients with meaningfully elevated risk of postdischarge suicide.…”

Ensembling Classical Machine Learning and Deep Learning Approaches for Morbidity Identification From Clinical Notes

“…To address this, Google introduced pre-trained embeddings models known as USE, which are optimized to train with a longer text sequence than a single word such as phrases, sentences, and short paragraphs [53], [54]. The pretrained USE 14 model is trained on several domains with a variety of data sources to dynamically accommodate a wide variety of natural language understanding tasks. It transforms the text into high-dimensional vectors by performing an encoding.…”

“…The state-of-theart research in this direction has already yielded significant results, and many challenges [11] are further explored with the goal of assisting the healthcare personnel. They include dynamic forecasting [12], personalized monitoring [13], and individualized treatment recommendations [14] of patients, especially those presenting multimorbidities as considered more vulnerable. According to [5], given that 25% of the world population is already suffering from multimorbidity, its early identification is paramount for preventing the severe health issues which can happen in the future to the patients.…”