Effectiveness of a positive psychology and mindfulness-based app on mental health for parents of children with a neurodevelopmental disorder: study protocol of a pragmatic international randomized controlled trial.

INTRODUCTION: Parents of children with a neurodevelopmental disorder (NDD) experience more stress than parents of typically developing children. In a cocreation process with experts and parents, a low-threshold application that uses exercises based on the principles of positive psychology and mindfulness was developed. This application, called "Adappt," aims at enhancing the ability to adapt of the parents and caregivers of children with NDDs and at supporting their mental health. This protocol describes the evaluation study of the effectiveness of Adappt, its core working mechanisms and user experiences. METHOD: A pragmatic international multicenter randomized controlled trial will compare the effectiveness of Adappt with a (delayed) waitlist control condition. At least 212 parents or primary caregivers of children younger than 18 years diagnosed with or suspected of a NDD will be randomly assigned to the intervention or waitlist control condition. Participants are excluded if they have severe anxiety or depression levels or are in treatment for mental health issues. Measures will be collected online at baseline, post-intervention (1 month after baseline), and 4 and 7 months after baseline. The primary outcome is the improvement in generic sense of ability to adapt as measured with the Generic Sense of Ability to Adapt Scale (GSAAS; (Front Psychol 14:985408, 2023)) at 4-month follow-up. Secondary outcomes are mental well-being, (parental) distress, and client satisfaction with "Adappt." DISCUSSION: Results of this study will contribute to knowledge on the effectiveness of a low-threshold application for parents of children with a NDD in multiple countries. If the application is found to be effective in improving mental health, recommendations will be made for implementation in health care. TRIAL REGISTRATION: This study is registered on clinicaltrials.gov (NCT06248762) on February 8, 2024, and the Open Science Framework ( https://osf.io/5znqv ).

Enhancing a deep learning model for pulmonary nodule malignancy risk estimation in chest CT with uncertainty estimation.

OBJECTIVE: To investigate the effect of uncertainty estimation on the performance of a Deep Learning (DL) algorithm for estimating malignancy risk of pulmonary nodules. METHODS AND MATERIALS: In this retrospective study, we integrated an uncertainty estimation method into a previously developed DL algorithm for nodule malignancy risk estimation. Uncertainty thresholds were developed using CT data from the Danish Lung Cancer Screening Trial (DLCST), containing 883 nodules (65 malignant) collected between 2004 and 2010. We used thresholds on the 90th and 95th percentiles of the uncertainty score distribution to categorize nodules into certain and uncertain groups. External validation was performed on clinical CT data from a tertiary academic center containing 374 nodules (207 malignant) collected between 2004 and 2012. DL performance was measured using area under the ROC curve (AUC) for the full set of nodules, for the certain cases and for the uncertain cases. Additionally, nodule characteristics were compared to identify trends for inducing uncertainty. RESULTS: The DL algorithm performed significantly worse in the uncertain group compared to the certain group of DLCST (AUC 0.62 (95% CI: 0.49, 0.76) vs 0.93 (95% CI: 0.88, 0.97); p < .001) and the clinical dataset (AUC 0.62 (95% CI: 0.50, 0.73) vs 0.90 (95% CI: 0.86, 0.94); p < .001). The uncertain group included larger benign nodules as well as more part-solid and non-solid nodules than the certain group. CONCLUSION: The integrated uncertainty estimation showed excellent performance for identifying uncertain cases in which the DL-based nodule malignancy risk estimation algorithm had significantly worse performance. CLINICAL RELEVANCE STATEMENT: Deep Learning algorithms often lack the ability to gauge and communicate uncertainty. For safe clinical implementation, uncertainty estimation is of pivotal importance to identify cases where the deep learning algorithm harbors doubt in its prediction. KEY POINTS: • Deep learning (DL) algorithms often lack uncertainty estimation, which potentially reduce the risk of errors and improve safety during clinical adoption of the DL algorithm. • Uncertainty estimation identifies pulmonary nodules in which the discriminative performance of the DL algorithm is significantly worse. • Uncertainty estimation can further enhance the benefits of the DL algorithm and improve its safety and trustworthiness.

Effectiveness of compassion-focused therapy for self-criticism in patients with personality disorders: a multiple baseline case series study.

