The effects of using the PReDicT Test to guide the antidepressant treatment of depressed patients: study protocol for a randomised controlled trial

When a test is more than just a test: Findings from patient interviews and survey in the trial of a technology to measure antidepressant medication response (the PReDicT Trial)

BACKGROUND

A RCT of a novel intervention to detect antidepressant medication response (the PReDicT Test) took place in five European countries, accompanied by a nested study of its acceptability and implementation presented here. The RCT results indicated no effect of the intervention on depression at 8 weeks (primary outcome), although effects on anxiety at 8 weeks and functioning at 24 weeks were found.

METHODS

The nested study used mixed methods. The aim was to explore patient experiences of the Test including acceptability and implementation, to inform its use within care. A bespoke survey was completed by trial participants in five countries (n = 778) at week 8. Semi-structured interviews were carried out in two countries soon after week 8 (UK n = 22, Germany n = 20). Quantitative data was analysed descriptively; for qualitative data, thematic analysis was carried out using a framework approach. Results of the two datasets were interrogated together.

OUTCOMES

Survey results showed the intervention was well received, with a majority of participants indicating they would use it again, and it gave them helpful extra information; a small minority indicated the Test made them feel worse. Qualitative data showed the Test had unexpected properties, including: instigating a process of reflection, giving participants feedback on progress and new understanding about their illness, and making participants feel supported and more engaged in treatment.

INTERPRETATION

The qualitative and quantitative results are generally consistent. The Test's unexpected properties may explain why the RCT showed little effect, as properties were experienced across both trial arms. Beyond the RCT, the qualitative data sheds light on measurement reactivity, i.e., how measurements of depression can impact patients.

Exploring the incidence of inadequate response to antidepressants in the primary care of depression

Data from the UK suggests 13-55 % of depression patients experience some level of treatment resistance. However, little is known about how physicians manage inadequate response to antidepressants in primary care. This study aimed to explore the incidence of inadequate response to antidepressants in UK primary care. One-hundred-eighty-four medication-free patients with low mood initiated antidepressant treatment and monitored severity of depression symptoms, using the QIDS-SR16, for 48 weeks. Medication changes, visits to healthcare providers, and health-related quality of life were also recorded. Patients were classified into one of four response types based on their QIDS scores at three study timepoints: persistent inadequate responders (<50 % reduction in baseline QIDS at all timepoints), successful responders (≥50 % reduction in baseline QIDS at all timepoints), slow responders (≥50 % reduction in QIDS at week 48, despite earlier inadequate responses), and relapse (initial ≥50 % reduction in baseline QIDS, but inadequate response by week 48). Forty-eight weeks after initiating treatment 47 % of patients continued to experience symptoms of depression (QIDS >5), and 20 % of patients had a persistent inadequate response. Regardless of treatment response, 96 % (n = 176) of patients did not visit their primary care physician over the 40-week follow-up period. These results suggest that despite receiving treatment, a considerable proportion of patients with low mood remain unwell and fail to recover. Monitoring depression symptoms remotely can enable physicians to identify inadequate responders, allowing patients to be reassessed or referred to secondary services, likely improving patients' quality of life and reducing the socioeconomic impacts of chronic mental illness.

Subjective experience of the environment determines serotoninergic antidepressant treatment outcome in male mice

BACKGROUND

The effects of the selective serotonin reuptake inhibitors (SSRIs), the first-line antidepressant treatment, have been proposed to be affected, at least in part, by the living environment. Since the quality of the environment depends not only on its objective features, but also on the subjective experience, we hypothesized that the latter plays a key role in determining SSRI treatment outcome.

METHODS

We chronically administered the SSRI fluoxetine to two groups of adult CD-1 male mice that reportedly show distinct subjective experiences of the environment measured as consistent and significantly different responses to the same emotional and social stimuli. These distinct socioemotional profiles were generated by rearing mice either in standard laboratory conditions (SN) or in a communal nest (CN) where three dams breed together their offspring, sharing caregiving behavior.

RESULTS

At adulthood, CN mice displayed higher levels of agonistic and anxiety-like behaviors than SN mice, indicating that they experience the environment as more socially challenging and potentially dangerous. We then administered fluoxetine, which increased offensive and anxious response in SN, while producing opposite effects in CN mice. BDNF regulation was modified by the treatment accordingly.

LIMITATIONS

Subjective experience in mice was assessed as behavioral response to the environment.

CONCLUSIONS

These results show that the subjective experience of the environment determines fluoxetine outcome. In a translational perspective, our findings suggest considering not only the objective quality, but also the subjective appraisal, of the patient's living environment for developing effective personalized therapeutic approaches in psychiatry.

Digital technology and mental health during the COVID-19 pandemic: a narrative review with a focus on depression, anxiety, stress, and trauma

The sudden appearance and devastating effects of the COVID-19 pandemic resulted in the need for multiple adaptive changes in societies, business operations and healthcare systems across the world. This review describes the development and increased use of digital technologies such as chat bots, electronic diaries, online questionnaires and even video gameplay to maintain effective treatment standards for individuals with mental health conditions such as depression, anxiety and post-traumatic stress syndrome. We describe how these approaches have been applied to help meet the challenges of the pandemic in delivering mental healthcare solutions. The main focus of this narrative review is on describing how these digital platforms have been used in diagnostics, patient monitoring and as a treatment option for the general public, as well as for frontline medical staff suffering with mental health issues.

Individual differences in computational psychiatry: a review of current challenges

Bringing precision to the understanding and treatment of mental disorders requires instruments for studying clinically relevant individual differences. One promising approach is the development of computational assays: integrating computational models with cognitive tasks to infer latent patient-specific disease processes in brain computations. While recent years have seen many methodological advancements in computational modelling and many cross-sectional patient studies, much less attention has been paid to basic psychometric properties (reliability and construct validity) of the computational measures provided by the assays. In this review, we assess the extent of this issue by examining emerging empirical evidence. We find that many computational measures suffer from poor psychometric properties, which poses a risk of invalidating previous findings and undermining ongoing research efforts using computational assays to study individual (and even group) differences. We provide recommendations for how to address these problems and, crucially, embed them within a broader perspective on key developments that are needed for translating computational assays to clinical practice.

Development of an Instrument for the Assessment of Health-Related Multi-sectoral Resource Use in Europe: The PECUNIA RUM

BACKGROUND

Measuring objective resource-use quantities is important for generating valid cost estimates in economic evaluations. In the absence of acknowledged guidelines, measurement methods are often chosen based on practicality rather than methodological evidence. Furthermore, few resource-use measurement (RUM) instruments focus on the measurement of resource use in multiple societal sectors and their development process is rarely described. Thorn and colleagues proposed a stepwise approach to the development of RUM instruments, which has been used for developing cost questionnaires for specific trials. However, it remains unclear how this approach can be translated into practice and whether it is applicable to the development of generic self-reported RUM instruments and instruments measuring resource use in multiple sectors. This study provides a detailed description of the practical application of this stepwise approach to the development of a multi-sectoral RUM instrument developed within the ProgrammE in Costing, resource use measurement and outcome valuation for Use in multi-sectoral National and International health economic evaluAtions (PECUNIA) project.

METHODS

For the development of the PECUNIA RUM, the methodological approach was based on best practice guidelines. The process included six steps, including the definition of the instrument attributes, identification of cost-driving elements in each sector, review of methodological literature and development of a harmonized cross-sectorial approach, development of questionnaire modules and their subsequent harmonization.

RESULTS

The selected development approach was, overall, applicable to the development of the PECUNIA RUM. However, due to the complexity of the development of a multi-sectoral RUM instrument, additional steps such as establishing a uniform methodological basis, harmonization of questionnaire modules and involvement of a broader range of stakeholders (healthcare professionals, sector-specific experts, health economists) were needed.

CONCLUSION

This is the first study that transparently describes the development process of a generic multi-sectoral RUM instrument in health economics and provides insights into the methodological aspects and overall validity of its development process.

Feasibility, acceptability and costs of nurse-led Alpha-Stim cranial electrostimulation to treat anxiety and depression in university students

Background

Only a relatively low proportion of university students seek help for anxiety and depression disorders, partly because they dislike current drug and psychological treatment options and would prefer home-based care. The aim of this study is to determine the feasibility, acceptability and cost utility of Alpha-Stim cranial electrostimulation (CES) delivered through a nurse led primary care clinic as a daily treatment for anxiety and depression symptoms by the student at home in contrast to usual primary care.

Method

Feasibility and acceptability of a nurse led clinic offering Alpha-Stim CES in terms of the take up and completion of the six-week course of Alpha-Stim CES. Change in score on the GAD-7 and PHQ-9 as measures of anxiety and depression symptoms at baseline and at 8 weeks following a course of Alpha-Stim CES. Similar evaluation in a non-randomised control group attending a family doctor over the same period. Cost-utility analysis of the nurse led Alpha-Stim CES and family doctor pathways with participants failing to improve following further NICE Guideline clinical care (facilitated self-help and cognitive behaviour therapy).

