RESUMO
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.
RESUMO
BACKGROUND: Systemic sclerosis (scleroderma; SSc) is a rare autoimmune connective tissue disease. Functional impairment of hands is common. The Scleroderma Patient-centered Intervention Network (SPIN)-HAND trial compared effects of offering access to an online self-guided hand exercise program to usual care on hand function (primary) and functional health outcomes (secondary) in people with SSc with at least mild hand function limitations. METHODS: The pragmatic, two-arm, parallel-group cohort multiple randomized controlled trial was embedded in the SPIN Cohort. Cohort participants with Cochin Hand Function Scale (CHFS) scores ≥ 3 and who indicated interest in using the SPIN-HAND Program were randomized (3:2 ratio) to an offer of program access or to usual care (targeted N = 586). The SPIN-HAND program consists of 4 modules that address (1) thumb flexibility and strength; (2) finger bending; (3) finger extension; and (4) wrist flexibility and strength. The primary outcome analysis compared CHFS scores 3 months post-randomization between participants offered versus not offered the program. Secondary outcomes were CHFS scores 6 months post-randomization and functional health outcomes (Patient-Reported Outcomes Measurement Information System profile version 2.0 domain scores) 3 and 6 months post-randomization. RESULTS: In total, 466 participants were randomized to intervention offer (N = 280) or usual care (N = 186). Of 280 participants offered the intervention, 170 (61%) consented to access the program. Of these, 117 (69%) viewed at least one hand exercise instruction video and 77 (45%) logged into the program website at least 3 times. In intent-to-treat analyses, CHFS scores were 1.2 points lower (95% CI - 2.8 to 0.3) for intervention compared to usual care 3 months post-randomization and 0.1 points lower (95% CI - 1.8 to 1.6 points) 6 months post-randomization. There were no statistically significant differences in other outcomes. CONCLUSION: The offer to use the SPIN-HAND Program did not improve hand function. Low offer uptake, program access, and minimal usage among those who accessed the program limited our ability to determine if using the program would improve function. To improve engagement, the program could be tested in a group format or as a resource to support care provided by a physical or occupational therapist. TRIAL REGISTRATION: NCT03419208 . Registered on February 1, 2018.
Assuntos
Escleroderma Sistêmico , Humanos , Escleroderma Sistêmico/diagnóstico , Escleroderma Sistêmico/terapia , Terapia por Exercício , Extremidade Superior , Assistência Centrada no PacienteRESUMO
Purpose: The Scleroderma Patient-centered Intervention Network (SPIN) online hand exercise program (SPIN-HAND), is an online self-help program of hand exercises designed to improve hand function for people with scleroderma. The objective of this feasibility trial was to evaluate aspects of feasibility for conducting a full-scale randomized controlled trial of the SPIN-HAND program. Materials and Methods: The feasibility trial was embedded in the SPIN cohort and utilized the cohort multiple randomized controlled trial (cmRCT) design. In the cmRCT design, at the time of cohort enrollment, cohort participants consent to be assessed for trial eligibility and randomized prior to being informed about trials conducted using the cohort. When trials were conducted in the cohort, participants randomized to the intervention were informed and consented to access the intervention. Participants randomized to control were not informed that they have not received an intervention. All participants eligible and randomized to participate in the trial were included in analyses on an intent-to-treat basis. Cohort participants with a Cochin Hand Function Scale score ≥ 3/90 and an interest in using an online hand-exercise intervention were randomized (1:1 ratio) to be offered as usual care plus the SPIN-HAND Program or usual care for 3 months. User satisfaction was assessed with semi-structured interviews. Results: Of the 40 randomized participants, 24 were allocated to SPIN-HAND and 16 to usual care. Of 24 participants randomized to be offered SPIN-HAND, 15 (63%) consented to use the program. Usage of SPIN-HAND content among the 15 participants who consented to use the program was low; only five (33%) logged in more than twice. Participants found the content relevant and easy to understand (satisfaction rating 8.5/10, N = 6). Automated eligibility and randomization procedures via the SPIN Cohort platform functioned properly. The required technical support was minimal. Conclusions: Trial methodology functioned as designed, and the SPIN-HAND Program was feasibly delivered; however, the acceptance of the offer and use of program content among accepters were low. Adjustments to information provided to potential participants will be implemented in the full-scale SPIN-HAND trial to attempt to increase offer acceptance.
Assuntos
Terapia Comportamental , Terapia por Exercício , Assistência Centrada no Paciente , Escleroderma Sistêmico , Humanos , Estudos de Viabilidade , Assistência Centrada no Paciente/métodos , Projetos de Pesquisa , Escleroderma Sistêmico/reabilitação , TelerreabilitaçãoRESUMO
BACKGROUND: The Scleroderma Patient-centered Intervention Network (SPIN) developed an online self-management program (SPIN-SELF) designed to improve disease-management self-efficacy in people with systemic sclerosis (SSc, or scleroderma). The aim of this study was to evaluate feasibility aspects for conducting a full-scale randomized controlled trial (RCT) of the SPIN-SELF Program. METHODS: This feasibility trial was embedded in the SPIN Cohort and utilized the cohort multiple RCT design. In this design, at the time of cohort enrollment, cohort participants consent to be assessed for trial eligibility and randomized prior to being informed about the trial. Participants in the intervention arm are informed and provide consent, but not the control group. Forty English-speaking SPIN Cohort participants from Canada, the USA, or the UK with low disease-management self-efficacy (Self-Efficacy for Managing Chronic Disease Scale [SEMCD] score ≤ 7) who were interested in using an online self-management program were randomized (3:2 ratio) to be offered the SPIN-SELF Program or usual care for 3 months. Program usage was examined via automated usage logs. User satisfaction was assessed with semi-structured interviews. Trial personnel time requirements and implementation challenges were logged. RESULTS: Of 40 SPIN Cohort participants randomized, 26 were allocated to SPIN-SELF and 14 to usual care. