Predictive modeling for response to lithium and quetiapine in bipolar disorder

Brain morphometric features predict medication response in youth with bipolar disorder: a prospective randomized clinical trial

BACKGROUND

Identification of treatment-specific predictors of drug therapies for bipolar disorder (BD) is important because only about half of individuals respond to any specific medication. However, medication response in pediatric BD is variable and not well predicted by clinical characteristics.

METHODS

A total of 121 youth with early course BD (acute manic/mixed episode) were prospectively recruited and randomized to 6 weeks of double-blind treatment with quetiapine (n = 71) or lithium (n = 50). Participants completed structural magnetic resonance imaging (MRI) at baseline before treatment and 1 week after treatment initiation, and brain morphometric features were extracted for each individual based on MRI scans. Positive antimanic treatment response at week 6 was defined as an over 50% reduction of Young Mania Rating Scale scores from baseline. Two-stage deep learning prediction model was established to distinguish responders and non-responders based on different feature sets.

RESULTS

Pre-treatment morphometry and morphometric changes occurring during the first week can both independently predict treatment outcome of quetiapine and lithium with balanced accuracy over 75% (all p < 0.05). Combining brain morphometry at baseline and week 1 allows prediction with the highest balanced accuracy (quetiapine: 83.2% and lithium: 83.5%). Predictions in the quetiapine and lithium group were found to be driven by different morphometric patterns.

CONCLUSIONS

These findings demonstrate that pre-treatment morphometric measures and acute brain morphometric changes can serve as medication response predictors in pediatric BD. Brain morphometric features may provide promising biomarkers for developing biologically-informed treatment outcome prediction and patient stratification tools for BD treatment development.

Methodological and Quality Flaws in the Use of Artificial Intelligence in Mental Health Research: Systematic Review

BACKGROUND

Artificial intelligence (AI) is giving rise to a revolution in medicine and health care. Mental health conditions are highly prevalent in many countries, and the COVID-19 pandemic has increased the risk of further erosion of the mental well-being in the population. Therefore, it is relevant to assess the current status of the application of AI toward mental health research to inform about trends, gaps, opportunities, and challenges.

OBJECTIVE

This study aims to perform a systematic overview of AI applications in mental health in terms of methodologies, data, outcomes, performance, and quality.

METHODS

A systematic search in PubMed, Scopus, IEEE Xplore, and Cochrane databases was conducted to collect records of use cases of AI for mental health disorder studies from January 2016 to November 2021. Records were screened for eligibility if they were a practical implementation of AI in clinical trials involving mental health conditions. Records of AI study cases were evaluated and categorized by the International Classification of Diseases 11th Revision (ICD-11). Data related to trial settings, collection methodology, features, outcomes, and model development and evaluation were extracted following the CHARMS (Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies) guideline. Further, evaluation of risk of bias is provided.

RESULTS

A total of 429 nonduplicated records were retrieved from the databases and 129 were included for a full assessment-18 of which were manually added. The distribution of AI applications in mental health was found unbalanced between ICD-11 mental health categories. Predominant categories were Depressive disorders (n=70) and Schizophrenia or other primary psychotic disorders (n=26). Most interventions were based on randomized controlled trials (n=62), followed by prospective cohorts (n=24) among observational studies. AI was typically applied to evaluate quality of treatments (n=44) or stratify patients into subgroups and clusters (n=31). Models usually applied a combination of questionnaires and scales to assess symptom severity using electronic health records (n=49) as well as medical images (n=33). Quality assessment revealed important flaws in the process of AI application and data preprocessing pipelines. One-third of the studies (n=56) did not report any preprocessing or data preparation. One-fifth of the models were developed by comparing several methods (n=35) without assessing their suitability in advance and a small proportion reported external validation (n=21). Only 1 paper reported a second assessment of a previous AI model. Risk of bias and transparent reporting yielded low scores due to a poor reporting of the strategy for adjusting hyperparameters, coefficients, and the explainability of the models. International collaboration was anecdotal (n=17) and data and developed models mostly remained private (n=126).

CONCLUSIONS

These significant shortcomings, alongside the lack of information to ensure reproducibility and transparency, are indicative of the challenges that AI in mental health needs to face before contributing to a solid base for knowledge generation and for being a support tool in mental health management.