Results

Of 47 students (mean age 22.1, years, 79% female opting for Alpha-Stim CES at the nurse-led clinic 46 (97.9%) completed a 6-week daily course. Forty-seven (47) students comprised a comparison group receiving usual family doctor care. Both Alpha-Stim CES and usual family doctor care were associated with large effect size reductions in GAD-7 and PHQ-9 scores from baseline to 8 weeks. There were no adverse effects and only one participant showed a clinically important deterioration in the Alpha-Stim group. In the cost utility analysis, Alpha-Stim CES was a cheaper option than usual family doctor care under all deterministic or probabilistic assumptions.

Conclusion

Nurse delivered Alpha-Stim CES may be a feasible, acceptable and cheaper way of providing greater choice and home-based care for some university students seeking help from primary care with new presentations of anxiety and depression.

Effects of add-on Celecoxib treatment on patients with schizophrenia spectrum disorders and inflammatory cytokine profile trial (TargetFlame): study design and methodology of a multicentre randomized, placebo-controlled trial

Neuroinflammation has been proposed to impact symptomatology in patients with schizophrenia spectrum disorders. While previous studies have shown equivocal effects of treatments with add-on anti-inflammatory drugs such as Aspirin, N-acetylcysteine and Celecoxib, none have used a subset of prospectively recruited patients exhibiting an inflammatory profile. The aim of the study is to evaluate the efficacy and safety as well as the cost-effectiveness of a treatment with 400 mg Celecoxib added to an ongoing antipsychotic treatment in patients with schizophrenia spectrum disorders exhibiting an inflammatory profile. The “Add-on Celecoxib treatment in patients with schizophrenia spectrum disorders and inflammatory cytokine profile trial (TargetFlame)” is a multicentre randomized, placebo-controlled phase III investigator-initiated clinical trial with the following two arms: patients exhibiting an inflammatory profile receiving either add-on Celecoxib 400 mg/day or add-on placebo. A total of 199 patients will be assessed for eligibility by measuring blood levels of three pro-inflammatory cytokines, and 109 patients with an inflammatory profile, i.e. inflamed, will be randomized, treated for 8 weeks and followed-up for additional four months. The primary endpoint will be changes in symptom severity as assessed by total Positive and Negative Syndrome Scale (PANSS) score changes from baseline to week 8. Secondary endpoints include various other measures of psychopathology and safety. Additional health economic analyses will be performed. TargetFlame is the first study aimed at evaluating the efficacy, safety and cost-effectiveness of the antiphlogistic agent Celecoxib in a subset of patients with schizophrenia spectrum disorders exhibiting an inflammatory profile. With TargetFlame, we intended to investigate a novel precision medicine approach towards anti-inflammatory antipsychotic treatment augmentation using drug repurposing.

Clinical trial registration:http://www.drks.de/DRKS00029044 and https://trialsearch.who.int/Trial2.aspx?TrialID=DRKS00029044

Cost-Effectiveness of Positive Memory Training (PoMeT) for the Treatment of Depression in Schizophrenia

The Positive Memory Training (PoMeT) trial demonstrated reduced depression symptoms at 3 months for schizophrenia, but its longer-term outcome and cost impacts remain unknown. This study is a within-trial cost-utility analysis with quality-adjusted life years (QALYs) as outcome based on health-related quality of life (HRQoL) measurement and secondary outcome analyses of capability well-being. The incremental cost-effectiveness of PoMeT was compared to Treatment As Usual only (TAU) over 9 months from the 'health and social' care and 'societal' perspectives. Uncertainty was explored using bootstrapping and sensitivity analyses for cost outliers and outcome methods. HRQoL improvement was observed for both PoMeT and TAU at 3 months, but reached statistical significance and was sustained only for TAU. There was no change in capability well-being and no significant group difference in QALYs gained over 9 months. Mean intervention cost was GBP 823. Compared to TAU, PoMeT had significantly higher mental health care costs (+GBP 1251, 95% CI GBP 185 to GBP 2316) during the trial, but 'health and social care' and 'societal' cost differences were non-significant. Compared to the before-trial period, psychiatric medication costs increased significantly in both groups. The probability of PoMeT being cost-effective in the given format over 9 months was <30% and decreased further in sensitivity analyses.. Generalizability remains limited since the before-after cost analysis revealed additional treatment effects also in the TAU group that likely diminished the incremental impacts and cost-effectiveness of PoMeT. It is not clear whether an active post-intervention follow-up could result in sustained longer-term effects and improved cost-effectiveness.

Does the relative importance of the OxCAP-MH's capability items differ according to mental ill-health experience?

BACKGROUND

Some capability dimensions may be more important than others in determining someone's well-being, and these preferences might be dependent on ill-health experience. This study aimed to explore the relative preference weights of the 16 items of the German language version of the OxCAP-MH (Oxford Capability questionnaire-Mental Health) capability instrument and their differences across cohorts with alternative levels of mental ill-health experience.

