RESUMEN
How low is the ideal first offer? Prior to any negotiation, decision-makers must balance a crucial tradeoff between two opposing effects. While lower first offers benefit buyers by anchoring the price in their favor, an overly ambitious offer increases the impasse risk, thus potentially precluding an agreement altogether. Past research with simulated laboratory or classroom exercises has demonstrated either a first offer's anchoring benefits or its impasse risk detriments, while largely ignoring the other effect. In short, there is no empirical answer to the conundrum of how low an ideal first offer should be. Our results from over 26 million incentivized real-world negotiations on eBay document (a) a linear anchoring effect of buyer offers on sales price, (b) a nonlinear, quartic effect on impasse risk, and (c) specific offer values with particularly low impasse risks but high anchoring benefits. Integrating these findings suggests that the ideal buyer offer lies at 80% of the seller's list price across all products-although this value ranges from 33% to 95% depending on the type of product, demand, and buyers' weighting of price versus impasse risk. We empirically amend the well-known midpoint bias, the assumption that buyer and seller eventually meet in the middle of their opening offers, and find evidence for a "buyer bias." Product demand moderates the (non)linear effects, the ideal buyer offer, and the buyer bias. Finally, we apply machine learning analyses to predict impasses and present a website with customizable first-offer advice configured to different products, prices, and buyers' risk preferences.
Asunto(s)
Comercio , NegociaciónRESUMEN
BACKGROUND: Clozapine is the most effective antipsychotic for treatment-resistant psychosis. However, clozapine is underutilised in part because of potential agranulocytosis. Accumulating evidence indicates that below-threshold haematological readings in isolation are not diagnostic of life-threatening clozapine-induced agranulocytosis (CIA). AIMS: To examine the prevalence and timing of CIA using different diagnostic criteria and to explore demographic differences of CIA in patients registered on the UK Central Non-Rechallenge Database (CNRD). METHOD: We analysed data of all patients registered on the UK Clozaril® Patient Monitoring Service Central Non-Rechallenge Database (at least one absolute neutrophil count (ANC) < 1.5 × 109/L and/or white blood cell count < 3.0 × 109/L) between May 2000 and February 2021. We calculated prevalence rates of agranulocytosis using threshold-based and pattern-based criteria, stratified by demographic factors (gender, age and ethnicity). Differences in epidemiology based on rechallenge status and clozapine indication were explored. The proportion of patients who recorded agranulocytosis from a normal ANC was explored. RESULTS: Of the 3029 patients registered on the CNRD with 283 726 blood measurements, 593 (19.6%) were determined to have threshold-based agranulocytosis and 348 (11.4%) pattern-based agranulocytosis. In the total sample (75 533), the prevalence of threshold-based agranulocytosis and pattern-based agranulocytosis was 0.8% and 0.5%, respectively. The median time to threshold-based agranulocytosis was 32 weeks (IQR 184) and 15 (IQR 170) weeks for pattern-based agranulocytosis. Among age groups, the prevalence of pattern-based agranulocytosis and threshold-based agranulocytosis was highest in the >48 age group. Prevalence rates were greatest for White (18%) and male individuals (13%), and lowest for Black individuals (0.1%). The proportion of people who were determined to have pattern-based agranulocytosis without passing through neutropenia was 70%. CONCLUSIONS: Threshold-based definition of agranulocytosis may over-diagnose CIA. Monitoring schemes should take into consideration neutrophil patterns to correctly identify clinically relevant CIA. In marked contrast to previous studies, CIA occurred least in Black individuals and most in White individuals.
RESUMEN
Digital guided self-help for eating disorders (GSH-ED) can reduce treatment disparities. Understanding program participants' interests throughout the program can help adapt programs to the service users' needs. Participants were 383 college students receiving a digital GSH-ED, who were each assigned a coach to help them better utilize the intervention through text correspondence. A thematic and affective analysis of the texts participants had sent found they primarily focused on: strategies for changing their ED-related cognitions, behaviors, and relationships; describing symptoms without expressing an active endeavor to change; and participants' relationship with their coach. Most texts also expressed affect, demonstrating emotional engagement with the intervention. Findings suggest that participants in GSH-ED demonstrate high involvement with the intervention, and discuss topics that are similar to those reported in clinician-facilitated interventions. The themes discussed by digital program participants can inform future iterations of GSH-ED, thereby increasing scalability and accessibility of digital evidence-based ED interventions.