OBJECTIVE: Targeting self-criticism, the tendency to negatively evaluate and judge aspects of oneself, may improve treatment efficacy for personality disorders (PDs). This study aimed to test whether adding 12-week group compassion-focused therapy (CFT) that explicitly targets self-criticism to treatment as usual (TAU) would reduce self-criticism in patients with PDs. METHOD: Twelve patients with PDs participated in a multiple baseline study, randomly allocated to different baseline lengths. The primary outcome was twice-weekly assessed self-critical beliefs during baseline, treatment, and follow-up phases. Secondary outcomes were self-criticism, self-compassion, and PD severity at the end of CFT and follow-up (trial registered: NL8131). Nine participants completed the intervention. No significant changes were observed during CFT, but at follow-up significant decrease in self-critical beliefs (Cohen's d = -0.43; 95% CI = -0.73 to -0.12) was reported compared to baseline. On secondary outcomes, most participants showed reliable improvement on self-reported criticism (66.7%) and self-compassion (55.6%), and a minority of patients showed reliable improvement in PD severity (33.3%). CONCLUSIONS: This study seems to provide preliminary evidence for the effectiveness of 12-week CFT for self-critical beliefs in patients with PDs compared to TAU. CFT for self-criticism in PDs may complement treatment offerings and warrant further research.

Compas-Y: A mixed methods pilot evaluation of a mobile self-compassion training for people with newly diagnosed cancer.

Objective: Compas-Y is a compassionate mind training app that was co-designed to be fully adapted to mobile technology and to people with newly diagnosed cancer. This study aimed to evaluate the use, appreciation and impact of the app. Methods: Seventy-one people with cancer who created an app account were included (38% breast cancer, 72% diagnosed <4 months ago, 76% received chemotherapy). Participants had very high baseline scores of self-compassion. In a convergent mixed methods design, back-end log-data (n = 71), pre-post surveys (n = 34) and semi-structured interviews (n = 23) collected for >8 weeks and were concurrently analysed using joint displays. Results: About half of the participants (45%) used 4 of the 6 modules. Compas-Y was highly appreciated, with all content considered relevant and a source of support. Experienced benefits related to improved mental health. Particularly, we found significant changes in anxiety, but not in depression or well-being. In the interviews, people reported experiencing more rest and more positive emotions due to using the app. Process benefits included significant reductions in self-criticism (inadequate self and self-blame), but not self-compassion. In the interviews, people reported improved self-compassion and less self-criticism, more self-awareness, recognition and support, and improved emotion regulation and coping. The surveys did not capture the full range of outcomes that participants reported in the interviews. Conclusions: Compas-Y is a highly appreciated mobile intervention that supported users in aspects of their mental health. Findings are discussed in terms of reach and adherence, app functionalities, co-design and tailoring of cancer-related and compassion-based eHealth.

Deep learning for the detection of benign and malignant pulmonary nodules in non-screening chest CT scans.

BACKGROUND: Outside a screening program, early-stage lung cancer is generally diagnosed after the detection of incidental nodules in clinically ordered chest CT scans. Despite the advances in artificial intelligence (AI) systems for lung cancer detection, clinical validation of these systems is lacking in a non-screening setting. METHOD: We developed a deep learning-based AI system and assessed its performance for the detection of actionable benign nodules (requiring follow-up), small lung cancers, and pulmonary metastases in CT scans acquired in two Dutch hospitals (internal and external validation). A panel of five thoracic radiologists labeled all nodules, and two additional radiologists verified the nodule malignancy status and searched for any missed cancers using data from the national Netherlands Cancer Registry. The detection performance was evaluated by measuring the sensitivity at predefined false positive rates on a free receiver operating characteristic curve and was compared with the panel of radiologists. RESULTS: On the external test set (100 scans from 100 patients), the sensitivity of the AI system for detecting benign nodules, primary lung cancers, and metastases is respectively 94.3% (82/87, 95% CI: 88.1-98.8%), 96.9% (31/32, 95% CI: 91.7-100%), and 92.0% (104/113, 95% CI: 88.5-95.5%) at a clinically acceptable operating point of 1 false positive per scan (FP/s). These sensitivities are comparable to or higher than the radiologists, albeit with a slightly higher FP/s (average difference of 0.6). CONCLUSIONS: The AI system reliably detects benign and malignant pulmonary nodules in clinically indicated CT scans and can potentially assist radiologists in this setting.

