Antipsychotic dopamine D2 affinity and negative symptoms in remitted first episode psychosis patients.

Negative symptoms can be an integral part of schizophrenia spectrum pathology and can be secondary to other psychotic symptoms or caused by antipsychotic medication. As antipsychotic drugs differ in their affinity to dopamine receptors and some antipsychotics have partial agonistic effects, antipsychotic drugs are expected to vary in their ability to cause negative symptoms. The association between negative symptoms and antipsychotic medication divided into partial agonists, or antagonists with high or low D2 affinity was assessed in 310 remitted first episode psychosis (FEP) patients. Severity of negative symptoms was assessed with the Comprehensive Assessment of Symptoms and History, and the Positive and Negative Syndrome Scale. Linear regression analyses were performed while controlling for differences in clinical and sociodemographic characteristics between the groups using inverse probability of treatment weighting. Patients using partial agonists (n = 78) showed fewer negative symptoms compared to those using high affinity antagonists (n = 84). Patients using partial agonists displayed less severe negative symptoms compared to those using low affinity antagonists (n = 148) at a trend level (p = 0.051). Negative symptom severity was higher in patients who had higher antipsychotic doses. In remitted FEP patients, we observed that the use of antipsychotic medication classified as partial agonists was associated with lower severity of negative symptoms, while the use of antagonists with high D2 affinity was associated with more severe negative symptoms.

The effectiveness and cost-effectiveness of attachment-based family therapy for young adults with high suicidal ideation: protocol of a randomized controlled trial.

BACKGROUND: Young adult suicidality is worldwide a prevalent mental health problem and the number one cause of death, with devastating consequences for individuals and their families, and substantial economic costs. However, psychological and pharmacological treatments currently recommended in guidelines for treatment of high-risk youth for fatal suicide have limited effect. In line with the World Health Organization's (WHO) recommendation to involve the family in treatment of these youth, attachment-based family therapy (ABFT) was developed, a 16-week attachment and emotion-focused treatment, implemented in mental health care settings across various European countries in the past years, and becoming increasingly popular among therapists. However, the (cost-)effectiveness of ABFT has not been studied in emerging adults. In the proposed pragmatic randomized controlled trial (RCT), we aim to evaluate the effectiveness and cost-effectiveness of ABFT compared to treatment as usual (TAU) on suicidality, as delivered in daily practice. METHODS: This pragmatic multicenter study in the Netherlands and Belgium includes 13 participating sites. Participants are suicidal young adults (≥ 31 SIQ-JR score) between 16 and 30 years old who seek mental health treatment (n = 142) and their caregivers. The primary outcome is suicidality (SIQ-JR), with assessments at baseline, post-intervention (5 months after baseline), 3, 6, and 12 months after intervention. We predict that, compared to TAU, ABFT will lead to a stronger reduction in suicidality and will be more cost-effective, over the course of all time points. We also expect stronger decreases in depressive symptoms, given that suicidality is very common in individuals with depressive disorder, as well as more improvement in family functioning, autonomy, entrapment, and young adult attachment, in the ABFT condition. DISCUSSION: This study can contribute to improving the care for suicidal youngsters with high mortality risk. Treatment of suicidal emerging adults is understudied. The results will inform clinical guidelines and policy makers and improve treatment of suicidal emerging adults. TRIAL REGISTRATION: This trial is registered on ClinicalTrials.gov (NCT05965622, first posted on July 28, 2023).

rTMS as a Next Step in Antidepressant Nonresponders: A Randomized Comparison With Current Antidepressant Treatment Approaches.

OBJECTIVE: Although repetitive transcranial magnetic stimulation (rTMS) is an effective treatment for depression, little is known about the comparative effectiveness of rTMS and other treatment options, such as antidepressants. In this multicenter randomized controlled trial, rTMS was compared with the next pharmacological treatment step in patients with treatment-resistant depression. METHODS: Patients with unipolar nonpsychotic depression (N=89) with an inadequate response to at least two treatment trials were randomized to treatment with rTMS or to a switch of antidepressants, both in combination with psychotherapy. Treatment duration was 8 weeks and consisted of either 25 high-frequency rTMS sessions to the left dorsolateral prefrontal cortex or a switch of antidepressant medication following the Dutch treatment algorithm. The primary outcome was change in depression severity based on the Hamilton Depression Rating Scale (HAM-D). Secondary outcomes were response and remission rates as well as change in symptom dimensions (anhedonia, anxiety, sleep, rumination, and cognitive reactivity). Finally, expectations regarding treatment were assessed. RESULTS: rTMS resulted in a significantly larger reduction in depressive symptoms than medication, which was also reflected in higher response (37.5% vs. 14.6%) and remission (27.1% vs. 4.9%) rates. A larger decrease in symptoms of anxiety and anhedonia was observed after rTMS compared with a switch in antidepressants, and no difference from the medication group was seen for symptom reductions in rumination, cognitive reactivity, and sleep disorders. Expectations regarding treatment correlated with changes in HAM-D scores. CONCLUSIONS: In a sample of patients with moderately treatment-resistant depression, rTMS was more effective in reducing depressive symptoms than a switch of antidepressant medication. In addition, the findings suggest that the choice of treatment may be guided by specific symptom dimensions.

Economic burden of suicides and suicide attempts in low- and middle-income countries: a systematic review of costing studies.

INTRODUCTION: Suicide is a major public health concern in low- and middle-income countries (LMICs) due to its substantial psychological, social, and economic impact. There is little synthesized evidence to estimate the economic burden of suicide and suicide attempts in such economies. The present systematic literature review aims to examine existing evidence on the cost of illness (COI) in the case of suicides and suicide attempts and assess their quality. METHODS: A systematic review was carried out using electronic databases, such as Medline, EMBASE, EconLit, PsycINFO, and CINAHL using keywords like 'suicide and suicide attempts,' 'cost of illness,' and economic burden." The quality assessment of studies was conducted along with the per-person cost estimation to understand the variation of methods followed across the studies. RESULT: 14 studies qualified for final data extraction and synthesis out of 4,164 studies. The studies showed heterogeneity across objectives, settings, and methods, with cost estimates reflecting a wide range of costings per person in suicide and suicide attempts. CONCLUSION: It is challenging to determine and compare the economic estimates of suicide. Intensive research is warranted with standardized cost assessment techniques and wider perspectives to understand the true economic burden of suicide. REGISTRATION: PROSPERO Registration No- CRD42022294080.

Cost-Effectiveness of Digital Mental Health Versus Usual Care During Humanitarian Crises in Lebanon: Pragmatic Randomized Trial.

BACKGROUND: There is evidence from meta-analyses and systematic reviews that digital mental health interventions for depression, anxiety, and stress-related disorders tend to be cost-effective. However, no such evidence exists for guided digital mental health care in low and middle-income countries (LMICs) facing humanitarian crises, where the needs are highest. Step-by-Step (SbS), a digital mental health intervention for depression, anxiety, and stress-related disorders, proved to be effective for Lebanese citizens and war-affected Syrians residing in Lebanon. Assessing the cost-effectiveness of SbS is crucial because Lebanon's overstretched health care system must prioritize cost-effective treatment options in the face of continuing humanitarian and economic crises. OBJECTIVE: This study aims to assess the cost-effectiveness of SbS in a randomized comparison with enhanced usual care (EUC). METHODS: The cost-effectiveness analysis was conducted alongside a pragmatic randomized controlled trial in 2 parallel groups comparing SbS (n=614) with EUC (n=635). The primary outcome was cost (in US $ for the reference year 2019) per treatment response of depressive symptoms, defined as >50% reduction of depressive symptoms measured using the Patient Health Questionnaire (PHQ). The secondary outcome was cost per remission of depressive symptoms, defined as a PHQ score <5 at last follow-up (5 months post baseline). The evaluation was conducted first from the health care perspective then from the societal perspective. RESULTS: Taking the health care perspective, SbS had an 80% probability to be regarded as cost-effective compared with EUC when there is a willingness to pay US $220 per additional treatment response or US $840 per additional remission. Taking the wider societal perspective, SbS had a >75% probability to be cost-saving while gaining response or remission. CONCLUSIONS: To our knowledge, this study is the first cost-effectiveness analysis based on a large randomized controlled trial (n=1249) of a guided digital mental health intervention in an LMIC. From the principal findings, 2 implications flowed, from the (1) health care perspective and (2) wider societal perspective. First, our findings suggest that SbS is associated with greater health benefits, albeit for higher costs than EUC. It is up to decision makers in health care to decide if they find the balance between additional health gains and additional health care costs acceptable. Second, as seen from the wider societal perspective, there is a substantial likelihood that SbS is not costing more than EUC but is associated with cost-savings as SBS participants become more productive, thus offsetting their health care costs. This finding may suggest to policy makers that it is in the interest of both population health and the wider Lebanese economy to implement SbS on a wide scale. In brief, SbS may offer a scalable, potentially cost-saving response to humanitarian emergencies in an LMIC. TRIAL REGISTRATION: ClinicalTrials.gov NCT03720769; https://clinicaltrials.gov/ct2/show/NCT03720769. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.2196/21585.

Software with artificial intelligence-derived algorithms for analysing CT brain scans in people with a suspected acute stroke: a systematic review and cost-effectiveness analysis.

Background: Artificial intelligence-derived software technologies have been developed that are intended to facilitate the review of computed tomography brain scans in patients with suspected stroke. Objectives: To evaluate the clinical and cost-effectiveness of using artificial intelligence-derived software to support review of computed tomography brain scans in acute stroke in the National Health Service setting. Methods: Twenty-five databases were searched to July 2021. The review process included measures to minimise error and bias. Results were summarised by research question, artificial intelligence-derived software technology and study type. The health economic analysis focused on the addition of artificial intelligence-derived software-assisted review of computed tomography angiography brain scans for guiding mechanical thrombectomy treatment decisions for people with an ischaemic stroke. The de novo model (developed in R Shiny, R Foundation for Statistical Computing, Vienna, Austria) consisted of a decision tree (short-term) and a state transition model (long-term) to calculate the mean expected costs and quality-adjusted life-years for people with ischaemic stroke and suspected large-vessel occlusion comparing artificial intelligence-derived software-assisted review to usual care. Results: A total of 22 studies (30 publications) were included in the review; 18/22 studies concerned artificial intelligence-derived software for the interpretation of computed tomography angiography to detect large-vessel occlusion. No study evaluated an artificial intelligence-derived software technology used as specified in the inclusion criteria for this assessment. For artificial intelligence-derived software technology alone, sensitivity and specificity estimates for proximal anterior circulation large-vessel occlusion were 95.4% (95% confidence interval 92.7% to 97.1%) and 79.4% (95% confidence interval 75.8% to 82.6%) for Rapid (iSchemaView, Menlo Park, CA, USA) computed tomography angiography, 91.2% (95% confidence interval 77.0% to 97.0%) and 85.0 (95% confidence interval 64.0% to 94.8%) for Viz LVO (Viz.ai, Inc., San Fransisco, VA, USA) large-vessel occlusion, 83.8% (95% confidence interval 77.3% to 88.7%) and 95.7% (95% confidence interval 91.0% to 98.0%) for Brainomix (Brainomix Ltd, Oxford, UK) e-computed tomography angiography and 98.1% (95% confidence interval 94.5% to 99.3%) and 98.2% (95% confidence interval 95.5% to 99.3%) for Avicenna CINA (Avicenna AI, La Ciotat, France) large-vessel occlusion, based on one study each. These studies were not considered appropriate to inform cost-effectiveness modelling but formed the basis by which the accuracy of artificial intelligence plus human reader could be elicited by expert opinion. Probabilistic analyses based on the expert elicitation to inform the sensitivity of the diagnostic pathway indicated that the addition of artificial intelligence to detect large-vessel occlusion is potentially more effective (quality-adjusted life-year gain of 0.003), more costly (increased costs of £8.61) and cost-effective for willingness-to-pay thresholds of £3380 per quality-adjusted life-year and higher. Limitations and conclusions: The available evidence is not suitable to determine the clinical effectiveness of using artificial intelligence-derived software to support the review of computed tomography brain scans in acute stroke. The economic analyses did not provide evidence to prefer the artificial intelligence-derived software strategy over current clinical practice. However, results indicated that if the addition of artificial intelligence-derived software-assisted review for guiding mechanical thrombectomy treatment decisions increased the sensitivity of the diagnostic pathway (i.e. reduced the proportion of undetected large-vessel occlusions), this may be considered cost-effective. Future work: Large, preferably multicentre, studies are needed (for all artificial intelligence-derived software technologies) that evaluate these technologies as they would be implemented in clinical practice. Study registration: This study is registered as PROSPERO CRD42021269609. Funding: This award was funded by the National Institute for Health and Care Research (NIHR) Evidence Synthesis programme (NIHR award ref: NIHR133836) and is published in full in Health Technology Assessment; Vol. 28, No. 11. See the NIHR Funding and Awards website for further award information.

Stroke is a serious life-threatening medical condition caused by a blood clot or haemorrhage in the brain. Quick and effective management, including a brain scan, of the patients with suspected stroke can make a big difference in their outcome. Artificial intelligence-derived computer programmes exist that are intended to help with the interpretation of computed tomography scans of the brain in stroke. We undertook a thorough review of the existing research into the effectiveness and value for money of using these programmes to help doctors and other specialists to interpret computed tomography brain scans. We found very little evidence to tell us how well artificial intelligence-derived computer programmes work in practice. Some studies have looked at artificial intelligence-derived computer programmes on their own (i.e. not taken together with a doctor's judgement, as they were designed to be used). Other studies have looked at what happens to patients who are treated for stroke when artificial intelligence-derived computer programmes are used; these studies provide no information about whether using artificial intelligence-derived computer programmes may have led to patients who could have benefitted from treatment being missed. It is unclear how well artificial intelligence-derived software-assisted review works when added to current clinical practice.

Prognostic Information on Progression to Dementia: Quantification of the Impact on Quality of Life.

Background: The increasing interest in early identification of people at risk of developing dementia, has led to the development of numerous models aimed at estimating the likelihood of progression from mild cognitive impairment (MCI) to dementia. It is important to study both the need for and possible outcomes related with such prediction models, including the impact of risk predictions on perceived quality of life (QoL). Objective: This study aimed to quantify the impact that receiving a risk prediction on progression from MCI to dementia has on QoL. Methods: A Discrete Choice Experiment (DCE) and Time Trade Off (TTO) study were performed. Participants completed choice tasks related to dementia prognosis while imagining having MCI. We collected DCE data by an online survey, and TTO data via videoconferencing interviews. DCE data were analyzed using a mixed multinomial logit model and were anchored to a health state utility scale using mean observed TTO valuations. Results: 296 people participated in the DCE and 42 in the TTO. Moderate and high predicted dementia risks were associated with decrements in utility (-0.05 and -0.18 respectively), compared to no prognostic information. Low predicted risk was associated with an increase in utility (0.06), as well as the availability of medication or lifestyle interventions (0.05 and 0.13 respectively). Conclusions: This study shows a significant impact of dementia risk predictions on QoL and highlights the importance of caution when sharing information about expected MCI disease courses.

Health-Economic Evaluation of Psychological Interventions for Anxiety Prevention: A Systematic Review.

OBJECTIVE: Although evidence supports the effectiveness of psychological interventions for prevention of anxiety, little is known about their cost-effectiveness. The aim of this study was to conduct a systematic review of health-economic evaluations of psychological interventions for anxiety prevention. METHODS: PubMed, PsycInfo, Web of Science, Embase, Cochrane Central Register of Controlled Trials, EconLit, National Health Service (NHS) Economic Evaluations Database, NHS Health Technology Assessment, and OpenGrey databases were searched electronically on December 23, 2022. Included studies focused on economic evaluations based on randomized controlled trials of psychological interventions to prevent anxiety. Study data were extracted, and the quality of the selected studies was assessed by using the Consensus on Health Economic Criteria and the Cochrane risk-of-bias tool. RESULTS: All included studies (N=5) had economic evaluations that were considered to be of good quality. In two studies, the interventions showed favorable cost-effectiveness compared with usual care groups. In one study, the intervention was not cost-effective. Findings from another study cast doubt on the cost-effectiveness of the intervention, and the cost-effectiveness of the intervention in the remaining study could not be established. CONCLUSIONS: Although the findings suggest some preliminary evidence of cost-effectiveness of psychological interventions for preventing anxiety, they were limited by the small number of included studies. Additional research on the cost-effectiveness of psychological interventions for anxiety in different countries and populations is required.

What do we not know (yet) about recovery colleges? A study protocol on their (cost-)effectiveness, mechanisms of action, fidelity and positioning.

BACKGROUND: Recovery Colleges (RCs) have spread across the globe as a new way of supporting people with mental vulnerabilities in their recovery journey. RCs focus on 'learning' rather than 'curing' and in that line facilitate a transition from being a passive, dependent patient/client to an active, empowered student learning to live life, despite vulnerabilities. Peer support and co-creation are central in RCs, as peers learn from each other by sharing personal experiences with mental vulnerabilities in an accessible, inspiring and stimulating atmosphere. The implementation of RCs is highly encouraged internationally, and as a result RCs and related self-help initiatives increasingly emerge. However, high-quality research on RCs is scarce and there is a call for thorough investigation of (cost-)effectiveness, mechanisms of action, cross-border fidelity and positioning of RCs. In response, this research project aims to fill these gaps. METHODS: This research project entails (1) a prospective quasi-experimental effectiveness study and economic evaluation, (2) a multifaceted qualitative study to elaborate on the mechanisms of action of RCs for those involved (3) a study to develop a (Dutch) Fidelity Measure of Recovery Colleges, and (4) an organisational case study to describe the positioning of RCs in relation to other mental health care services and community-based initiatives. Following the ideals of co-creation and empowerment in RCs we conduct this research project in co-creation with RC students from Enik Recovery College in Utrecht, the Netherlands. DISCUSSION: This research project will lead to one of the first longitudinal controlled quantitative evaluations of both cost-effectiveness and effectiveness of RC attendance in a broad sense (beyond attending courses alone). Moreover, we will gather data on a micro level (i.e., impact on RC students), meso level (i.e., organisational fidelity) and macro level (i.e., positioning in the care and support domain), capturing all important perspectives when scrutinizing the impact of complex systems. Finally, we will demonstrate the validity and value of embracing experiential knowledge in science as a complementary source of information, leading to a more profound understanding of what is researched. TRIAL REGISTRATION: The prospective quasi-experimental study has been pre-registered at clinicaltrails.gov (#NCT05620212).

Risk stratification for treating people at ultra-high risk for psychosis: A cost-effectiveness analysis.

People who are at ultra-high risk (UHR) for psychosis receive clinical care with the aim to prevent first-episode psychosis (FEP), regardless of the risk of conversion to psychosis. An economic model from the Canadian health system perspective was developed to evaluate the cost-effectiveness of treating all with UHR compared to risk stratification over a 15-year time horizon, based on conversion probability, expected quality-of-life and costs. The analysis used a decision tree followed by a Markov model. Health states included: Not UHR, UHR with <20 % risk of conversion to FEP (based on the North American Prodrome Longitudinal Study risk calculator), UHR with ≥20 % risk, FEP, Remission, Post-FEP, and Death. The analysis found that: risk stratification (i.e., only treating those with ≥20 % risk) had lower costs ($1398) and quality-adjusted life-years (0.055 QALYs) per person compared to treating all. The incremental cost-effectiveness ratio for 'treat all' was $25,448/QALY, and suggests treating all may be cost-effective. The model was sensitive to changes to the probability of conversion.

Testing the combination of Feeling Safe and peer counselling against formulation-based cognitive behaviour therapy to promote psychological wellbeing in people with persecutory delusions: study protocol for a randomized controlled trial (the Feeling Safe-NL Trial).

BACKGROUND: Persecutory delusions are strong threat beliefs about others' negative intentions. They can have a major impact on patients' day-to-day life. The Feeling Safe Programme is a new translational cognitive-behaviour therapy that helps patients modify threat beliefs and relearn safety by targeting key psychological causal factors. A different intervention approach, with growing international interest, is peer counselling to facilitate personal recovery. Combining these two approaches is a potential avenue to maximize patient outcomes. This combination of two different treatments will be tested as the Feeling Safe-NL Programme, which aims to promote psychological wellbeing. We will test whether Feeling Safe-NL is more effective and more cost-effective in improving mental wellbeing and reducing persecutory delusions than the current guideline intervention of formulation-based CBT for psychosis (CBTp). METHODS: A single-blind parallel-group randomized controlled trial for 190 out-patients who experience persecutory delusions and low mental wellbeing. Patients will be randomized (1:1) to Feeling Safe-NL (Feeling Safe and peer counselling) or to formulation-based CBTp, both provided over a period of 6 months. Participants in both conditions are offered the possibility to self-monitor their recovery process. Blinded assessments will be conducted at 0, 6 (post-treatment), 12, and 18 months. The primary outcome is mental wellbeing. The overall effect over time (baseline to 18-month follow-up) and the effects at each timepoint will be determined. Secondary outcomes include the severity of the persecutory delusion, general paranoid ideation, patient-chosen therapy outcomes, and activity. Service use data and quality of life data will be collected for the health-economic evaluation. DISCUSSION: The Feeling Safe-NL Trial is the first to evaluate a treatment for people with persecutory delusions, while using mental wellbeing as the primary outcome. It will also provide the first evaluation of the combination of a peer counselling intervention and a CBT-based program for recovery from persecutory delusions. TRIAL REGISTRATION: Current Controlled Trials ISRCTN25766661 (retrospectively registered 7 July 2022).

Trial-based economic evaluation of mindfulness-based cognitive therapy compared to treatment as usual for bipolar disorder.

OBJECTIVE: Aim of this study was to assess the cost-effectiveness and cost-utility of mindfulness-based cognitive therapy (MBCT) and treatment as usual (TAU) compared to TAU alone in adults with Bipolar disorder (BD). METHODS: An economic evaluation with a time horizon of 15 months was conducted from a societal perspective. Outcomes were expressed in costs per quality adjusted life years (QALYs) and costs per responder using the inventory of depressive symptomatology clinician rating score. RESULTS: People with BD (N = 144) were included in this study. From a societal perspective, the difference of total costs between MBCT + TAU and TAU was €615, with lower costs in the MBCT + TAU group. Only healthcare costs differed significantly between the two groups. A small difference in QALYs in favor of MBCT + TAU was found combined with lower costs (-€836; baseline adjusted) for MBCT + TAU compared to TAU, resulting in a dominant incremental cost-utility ratio. The probability that the MBCT + TAU was cost-effective was 65%. All sensitivity analyses attested to the robustness of the base case analyses. CONCLUSION: Concludingly, MBCT + TAU seems to be cost-effective compared to TAU alone, indicated by a small or neglectable difference in effect, in favor of MBCT + TAU, while resulting in lower costs.

Economic evaluations of nonpharmacological treatments for drug-resistant epilepsy: A systematic review.

This study was undertaken to systematically identify and critically appraise all published full economic evaluations assessing the cost-effectiveness of nonpharmacological interventions for patients with drug-resistant epilepsy. The Population, Intervention, Comparison, Outcome, Study criteria was used to design search strategies for the identification and selection of relevant studies. Literature search was performed using the MEDLINE (via PubMed), Embase, International Health Technology Assessment, National Institute for Health Research Economic Evaluation Database, and Cost-Effectiveness Analysis Registry databases to identify articles published between January 2000 and May 2023. Web of Science was additionally used to perform forward and backward referencing. Title, abstract, and full-text screening was performed by two independent researchers. The Consensus Health Economic Criteria (CHEC) checklist and Consolidated Health Economic Evaluation Reporting Standards (CHEERS) 2022 were applied for quality assessment. A total of 4470 studies were identified, of which 18 met our inclusion criteria. Twelve of the studies conducted model-based economic evaluation, and others were trial-based. Three studies showed that epilepsy surgery was cost-effective in adults, whereas this remained inconclusive for children (two positive, three negative). Three studies showed negative economic outcome for ketogenic diet in children. One of four studies showed positive results for self-management. For vagus nerve stimulation, one study showed positive results in adults and another one negative results in children. One recent study showed cost-effectiveness of responsive neurostimulation (RNS) in adults. Finally, one study showed promising but inconclusive results for deep brain stimulation (DBS). The mean scores for risk of bias assessment (based on CHEC) and for reporting quality (CHEERS 2022) were 95.8% and 80.5%, respectively. This review identified studies that assessed the cost-effectiveness of nonpharmacological treatments in both adults and children with drug-resistant epilepsy, suggesting that in adults, epilepsy surgery, vagus nerve stimulation, and RNS are cost-effective, and that DBS and self-management appear to be promising. In children, the cost-effectiveness of epilepsy surgery remains inconclusive. Finally, the use of ketogenic diet was shown not to be cost-effective. However, limited long-term data were available for newer interventions (i.e., ketogenic diet, DBS, and RNS).

Predicting Undesired Treatment Outcomes With Machine Learning in Mental Health Care: Multisite Study.

Background: Predicting which treatment will work for which patient in mental health care remains a challenge. Objective: The aim of this multisite study was 2-fold: (1) to predict patients' response to treatment in Dutch basic mental health care using commonly available data from routine care and (2) to compare the performance of these machine learning models across three different mental health care organizations in the Netherlands by using clinically interpretable models. Methods: Using anonymized data sets from three different mental health care organizations in the Netherlands (n=6452), we applied a least absolute shrinkage and selection operator regression 3 times to predict the treatment outcome. The algorithms were internally validated with cross-validation within each site and externally validated on the data from the other sites. Results: The performance of the algorithms, measured by the area under the curve of the internal validations as well as the corresponding external validations, ranged from 0.77 to 0.80. Conclusions: Machine learning models provide a robust and generalizable approach in automated risk signaling technology to identify cases at risk of poor treatment outcomes. The results of this study hold substantial implications for clinical practice by demonstrating that the performance of a model derived from one site is similar when applied to another site (ie, good external validation).