METHODS

A Best-Worst-Scaling (BWS) survey was conducted in Austria among 1) psychiatric patients (direct mental ill-health experience), 2) (mental) healthcare experts (indirect mental ill-health experience), and 3) primary care patients with no mental ill-health experience. Relative importance scores for each item of the German OxCAP-MH instrument were calculated using Hierarchical Bayes estimation. Rank analysis and multivariable linear regression analysis with robust standard errors were used to explore the relative importance of the OxCAP-MH items across the three cohorts.

RESULTS

The study included 158 participants with complete cases and acceptable fit statistic. The relative importance scores for the full cohort ranged from 0.76 to 15.72. Findings of the BWS experiment indicated that the items Self-determination and Limitation in daily activities were regarded as the most important for all three cohorts. Freedom of expression was rated significantly less important by psychiatric patients than by the other two cohorts, while Having suitable accommodation appeared significantly less important by the expert cohort. There were no further significant differences in the relative preference weights of OxCAP-MH items between the cohorts or according to gender.

CONCLUSIONS

Our study indicates significant between-item but limited mental ill-health related heterogeneity in the relative preference weights of the different capability items within the OxCAP-MH. The findings support the future development of preference-based value sets elicited from the general population for comparative economic evaluation purposes.

Prediction of Prognostic Risk Factors in Patients with Invasive Candidiasis and Cancer: A Single-Centre Retrospective Study

Background

Invasive candidiasis is a common cancer-related complication with a high fatality rate. If patients with a high risk of dying in the hospital are identified early and accurately, physicians can make better clinical judgments. However, epidemiological analyses and mortality prediction models of cancer patients with invasive candidiasis remain limited.

Method

A set of 40 potential risk factors was acquired in a sample of 258 patients with both invasive candidiasis and cancer. To begin, risk factors for Candida albicans vs. non-Candida albicans infections and persistent vs. nonpersistent Candida infections were analysed using classic statistical methods. Then, we applied three machine learning models (random forest, logistic regression, and support vector machine) to identify prognostic indicators related to mortality. Prediction performance of different models was assessed by precision, recall, F1 score, accuracy, and AUC.

Results

Of the 258 patients both with invasive candidiasis and cancer included in the analysis. The median age of patients was 62 years, and 95 (36.82%) patients were older than 65 years, of which 178 (66.28%) were male. And 186 (72.1%) patients underwent surgery 2 weeks before data collection, 100 (39.1%) patients stayed in ICU during hospitalisation, 99 (38.4%) patients had bacterial blood infection, 85 (32.9%) patients had persistent invasive candidiasis, and 41 (15.9%) patients died within 30 days. The usage of drainage catheter and prolonged length of hospitalisation are the dominant risk factors for non-Candida albicans infections and persistent Candida infections, respectively. Risk factors, such as septic shock, history of surgery within the past 2 weeks, usage of drainage tubes, length of stay in ICU, total parenteral nutrition, serum creatinine level, fungal antigen, stay in ICU during hospitalisation, and total bilirubin level, were significant predictors of death. The RF model outperformed the LR and SVM models. Precision, recall, F1 score, accuracy, and AUC for RF were 64.29%, 75.63%, 69.23%, 89.61%, and 91.28%.

Conclusions

In this study, the machine learning-based models accurately predicted the prognosis of cancer and invasive candidiasis patients. The algorithm could be used to help clinicians in high-risk patients' early intervention.

A single oral dose of citalopram increases interoceptive insight in healthy volunteers

RATIONALE

Interoception is the signalling, perception, and interpretation of internal physiological states. Many mental disorders associated with changes of interoception, including depressive and anxiety disorders, are treated with selective serotonin reuptake inhibitors (SSRIs). However, the causative link between SSRIs and interoception is not yet clear.

OBJECTIVES

To ascertain the causal effect of acute changes of serotonin levels on cardiac interoception.

METHODS

Using a within-participant placebo-controlled design, forty-seven healthy human volunteers (31 female, 16 male) were tested on and off a 20 mg oral dose of the commonly prescribed SSRI, citalopram. Participants made judgements on the synchrony between their heartbeat and auditory tones and then expressed confidence in each judgement. We measured three types of interoceptive cognition.

RESULTS

Citalopram increased cardiac interoceptive insight, measured as correspondence of self-reported confidence to the likelihood that interoceptive judgements were actually correct. This effect was driven by enhanced confidence for correct interoceptive judgements and was independent of measured cardiac and reported subjective effects of the drug.

CONCLUSIONS

An acute change of serotonin levels can increase insight into the reliability of inferences made from cardiac interoceptive sensations.

Suppressed activity of the rostral anterior cingulate cortex as a biomarker for depression remission

BACKGROUND

Suppression of the rostral anterior cingulate cortex (rACC) has shown promise as a prognostic biomarker for depression. We aimed to use machine learning to characterise its ability to predict depression remission.

METHODS

Data were obtained from 81 15- to 25-year-olds with a major depressive disorder who had participated in the YoDA-C trial, in which they had been randomised to receive cognitive behavioural therapy plus either fluoxetine or placebo. Prior to commencing treatment patients performed a functional magnetic resonance imaging (fMRI) task to assess rACC suppression. Support vector machines were trained on the fMRI data using nested cross-validation, and were similarly trained on clinical data. We further tested our fMRI model on data from the YoDA-A trial, in which participants had completed the same fMRI paradigm.

RESULTS

Thirty-six of 81 (44%) participants in the YoDA-C trial achieved remission. Our fMRI model was able to predict remission status (AUC = 0.777 [95% confidence interval (CI) 0.638-0.916], balanced accuracy = 67%, negative predictive value = 74%, p < 0.0001). Clinical models failed to predict remission status at better than chance levels. Testing the model on the alternative YoDA-A dataset confirmed its ability to predict remission (AUC = 0.776, balanced accuracy = 64%, negative predictive value = 70%, p < 0.0001).

CONCLUSIONS

We confirm that rACC activity acts as a prognostic biomarker for depression. The machine learning model can identify patients who are likely to have difficult-to-treat depression, which might direct the earlier provision of enhanced support and more intensive therapies.

Hot and cold cognitive disturbances in antidepressant-free patients with major depressive disorder: a NeuroPharm study

BACKGROUND

Cognitive disturbances are common and disabling features of major depressive disorder (MDD). Previous studies provide limited insight into the co-occurrence of hot (emotion-dependent) and cold (emotion-independent) cognitive disturbances in MDD. Therefore, we here map both hot and cold cognition in depressed patients compared to healthy individuals.

METHODS

We collected neuropsychological data from 92 antidepressant-free MDD patients and 103 healthy controls. All participants completed a comprehensive neuropsychological test battery assessing hot cognition including emotion processing, affective verbal memory and social cognition as well as cold cognition including verbal and working memory and reaction time.

RESULTS

The depressed patients showed small to moderate negative affective biases on emotion processing outcomes, moderate increases in ratings of guilt and shame and moderate deficits in verbal and working memory as well as moderately slowed reaction time compared to healthy controls. We observed no correlations between individual cognitive tasks and depression severity in the depressed patients. Lastly, an exploratory cluster analysis suggested the presence of three cognitive profiles in MDD: one characterised predominantly by disturbed hot cognitive functions, one characterised predominantly by disturbed cold cognitive functions and one characterised by global impairment across all cognitive domains. Notably, the three cognitive profiles differed in depression severity.

CONCLUSION

We identified a pattern of small to moderate disturbances in both hot and cold cognition in MDD. While none of the individual cognitive outcomes mapped onto depression severity, cognitive profile clusters did. Overall cognition-based stratification tools may be useful in precision medicine approaches to MDD.

Clinical effectiveness of patient-oriented depression feedback in primary care: The empirical method of the GET.FEEDBACK.GP multicenter randomized controlled trial

GET.FEEDBACK.GP₁ is a multicenter randomized controlled trial testing the efficacy of patient-oriented depression feedback in primary care. This paper describes the complex methods and procedures of the trial. The primary outcome is depression severity six months after feedback, and we vary who is the target of the feedback as follows: no one receives feedback, only general practitioners receive feedback, and both patients and general practitioners receive feedback. The procedure includes a baseline assessment in primary care practices and three telephone follow-up interviews after one, six, and twelve months. The patients completed a baseline assessment, which determined their depression severity. Those with at least a moderate depression severity (PHQ-9₅ ≥ 10) were randomly allocated to three groups stratified by depression severity. A standardized mean difference of d = 0.25 with power 1 - β = 0.80 required a total sample size of N = 699. The patients provided responses regarding the primary and secondary outcomes at follow-up. The extensive planning for GET.FEEDBACK.GP involved experts from diverse medical specialties and external corporations. Of particular importance were (a) blinding in the study inclusion and random assignment with data capture software, (b) representative and unbiased patient selection in practice waiting rooms, (c) a data management and safety plan supplied by a specialized trial center, and (d) the use of participant pseudonyms supplied by a specialized service (Mainzelliste). The data collection started in July 2019 and will continue until June 2022. Five university study centers in Germany are participating in the trial.

The clinical effectiveness of using a predictive algorithm to guide antidepressant treatment in primary care (PReDicT): an open-label, randomised controlled trial

Depressed patients often do not respond to the first antidepressant prescribed, resulting in sequential trials of different medications. Personalised medicine offers a means of reducing this delay; however, the clinical effectiveness of personalised approaches to antidepressant treatment has not previously been tested. We assessed the clinical effectiveness of using a predictive algorithm, based on behavioural tests of affective cognition and subjective symptoms, to guide antidepressant treatment. We conducted a multicentre, open-label, randomised controlled trial in 913 medication-free depressed patients. Patients were randomly assigned to have their antidepressant treatment guided by a predictive algorithm or treatment as usual (TaU). The primary outcome was the response of depression symptoms, defined as a 50% or greater reduction in baseline score of the QIDS-SR-16 scale, at week 8. Additional prespecified outcomes included symptoms of anxiety at week 8, and symptoms of depression and functional outcome at weeks 8, 24 and 48. The response rate of depressive symptoms at week 8 in the PReDicT (55.9%) and TaU (51.8%) arms did not differ significantly (odds ratio: 1.18 (95% CI: 0.89-1.56), P = 0.25). However, there was a significantly greater reduction of anxiety in week 8 and a greater improvement in functional outcome at week 24 in the PReDicT arm. Use of the PReDicT test did not increase the rate of response to antidepressant treatment estimated by depressive symptoms but did improve symptoms of anxiety at week 8 and functional outcome at week 24. Our findings indicate that personalisation of antidepressant treatment may improve outcomes in depressed patients.

Computational approaches and machine learning for individual-level treatment predictions

RATIONALE

The impact of neuroscience-based approaches for psychiatry on pragmatic clinical decision-making has been limited. Although neuroscience has provided insights into basic mechanisms of neural function, these insights have not improved the ability to generate better assessments, prognoses, diagnoses, or treatment of psychiatric conditions.

OBJECTIVES

To integrate the emerging findings in machine learning and computational psychiatry to address the question: what measures that are not derived from the patient's self-assessment or the assessment by a trained professional can be used to make more precise predictions about the individual's current state, the individual's future disease trajectory, or the probability to respond to a particular intervention?

RESULTS

Currently, the ability to use individual differences to predict differential outcomes is very modest possibly related to the fact that the effect sizes of interventions are small. There is emerging evidence of genetic and neuroimaging-based heterogeneity of psychiatric disorders, which contributes to imprecise predictions. Although the use of machine learning tools to generate clinically actionable predictions is still in its infancy, these approaches may identify subgroups enabling more precise predictions. In addition, computational psychiatry might provide explanatory disease models based on faulty updating of internal values or beliefs.

CONCLUSIONS

There is a need for larger studies, clinical trials using machine learning, or computational psychiatry model parameters predictions as actionable outcomes, comparing alternative explanatory computational models, and using translational approaches that apply similar paradigms and models in humans and animals.

Cost and quality-of-life impacts of community treatment orders (CTOs) for patients with psychosis: economic evaluation of the OCTET trial

PURPOSE

Current RCT and meta-analyses have not found any effect of community treatment orders (CTOs) on hospital or social outcomes. Assumed positive impacts of CTOs on quality-of-life outcomes and reduced hospital costs are potentially in conflict with patient autonomy. Therefore, an analysis of the cost and quality-of-life consequences of CTOs was conducted within the OCTET trial.

METHODS

The economic evaluation was carried out comparing patients (n = 328) with psychosis discharged from involuntary hospitalisation either to treatment under a CTO (CTO group) or voluntary status via Section 17 leave (non-CTO group) from the health and social care and broader societal perspectives (including cost implication of informal family care and legal procedures). Differences in costs and outcomes defined as quality-adjusted life years (QALYs) based on the EQ-5D-3L or capability-weighted life years (CWLYs) based on the OxCAP-MH were assessed over 12 months (£, 2012/13 tariffs).

RESULTS

Mean total costs from the health and social care perspective [CTO: £35,595 (SD: £44,886); non-CTO: £36,003 (SD: £41,406)] were not statistically significantly different in any of the analyses or cost categories. Mental health hospitalisation costs contributed to more than 85% of annual health and social care costs. Informal care costs were significantly higher in the CTO group, in which there were also significantly more manager hearings and tribunals. No difference in health-related quality of life or capability wellbeing was found between the groups.

CONCLUSION

CTOs are unlikely to be cost-effective. No evidence supports the hypothesis that CTOs decrease hospitalisation costs or improve quality of life. Future decisions should consider impacts outside the healthcare sector such as higher informal care costs and legal procedure burden of CTOs.

Comparison of Conventional Statistical Methods with Machine Learning in Medicine: Diagnosis, Drug Development, and Treatment

Futurists have anticipated that novel autonomous technologies, embedded with machine learning (ML), will substantially influence healthcare. ML is focused on making predictions as accurate as possible, while traditional statistical models are aimed at inferring relationships between variables. The benefits of ML comprise flexibility and scalability compared with conventional statistical approaches, which makes it deployable for several tasks, such as diagnosis and classification, and survival predictions. However, much of ML-based analysis remains scattered, lacking a cohesive structure. There is a need to evaluate and compare the performance of well-developed conventional statistical methods and ML on patient outcomes, such as survival, response to treatment, and patient-reported outcomes (PROs). In this article, we compare the usefulness and limitations of traditional statistical methods and ML, when applied to the medical field. Traditional statistical methods seem to be more useful when the number of cases largely exceeds the number of variables under study and a priori knowledge on the topic under study is substantial such as in public health. ML could be more suited in highly innovative fields with a huge bulk of data, such as omics, radiodiagnostics, drug development, and personalized treatment. Integration of the two approaches should be preferred over a unidirectional choice of either approach.

Predicting Treatment Outcome in Major Depressive Disorder Using Serotonin 4 Receptor PET Brain Imaging, Functional MRI, Cognitive-, EEG-Based, and Peripheral Biomarkers: A NeuroPharm Open Label Clinical Trial Protocol

BACKGROUND

Between 30 and 50% of patients with major depressive disorder (MDD) do not respond sufficiently to antidepressant regimens. The conventional pharmacological treatments predominantly target serotonergic brain signaling but better tools to predict treatment response and identify relevant subgroups of MDD are needed to support individualized and mechanistically targeted treatment strategies. The aim of this study is to investigate antidepressant-free patients with MDD using neuroimaging, electrophysiological, molecular, cognitive, and clinical examinations and evaluate their ability to predict clinical response to SSRI treatment as individual or combined predictors.

METHODS

We will include 100 untreated patients with moderate to severe depression (>17 on the Hamilton Depression Rating Scale 17) in a non-randomized open clinical trial. We will collect data from serotonin 4 receptor positron emission tomography (PET) brain scans, functional magnetic resonance imaging (fMRI), electroencephalogram (EEG), cognitive tests, psychometry, and peripheral biomarkers, before (at baseline), during, and after 12 weeks of standard antidepressant treatment. Patients will be treated with escitalopram, and in case of non-response at week 4 or intolerable side effects, offered to switch to a second line treatment with duloxetine. Our primary outcome (treatment response) is assessed using the Hamilton depression rating subscale 6-item scores at week 8, compared to baseline. In a subset of the patients (n = ~40), we will re-assess the neurobiological response (using PET, fMRI, and EEG) 8 weeks after initiated pharmacological antidepressant treatment, to map neurobiological signatures of treatment responses. Data from matched controls will either be collected or is already available from other cohorts.

DISCUSSION

The extensive investigational program with follow-up in this large cohort of participants provides a unique possibility to (a) uncover potential biomarkers for antidepressant treatment response, (b) apply the findings for future stratification of MDD, (c) advance the understanding of pathophysiological underpinnings of MDD, and (d) uncover how putative biomarkers change in response to 8 weeks of pharmacological antidepressant treatment. Our data can pave the way for a precision medicine approach for optimized treatment of MDD and also provides a resource for future research and data sharing.

CLINICAL TRIAL REGISTRATION

The study was registered at clinicaltrials.gov prior to initiation (NCT02869035; 08.16.2016, URL: https://clinicaltrials.gov/ct2/results?cond=&term=NCT02869035&cntry=&state=&city=&dist=).

Value of monitoring negative emotional bias in primary care in England for personalised antidepressant treatment: a modelling study

BACKGROUND

Depressed patients often focus on negative life events. Effective antidepressant therapy reverses this negative emotional bias (NEB) within 1 week. Clinical therapeutic effect usually requires 4-6 weeks. The value of implementing NEB monitoring for the personalisation of antidepressant therapy is unknown.

OBJECTIVE

To estimate the likely outcome and cost consequences of adopting the P1vital Oxford Emotional Test Battery (ETB) for this purpose in routine primary care in England.

METHODS

A hybrid decision analytic model (decision tree plus Markov model) was developed to estimate the cost-effectiveness of ETB monitoring versus no ETB over 52 weeks using quality-adjusted life years (QALYs). Differences in depression severity, episode type and analytical perspectives were considered. Input data were derived from relevant guidelines, literature, national databases, expert opinion and the developers for the year 2013. Multiple sensitivity analyses addressed uncertainty.

FINDINGS

The mean number of ETB tests is 2.162 per newly diagnosed patient and 2.166 per patient with recurrent depression. The incremental cost-effectiveness of ETB versus 'no ETB' is £4355/QALY from the healthcare perspective. From the broader societal perspective, ETB is more effective and cost saving.