Early-stage lung cancer can be diagnosed after identifying an abnormal spot on a chest CT scan ordered for other medical reasons. These spots or lung nodules can be overlooked by radiologists, as they are not necessarily the focus of an examination and can be as small as a few millimeters. Software using Artificial Intelligence (AI) technology has proven to be successful for aiding radiologists in this task, but its performance is understudied outside a lung cancer screening setting. We therefore developed and validated AI software for the detection of cancerous nodules or non-cancerous nodules that would need attention. We show that the software can reliably detect these nodules in a non-screening setting and could potentially aid radiologists in daily clinical practice.

Exploring mental health dynamics during eating disorder treatment: A psychometric network study with panel data.

To explore mental health associations during eating disorder (ED) treatment. Based on the dual-continua model of mental health, general and ED-specific psychopathology, as well as emotional, psychological, and social well-being were considered as mental health domains.Network analyses with panel data were applied to explore within- (temporal and contemporaneous networks) and between-person effects in a sample of 1250 female ED patients during 12 months of outpatient treatment. The associations between the domains and their centrality were examined. Autoregressive and cross-lagged effects were also estimated.ED psychopathology was the most central domain in the temporal network. ED psychopathology changes predicted further ED psychopathology changes and small changes in the other domains. Weak bi-directional associations were found between changes in the well-being domains and general psychopathology. In contrast to the temporal network, ED psychopathology was the least central and psychological well-being the most central domain in the contemporaneous and between-subjects networks. This suggests a central role of psychological well-being for experiencing mental health within time points.ED psychopathology may change relatively independent from other mental health domains. Well-being domains may be considered as more stable aspects of mental health.

Compassion apps for better mental health: qualitative review.

BACKGROUND: There is increasing empirical evidence for the positive mental health effects of compassion-based interventions. Although numerous smartphone apps offering compassion-based interventions ('compassion apps') are now available for the general public, the quality of these apps has not yet been reviewed. A qualitative review of existing compassion apps serves as a crucial first step toward testing the efficacy of these apps, by identifying good-quality compassion apps that might be worth the investment of a scientific trial. AIMS: The current study focuses on reviewing the quality of existing compassion apps. METHOD: Existing compassion apps were identified through searches in the Google Play Store and App Store. The 24 included apps were reviewed on their quality by using the Mobile App Rating Scale, and on their consistency with current evidence by comparing them to existing and studied compassion-based interventions. RESULTS: Of the 24 included apps, eight were identified that met the criteria of being consistent with existing and studied compassion-based interventions, and acceptable to good overall quality. The other 16 apps failed to meet one or both of these criteria. CONCLUSIONS: Good-quality compassion apps are available, but many of the available apps fail to meet certain quality criteria. In particular, many apps failed to offer sufficient relevant and correct information, or failed to offer this information in an entertaining and interesting way. It is recommended that future compassion apps are based on a clear definition of compassion, offer evidence- and theory-based exercises and implement tools for increasing engagement.

Prior CT Improves Deep Learning for Malignancy Risk Estimation of Screening-detected Pulmonary Nodules.

Background Prior chest CT provides valuable temporal information (eg, changes in nodule size or appearance) to accurately estimate malignancy risk. Purpose To develop a deep learning (DL) algorithm that uses a current and prior low-dose CT examination to estimate 3-year malignancy risk of pulmonary nodules. Materials and Methods In this retrospective study, the algorithm was trained using National Lung Screening Trial data (collected from 2002 to 2004), wherein patients were imaged at most 2 years apart, and evaluated with two external test sets from the Danish Lung Cancer Screening Trial (DLCST) and the Multicentric Italian Lung Detection Trial (MILD), collected in 2004-2010 and 2005-2014, respectively. Performance was evaluated using area under the receiver operating characteristic curve (AUC) on cancer-enriched subsets with size-matched benign nodules imaged 1 and 2 years apart from DLCST and MILD, respectively. The algorithm was compared with a validated DL algorithm that only processed a single CT examination and the Pan-Canadian Early Lung Cancer Detection Study (PanCan) model. Results The training set included 10 508 nodules (422 malignant) in 4902 trial participants (mean age, 64 years ± 5 [SD]; 2778 men). The size-matched external test sets included 129 nodules (43 malignant) and 126 nodules (42 malignant). The algorithm achieved AUCs of 0.91 (95% CI: 0.85, 0.97) and 0.94 (95% CI: 0.89, 0.98). It significantly outperformed the DL algorithm that only processed a single CT examination (AUC, 0.85 [95% CI: 0.78, 0.92; P = .002]; and AUC, 0.89 [95% CI: 0.84, 0.95; P = .01]) and the PanCan model (AUC, 0.64 [95% CI: 0.53, 0.74; P < .001]; and AUC, 0.63 [95% CI: 0.52, 0.74; P < .001]). Conclusion A DL algorithm using current and prior low-dose CT examinations was more effective at estimating 3-year malignancy risk of pulmonary nodules than established models that only use a single CT examination. Clinical trial registration nos. NCT00047385, NCT00496977, NCT02837809 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Horst and Nishino in this issue.

