The long shadow of early-change patterns: a 3-year follow-up after the use of a web-based intervention for mild to moderate depressive symptoms.

Web-based interventions can be effective in treating depressive symptoms. Patients with risk not responding to treatment have been identified by early change patterns. This study aims to examine whether early changes are superior to baseline parameters in predicting long-term outcome. In a randomized clinical trial with 409 individuals experiencing mild to moderate depressive symptoms using the web-based intervention deprexis, three latent classes were identified (early response after registration, early response after screening and early deterioration) based on early change in the first four weeks of the intervention. Baseline variables and these classes were included in a Stepwise Cox Proportional Hazard Multiple Regression to identify predictors associated with the onset of remission over 36-months. Early change class was a significant predictor of remission over 36 months. Compared to early deterioration after screening, both early response after registration and after screening were associated with a higher likelihood of remission. In sensitivity and secondary analyses, only change class consistently emerged as a predictor of long-term outcome. Early improvement in depression symptoms predicted long-term outcome and those showing early improvement had a higher likelihood of long-term remission. These findings suggest that early changes might be a robust predictor for long-term outcome beyond baseline parameters.

Towards a taxonomy of mechanisms of change? Findings from an expert survey on the association between common factors and specific techniques in psychotherapy.

OBJECTIVE: In the present study, we used structural equation modeling (SEM) to investigate the complex relationship between common factors, i.e., mechanisms of change, and specific factors, i.e., therapeutic techniques. METHOD: N = 256 psychotherapy experts were asked to rate the appropriateness of 14 techniques commonly used in psychotherapy to facilitate five different common factors - resource activation, motivational clarification, self-management & emotion regulation, social competence, and therapeutic relationship. Using SEM, we defined techniques as indicators and common factors as latent variables. Data were split randomly into two subsets. Indicators were selected if three a priori defined criteria were met based on training data (n = 128). Subsequently, the goodness of model fit was assessed in the test data (n = 128). RESULTS: The proposed model revealed adequate fit. All factor loadings were theoretically sound and significant in magnitude. Findings suggest that psychotherapy experts discriminate between common factors by their various associations with therapeutic techniques. CONCLUSION: Suggestions are made, how therapeutic techniques are to be used to facilitate desirable change in the patient. Our model is a step towards a taxonomy of mechanisms of change that may help to improve research-informed decision-making.

Decoding emotions: Exploring the validity of sentiment analysis in psychotherapy.

OBJECTIVE: Given the importance of emotions in psychotherapy, valid measures are essential for research and practice. As emotions are expressed at different levels, multimodal measurements are needed for a nuanced assessment. Natural Language Processing (NLP) could augment the measurement of emotions. The study explores the validity of sentiment analysis in psychotherapy transcripts. METHOD: We used a transformer-based NLP algorithm to analyze sentiments in 85 transcripts from 35 patients. Construct and criterion validity were evaluated using self- and therapist reports and process and outcome measures via correlational, multitrait-multimethod, and multilevel analyses. RESULTS: The results provide indications in support of the sentiments' validity. For example, sentiments were significantly related to self- and therapist reports of emotions in the same session. Sentiments correlated significantly with in-session processes (e.g., coping experiences), and an increase in positive sentiments throughout therapy predicted better outcomes after treatment termination. DISCUSSION: Sentiment analysis could serve as a valid approach to assessing the emotional tone of psychotherapy sessions and may contribute to the multimodal measurement of emotions. Future research could combine sentiment analysis with automatic emotion recognition in facial expressions and vocal cues via the Nonverbal Behavior Analyzer (NOVA). Limitations (e.g., exploratory study with numerous tests) and opportunities are discussed.

Love yourself as a therapist, doubt yourself as an institution? Therapist and institution effects on outcome, treatment length, and dropout.

