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.

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.

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.

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.

Prevalence of suicidal ideation in German psychotherapy outpatients: A large multicenter assessment

BACKGROUND

Suicidal ideation is a major concern in clinical practice. Yet, little is known about prevalence rates of suicidal ideation in patients undergoing outpatient psychotherapeutic treatment. Therefore, the aim of the current study is to assess the prevalence of suicidal ideation in a large sample of psychotherapy outpatients in Germany. The data analyzed in this study is taken from the KODAP-project on the coordination of data collection and analysis at German university-based research and training outpatient clinics for psychotherapy.

METHODS

A total of N = 10,357 adult outpatients (64.4 % female; age: M(SD) = 35.94 (13.54), range: 18-92 years of age) starting cognitive-behavioral therapy at one of 27 outpatient clinics in Germany were included in the current study. Prevalence of suicidal ideation was assessed with the Suicide Item (Item 9) of the Beck-Depression Inventory II.

RESULTS

Suicidal ideation was reported by 36.7 % (n = 3795) of the participants. Borderline Personality Disorder, Posttraumatic Stress Disorder, and recurrent Major Depression were the diagnoses most strongly associated with the presence and severity of suicidal ideation.

LIMITATION

Suicide ideation was assessed only with the respective item of the Beck Depression Inventory II.

CONCLUSION

Suicidal ideation is very common among adult patients who start psychotherapy in Germany. A well-founded knowledge of risk assessment in suicidal patients and suicide-specific treatment options is therefore highly relevant.

From Theory to Practice: A Transtheoretical Treatment and Training Model (4TM)

Background

In this paper, we present the conceptual background and clinical implications of a research-based transtheoretical treatment and training model (4TM).

Method

The model implements findings from psychotherapy outcome, process, and feedback research into a clinical and training framework that is open to future research.

Results

The framework is based on interventions targeting patient processes on a behavioral, cognitive, emotional, motivational, interpersonal, and systemic/socio-cultural level. The 4TM also includes a data-based decision support and feedback system called the Trier Treatment Navigator (TTN).

Conclusion

We discuss important problems associated with clinical orientations solely based on one school of thought. We then contrast these concerns with a clinical and training framework that embraces ongoing research, serving as a guiding structure for process-based transtheoretical interventions. Such research-based psychological therapy can take both traditional and novel clinical developments as well as findings from psychotherapy research into account and be adaptively disseminated to a variety of patient populations.

Symptom Reduction and Engagement in a Cognitive-Behavioral Mobile Phone App: A Study of User Profiling to Determine Prognostic Indicators

OBJECTIVE

We investigated the presence of latent transition profiles in a sample of users of a cognitive-behavioral mental health app for the general population. Users' baseline characteristics were used as predictors of the profiles. The role of engagement with the app in the transition profiles was examined.

METHOD

A total of 541 users completed the Patient Health Questionnaire-9 and the General Anxiety Disorder-7 when started using the app and 30 days after. Random-Intercept Latent Transition Analysis was implemented to identify users' profiles and transition patterns as classes. The age of the users and the Emotional Self-Awareness Scale-Revised (ESAS-R) were used as predictors of class membership at baseline. The Homework Rating Scale-Mobile Application (HRS-MA; as a measure of engagement) was used as a predictor of class membership at 30 days of app use.

RESULTS

A 3-class solution was obtained according to the severity of symptoms (from mild to moderately severe). Age and ESAS-R predicted class membership initially; the higher the age and ESAS-R, the higher the probability of starting using the app with lower distress levels. The HRS-MA predicted class membership at 30 days of app use; the higher the engagement for more symptomatic and younger users, the higher the probability of improvement. However, older users tended to engage less.

CONCLUSION

Our findings underpin the relevance of easily accessible digital interventions for young adults with mild to moderate mental health problems. Further studies and developments are required to enhance these apps for older cohorts.

Emotion dynamics of clients with test anxiety before and after an imagery-based treatment

BACKGROUND AND OBJECTIVES

Imagery-based techniques have become a promising means in the treatment of test anxiety (TA). Although previous studies have demonstrated the effectiveness of imagery-based treatment, not all clients seem to benefit from it. The present study compares clients' pre- as well as post-treatment emotion dynamics between responders and non-responders. Furthermore, it examines treatment-related changes in emotion dynamics in both subgroups.