CONCLUSIONS

Monitoring negative emotional bias in primary care in England for personalised antidepressant treatment using ETB seems as an effective and cost-effective option under all considered scenarios (including worst case). Its main economic value seems to lie in reduced productivity loss as opposed to healthcare savings.

CLINICAL IMPLICATIONS

The test supports accelerated application of evidence-based depression care. Further optimisation and implementation in the ongoing European PReDicT trial is ongoing.

Measuring broader wellbeing in mental health services: validity of the German language OxCAP-MH capability instrument

PURPOSE

The OxCAP-MH capabilities questionnaire was developed and validated in the UK for outcome measurement in mental health clinical studies. Its broader wellbeing construct or validity in routine mental health services so far has not been assessed. The objectives were to investigate the extent the OxCAP-MH measures broader wellbeing compared to the EQ-5D-5L and to test psychometric properties of the German language OxCAP-MH in routine mental health services in Austria.

METHODS

Study sample consisted of patients in socio-psychiatric services (n = 159) assessed at baseline and 6-month follow-up. Underlying factors associated with quality-of-life/wellbeing concepts measured by the OxCAP-MH and EQ-5D-5L were identified in exploratory factor analysis (EFA). Responsiveness was assessed using anchor questionnaires and standardised response mean (SRM). For discriminant validity, subgroups of respondents were compared using t test and one-way ANOVA. Test-retest analysis was assessed for a period of maximum 30 days from the baseline assessment with intra-class correlation coefficient (ICC).

RESULTS

EFA identified a two-factor structure. All EQ-5D-5L items and seven OxCAP-MH items loaded on one factor and nine remaining OxCAP-MH items loaded on a separate factor. Responsiveness was found for patients who improved in anchor questionnaire scores with large or moderate SRM statistics. OxCAP-MH discriminated between various groups in univariable and multivariable analyses. Reliability of the German language OxCAP-MH was confirmed by ICC of 0.80.

CONCLUSIONS

Besides providing evidence that the OxCAP-MH measures broader wellbeing constructs beyond traditional health-related quality of life, the study also confirms the validity of the instrument for implementation in routine evaluation of mental health services.

Predicting treatment response to antidepressant medication using early changes in emotional processing

Antidepressants must be taken for weeks before response can be assessed with many patients not responding to the first medication prescribed. This often results in long delays before effective treatment is started. Antidepressants induce changes in the processing of emotional stimuli early in the course of treatment. In the current study we assessed whether changes in emotional processing and subjective symptoms over the first week of antidepressant treatment predicted clinical response after 4-8 weeks of treatment. Such a predictive test may shorten the time taken to initiate effective treatment in depressed patients. Seventy-four depressed primary care patients completed measures of emotional bias and subjective symptoms before starting antidepressant treatment and then again 1 week later. Response to treatment was assessed after 4-6 weeks. The performance of classifiers based on these measures was assessed using a leave-one-out validation procedure with the best classifier then tested in an independent sample from a second study of 239 patients. The combination of a facial emotion recognition task and subjective symptoms predicted response with 77% accuracy in the training sample and 60% accuracy in the independent study, significantly better than possible using baseline response rates. The face based measure of emotional bias provided good quality data with high acceptability ratings. Changes in emotional processing can provide a sensitive early measure of antidepressant efficacy for individual patients. Early treatment induced changes in emotional processing may be used to guide antidepressant therapy and reduce the time taken for depressed patients to return to good mental health.

Precision pharmacotherapy: psychiatry's future direction in preventing, diagnosing, and treating mental disorders

Mental disorders account for around one-third of disability worldwide and cause enormous personal and societal burden. Current pharmacotherapies and nonpharmacotherapies do help many patients, but there are still high rates of partial or no response, delayed effect, and unfavorable adverse effects. The current diagnostic taxonomy of mental disorders by the Diagnostic and Statistical Manual of Mental Disorders and the International Classification of Diseases relies on presenting signs and symptoms, but does not reflect evidence from neurobiological and behavioral systems. However, in the last decades, the understanding of biological mechanisms underlying mental disorders has grown and can be used for the development of precision medicine, that is, to deliver a patient-tailored individual treatment. Precision medicine may incorporate genetic variants contributing to the mental disorder and the response to pharmacotherapies, but also consider gene ¥ environment interactions, blood-based markers, neuropsychological tests, data from electronic health records, early life adversity, stressful life events, and very proximal factors such as lifestyle, nutrition, and sport. Methods such as artificial intelligence and the underlying machine learning and deep learning approaches provide the framework to stratify patients, initiate specific tailored treatments and thus increase response rates, reduce adverse effects and medical errors. In conclusion, precision medicine uses measurable health parameters to identify individuals at risk of a mental disorder, to improve the diagnostic process and to deliver a patient-tailored treatment.