Asunto(s)
Trastornos de Alimentación y de la Ingestión de Alimentos , Envío de Mensajes de Texto , Humanos , Conductas Relacionadas con la Salud , Trastornos de Alimentación y de la Ingestión de Alimentos/terapia , EstudiantesRESUMEN
BACKGROUND: Simulation study results suggest that COVID-19 contact tracing apps have the potential to achieve pandemic control. Concordantly, high app adoption rates were a stipulated prerequisite for success. Early studies on potential adoption were encouraging. Several factors predicting adoption rates were investigated, especially pertaining to user characteristics. Since then, several countries have released COVID-19 contact tracing apps. OBJECTIVE: This study's primary aim is to investigate the quality characteristics of national European COVID-19 contact tracing apps, thereby shifting attention from user to app characteristics. The secondary aim is to investigate associations between app quality and adoption. Finally, app features contributing to higher app quality were identified. METHODS: Eligible COVID-19 contact tracing apps were those released by national health authorities of European Union member states, former member states, and countries of the European Free Trade Association, all countries with comparable legal standards concerning personal data protection and app use voluntariness. The Mobile App Rating Scale was used to assess app quality. An interdisciplinary team, consisting of two health and two human-computer interaction scientists, independently conducted Mobile App Rating Scale ratings. To investigate associations between app quality and adoption rates and infection rates, Bayesian linear regression analyses were conducted. RESULTS: We discovered 21 national COVID-19 contact tracing apps, all demonstrating high quality overall and high-level functionality, aesthetics, and information quality. However, the average app adoption rate of 22.9% (SD 12.5%) was below the level recommended by simulation studies. Lower levels of engagement-oriented app design were detected, with substantial variations between apps. By regression analyses, the best-case adoption rate was calculated by assuming apps achieve the highest ratings. The mean best-case adoption rates for engagement and overall app quality were 39.5% and 43.6%, respectively. Higher adoption rates were associated with lower cumulative infection rates. Overall, we identified 5 feature categories (symptom assessment and monitoring, regularly updated information, individualization, tracing, and communication) and 14 individual features that contributed to higher app quality. These 14 features were a symptom checker, a symptom diary, statistics on COVID-19, app use, public health instructions and restrictions, information of burden on health care system, assigning personal data, regional updates, control over tracing activity, contact diary, venue check-in, chats, helplines, and app-sharing capacity. CONCLUSIONS: European national health authorities have generally released high quality COVID-19 contact tracing apps, with regard to functionality, aesthetics, and information quality. However, the app's engagement-oriented design generally was of lower quality, even though regression analyses results identify engagement as a promising optimization target to increase adoption rates. Associations between higher app adoption and lower infection rates are consistent with simulation study results, albeit acknowledging that app use might be part of a broader set of protective attitudes and behaviors for self and others. Various features were identified that could guide further engagement-enhancing app development.
Asunto(s)
COVID-19/epidemiología , Trazado de Contacto/métodos , Aplicaciones Móviles/estadística & datos numéricos , Europa (Continente)/epidemiología , Humanos , Estudios Interdisciplinarios , Pandemias , Calidad de la Atención de Salud , SARS-CoV-2/aislamiento & purificaciónRESUMEN
BACKGROUND: Previous studies provide evidence for the effectiveness of web-based interventions for panic disorder with and without agoraphobia. Smartphone-based technologies hold significant potential for further enhancing the accessibility and efficacy of such interventions. OBJECTIVE: This randomized controlled trial aims to evaluate the efficacy of a guided, hybrid web-based training program based on cognitive behavioral therapy for adults with symptoms of panic disorder. METHODS: Participants (N=92) with total scores in the Panic and Agoraphobia Scale ranging from 9 to 28 were recruited from the general population and allocated either to a hybrid intervention (GET.ON Panic) or to a wait-list control group. The primary outcome was the reduction in panic symptoms, as self-assessed using a web-based version of the Panic and Agoraphobia Scale. RESULTS: Analysis of covariance-based intention-to-treat analyses revealed a significantly stronger decrease in panic symptoms posttreatment (F=9.77; P=.002; Cohen d=0.66; 95% CI 0.24-1.08) in the intervention group than in the wait-list control group. Comparisons between groups of the follow-up measures at 3 and 6 months yielded even stronger effects (3-month follow-up: F=17.40, P<.001, Cohen d=0.89, 95% CI 0.46-1.31; 6-month follow-up: F=14.63, P<.001, Cohen d=0.81, 95% CI 0.38-1.24). CONCLUSIONS: Hybrid web-based training programs may help reduce the symptoms of panic disorder and hence play an important role in improving health care for patients with this debilitating disorder. TRIAL REGISTRATION: German Clinical Trial Register DRKS00005223; https://tinyurl.com/f4zt5ran. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.1186/1745-6215-15-427.
Asunto(s)
Terapia Cognitivo-Conductual , Intervención basada en la Internet , Trastorno de Pánico , Adulto , Agorafobia/terapia , Humanos , Internet , Trastorno de Pánico/terapia , Resultado del Tratamiento , Listas de EsperaRESUMEN
BACKGROUND: Emerging evidence indicates the effectiveness of internet-based mobile-supported stress management interventions (iSMIs) in highly stressed employees. It is yet unclear, however, whether iSMIs are also effective without a preselection process in a universal prevention approach, which more closely resembles routine occupational health care. Moreover, evidence for whom iSMIs might be suitable and for whom not is scarce. OBJECTIVE: The aim of this study was to evaluate the iSMI GET.ON Stress in a universal prevention approach without baseline inclusion criteria and to examine the moderators of the intervention effects. METHODS: A total of 396 employees were randomly assigned to the intervention group or the 6-month waiting list control group. The iSMI consisted of 7 sessions and 1 booster session and offered no therapeutic guidance. Self-report data were assessed at baseline, 7 weeks, and at 6 months following randomization. The primary outcome was perceived stress. Several a priori defined moderators were explored as potential effect modifiers. RESULTS: Participants in the intervention group reported significantly lower perceived stress at posttreatment (d=0.71, 95% CI 0.51-0.91) and at 6-month follow-up (d=0.61, 95% CI 0.41-0.81) compared to those in the waiting list control group. Significant differences with medium-to-large effect sizes were found for all mental health and most work-related outcomes. Resilience (at 7 weeks, P=.04; at 6 months, P=.01), agreeableness (at 7 weeks, P=.01), psychological strain (at 6 months, P=.04), and self-regulation (at 6 months, P=.04) moderated the intervention effects. CONCLUSIONS: This study indicates that iSMIs can be effective in a broad range of employees with no need for preselection to achieve substantial effects. The subgroups that might not profit had extreme values on the respective measures and represented only a very small proportion of the investigated sample, thereby indicating the broad applicability of GET.ON Stress. TRIAL REGISTRATION: German Clinical Trials Register DRKS00005699; https://www.drks.de/DRKS00005699.
Asunto(s)
Intervención basada en la Internet , Servicios de Salud del Trabajador , Consejo , Humanos , Internet , Psicoterapia , Estrés Psicológico/prevención & controlRESUMEN
OBJECTIVE: Scaling an online screen that provides referrals may be key in closing the treatment gap for eating disorders (EDs), but we need to understand respondents' help-seeking intentions and behaviors after receiving screen results. This study reported on these constructs among respondents to the National Eating Disorders Association online screen who screened positive or at high risk for an ED. METHOD: Respondents completed the screen over 18 months (February 9, 2018-August 28, 2019). Those screening positive or at high risk for an ED (n = 343,072) had the option to provide data on help-seeking intentions (after screen completion) and behaviors (2-month follow-up). RESULTS: Of eligible respondents, 4.8% (n = 16,396) provided data on help-seeking intentions, with only 33.7% of those reporting they would seek help. Only 7.6% of eligible respondents opted in to the 2-month follow-up, with 10.6% of those completing it (n = 2,765). Overall, 8.9% of respondents to the follow-up reported being in treatment when they took the screen, 15.5% subsequently initiated treatment, and 75.5% did not initiate/were not already in treatment. DISCUSSION: Preliminary results suggest that among the small minority who provided data, only one-third expressed help-seeking intentions and 16% initiated treatment. Online screening should consider ways to increase respondents' motivation for and follow-through with care.
Asunto(s)
Trastornos de Alimentación y de la Ingestión de Alimentos/psicología , Tamizaje Masivo/métodos , Femenino , Conducta de Búsqueda de Ayuda , Humanos , Intención , Internet , Masculino , Encuestas y Cuestionarios , Estados UnidosRESUMEN
BACKGROUND: User dropout is a widespread concern in the delivery and evaluation of digital (ie, web and mobile apps) health interventions. Researchers have yet to fully realize the potential of the large amount of data generated by these technology-based programs. Of particular interest is the ability to predict who will drop out of an intervention. This may be possible through the analysis of user journey data-self-reported as well as system-generated data-produced by the path (or journey) an individual takes to navigate through a digital health intervention. OBJECTIVE: The purpose of this study is to provide a step-by-step process for the analysis of user journey data and eventually to predict dropout in the context of digital health interventions. The process is applied to data from an internet-based intervention for insomnia as a way to illustrate its use. The completion of the program is contingent upon completing 7 sequential cores, which include an initial tutorial core. Dropout is defined as not completing the seventh core. METHODS: Steps of user journey analysis, including data transformation, feature engineering, and statistical model analysis and evaluation, are presented. Dropouts were predicted based on data from 151 participants from a fully automated web-based program (Sleep Healthy Using the Internet) that delivers cognitive behavioral therapy for insomnia. Logistic regression with L1 and L2 regularization, support vector machines, and boosted decision trees were used and evaluated based on their predictive performance. Relevant features from the data are reported that predict user dropout. RESULTS: Accuracy of predicting dropout (area under the curve [AUC] values) varied depending on the program core and the machine learning technique. After model evaluation, boosted decision trees achieved AUC values ranging between 0.6 and 0.9. Additional handcrafted features, including time to complete certain steps of the intervention, time to get out of bed, and days since the last interaction with the system, contributed to the prediction performance. CONCLUSIONS: The results support the feasibility and potential of analyzing user journey data to predict dropout. Theory-driven handcrafted features increased the prediction performance. The ability to predict dropout at an individual level could be used to enhance decision making for researchers and clinicians as well as inform dynamic intervention regimens.
Asunto(s)
Intervención basada en la Internet/tendencias , Aprendizaje Automático/normas , Aplicaciones Móviles/normas , Adulto , Anciano , Femenino , Humanos , Masculino , Persona de Mediana Edad , Adulto JovenRESUMEN
BACKGROUND: Digital health interventions (DHIs) are poised to reduce target symptoms in a scalable, affordable, and empirically supported way. DHIs that involve coaching or clinical support often collect text data from 2 sources: (1) open correspondence between users and the trained practitioners supporting them through a messaging system and (2) text data recorded during the intervention by users, such as diary entries. Natural language processing (NLP) offers methods for analyzing text, augmenting the understanding of intervention effects, and informing therapeutic decision making. OBJECTIVE: This study aimed to present a technical framework that supports the automated analysis of both types of text data often present in DHIs. This framework generates text features and helps to build statistical models to predict target variables, including user engagement, symptom change, and therapeutic outcomes. METHODS: We first discussed various NLP techniques and demonstrated how they are implemented in the presented framework. We then applied the framework in a case study of the Healthy Body Image Program, a Web-based intervention trial for eating disorders (EDs). A total of 372 participants who screened positive for an ED received a DHI aimed at reducing ED psychopathology (including binge eating and purging behaviors) and improving body image. These users generated 37,228 intervention text snippets and exchanged 4285 user-coach messages, which were analyzed using the proposed model. RESULTS: We applied the framework to predict binge eating behavior, resulting in an area under the curve between 0.57 (when applied to new users) and 0.72 (when applied to new symptom reports of known users). In addition, initial evidence indicated that specific text features predicted the therapeutic outcome of reducing ED symptoms. CONCLUSIONS: The case study demonstrates the usefulness of a structured approach to text data analytics. NLP techniques improve the prediction of symptom changes in DHIs. We present a technical framework that can be easily applied in other clinical trials and clinical presentations and encourage other groups to apply the framework in similar contexts.