METHODS

The results are based on 44 clients suffering from TA who underwent a six-session imagery-based treatment and include Ecological Momentary Assessment (EMA). Emotions were assessed with the Profile of Mood States four times a day over the course of two weeks before and after the treatment. Temporal networks were computed to index emotion dynamics.

RESULTS

Pre-treatment emotion dynamics differed between responders and non-responders. Similarly, post-treatment emotion dynamics differed as well between both groups. Some changes were also observed between pre-treatment and post-treatment networks: for responders, fatigue no longer predicted anger, and depression predicted itself; for non-responders, calmness predicted fatigue, anger, depression, contentment, and anxiety. In addition, fatigue no longer predicted itself and anxiety predicted vigor.

LIMITATIONS

The investigation is marked by several limitations: a liberal inclusion threshold of at least a 50% response to EMA prompts, and a relatively homogenous sample.

CONCLUSION

These results provide first evidence for the idea that emotion dynamics may be associated with response to treatment for TA. Furthermore, effective imagery-based treatments may be tied to changes within these dynamics.

Treatment credibility as a mechanism of change in cognitive behavioral therapy: Effects on depression and anxiety

OBJECTIVE

This study aimed to provide evidence for treatment credibility (TC) as a potential mechanism of change in cognitive behavioral therapy (CBT). Therefore, it focused on within-person effects that are free of the influence of stable characteristics and thus allow to exclude certain alternative explanations for the association under study.

METHOD

The sample included 1,423 patients receiving outpatient CBT, who presented a wide variety of psychiatric diagnoses (mostly affective and anxiety disorders). TC, depression, and anxiety were measured every fifth session from Session 5 to 25 using the Credibility Expectancy Questionnaire (CEQ), the Patient Health Questionnaire-9 (PHQ-9), and the General Anxiety Disorder-7 (GAD-7), respectively. Symptom severity was assessed every session using the Hopkins Symptom Checklist-11. Within- and between-person effects of TC, depression, and anxiety were analyzed using the latent curve model with structured residuals (LCM-SRs). In exploratory analyses, within-person effects of TC on next-session symptom severity were assessed using a modification of the LCM-SR.

RESULTS

LCM-SRs exhibited excellent fit in main analyses. There were significant negative correlations of both intercepts and slopes (between-person level) of CEQ and PHQ-9 as well GAD-7. No significant cross-lagged effects (within-person level) were found over the five-session interval. However, session-wise analyses revealed significant cross-lagged effects of CEQ on Hopkins Symptom Checklist-11.

CONCLUSIONS

This study is the first to find significant within-person effects of TC in session-wise analyses. This lends preliminary support to the notion of TC as a mechanism of change. The lack of significant findings at the five-session interval is discussed considering the specific design used in this study. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

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.

Where it all begins: Predicting initial therapeutic skills before clinical training in cognitive behavior therapy

To train novice students adequately, it is crucial to understand where they start and how they develop their skills. This study examined the impact of novice students' characteristics on their initial clinical micro-skills when treating simulated patients with cognitive behavior therapy. The sample consisted of 44 graduate psychology students treating seven simulated patients. Clinical micro-skills were measured both using video-based ratings in reaction to short video clips of simulated patients (via the Facilitative Interpersonal Skills (FIS) performance task) and by using video-based ratings within a session with a simulated patient (using the Inventory of Therapeutic Interventions and Skills; ITIS). Two separate LASSO regressions were performed using machine learning to select potential predictors for both skills assessments. Subsequently, a bootstrapping algorithm with 10,000 iterations was used to examine the variability of regression coefficients. Using LASSO regression, we identified two predictors for clinical micro-skills in standardized scenarios: extraversion (b = 0.10) and resilience (b = 0.09), both were not significantly associated with clinical micro-skills. Together, they explained 15% of the skill variation. Bootstrapping confirmed the stability of these predictors. For clinical micro-skills in sessions, only competitiveness was excluded by LASSO regression, and all predictors showed significant instability. The results provide initial evidence that trainees' resilience and extraversion should be promoted in the clinical training of cognitive behavior therapy. More studies on clinical micro-skills and training with larger sample sizes are needed to fully understand clinical development.

First-in-Human Study of the Reversible BTK Inhibitor Nemtabrutinib in Patients with Relapsed/Refractory Chronic Lymphocytic Leukemia and B-Cell Non-Hodgkin Lymphoma

Nemtabrutinib is an orally bioavailable, reversible inhibitor of Bruton tyrosine kinase (BTK) and C481S mutant BTK. We evaluated the safety, pharmacology, and antitumor activity of nemtabrutinib in relapsed/refractory hematologic malignancies. Forty-eight patients with chronic lymphocytic leukemia (CLL), B-cell non-Hodgkin lymphoma (NHL), or Waldenström macroglobulinemia (WM), relapsed/refractory after ≥2 prior therapies were enrolled in the open-label, single-arm, phase I MK-1026-001 study (NCT03162536) to receive nemtabrutinib 5 to 75 mg once daily in 28-day cycles. Dose finding progressed using a 3 + 3 dose escalation design. Primary endpoints were safety and the recommended phase II dose (RP2D). Among 47 treated patients, 29 had CLL, 17 had NHL, and 1 had WM. Grade ≥3 treatment-emergent adverse events occurred in 37 (89%), most commonly neutropenia (11; 23.4%), febrile neutropenia (7; 14.9%), and pneumonia (7; 14.9%). The RP2D was 65 mg daily. An overall response rate of 75% was observed in patients with CLL at 65 mg daily.

SIGNIFICANCE

This first-in-human phase I study demonstrates the safety and preliminary efficacy of nemtabrutinib in patients with relapsed/refractory B-cell malignancies. These data support further exploration of nemtabrutinib in larger clinical studies. This article is featured in Selected Articles from This Issue, p. 5.

Allele-specific control of rodent and human lncRNA KMT2E-AS1 promotes hypoxic endothelial pathology in pulmonary hypertension

Hypoxic reprogramming of vasculature relies on genetic, epigenetic, and metabolic circuitry, but the control points are unknown. In pulmonary arterial hypertension (PAH), a disease driven by hypoxia inducible factor (HIF)-dependent vascular dysfunction, HIF-2α promoted expression of neighboring genes, long noncoding RNA (lncRNA) histone lysine N-methyltransferase 2E-antisense 1 (KMT2E-AS1) and histone lysine N-methyltransferase 2E (KMT2E). KMT2E-AS1 stabilized KMT2E protein to increase epigenetic histone 3 lysine 4 trimethylation (H3K4me3), driving HIF-2α-dependent metabolic and pathogenic endothelial activity. This lncRNA axis also increased HIF-2α expression across epigenetic, transcriptional, and posttranscriptional contexts, thus promoting a positive feedback loop to further augment HIF-2α activity. We identified a genetic association between rs73184087, a single-nucleotide variant (SNV) within a KMT2E intron, and disease risk in PAH discovery and replication patient cohorts and in a global meta-analysis. This SNV displayed allele (G)-specific association with HIF-2α, engaged in long-range chromatin interactions, and induced the lncRNA-KMT2E tandem in hypoxic (G/G) cells. In vivo, KMT2E-AS1 deficiency protected against PAH in mice, as did pharmacologic inhibition of histone methylation in rats. Conversely, forced lncRNA expression promoted more severe PH. Thus, the KMT2E-AS1/KMT2E pair orchestrates across convergent multi-ome landscapes to mediate HIF-2α pathobiology and represents a key clinical target in pulmonary hypertension.

[How Cooperation Instead of Coexistence in Psychotherapy Research can Improve Science, Practice and Continuing Education]

Die kontinuierliche Erhebung psychometrischer Daten vor, während und nach einer psychotherapeutischen Behandlung kann als Qualitätssicherungsmaßnahme Therapeut:innen in ihrer klinischen Arbeit unterstützen und zugleich eine belastbare Datengrundlage für die Psychotherapieforschung schaffen. Im Rahmen der Qualitätssicherung können die erhobenen Daten als zusätzliche Informationsquelle den klinischen Eindruck der Therapeut:innen erweitern und zur Evaluation der Behandlung am Einzelfall aber auch auf der Ebene des Versorgungssystems herangezogen werden. Darüber hinaus können prognostische Vorhersagen von Therapieergebnissen und Abbruchwahrscheinlichkeiten, Behandlungsempfehlungen sowie adaptive Behandlungsanpassungen während der Behandlung auf ihnen aufgebaut werden, die Therapeut:innen in ihren klinischen Entscheidungen unterstützen 1. Eine solche daten-gestützte und evidenzbasierte psychologische Psychotherapie kann die wissenschaftliche Fundierung der therapeutischen Herangehensweise und die Wirksamkeit der Behandlung verbessern. Dazu bedarf es umfangreicher Datenerhebungen, die verlässliche und aussagekräftige Forschungsbefunde ermöglichen 2.