The development and internal evaluation of a predictive model to identify for whom Mindfulness-Based Cognitive Therapy (MBCT) offers superior relapse prevention for recurrent depression versus maintenance antidepressant medication

Depression is highly recurrent, even following successful pharmacological and/or psychological intervention. We aimed to develop clinical prediction models to inform adults with recurrent depression choosing between antidepressant medication (ADM) maintenance or switching to Mindfulness-Based Cognitive Therapy (MBCT). Using data from the PREVENT trial (N=424), we constructed prognostic models using elastic net regression that combined demographic, clinical and psychological factors to predict relapse at 24 months under ADM or MBCT. Only the ADM model (discrimination performance: AUC=.68) predicted relapse better than baseline depression severity (AUC=.54; one-tailed DeLong's test: z=2.8, p=.003). Individuals with the poorest ADM prognoses who switched to MBCT had better outcomes compared to those who maintained ADM (48% vs. 70% relapse, respectively; superior survival times [z=-2.7, p=.008]). For individuals with moderate-to-good ADM prognosis, both treatments resulted in similar likelihood of relapse. If replicated, the results suggest that predictive modeling can inform clinical decision-making around relapse prevention in recurrent depression.

Clinical predictors of non-response to lithium treatment in the Pharmacogenomics of Bipolar Disorder (PGBD) study

BACKGROUND

Lithium is regarded as a first-line treatment for bipolar disorder (BD), but partial response and non-response commonly occurs. There exists a need to identify lithium non-responders prior to initiating treatment. The Pharmacogenomics of Bipolar Disorder (PGBD) Study was designed to identify predictors of lithium response.

METHODS

The PGBD Study was an eleven site prospective trial of lithium treatment in bipolar I disorder. Subjects were stabilized on lithium monotherapy over 4 months and gradually discontinued from all other psychotropic medications. After ensuring a sustained clinical remission (defined by a score of ≤3 on the CGI for 4 weeks) had been achieved, subjects were followed for up to 2 years to monitor clinical response. Cox proportional hazard models were used to examine the relationship between clinical measures and time until failure to remit or relapse.

RESULTS

A total of 345 individuals were enrolled into the study and included in the analysis. Of these, 101 subjects failed to remit or relapsed, 88 achieved remission and continued to study completion, and 156 were terminated from the study for other reasons. Significant clinical predictors of treatment failure (p < 0.05) included baseline anxiety symptoms, functional impairments, negative life events and lifetime clinical features such as a history of migraine, suicidal ideation/attempts, and mixed episodes, as well as a chronic course of illness.

CONCLUSIONS

In this PGBD Study of lithium response, several clinical features were found to be associated with failure to respond to lithium. Future validation is needed to confirm these clinical predictors of treatment failure and their use clinically to distinguish who will do well on lithium before starting pharmacotherapy.

Association of Attention-Deficit/Hyperactivity Disorder and Depression Polygenic Scores with Lithium Response: A Consortium for Lithium Genetics Study

Response to lithium varies widely between individuals with bipolar disorder (BD). Polygenic risk scores (PRSs) can uncover pharmacogenomics effects and may help predict drug response. Patients (N = 2,510) with BD were assessed for long-term lithium response in the Consortium on Lithium Genetics using the Retrospective Criteria of Long-Term Treatment Response in Research Subjects with Bipolar Disorder score. PRSs for attention-deficit/hyperactivity disorder (ADHD), major depressive disorder (MDD), and schizophrenia (SCZ) were computed using lassosum and in a model including all three PRSs and other covariates, and the PRS of ADHD (β = -0.14; 95% confidence interval [CI]: -0.24 to -0.03; p value = 0.010) and MDD (β = -0.16; 95% CI: -0.27 to -0.04; p value = 0.005) predicted worse quantitative lithium response. A higher SCZ PRS was associated with higher rates of medication nonadherence (OR = 1.61; 95% CI: 1.34-1.93; p value = 2e-7). This study indicates that genetic risk for ADHD and depression may influence lithium treatment response. Interestingly, a higher SCZ PRS was associated with poor adherence, which can negatively impact treatment response. Incorporating genetic risk of ADHD, depression, and SCZ in combination with clinical risk may lead to better clinical care for patients with BD.