OBJECTIVE: Research suggests that some therapists achieve better outcomes than others. However, an overlooked area of study is how institution differences impact patient outcomes independent of therapist variance. This study aimed to examine the role of institution and therapist differences in adult outpatient psychotherapy. METHOD: The study included 1428 patients who were treated by 196 therapists at 10 clinics. Two- and three-level hierarchical linear regression models were employed to investigate the effects of therapists and institutions on three dependent patient variables: (1) symptom change, (2) treatment duration, and (3) dropout. Level three explanatory variables were tested. RESULTS: The results showed that therapist effects (TE) were significant for all three types of treatment outcome (7.8%-18.2%). When a third level (institution) was added to the model, the differences between therapists decreased, and significant institution effects (IE) were found: 6.3% for symptom change, 10.6% for treatment duration, and 6.5% for dropout. The exploratory analyses found no predictors able to explain the systematic variation at the institution level. DISCUSSION: TE on psychotherapy outcomes remain a relevant factor but may have been overestimated in previous studies due to not properly distinguishing them from differences at the institution level.

The Effects of Switching to Video Therapy on In-Session Processes in Psychotherapy During the COVID-19 Pandemic.

OBJECTIVE AND AIM: This study aimed to assess the impact of switching from face-to-face (f2f) psychotherapy to video therapy (VT) due to the COVID-19 pandemic on in-session processes, i.e., the therapeutic alliance, coping skills, and emotional involvement, as rated by both patients and therapists. METHODS: A total of N = 454 patients with mood or anxiety disorders were examined. The intervention group (IG) consisted of n = 227 patient-therapist dyads, who switched from f2f to VT, while the control group (CG) consisted of n = 227 patient-therapist dyads, who were treated f2f before the pandemic. To evaluate the effects of switching to VT on in-session processes, three longitudinal piecewise multilevel models, one per process variable, were fitted. Each process variable was regressed on the session number with a slope for the three sessions before switching to VT and a second slope for up to six VT sessions afterwards. RESULTS: The therapeutic alliance significantly increased after switching from f2f to VT across the two groups (IG and CG) and raters (patients and therapists) with no differences between IG and CG. On average, patients rated the therapeutic alliance better than therapists. Coping skills significantly increased after switching from f2f to VT across the two groups and raters, but the CG rated coping skills higher than the IG after the switch. Overall, therapists rated coping skills higher than patients. Emotional involvement did not significantly increase after switching to VT across the two groups and raters and there was no significant difference between patient and therapist ratings. DISCUSSION: In conclusion, the switch to VT had no negative impact on the therapeutic alliance and emotional involvement. However, more coping skills were reported in the CG than in the IG after the switch to VT, which was mainly due to a stagnation in patient-rated coping skills in the IG.

Measuring Alliance and Symptom Severity in Psychotherapy Transcripts Using Bert Topic Modeling.

We aim to use topic modeling, an approach for discovering clusters of related words ("topics"), to predict symptom severity and therapeutic alliance in psychotherapy transcripts, while also identifying the most important topics and overarching themes for prediction. We analyzed 552 psychotherapy transcripts from 124 patients. Using BERTopic (Grootendorst, 2022), we extracted 250 topics each for patient and therapist speech. These topics were used to predict symptom severity and alliance with various competing machine-learning methods. Sensitivity analyses were calculated for a model based on 50 topics, LDA-based topic modeling, and a bigram model. Additionally, we grouped topics into themes using qualitative analysis and identified key topics and themes with eXplainable Artificial Intelligence (XAI). Symptom severity could be predicted with highest accuracy by patient topics ( r =0.45, 95%-CI 0.40, 0.51), whereas alliance was better predicted by therapist topics ( r =0.20, 95%-CI 0.16, 0.24). Drivers for symptom severity were themes related to health and negative experiences. Lower alliance was correlated with various themes, especially psychotherapy framework, income, and everyday life. This analysis shows the potential of using topic modeling in psychotherapy research allowing to predict several treatment-relevant metrics with reasonable accuracy. Further, the use of XAI allows for an analysis of the individual predictive value of topics and themes. Limitations entail heterogeneity across different topic modeling hyperparameters and a relatively small sample size.

Skills, Not Just Knowledge: Infectious Diseases Fellows' Recommendations Regarding Antimicrobial Stewardship Training.