Asunto(s)
Promoción de la Salud/métodos , Procesamiento de Lenguaje Natural , Telemedicina/métodos , Femenino , Humanos , MasculinoRESUMEN
OBJECTIVE: The treatment gap between those who need and those who receive care for eating disorders is wide. Scaling a validated, online screener that makes individuals aware of the significance of their symptoms/behaviors is a crucial first step for increasing access to care. The objective of the current study was to determine the reach of disseminating an online eating disorder screener in partnership with the National Eating Disorders Association (NEDA), as well to examine the probable eating disorder diagnostic and risk breakdown of adult respondents. We also assessed receipt of any treatment. METHOD: Participants completed a validated eating disorder screen on the NEDA website over 6 months in 2017. RESULTS: Of 71,362 respondents, 91.0% were female, 57.7% 18-24 years, 89.6% non-Hispanic, and 84.7% White. Most (86.3%) screened positive for an eating disorder. In addition, 10.2% screened as high risk for the development of an eating disorder, and only 3.4% as not at risk. Of those screening positive for an eating disorder, 85.9% had never received treatment and only 3.0% were currently in treatment. DISCUSSION: The NEDA online screen may represent an important eating disorder detection tool, as it was completed by >71,000 adult respondents over just 6 months, the majority of whom screened positive for a clinical/subclinical eating disorder. The extremely high percentage of individuals screening positive for an eating disorder who reported not being in treatment suggests a wide treatment gap and the need to offer accessible, affordable, evidence-based intervention options, directly linked with screening.
Asunto(s)
Trastornos de Alimentación y de la Ingestión de Alimentos/diagnóstico , Adolescente , Adulto , Anciano , Educación a Distancia , Femenino , Humanos , Masculino , Tamizaje Masivo , Persona de Mediana Edad , Estados Unidos , Adulto JovenRESUMEN
In recent years, online screens have been commonly used to identify individuals who may have eating disorders (EDs), many of whom may be interested in treatment. We describe a new empirical approach that takes advantage of current evidence on empirically supported, effective treatments, while at the same time, uses modern statistical frameworks and experimental designs, data-driven science, and user-centered design methods to study ways to expand the reach of programs, enhance our understanding of what works for whom, and improve outcomes, overall and in subpopulations. The research would focus on individuals with EDs identified through screening and would use continuously monitored data, and interactions of interventions/approaches to optimize reach, uptake, engagement, and outcome. Outcome would be assessed at the population, rather than individual level. The idea worth researching is to determine if an optimization outcome model produces significantly higher rates of clinical improvement at a population level than do current approaches, in which traditional interventions are only offered to the few people who are interested in and able to access them.
Asunto(s)
Trastornos de Alimentación y de la Ingestión de Alimentos/diagnóstico , Trastornos de Alimentación y de la Ingestión de Alimentos/terapia , Humanos , Tamizaje Masivo , Proyectos de Investigación , Resultado del TratamientoRESUMEN
BACKGROUND: Web-based interventions are effective in reducing depression. However, the evidence for the cost-effectiveness of these interventions is scarce.AimsThe aim is to assess the cost-effectiveness of a web-based intervention (GET.ON M.E.D.) for individuals with diabetes and comorbid depression compared with an active control group receiving web-based psychoeducation. METHOD: We conducted a cost-effectiveness analysis with treatment response as the outcome and a cost-utility analysis with quality-adjusted life-years (QALYs) alongside a randomised controlled trial with 260 participants. RESULTS: At a willingness-to-pay ceiling of 5000 for a treatment response, the intervention has a 97% probability of being regarded as cost-effective compared with the active control group. If society is willing to pay 14 000 for an additional QALY, the intervention has a 51% probability of being cost-effective. CONCLUSIONS: This web-based intervention for individuals with diabetes and comorbid depression demonstrated a high probability of being cost-effective compared with an active control group.Declaration of interestS.N., D.D.E., D.L., M.B. and B.F. are stakeholders of the Institute for Online Health Trainings, which aims to transfer scientific knowledge related to this research into routine healthcare.
Asunto(s)
Terapia Cognitivo-Conductual , Análisis Costo-Beneficio , Depresión , Trastorno Depresivo , Diabetes Mellitus Tipo 1 , Diabetes Mellitus Tipo 2 , Evaluación de Resultado en la Atención de Salud , Telemedicina , Adulto , Terapia Cognitivo-Conductual/economía , Terapia Cognitivo-Conductual/métodos , Comorbilidad , Depresión/economía , Depresión/epidemiología , Depresión/terapia , Trastorno Depresivo/economía , Trastorno Depresivo/epidemiología , Trastorno Depresivo/terapia , Diabetes Mellitus Tipo 1/economía , Diabetes Mellitus Tipo 1/epidemiología , Diabetes Mellitus Tipo 2/economía , Diabetes Mellitus Tipo 2/epidemiología , Femenino , Humanos , Internet , Masculino , Persona de Mediana Edad , Años de Vida Ajustados por Calidad de Vida , Telemedicina/economía , Telemedicina/métodosRESUMEN
BACKGROUND: Different treatment alternatives exist for psychological disorders. Both clinical and cost effectiveness of treatment are crucial aspects for policy makers, therapists, and patients and thus play major roles for healthcare decision-making. At the start of an intervention, it is often not clear which specific individuals benefit most from a particular intervention alternative or how costs will be distributed on an individual patient level. OBJECTIVE: This study aimed at predicting the individual outcome and costs for patients before the start of an internet-based intervention. Based on these predictions, individualized treatment recommendations can be provided. Thus, we expand the discussion of personalized treatment recommendation. METHODS: Outcomes and costs were predicted based on baseline data of 350 patients from a two-arm randomized controlled trial that compared treatment as usual and blended therapy for depressive disorders. For this purpose, we evaluated various machine learning techniques, compared the predictive accuracy of these techniques, and revealed features that contributed most to the prediction performance. We then combined these predictions and utilized an incremental cost-effectiveness ratio in order to derive individual treatment recommendations before the start of treatment. RESULTS: Predicting clinical outcomes and costs is a challenging task that comes with high uncertainty when only utilizing baseline information. However, we were able to generate predictions that were more accurate than a predefined reference measure in the shape of mean outcome and cost values. Questionnaires that include anxiety or depression items and questions regarding the mobility of individuals and their energy levels contributed to the prediction performance. We then described how patients can be individually allocated to the most appropriate treatment type. For an incremental cost-effectiveness threshold of 25,000 /quality-adjusted life year, we demonstrated that our recommendations would have led to slightly worse outcomes (1.98%), but with decreased cost (5.42%). CONCLUSIONS: Our results indicate that it was feasible to provide personalized treatment recommendations at baseline and thus allocate patients to the most beneficial treatment type. This could potentially lead to improved decision-making, better outcomes for individuals, and reduced health care costs.
Asunto(s)
Análisis Costo-Beneficio/métodos , Costos de la Atención en Salud/tendencias , Aprendizaje Automático/tendencias , Femenino , Humanos , Masculino , Encuestas y Cuestionarios , Resultado del TratamientoRESUMEN
OBJECTIVE: This randomised controlled trial (RCT) aimed to evaluate the efficacy of a self-guided internet-based stress management intervention (iSMI) for employees compared to a 6-month wait-list control group (WLC) with full access for both groups to treatment as usual. METHOD: A sample of 264 employees with elevated symptoms of perceived stress (Perceived Stress Scale, PSS-10 ≥22) was randomly assigned to either the iSMI or to the WLC. The iSMI consisted of seven sessions and one booster session including problem-solving and emotion regulation techniques. Self-report data were assessed at baseline, at 7â weeks and at 6â months following randomisation. The primary outcome was perceived stress (PSS-10). The secondary outcomes included other relevant mental-related and work-related health outcomes. Data were analysed based on intention-to-treat principles. RESULTS: The iSMI participants showed a significantly higher reduction in perceived stress from baseline to post-treatment at 7â weeks (d=0.96, 95% CI 0.70 to 1.21) and to the 6-month follow-up (d=0.65, 95% CI 0.40 to 0.89) compared to the WLC. Significant differences with small to moderate effect sizes were also found for depression, anxiety, emotional exhaustion, sleeping problems, worrying, mental health-related quality of life, psychological detachment, emotion regulation skills and presenteeism, in favour of the experimental group. At the 6â -month follow-up, all outcomes remained significantly better for the experimental group with the exception of work engagement, physical health-related quality of life and absenteeism, which were not found to significantly differ between the iSMI and WLC groups. CONCLUSIONS: The iSMI investigated in this study was found to be effective in reducing typical mental-related and work-related health symptoms of stressed employees. Internet-based self-guided interventions could be an acceptable, effective and potentially cost-effective approach to reduce the negative consequences associated with work-related stress.