Trends in the incidence of pulmonary nodules in chest computed tomography: 10-year results from two Dutch hospitals.

OBJECTIVE: To study trends in the incidence of reported pulmonary nodules and stage I lung cancer in chest CT. METHODS: We analyzed the trends in the incidence of detected pulmonary nodules and stage I lung cancer in chest CT scans in the period between 2008 and 2019. Imaging metadata and radiology reports from all chest CT studies were collected from two large Dutch hospitals. A natural language processing algorithm was developed to identify studies with any reported pulmonary nodule. RESULTS: Between 2008 and 2019, a total of 74,803 patients underwent 166,688 chest CT examinations at both hospitals combined. During this period, the annual number of chest CT scans increased from 9955 scans in 6845 patients in 2008 to 20,476 scans in 13,286 patients in 2019. The proportion of patients in whom nodules (old or new) were reported increased from 38% (2595/6845) in 2008 to 50% (6654/13,286) in 2019. The proportion of patients in whom significant new nodules (≥ 5 mm) were reported increased from 9% (608/6954) in 2010 to 17% (1660/9883) in 2017. The number of patients with new nodules and corresponding stage I lung cancer diagnosis tripled and their proportion doubled, from 0.4% (26/6954) in 2010 to 0.8% (78/9883) in 2017. CONCLUSION: The identification of incidental pulmonary nodules in chest CT has steadily increased over the past decade and has been accompanied by more stage I lung cancer diagnoses. CLINICAL RELEVANCE STATEMENT: These findings stress the importance of identifying and efficiently managing incidental pulmonary nodules in routine clinical practice. KEY POINTS: • The number of patients who underwent chest CT examinations substantially increased over the past decade, as did the number of patients in whom pulmonary nodules were identified. • The increased use of chest CT and more frequently identified pulmonary nodules were associated with more stage I lung cancer diagnoses.

Strength Back - A qualitative study on the co-creation of a positive psychology digital health intervention for spinal surgery patients.

Introduction: Spinal surgery patients often experience pain as well as stress, anxiety or even depression before surgery, highlighting the need for better mental preparation before undergoing surgery. Acceptance and Commitment Therapy and positive psychology have proven effective in coping with chronic pain and providing long-term skills that enhance psychological flexibility and mental well-being.The aim of this study is to develop a digital intervention (app) based on Acceptance and Commitment Therapy and positive psychology in co-creation with all stakeholders, including patients and professionals. The aim of the intervention is to increase psychological flexibility and positive skills of spinal surgery patients to promote long-term resilience. Materials and methods: In this qualitative study, individual, semi-structured interviews were held with healthcare professionals (N = 9) and spinal surgery patients (N = 12) to identify contextual factors and needs for the app. Subsequently, three focus-group sessions were held with healthcare professionals and newly recruited patients to specify relevant values. Also, a first version of the app, named Strength Back, was developed using a participatory design. Results: The interviews confirmed the need for information and digital support to cope with insecurity, anxiety and pain, both before and after surgery. Based on iterative steps in the focus-group sessions, thirteen modules were developed focusing on procedural information, pain education, psychological flexibility and mental well-being. Discussion: The intervention Strength Back, containing information as well as Acceptance and Commitment Therapy and positive psychology exercises, has the potential to increase psychological flexibility, enhance well-being and improve postoperative recovery after spinal surgery.