BACKGROUND: Antimicrobial stewardship (AS) is an important topic in infectious diseases (ID) training, yet many ID fellowships lack formal training, and little is known about fellows' learning preferences. METHODS: We conducted 24 in-depth interviews with ID fellows across the United States during 2018 and 2019 to explore their experiences with and preferences for AS education during fellowship. Interviews were transcribed, deidentified, and analyzed to identify themes. RESULTS: Fellows had variable exposure to AS before and during fellowship, which impacted their knowledge about and attitude toward stewardship as a career; however, all fellows expressed the importance of learning general stewardship principles during fellowship. Some fellows' training included mandatory stewardship lectures and/or rotations, but most fellows felt their primary stewardship learning occurred through informal experiences in the clinical setting, such as holding the antimicrobial approval pager. Fellows expressed a preference for a standardized, structured curriculum that included in-person practical, interactive discussions with multidisciplinary faculty along with the opportunity to practice and apply their skills; however, they emphasized that time needed to be set aside for those educational activities. Although they wanted to learn the evidence and rationale for stewardship recommendations, they especially wanted training in and feedback on how to communicate stewardship recommendations to other health professionals, particularly in the setting of conflict. CONCLUSIONS: ID fellows believe that standardized AS curricula should be included in their fellowship training, and they prefer structured, practical, and interactive learning experiences.

Sinus inflammation and chronic rhinosinusitis are associated with a diagnosis of new onset asthma in the following year.

BACKGROUND: Chronic rhinosinusitis (CRS) and asthma commonly co-occur. No studies have leveraged large samples needed to formally address whether preexisting CRS is associated with new onset asthma over time. METHODS: We evaluated whether prevalent CRS [identified in two ways: validated text algorithm applied to sinus computerized tomography (CT) scan or two diagnoses] was associated with new onset adult asthma in the following year. We used electronic health record data from Geisinger from 2008 to 2019. For each year we removed persons with any evidence of asthma through the end of the year, then identified those with new diagnosis of asthma in the following year. Complementary log-log regression was used to adjust for confounding variables (e.g., sociodemographic, contact with the health system, comorbidities), and hazard ratios (HRs) and 95% confidence intervals (CI) were calculated. RESULTS: A total of 35,441 persons were diagnosed with new onset asthma and were compared to 890,956 persons who did not develop asthma. Persons with new onset asthma tended to be female (69.6%) and younger (mean [SD] age 45.9 [17.0] years). Both CRS definitions were associated (HR, 95% CI) with new onset asthma, with 2.21 (1.93, 2.54) and 1.48 (1.38, 1.59) for CRS based on sinus CT scan and two diagnoses, respectively. New onset asthma was uncommonly observed in persons with a history of sinus surgery. CONCLUSION: Prevalent CRS identified with two complementary approaches was associated with a diagnosis of new onset asthma in the following year. The findings may have clinical implications for the prevention of asthma.

Associations between PM2.5 and O3 exposures and new onset type 2 diabetes in regional and national samples in the United States.

BACKGROUND: Exposure to particulate matter ≤2.5 µm in diameter (PM2.5) and ozone (O3) has been linked to numerous harmful health outcomes. While epidemiologic evidence has suggested a positive association with type 2 diabetes (T2D), there is heterogeneity in findings. We evaluated exposures to PM2.5 and O3 across three large samples in the US using a harmonized approach for exposure assignment and covariate adjustment. METHODS: Data were obtained from the Veterans Administration Diabetes Risk (VADR) cohort (electronic health records [EHRs]), the Reasons for Geographic and Racial Disparities in Stroke (REGARDS) cohort (primary data collection), and the Geisinger health system (EHRs), and reflect the years 2003-2016 (REGARDS) and 2008-2016 (VADR and Geisinger). New onset T2D was ascertained using EHR information on medication orders, laboratory results, and T2D diagnoses (VADR and Geisinger) or report of T2D medication or diagnosis and/or elevated blood glucose levels (REGARDS). Exposure was assigned using pollutant annual averages from the Downscaler model. Models stratified by community type (higher density urban, lower density urban, suburban/small town, or rural census tracts) evaluated likelihood of new onset T2D in each study sample in single- and two-pollutant models of PM2.5 and O3. RESULTS: In two pollutant models, associations of PM2.5, and new onset T2D were null in the REGARDS cohort except for in suburban/small town community types in models that also adjusted for NSEE, with an odds ratio (95% CI) of 1.51 (1.01, 2.25) per 5 µg/m3 of PM2.5. Results in the Geisinger sample were null. VADR sample results evidenced nonlinear associations for both pollutants; the shape of the association was dependent on community type. CONCLUSIONS: Associations between PM2.5, O3 and new onset T2D differed across three large study samples in the US. None of the results from any of the three study populations found strong and clear positive associations.

Public health emergency preparedness for infectious disease emergencies: a scoping review of recent evidence.

BACKGROUND: The COVID-19 pandemic continues to demonstrate the risks and profound health impacts that result from infectious disease emergencies. Emergency preparedness has been defined as the knowledge, capacity and organizational systems that governments, response and recovery organizations, communities and individuals develop to anticipate, respond to, or recover from emergencies. This scoping review explored recent literature on priority areas and indicators for public health emergency preparedness (PHEP) with a focus on infectious disease emergencies. METHODS: Using scoping review methodology, a comprehensive search was conducted for indexed and grey literature with a focus on records published from 2017 to 2020 onward, respectively. Records were included if they: (a) described PHEP, (b) focused on an infectious emergency, and (c) were published in an Organization for Economic Co-operation and Development country. An evidence-based all-hazards Resilience Framework for PHEP consisting of 11 elements was used as a reference point to identify additional areas of preparedness that have emerged in recent publications. The findings were analyzed deductively and summarized thematically. RESULTS: The included publications largely aligned with the 11 elements of the all-hazards Resilience Framework for PHEP. In particular, the elements related to collaborative networks, community engagement, risk analysis and communication were frequently observed across the publications included in this review. Ten emergent themes were identified that expand on the Resilience Framework for PHEP specific to infectious diseases. Planning to mitigate inequities was a key finding of this review, it was the most frequently identified emergent theme. Additional emergent themes were: research and evidence-informed decision making, building vaccination capacity, building laboratory and diagnostic system capacity, building infection prevention and control capacity, financial investment in infrastructure, health system capacity, climate and environmental health, public health legislation and phases of preparedness. CONCLUSION: The themes from this review contribute to the evolving understanding of critical public health emergency preparedness actions. The themes expand on the 11 elements outlined in the Resilience Framework for PHEP, specifically relevant to pandemics and infectious disease emergencies. Further research will be important to validate these findings, and expand understanding of how refinements to PHEP frameworks and indicators can support public health practice.

Entity and relation extraction from clinical case reports of COVID-19: a natural language processing approach.

BACKGROUND: Extracting relevant information about infectious diseases is an essential task. However, a significant obstacle in supporting public health research is the lack of methods for effectively mining large amounts of health data. OBJECTIVE: This study aims to use natural language processing (NLP) to extract the key information (clinical factors, social determinants of health) from published cases in the literature. METHODS: The proposed framework integrates a data layer for preparing a data cohort from clinical case reports; an NLP layer to find the clinical and demographic-named entities and relations in the texts; and an evaluation layer for benchmarking performance and analysis. The focus of this study is to extract valuable information from COVID-19 case reports. RESULTS: The named entity recognition implementation in the NLP layer achieves a performance gain of about 1-3% compared to benchmark methods. Furthermore, even without extensive data labeling, the relation extraction method outperforms benchmark methods in terms of accuracy (by 1-8% better). A thorough examination reveals the disease's presence and symptoms prevalence in patients. CONCLUSIONS: A similar approach can be generalized to other infectious diseases. It is worthwhile to use prior knowledge acquired through transfer learning when researching other infectious diseases.

Strong and consistent associations of precedent chronic rhinosinusitis with risk of non-cystic fibrosis bronchiectasis.

BACKGROUND: Chronic rhinosinusitis (CRS) and bronchiectasis commonly co-occur, but most prior studies were not designed to evaluate temporality and causality. OBJECTIVES: In a sample representing the general population in 37 counties in Pennsylvania, and thus the full spectrum of sinonasal and relevant lung diseases, we aimed to evaluate the temporality and strength of associations of CRS with non-cystic fibrosis bronchiectasis. METHODS: We completed case-control analyses for each of 3 primary bronchiectasis case finding methods. We used electronic health records to identify CRS and bronchiectasis with diagnoses, procedure orders, and/or specific text in sinus or chest computerized tomography scan radiology reports. The controls never had any indication of bronchiectasis and were frequency-matched to the 3 bronchiectasis groups on the basis of age, sex, and encounter year. There were 5,329 unique persons with bronchiectasis and 33,363 without bronchiectasis in the 3 analyses. Important co-occurring conditions were identified with diagnoses, medication orders, and encounter types. Logistic regression was used to evaluate associations (odds ratios [ORs] and 95% CIs) of CRS with bronchiectasis while adjusting for confounding variables. RESULTS: In adjusted analyses, CRS was consistently and strongly associated with all 3 bronchiectasis definitions. The strongest associations for CRS (ORs and 95% CIs) were those that were based on the text of sinus computerized tomography scan reports; the associations were generally stronger for CRS without nasal polyps (eg, OR = 4.46 [95% CI = 2.09-9.51] for diagnosis-based bronchiectasis). On average, CRS was identified more than 6 years before bronchiectasis. CONCLUSION: Precedent CRS was strongly and consistently associated with increased risk of bronchiectasis.

Is it me, is it you or is it both of US? Applying the social relations model to disentangle the components of the therapeutic bond.

OBJECTIVE: The study investigated the contribution of therapists and patients to the therapeutic bond and their associations (at the within and between levels) to treatment outcome. On this aim, the social relations model (SRM, aimed to analyze dyadic interpersonal data) was implemented. METHOD: A novel design for individual psychotherapy studies was adopted, a many-with-many asymmetrical block dyadic design, in which several patients interact with several therapists. Hierarchical linear models were computed to study through variance partitioning the different components of the SRM and their association to treatment outcome. RESULTS: All SRM components (with significant effects at therapist- and patient- within and between levels) resulted in significant contributions to the bond. However, only components at the within- and between-therapist, and within-patient levels resulted in significant associations with outcome. CONCLUSION: Given the dyadic nature of the bond, our results support not only studying and offering clinical training on interpersonal therapeutic skills but also on constant monitoring and feedback of the relationship at the more idiosyncratic level.

Predicting dropout from psychological treatment using different machine learning algorithms, resampling methods, and sample sizes.

Objective: The occurrence of dropout from psychological interventions is associated with poor treatment outcome and high health, societal and economic costs. Recently, machine learning (ML) algorithms have been tested in psychotherapy outcome research. Dropout predictions are usually limited by imbalanced datasets and the size of the sample. This paper aims to improve dropout prediction by comparing ML algorithms, sample sizes and resampling methods. Method: Twenty ML algorithms were examined in twelve subsamples (drawn from a sample of N = 49,602) using four resampling methods in comparison to the absence of resampling and to each other. Prediction accuracy was evaluated in an independent holdout dataset using the F1-Measure. Results: Resampling methods improved the performance of ML algorithms and down-sampling can be recommended, as it was the fastest method and as accurate as the other methods. For the highest mean F1-Score of .51 a minimum sample size of N = 300 was necessary. No specific algorithm or algorithm group can be recommended. Conclusion: Resampling methods could improve the accuracy of predicting dropout in psychological interventions. Down-sampling is recommended as it is the least computationally taxing method. The training sample should contain at least 300 cases.

Process-Based psychotherapy personalization: considering causality with continuous-time dynamic modeling.