Perceived helpfulness of bipolar disorder treatment: Findings from the World Health Organization World Mental Health Surveys

OBJECTIVES

To examine patterns and predictors of perceived treatment helpfulness for mania/hypomania and associated depression in the WHO World Mental Health Surveys.

METHODS

Face-to-face interviews with community samples across 15 countries found n = 2,178 who received lifetime mania/hypomania treatment and n = 624 with lifetime mania/hypomania who received lifetime major depression treatment. These respondents were asked whether treatment was ever helpful and, if so, the number of professionals seen before receiving helpful treatment. Patterns and predictors of treatment helpfulness were examined separately for mania/hypomania and depression.

RESULTS

63.1% (mania/hypomania) and 65.1% (depression) of patients reported ever receiving helpful treatment. However, only 24.5-22.5% were helped by the first professional seen, which means that the others needed to persist in help seeking after initial unhelpful treatments in order to find helpful treatment. Projections find only 22.9% (mania/hypomania) and 43.3% (depression) would persist through a series of unhelpful treatments but that the proportion helped would increase substantially if persistence increased. Few patient-level significant predictors of helpful treatment emerged and none consistently either across the two components (i.e., provider-level helpfulness and persistence after earlier unhelpful treatment) or for both mania/hypomania and depression. Although prevalence of treatment was higher in high-income than low/middle-income countries, proportional helpfulness among treated cases was nearly identical in the two groups of countries.

CONCLUSIONS

Probability of patients with mania/hypomania and associated depression obtaining helpful treatment might increase substantially if persistence in help-seeking increased after initially unhelpful treatments, although this could require seeing numerous additional treatment providers. In addition to investigating reasons for initial treatments not being helpful, messages reinforcing the importance of persistence should be emphasized to patients.

The promise of machine learning in predicting treatment outcomes in psychiatry

For many years, psychiatrists have tried to understand factors involved in response to medications or psychotherapies, in order to personalize their treatment choices. There is now a broad and growing interest in the idea that we can develop models to personalize treatment decisions using new statistical approaches from the field of machine learning and applying them to larger volumes of data. In this pursuit, there has been a paradigm shift away from experimental studies to confirm or refute specific hypotheses towards a focus on the overall explanatory power of a predictive model when tested on new, unseen datasets. In this paper, we review key studies using machine learning to predict treatment outcomes in psychiatry, ranging from medications and psychotherapies to digital interventions and neurobiological treatments. Next, we focus on some new sources of data that are being used for the development of predictive models based on machine learning, such as electronic health records, smartphone and social media data, and on the potential utility of data from genetics, electrophysiology, neuroimaging and cognitive testing. Finally, we discuss how far the field has come towards implementing prediction tools in real-world clinical practice. Relatively few retrospective studies to-date include appropriate external validation procedures, and there are even fewer prospective studies testing the clinical feasibility and effectiveness of predictive models. Applications of machine learning in psychiatry face some of the same ethical challenges posed by these techniques in other areas of medicine or computer science, which we discuss here. In short, machine learning is a nascent but important approach to improve the effectiveness of mental health care, and several prospective clinical studies suggest that it may be working already.

Precision medicine for long-term depression outcomes using the Personalized Advantage Index approach: cognitive therapy or interpersonal psychotherapy?

BACKGROUND

Psychotherapies for depression are equally effective on average, but individual responses vary widely. Outcomes can be improved by optimizing treatment selection using multivariate prediction models. A promising approach is the Personalized Advantage Index (PAI) that predicts the optimal treatment for a given individual and the magnitude of the advantage. The current study aimed to extend the PAI to long-term depression outcomes after acute-phase psychotherapy.

METHODS

Data come from a randomized trial comparing cognitive therapy (CT, n = 76) and interpersonal psychotherapy (IPT, n = 75) for major depressive disorder (MDD). Primary outcome was depression severity, as assessed by the BDI-II, during 17-month follow-up. First, predictors and moderators were selected from 38 pre-treatment variables using a two-step machine learning approach. Second, predictors and moderators were combined into a final model, from which PAI predictions were computed with cross-validation. Long-term PAI predictions were then compared to actual follow-up outcomes and post-treatment PAI predictions.