A multicomponent positive psychology intervention for euthymic patients with bipolar disorder to improve mental well-being and personal recovery: A pragmatic randomized controlled trial.

OBJECTIVE: Mental well-being and personal recovery are important treatment targets for patients with bipolar disorder (BD). The goal of this study was to evaluate the effectiveness of an 8-week group multicomponent positive psychology intervention (PPI) for euthymic patients with BD as an adjunct to treatment as usual (TAU) compared to TAU alone. METHODS: Patients with BD were randomized to receive TAU (n = 43) or the PPI in addition to TAU (n = 54). The primary outcome was well being measured with the Mental Health Continuum-Short Form. Personal recovery was measured with the Questionnaire about the Process of Recovery. Data were collected at baseline, mid-treatment, post-treatment and 6- and 12-month follow-up. Life chart interviews were conducted at 12 months to retrospectively assess recurrence of depression and mania. RESULTS: Significant group-by-time interaction effects for well-being and personal recovery were found favouring the PPI. At post-treatment, between-group differences were significant for well-being (d = 0.77) and personal recovery (d = 0.76). Between-group effects for well-being were still significant at 6-month follow-up (d = 0.72). Effects on well-being and personal recovery within the intervention group were sustained until 12-month follow-up. Survival analyses showed no significant differences in time to recurrence. CONCLUSIONS: The multicomponent PPI evaluated in this study is effective in improving mental well-being and personal recovery in euthymic patients with BD and would therefore be a valuable addition to the current treatment of euthymic BD patients. The fact that the study was carried out in a pragmatic RCT demonstrates that this intervention can be applied in a real-world clinical setting.

Augmenting outpatient alcohol treatment as usual with online approach bias modification training: A double-blind randomized controlled trial.

Previous research shows that automatic tendency to approach alcohol plays a causal role in problematic alcohol use and can be retrained by Approach Bias Modification (ApBM). ApBM has been shown to be effective for patients diagnosed with alcohol use disorder (AUD) in inpatient treatment. This study aimed to investigate the effectiveness of adding an online ApBM to treatment as usual (TAU) in an outpatient setting compared to receiving TAU with an online placebo training. 139 AUD patients receiving face-to-face or online treatment as usual (TAU) participated in the study. The patients were randomized to an active or placebo version of 8 sessions of online ApBM over a 5-week period. The weekly consumed standard units of alcohol (primary outcome) was measured at pre-and post-training, 3 and 6 months follow-up. Approach tendency was measured pre-and-post ApBM training. No additional effect of ApBM was found on alcohol intake, nor other outcomes such as craving, depression, anxiety, or stress. A significant reduction of the alcohol approach bias was found. This research showed that approach bias retraining in AUD patients in an outpatient treatment setting reduces the tendency to approach alcohol, but this training effect does not translate into a significant difference in alcohol reduction between groups. Explanations for the lack of effects of ApBM on alcohol consumption are treatment goal and severity of AUD. Future ApBM research should target outpatients with an abstinence goal and offer alternative, more user-friendly modes of delivering ApBM training.

Why patients diagnosed with bipolar disorder start, continue or discontinue health-related apps supporting their self-management.