Psychotherapy can be improved by integrating the study of mediators (how it works) and moderators (for whom it works). To demonstrate this integration, we studied the relationship between resource activation, problem-coping experiences and symptoms in cognitive-behavior therapy (CBT) for depression, to obtain preliminary insights on causal inference (which process leads to symptom improvement?) and prediction (which one for whom?).A sample of 715 patients with depression who received CBT was analyzed. Hierarchical Bayesian continuous time dynamic modeling was used to study the temporal dynamics between the variables analyzed within the first ten sessions. Depression and self-efficacy at baseline were examined as predictors of these dynamics.There were significant cross-effects between the processes studied. Under typical assumptions, resource activation had a significant effect on symptom improvement. Problem-coping experience had a significant effect on resource activation. Depression and self-efficacy moderated these effects. However, when system noise was considered, these effects may be affected by other processes.Resource activation was strongly associated with symptom improvement. To the extent of inferring causality, for patients with mild-moderate depression and high self-efficacy, promoting resource activation can be recommended. For patients with severe depression and low self-efficacy, promoting problem-coping experiences can be recommended.

Precision Mental Health and Data-Informed Decision Support in Psychological Therapy: An Example.

Outcome measurement including data-informed decision support for therapists in psychological therapy has developed impressively over the past two decades. New technological developments such as computerized data assessment, and feedback tools have facilitated advanced implementation in several seetings. Recent developments try to improve the clinical decision-making process by connecting clinical practice better with empirical data. For example, psychometric data can be used by clinicians to personalize the selection of therapeutic programs, strategies or modules and to monitor a patient's response to therapy in real time. Furthermore, clinical support tools can be used to improve the treatment for patients at risk for a negative outcome. Therefore, measurement-based care can be seen as an important and integral part of clinical competence, practice, and training. This is comparable to many other areas in the healthcare system, where continuous monitoring of health indicators is common in day-to-day clinical practice (e.g., fever, blood pressure). In this paper, we present the basic concepts of a data-informed decision support system for tailoring individual psychological interventions to specific patient needs, and discuss the implications for implementing this form of precision mental health in clinical practice.

CoQUAD: a COVID-19 question answering dataset system, facilitating research, benchmarking, and practice.

BACKGROUND: Due to the growing amount of COVID-19 research literature, medical experts, clinical scientists, and researchers frequently struggle to stay up to date on the most recent findings. There is a pressing need to assist researchers and practitioners in mining and responding to COVID-19-related questions on time. METHODS: This paper introduces CoQUAD, a question-answering system that can extract answers related to COVID-19 questions in an efficient manner. There are two datasets provided in this work: a reference-standard dataset built using the CORD-19 and LitCOVID initiatives, and a gold-standard dataset prepared by the experts from a public health domain. The CoQUAD has a Retriever component trained on the BM25 algorithm that searches the reference-standard dataset for relevant documents based on a question related to COVID-19. CoQUAD also has a Reader component that consists of a Transformer-based model, namely MPNet, which is used to read the paragraphs and find the answers related to a question from the retrieved documents. In comparison to previous works, the proposed CoQUAD system can answer questions related to early, mid, and post-COVID-19 topics. RESULTS: Extensive experiments on CoQUAD Retriever and Reader modules show that CoQUAD can provide effective and relevant answers to any COVID-19-related questions posed in natural language, with a higher level of accuracy. When compared to state-of-the-art baselines, CoQUAD outperforms the previous models, achieving an exact match ratio score of 77.50% and an F1 score of 77.10%. CONCLUSION: CoQUAD is a question-answering system that mines COVID-19 literature using natural language processing techniques to help the research community find the most recent findings and answer any related questions.

Evaluation of the Infectious Diseases Society of America's Core Antimicrobial Stewardship Curriculum for Infectious Diseases Fellows.