RESULTS

One predictor (parental alcohol abuse) and two moderators (recent life events; childhood maltreatment) were identified. Individuals assigned to their PAI-indicated treatment had lower follow-up depression severity compared to those assigned to their PAI-non-indicated treatment. This difference was significant in two subsets of the overall sample: those whose PAI score was in the upper 60%, and those whose PAI indicated CT, irrespective of magnitude. Long-term predictions did not overlap substantially with predictions for acute benefit.

CONCLUSIONS

If replicated, long-term PAI predictions could enhance precision medicine by selecting the optimal treatment for a given depressed individual over the long term.

Predictors of 1-year rehospitalization in inpatients with bipolar I disorder treated with atypical antipsychotics

Bipolar disorder (BPD) is debilitating disorder, and patients can experience multiple relapses and subsequent hospitalizations. Since pharmacotherapy is the mainstay of treatment for patients with BPD, investigations on the effects of atypical antipsychotics (AAP) on reducing rehospitalization risk are crucial. The objective of study is to explore predictors of 1-year rehospitalization in patients with bipolar I disorder treated with AAP. A retrospective chart review on inpatients with bipolar I disorder was conducted. All participants were followed up for 1 year, and they were subdivided into three AAP treatment groups (olanzapine, risperidone, and quetiapine group). Kaplan-Meier survival analysis was implemented to detect time to rehospitalization due to any mood episodes within 1 year after discharge. Cox proportional regression model was adopted to find predictors of 1-year hospitalization in patients who experienced rehospitalization. One hundred thirty-eight participants were included in the study, and a 1-year rehospitalization rate was 18.1%. Time to rehospitalization did not differ between three AAP treatment groups. Predictors of rehospitalization due to any episode within 1 year were family history of depression and number of previous admission. Our findings can be conducive to understanding prognosis, and predicting rehospitalization risk in patients with BPD on AAP.

Challenges and Future Prospects of Precision Medicine in Psychiatry

Precision medicine is increasingly recognized as a promising approach to improve disease treatment, taking into consideration the individual clinical and biological characteristics shared by specific subgroups of patients. In specific fields such as oncology and hematology, precision medicine has already started to be implemented in the clinical setting and molecular testing is routinely used to select treatments with higher efficacy and reduced adverse effects. The application of precision medicine in psychiatry is still in its early phases. However, there are already examples of predictive models based on clinical data or combinations of clinical, neuroimaging and biological data. While the power of single clinical predictors would remain inadequate if analyzed only with traditional statistical approaches, these predictors are now increasingly used to impute machine learning models that can have adequate accuracy even in the presence of relatively small sample size. These models have started to be applied to disentangle relevant clinical questions that could lead to a more effective management of psychiatric disorders, such as prediction of response to the mood stabilizer lithium, resistance to antidepressants in major depressive disorder or stratification of the risk and outcome prediction in schizophrenia. In this narrative review, we summarized the most important findings in precision medicine in psychiatry based on studies that constructed machine learning models using clinical, neuroimaging and/or biological data. Limitations and barriers to the implementation of precision psychiatry in the clinical setting, as well as possible solutions and future perspectives, will be presented.

Prediction of lithium response using clinical data

OBJECTIVE

Promptly establishing maintenance therapy could reduce morbidity and mortality in patients with bipolar disorder. Using a machine learning approach, we sought to evaluate whether lithium responsiveness (LR) is predictable using clinical markers.

METHOD

Our data are the largest existing sample of direct interview-based clinical data from lithium-treated patients (n = 1266, 34.7% responders), collected across seven sites, internationally. We trained a random forest model to classify LR-as defined by the previously validated Alda scale-against 180 clinical predictors.

RESULTS

Under appropriate cross-validation procedures, LR was predictable in the pooled sample with an area under the receiver operating characteristic curve of 0.80 (95% CI 0.78-0.82) and a Cohen kappa of 0.46 (0.4-0.51). The model demonstrated a particularly low false-positive rate (specificity 0.91 [0.88-0.92]). Features related to clinical course and the absence of rapid cycling appeared consistently informative.

CONCLUSION

Clinical data can inform out-of-sample LR prediction to a potentially clinically relevant degree. Despite the relevance of clinical course and the absence of rapid cycling, there was substantial between-site heterogeneity with respect to feature importance. Future work must focus on improving classification of true positives, better characterizing between- and within-site heterogeneity, and further testing such models on new external datasets.