WHAT IS KNOWN ABOUT THE SUBJECT?: Self-management is essential in the treatment of those who have bipolar disorder. There are many apps to support self-management, but we know that these apps only sometimes cover the users' needs. WHAT IS ADDED TO EXISTING KNOWLEDGE?: In our research, we made an inventory of apps that people with bipolar disorder use to cover their needs in self-management. We also have searched for the reasons to start, continue, switch or quit the use of those apps. We found that 44% (n = 18) of our respondents use health-related apps for self-management purposes. Apps for physical activity, planning and structure and apps for relaxation were most used. In the use of apps, the "freedom of choice" and user-friendliness are the most important in continuing the use of apps, while malfunctioning and "not fitting in individual needs" the main reasons were for quitting the use of apps. IMPLICATIONS FOR PRACTICE: Various apps can be used for self-management purposes as long as these apps meet the individual user's requirements. Clinicians and patients should have a broad view when looking for suitable apps and not limit the search to just professional apps. In developing new apps, patients, clinicians and developers should collaborate in the development process, requirements and design. ABSTRACT: INTRODUCTION: Self-management is one of the cornerstones in the treatment of bipolar disorder (BD). Complementing interventions by apps are seen as a good opportunity to support self-management. However, there is insufficient knowledge about understanding the use of health-related applications by consumers with BD for self-management purposes. AIM: The study aims to gain insight from patients diagnosed with BD about reasons to use, continue or discontinue health-related apps. METHOD: This study employed a mixed-method design in which 41 participants diagnosed with BD participated in a quantitative survey, and 11 participants also participated in an in-depth interview. RESULTS: The survey showed that 44% (n = 18) of the participants use health-related apps, and 26.8% (n = 11) use those apps consistently. Interviews revealed that adjustability, usability, trustworthiness and the guarantee of privacy were the main reasons determining whether participants used or terminated the use of a health-related app. IMPLICATIONS FOR PRACTICE: Although we found that a substantial number of patients diagnosed with BD use one or more apps to support self-management, their use is often discontinued due to content that needs more robust to address their needs. Besides appropriate content, tailoring and persuasive technologies will likely promote the continued use of an app for self-management purposes. Cooperation between those diagnosed with bipolar disorder and health professionals (like mental health nurses) in developing and designing applications that are aimed to support self-management in BD is necessary for successful implementation and adaptation.

Modelling trajectories of change in psychopathology and well-being during eating disorder outpatient treatment.

Objective: There are considerable differences in how eating disorder (ED) patients respond to treatment. This study aimed to identify change trajectories of mental health during treatment. Method: Longitudinal data of 442 patients was used with five time points during a year of outpatient treatment. ED psychopathology and well-being were used as primary measures. A series of latent growth mixture models were applied to model trajectories of change. Results: Three latent classes were found for ED psychopathology and well-being. For ED psychopathology, a high baseline severity and slow recovery class (55.9% of the patients), a high baseline severity followed by a substantial recovery class (19.9%) and a moderate baseline severity and no significant recovery class (24.2%) were found. For well-being, a low baseline followed by a slow growth class (44.6%), a low baseline and substantial growth class (9.5%) and a moderate and stable well-being class (45.9%) was found. General psychopathology, early symptom change, hope for recovery, intrinsic motivation and the ED type were predictive of class membership in either ED psychopathology or well-being. Conclusions: This study shows variability in ED psychopathology and well-being change trajectories, modelled in meaningful latent recovery classes. These results may have clinical implications, such as adjusting patients' treatment based on change trajectories.

Integrating Top-down and Bottom-up Requirements in eHealth Development: The Case of a Mobile Self-compassion Intervention for People With Newly Diagnosed Cancer.

BACKGROUND: Psychosocial eHealth interventions for people with cancer are promising in reducing distress; however, their results in terms of effects and adherence rates are quite mixed. Developing interventions with a solid evidence base while still ensuring adaptation to user wishes and needs is recommended to overcome this. As most models of eHealth development are based primarily on examining user experiences (so-called bottom-up requirements), it is not clear how theory and evidence (so-called top-down requirements) may best be integrated into the development process. OBJECTIVE: This study aims to investigate the integration of top-down and bottom-up requirements in the co-design of eHealth applications by building on the development of a mobile self-compassion intervention for people with newly diagnosed cancer. METHODS: Four co-design tasks were formulated at the start of the project and adjusted and evaluated throughout: explore bottom-up experiences, reassess top-down content, incorporate bottom-up and top-down input into concrete features and design, and synergize bottom-up and top-down input into the intervention context. These tasks were executed iteratively during a series of co-design sessions over the course of 2 years, in which 15 people with cancer and 7 nurses (recruited from 2 hospitals) participated. On the basis of the sessions, a list of requirements, a final intervention design, and an evaluation of the co-design process and tasks were yielded. RESULTS: The final list of requirements included intervention content (eg, major topics of compassionate mind training such as psychoeducation about 3 emotion systems and main issues that people with cancer encounter after diagnosis such as regulating information consumption), navigation, visual design, implementation strategies, and persuasive elements. The final intervention, Compas-Y, is a mobile self-compassion training comprising 6 training modules and several supportive functionalities such as a mood tracker and persuasive elements such as push notifications. The 4 co-design tasks helped overcome challenges in the development process such as dealing with conflicting top-down and bottom-up requirements and enabled the integration of all main requirements into the design. CONCLUSIONS: This study addressed the necessary integration of top-down and bottom-up requirements into eHealth development by examining a preliminary model of 4 co-design tasks. Broader considerations regarding the design of a mobile intervention based on traditional intervention formats and merging the scientific disciplines of psychology and design research are discussed.

A Web-Based Positive Psychology App for Patients With Bipolar Disorder: Development Study.

BACKGROUND: Patients with bipolar disorder (BD) report lower quality of life and lower levels of well-being than the general population. Despite the growing availability of psychotherapeutic and self-management interventions, important unmet needs remain. These unmet needs are closely linked to positive psychology domains. Although a growing number of studies have evaluated the impact of positive psychology interventions (PPIs) on patients with severe mental illness in general, only few have addressed the application of positive psychology for BD. OBJECTIVE: This study aimed to gain insight into the opinions of patients with BD and health care professionals about (web-based) PPIs for BD and to develop and pilot-test an app containing PPIs specifically designed for patients with BD. METHODS: The study was conducted in accordance with the Center for eHealth and Disease Management road map principles and incorporated cocreation and designing for implementation. Data were collected using focus group discussions, questionnaires, rapid prototyping, and web-based feedback on a prototype from the participants. In total, 3 focus groups were conducted with 62% (8/13) of patients with BD and 38% (5/13) of professionals. The collected data were used to develop a smartphone app containing short PPIs. The content was based on PPIs for which a solid base of evidence is available. Finally, a pilot test was conducted to test the app. RESULTS: Focus groups revealed that PPIs as part of the current BD treatment can potentially meet the following needs: offering hope, increasing self-esteem, expressing feelings, acceptance, and preventing social isolation. Some patients expressed concern that PPIs may provoke a manic or hypomanic episode by increasing positive affect. The pilot of the app showed that the PPIs are moderately to highly valued by the participants. There were no adverse effects such as increase in manic or hypomanic symptoms. CONCLUSIONS: With the systematic use of user involvement (patients and professionals) in all steps of the development process, we were able to create an app that can potentially fulfill some of the current unmet needs in the treatment of BD. We reached consensus among consumers and professionals about the potential benefits of PPIs to address the unmet needs of patients with BD. The use of PPI for BD is intriguing and can be usefully explored in further studies. We emphasize that more evaluation studies (quantitative and qualitative) that are focused on the effect of PPIs in the treatment of BD should be conducted. In addition, to establish the working mechanisms in BD, explorative, qualitative, designed studies are required to reveal whether PPIs can address unmet needs in BD.

Explainable emphysema detection on chest radiographs with deep learning.

We propose a deep learning system to automatically detect four explainable emphysema signs on frontal and lateral chest radiographs. Frontal and lateral chest radiographs from 3000 studies were retrospectively collected. Two radiologists annotated these with 4 radiological signs of pulmonary emphysema identified from the literature. A patient with ≥2 of these signs present is considered emphysema positive. Using separate deep learning systems for frontal and lateral images we predict the presence of each of the four visual signs and use these to determine emphysema positivity. The ROC and AUC results on a set of 422 held-out cases, labeled by both radiologists, are reported. Comparison with a black-box model which predicts emphysema without the use of explainable visual features is made on the annotations from both radiologists, as well as the subset that they agreed on. DeLong's test is used to compare with the black-box model ROC and McNemar's test to compare with radiologist performance. In 422 test cases, emphysema positivity was predicted with AUCs of 0.924 and 0.946 using the reference standard from each radiologist separately. Setting model sensitivity equivalent to that of the second radiologist, our model has a comparable specificity (p = 0.880 and p = 0.143 for each radiologist respectively). Our method is comparable with the black-box model with AUCs of 0.915 (p = 0.407) and 0.935 (p = 0.291), respectively. On the 370 cases where both radiologists agreed (53 positives), our model achieves an AUC of 0.981, again comparable to the black-box model AUC of 0.972 (p = 0.289). Our proposed method can predict emphysema positivity on chest radiographs as well as a radiologist or a comparable black-box method. It additionally produces labels for four visual signs to ensure the explainability of the result. The dataset is publicly available at https://doi.org/10.5281/zenodo.6373392.