Asunto(s)
Teléfono Celular , Internet , Enfermedades Profesionales/prevención & control , Exposición Profesional/efectos adversos , Psicoterapia/métodos , Estrés Psicológico/terapia , Telemedicina/métodos , Absentismo , Adulto , Emociones , Femenino , Humanos , Masculino , Trastornos Mentales/terapia , Salud Mental , Persona de Mediana Edad , Enfermedades Profesionales/psicología , Solución de Problemas , Calidad de Vida , Autocuidado , Autoinforme , Trastornos del Sueño-Vigilia/terapia , Resultado del TratamientoRESUMEN
Objective: This study proposes a way of increasing dataset sizes for machine learning tasks in Internet-based Cognitive Behavioral Therapy through pooling interventions. To this end, it (1) examines similarities in user behavior and symptom data among online interventions for patients with depression, social anxiety, and panic disorder and (2) explores whether these similarities suffice to allow for pooling the data together, resulting in more training data when prediction intervention dropout. Methods: A total of 6418 routine care patients from the Internet Psychiatry in Stockholm are analyzed using (1) clustering and (2) dropout prediction models. For the latter, prediction models trained on each individual intervention's data are compared to those trained on all three interventions pooled into one dataset. To investigate if results vary with dataset size, the prediction is repeated using small and medium dataset sizes. Results: The clustering analysis identified three distinct groups that are almost equally spread across interventions and are instead characterized by different activity levels. In eight out of nine settings investigated, pooling the data improves prediction results compared to models trained on a single intervention dataset. It is further confirmed that models trained on small datasets are more likely to overestimate prediction results. Conclusion: The study reveals similar patterns of patients with depression, social anxiety, and panic disorder regarding online activity and intervention dropout. As such, this work offers pooling different interventions' data as a possible approach to counter the problem of small dataset sizes in psychological research.
RESUMEN
Research in machine learning (ML) algorithms using natural behavior (i.e., text, audio, and video data) suggests that these techniques could contribute to personalization in psychology and psychiatry. However, a systematic review of the current state of the art is missing. Moreover, individual studies often target ML experts who may overlook potential clinical implications of their findings. In a narrative accessible to mental health professionals, we present a systematic review conducted in 5 psychology and 2 computer science databases. We included 128 studies that assessed the predictive power of ML algorithms using text, audio, and/or video data in the prediction of anxiety and posttraumatic stress disorder. Most studies (n = 87) were aimed at predicting anxiety, while the remainder (n = 41) focused on posttraumatic stress disorder. They were mostly published since 2019 in computer science journals and tested algorithms using text (n = 72) as opposed to audio or video. Studies focused mainly on general populations (n = 92) and less on laboratory experiments (n = 23) or clinical populations (n = 13). Methodological quality varied, as did reported metrics of the predictive power, hampering comparison across studies. Two-thirds of studies, which focused on both disorders, reported acceptable to very good predictive power (including high-quality studies only). The results of 33 studies were uninterpretable, mainly due to missing information. Research into ML algorithms using natural behavior is in its infancy but shows potential to contribute to diagnostics of mental disorders, such as anxiety and posttraumatic stress disorder, in the future if standardization of methods, reporting of results, and research in clinical populations are improved.
RESUMEN
With the need for psychological help long exceeding the supply, finding ways of scaling, and better allocating mental health support is a necessity. This paper contributes by investigating how to best predict intervention dropout and failure to allow for a need-based adaptation of treatment. We systematically compare the predictive power of different text representation methods (metadata, TF-IDF, sentiment and topic analysis, and word embeddings) in combination with supplementary numerical inputs (socio-demographic, evaluation, and closed-question data). Additionally, we address the research gap of which ML model types - ranging from linear to sophisticated deep learning models - are best suited for different features and outcome variables. To this end, we analyze nearly 16.000 open-text answers from 849 German-speaking users in a Digital Mental Health Intervention (DMHI) for stress. Our research proves that - contrary to previous findings - there is great promise in using neural network approaches on DMHI text data. We propose a task-specific LSTM-based model architecture to tackle the challenge of long input sequences and thereby demonstrate the potential of word embeddings (AUC scores of up to 0.7) for predictions in DMHIs. Despite the relatively small data set, sequential deep learning models, on average, outperform simpler features such as metadata and bag-of-words approaches when predicting dropout. The conclusion is that user-generated text of the first two sessions carries predictive power regarding patients' dropout and intervention failure risk. Furthermore, the match between the sophistication of features and models needs to be closely considered to optimize results, and additional non-text features increase prediction results. Supplementary Information: The online version contains supplementary material available at 10.1007/s41666-023-00148-z.