A roadmap for applying machine learning when working with privacy-sensitive data: predicting non-response to treatment for eating disorders.

OBJECTIVES: Applying machine-learning methodology to clinical data could present a promising avenue for predicting outcomes in patients receiving treatment for psychiatric disorders. However, preserving privacy when working with patient data remains a critical concern. METHODS: In showcasing how machine-learning can be used to build a clinically relevant prediction model on clinical data, we apply two commonly used machine-learning algorithms (Random Forest and least absolute shrinkage and selection operator) to routine outcome monitoring data collected from 593 patients with eating disorders to predict absence of reliable improvement 12 months after entering outpatient treatment. RESULTS: An RF model trained on data collected at baseline and after three months made 31.3% fewer errors in predicting lack of reliable improvement at 12 months, in comparison with chance. Adding data from a six-month follow-up resulted in only marginal improvements to accuracy. CONCLUSION: We were able to build and validate a model that could aid clinicians and researchers in more accurately predicting treatment response in patients with EDs. We also demonstrated how this could be done without compromising privacy. ML presents a promising approach to developing accurate prediction models for psychiatric disorders such as ED.

Fenfluramine for Treating Dravet Syndrome: An Evidence Review Group Perspective of a NICE Single Technology Appraisal.

Fenfluramine, tradename Fintepla®, was appraised within the National Institute for Health and Care Excellence (NICE) single technology appraisal (STA) process as Technology Appraisal 808. Within the STA process, the company (Zogenix International) provided NICE with a written submission and a mathematical health economic model, summarising the company's estimates of the clinical effectiveness and cost-effectiveness of fenfluramine for patients with Dravet syndrome (DS). This company submission (CS) was reviewed by an evidence review group (ERG) independent of NICE. The ERG, Kleijnen Systematic Reviews in collaboration with Maastricht University Medical Centre, produced an ERG report. This paper presents a summary of the ERG report and the development of the NICE guidance. The CS included a systematic review of the evidence for fenfluramine. From this review the company identified and presented evidence from two randomised trials (Study 1 and Study 1504), an open-label extension study (Study 1503) and 'real world evidence' from a prospective and retrospective study. Both randomised trials were conducted in patients up to 18 years of age with DS, whose seizures were incompletely controlled with previous anti-epileptic drugs. A Bayesian network meta-analysis was performed to compare fenfluramine with cannabidiol plus clobazam. There was no evidence of a difference between any doses of fenfluramine and cannabidiol in the mean convulsive seizure frequency (CSF) rate during treatment. However, fenfluramine increased the number of patients achieving ≥ 50% reduction in CSF frequency from baseline compared to cannabidiol. The company used an individual-patient state-transition model (R version 3.5.2) to model cost-effectiveness of fenfluramine. The CSF and convulsive seizure-free days were estimated using patient-level data from the placebo arm of the fenfluramine registration studies. Subsequently, a treatment effect of either fenfluramine or cannabidiol was applied. Utility values for the economic model were obtained by mapping Pediatric Quality of Life Inventory data from the registration studies to EuroQol-5D-3L Youth (EQ-5D-Y-3L). The company included caregiver utilities in their base-case, as the severe needs of patients with DS have a major impact on parents and caregivers. There were several key issues. First, the company included caregiver utilities in the model in a way that when patients in the economic model died, the corresponding caregiver utility was also set to zero. Second, the model was built in R statistical software, resulting in transparency issues. Third, the company assumed the same percentage reduction for convulsive seizure days as was estimated for CSF. Fourth, during the final appraisal committee meeting, influential changes were made to the model that were not in line with the ERG's preferences (but were accepted by the appraisal committee). The company's revised and final incremental cost effectiveness ratio (ICER) in line with committee preferences resulted in fenfluramine dominating cannabidiol. Fenfluramine was recommended as an add-on to other antiepileptic medicines for treating seizures associated with DS in people aged 2 years and older in the National Health Service (NHS).