Examining well-being in posttraumatic stress disorder treatment: An explorative study.

Although the importance of well-being in mental health is widely acknowledged, well-being as a predictor of and outcome in the treatment for posttraumatic stress disorder (PTSD) has received little attention. This naturalistic study aimed to investigate well-being in the context of care-as-usual treatment for PTSD. Patients with PTSD attending a community mental health center (N = 318) completed measures of well-being and PTSD symptoms before and after symptom-focused treatment. Following treatment, well-being increased among patients with PTSD, with emotional, d = -0.25, and psychological well-being, d = -0.24, showing the largest improvements relative to social well-being, d = -0.15. Although levels of well-being improved overall within the sample, participant scores on measures of well-being remained low compared with the general population. Well-being predicted treatment efficiency such that participants with more severe PTSD symptoms benefitted more from care-as-usual treatment when they reported relatively high levels of well-being at the start of treatment. The findings suggest a benefit to including well-being as a pretreatment and outcome variable when evaluating PTSD treatments.

Exploring associations between personality trait facets and emotional, psychological and social well-being in eating disorder patients.

PURPOSE: Personality functioning is strongly linked to well-being in the general population. Yet, there is a lack of scientific knowledge about the pathways between personality trait facets and emotional, psychological and social well-being in ED patients. The general aim was to examine potential associations between maladaptive personality trait facets and the three main dimensions of well-being. METHODS: Participants were 1187 female eating disorder patients who were referred for specialized treatment. Patients were diagnosed with anorexia nervosa (31.7%), bulimia nervosa (21.7%), binge eating disorder (11%) and other specified eating disorders (35.5%). The Personality Inventory for the DSM 5 (PID-5) was used to measure 25 trait facets, and well-being was measured with the Mental Health Continuum Short Form (MHC-SF). Multiple hierarchical regression analyses were applied to examine potential associations between personality and well-being while controlling for background and illness characteristics. RESULTS: Personality trait facets led to a statistically significant increase of the explained variance in emotional (38%), psychological (39%), and social well-being (26%) in addition to the background and illness characteristics. The personality trait facets anhedonia and depression were strongly associated with all three well-being dimensions. CONCLUSION: Personality traits may play an essential role in the experience of well-being among patients with EDs. To promote overall mental health, it may be critical for clinicians to address relevant personality trait facets, such as anhedonia and depression, associated with well-being in treatment. LEVEL OF EVIDENCE: Level V, cross-sectional descriptive study.

Deep Learning for Lung Cancer Detection on Screening CT Scans: Results of a Large-Scale Public Competition and an Observer Study with 11 Radiologists.

PURPOSE: To determine whether deep learning algorithms developed in a public competition could identify lung cancer on low-dose CT scans with a performance similar to that of radiologists. MATERIALS AND METHODS: In this retrospective study, a dataset consisting of 300 patient scans was used for model assessment; 150 patient scans were from the competition set and 150 were from an independent dataset. Both test datasets contained 50 cancer-positive scans and 100 cancer-negative scans. The reference standard was set by histopathologic examination for cancer-positive scans and imaging follow-up for at least 2 years for cancer-negative scans. The test datasets were applied to the three top-performing algorithms from the Kaggle Data Science Bowl 2017 public competition: grt123, Julian de Wit and Daniel Hammack (JWDH), and Aidence. Model outputs were compared with an observer study of 11 radiologists that assessed the same test datasets. Each scan was scored on a continuous scale by both the deep learning algorithms and the radiologists. Performance was measured using multireader, multicase receiver operating characteristic analysis. RESULTS: The area under the receiver operating characteristic curve (AUC) was 0.877 (95% CI: 0.842, 0.910) for grt123, 0.902 (95% CI: 0.871, 0.932) for JWDH, and 0.900 (95% CI: 0.870, 0.928) for Aidence. The average AUC of the radiologists was 0.917 (95% CI: 0.889, 0.945), which was significantly higher than grt123 (P = .02); however, no significant difference was found between the radiologists and JWDH (P = .29) or Aidence (P = .26). CONCLUSION: Deep learning algorithms developed in a public competition for lung cancer detection in low-dose CT scans reached performance close to that of radiologists.Keywords: Lung, CT, Thorax, Screening, Oncology Supplemental material is available for this article. © RSNA, 2021.