BACKGROUND: Antimicrobial stewardship (AS) programs are required by Centers for Medicare and Medicaid Services and should ideally have infectious diseases (ID) physician involvement; however, only 50% of ID fellowship programs have formal AS curricula. The Infectious Diseases Society of America (IDSA) formed a workgroup to develop a core AS curriculum for ID fellows. Here we study its impact. METHODS: ID program directors and fellows in 56 fellowship programs were surveyed regarding the content and effectiveness of their AS training before and after implementation of the IDSA curriculum. Fellows' knowledge was assessed using multiple-choice questions. Fellows completing their first year of fellowship were surveyed before curriculum implementation ("pre-curriculum") and compared to first-year fellows who complete the curriculum the following year ("post-curriculum"). RESULTS: Forty-nine (88%) program directors and 105 (67%) fellows completed the pre-curriculum surveys; 35 (64%) program directors and 79 (50%) fellows completed the post-curriculum surveys. Prior to IDSA curriculum implementation, only 51% of programs had a "formal" curriculum. After implementation, satisfaction with AS training increased among program directors (16% to 68%) and fellows (51% to 68%). Fellows' confidence increased in 7/10 AS content areas. Knowledge scores improved from a mean of 4.6 to 5.1 correct answers of 9 questions (P = .028). The major hurdle to curriculum implementation was time, both for formal teaching and for e-learning. CONCLUSIONS: Effective AS training is a critical component of ID fellowship training. The IDSA Core AS Curriculum can enhance AS training, increase fellow confidence, and improve overall satisfaction of fellows and program directors.

Pharmacodynamic Study of Miransertib in Individuals with Proteus Syndrome.

Proteus syndrome is a life-threatening segmental overgrowth syndrome caused by a mosaic gain-of-function AKT1 variant. There are no effective treatments for Proteus syndrome. Miransertib is an AKT1 inhibitor that, prior to this study, has been evaluated only in adult oncology trials. We designed a non-randomized, phase 0/1 pilot study of miransertib in adults and children with Proteus syndrome to identify an appropriate dosage starting point for a future efficacy trial using a pharmacodynamic endpoint. The primary endpoint was a 50% reduction in the tissue levels of AKT phosphorylation from biopsies in affected individuals. We also evaluated secondary efficacy endpoints. We found that a dose of 5 mg/m2/day (1/7 the typical dose used in oncology) led to a 50% reduction in phosphorylated AKT (pAKT) in affected tissues from five of six individuals. This dose was well tolerated. Two of the six efficacy endpoints (secondary objectives) suggested that this agent may be efficacious. We observed a decrease in a cerebriform connective tissue nevus and a reduction in pain in children. We conclude that 5 mg/m2/day of miransertib is an appropriate starting point for future efficacy trials and that this agent shows promise of therapeutic efficacy in children with Proteus syndrome.

Predicting patients who will drop out of out-patient psychotherapy using machine learning algorithms.

BACKGROUND: About 30% of patients drop out of cognitive-behavioural therapy (CBT), which has implications for psychiatric and psychological treatment. Findings concerning drop out remain heterogeneous. AIMS: This paper aims to compare different machine-learning algorithms using nested cross-validation, evaluate their benefit in naturalistic settings, and identify the best model as well as the most important variables. METHOD: The data-set consisted of 2543 out-patients treated with CBT. Assessment took place before session one. Twenty-one algorithms and ensembles were compared. Two parameters (Brier score, area under the curve (AUC)) were used for evaluation. RESULTS: The best model was an ensemble that used Random Forest and nearest-neighbour modelling. During the training process, it was significantly better than generalised linear modelling (GLM) (Brier score: d = -2.93, 95% CI (-3.95, -1.90)); AUC: d = 0.59, 95% CI (0.11 to 1.06)). In the holdout sample, the ensemble was able to correctly identify 63.4% of cases of patients, whereas the GLM only identified 46.2% correctly. The most important predictors were lower education, lower scores on the Personality Style and Disorder Inventory (PSSI) compulsive scale, younger age, higher scores on the PSSI negativistic and PSSI antisocial scale as well as on the Brief Symptom Inventory (BSI) additional scale (mean of the four additional items) and BSI overall scale. CONCLUSIONS: Machine learning improves drop-out predictions. However, not all algorithms are suited to naturalistic data-sets and binary events. Tree-based and boosted algorithms including a variable selection process seem well-suited, whereas more advanced algorithms such as neural networks do not.