RESUMEN
Introduction: Personalization is a much-discussed approach to improve adherence and outcomes for Digital Mental Health interventions (DMHIs). Yet, major questions remain open, such as (1) what personalization is, (2) how prevalent it is in practice, and (3) what benefits it truly has. Methods: We address this gap by performing a systematic literature review identifying all empirical studies on DMHIs targeting depressive symptoms in adults from 2015 to September 2022. The search in Pubmed, SCOPUS and Psycinfo led to the inclusion of 138 articles, describing 94 distinct DMHIs provided to an overall sample of approximately 24,300 individuals. Results: Our investigation results in the conceptualization of personalization as purposefully designed variation between individuals in an intervention's therapeutic elements or its structure. We propose to further differentiate personalization by what is personalized (i.e., intervention content, content order, level of guidance or communication) and the underlying mechanism [i.e., user choice, provider choice, decision rules, and machine-learning (ML) based approaches]. Applying this concept, we identified personalization in 66% of the interventions for depressive symptoms, with personalized intervention content (32% of interventions) and communication with the user (30%) being particularly popular. Personalization via decision rules (48%) and user choice (36%) were the most used mechanisms, while the utilization of ML was rare (3%). Two-thirds of personalized interventions only tailored one dimension of the intervention. Discussion: We conclude that future interventions could provide even more personalized experiences and especially benefit from using ML models. Finally, empirical evidence for personalization was scarce and inconclusive, making further evidence for the benefits of personalization highly needed. Systematic Review Registration: Identifier: CRD42022357408.
RESUMEN
Background Self-reported client assessments during online treatments enable the development of statistical models for the prediction of client improvement and symptom development. Evaluation of these models is mandatory to ensure their validity. Methods For this purpose, we suggest besides a model evaluation based on study data the use of a simulation analysis. The simulation analysis provides insight into the model performance and enables to analyse reasons for a low predictive accuracy. In this study, we evaluate a temporal causal model (TCM) and show that it does not provide reliable predictions of clients' future mood levels. Results Based on the simulation analysis we investigate the potential reasons for the low predictive performance, for example, noisy measurements and sampling frequency. We conclude that the analysed TCM in its current form is not sufficient to describe the underlying psychological processes. Conclusions The results demonstrate the importance of model evaluation and the benefit of a simulation analysis. The current manuscript provides practical guidance for conducting model evaluation including simulation analysis.
Asunto(s)
Afecto , Intervención basada en la Internet , Servicios de Salud Mental , Modelos Estadísticos , Autoinforme/estadística & datos numéricos , Interacción Social , Red Social , Adulto , Simulación por Computador , Evaluación Ecológica Momentánea , HumanosRESUMEN
BACKGROUND: Panic disorder with and without agoraphobia (PD) is a common psychological disorder. Internet-based interventions have the potential to offer highly scalable low-threshold evidence-based care to people suffering from PD. GET.ON Panic is a newly developed internet-based intervention addressing symptoms of PD. In order to transfer the training into the daily life of the individuals, we integrated mobile components in the training and created a so-called hybrid online training. The development and beta-testing of such a training requires a novel interdisciplinary approach between IT specialists and psychologists. From this point of view, we would like to share our experiences in this exploratory paper. METHODS: This initial feasibility study (N = 10) offers, on the one hand, a brief overview of the interdisciplinary development phase of the mobile application and on the other hand, provides first insights into the usage, usability and acceptance of this mobile application using qualitative interview data as well quantitative measures of 8 completing participants. For these reasons, we used a pre-posttest design without a control group. Furthermore, we present initial clinical outcomes of the intervention on e.g. panic symptom severity, depressive symptoms as well additional anxiety measures. Finally, we end with implications for further research in the relatively new field of mobile mental health. RESULTS: Overall, usability, user satisfaction, motivational value and technology acceptance of the app were perceived as high. The usage of app components was diverse: The use of interoceptive exposure exercises and daily summaries on anxiety and mood was highest while using in-vivo exposure exercises and monitoring panic symptoms was perceived as difficult. Furthermore, participants showed after the training less clinical symptoms as at baseline-assessment. DISCUSSION: The current feasibility study contributes to an in-depth understanding of the potential of mobile technology in e-mental health. Overall, the GET.ON Panic app appears to be an acceptable and motivational part of a CBT-based hybrid online training for PD that has the potential to promote training success. After some suggested adjustments have been made, the efficacy should be investigated in a randomized controlled trial.