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.

A framework for multi-faceted content analysis of social media chatter regarding non-medical use of prescription medications

Background

Substance use, including the non-medical use of prescription medications, is a global health problem resulting in hundreds of thousands of overdose deaths and other health problems. Social media has emerged as a potent source of information for studying substance use-related behaviours and their consequences. Mining large-scale social media data on the topic requires the development of natural language processing (NLP) and machine learning frameworks customized for this problem. Our objective in this research is to develop a framework for conducting a content analysis of Twitter chatter about the non-medical use of a set of prescription medications.

Methods

We collected Twitter data for four medications-fentanyl and morphine (opioids), alprazolam (benzodiazepine), and Adderall® (stimulant), and identified posts that indicated non-medical use using an automatic machine learning classifier. In our NLP framework, we applied supervised named entity recognition (NER) to identify other substances mentioned, symptoms, and adverse events. We applied unsupervised topic modelling to identify latent topics associated with the chatter for each medication.

Results

The quantitative analysis demonstrated the performance of the proposed NER approach in identifying substance-related entities from data with a high degree of accuracy compared to the baseline methods. The performance evaluation of the topic modelling was also notable. The qualitative analysis revealed knowledge about the use, non-medical use, and side effects of these medications in individuals and communities.

Conclusions

NLP-based analyses of Twitter chatter associated with prescription medications belonging to different categories provide multi-faceted insights about their use and consequences. Our developed framework can be applied to chatter about other substances. Further research can validate the predictive value of this information on the prevention, assessment, and management of these disorders.

Constructing a disease database and using natural language processing to capture and standardize free text clinical information

The ability to extract critical information about an infectious disease in a timely manner is critical for population health research. The lack of procedures for mining large amounts of health data is a major impediment. The goal of this research is to use natural language processing (NLP) to extract key information (clinical factors, social determinants of health) from free text. The proposed framework describes database construction, NLP modules for locating clinical and non-clinical (social determinants) information, and a detailed evaluation protocol for evaluating results and demonstrating the effectiveness of the proposed framework. The use of COVID-19 case reports is demonstrated for data construction and pandemic surveillance. The proposed approach outperforms benchmark methods in F1-score by about 1-3%. A thorough examination reveals the disease's presence as well as the frequency of symptoms in patients. The findings suggest that prior knowledge gained through transfer learning can be useful when researching infectious diseases with similar presentations in order to accurately predict patient outcomes.

Clinical Impact of Standardized TAVR Technique and Care Pathway: Insights From the Optimize PRO Study

BACKGROUND

Procedural success and clinical outcomes after transcatheter aortic valve replacement (TAVR) have improved, but residual aortic regurgitation (AR) and new permanent pacemaker implantation (PPI) rates remain variable because of a lack of uniform periprocedural management and implantation.

OBJECTIVES

The Optimize PRO study evaluates valve performance and procedural outcomes using an "optimized" TAVR care pathway and the cusp overlap technique (COT) in patients receiving the Evolut PRO/PRO+ (Medtronic) self-expanding valves.

METHODS

Optimize PRO, a nonrandomized, prospective, postmarket study conducted in the United States, Canada, Europe, Middle East, and Australia, is enrolling patients with severe symptomatic aortic stenosis and no pre-existing pacemaker. Sites follow a standardized TAVR care pathway, including early discharge and a conduction disturbance management algorithm, and transfemoral deployment using the COT.

RESULTS

A total of 400 attempted implants from the United States and Canada comprised the main cohort of this second interim analysis. The mean age was 78.7 ± 6.6 years, and the mean Society of Thoracic Surgeons predictive risk of mortality was 3.0 ± 2.4. The median length of stay was 1 day. There were no instances of moderate or severe AR at discharge. At 30 days, all-cause mortality or stroke was 3.8%, all-cause mortality was 0.8%, disabling stroke was 0.7%, hospital readmission was 10.1%, and cardiovascular rehospitalization was 6.1%. The new PPI rate was 9.8%, 5.8% with 4-step COT compliance. In the multivariable model, right bundle branch block and the depth of the implant increased the risk of PPI, whereas using the 4-step COT lowered 30-day PPI.

CONCLUSIONS

The use of the TAVR care pathway and COT resulted in favorable clinical outcomes with no moderate or severe AR and low PPI rates at 30 days while facilitating early discharge and reproducible outcomes across various sites and operators. (Optimize PRO; NCT04091048).

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.

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.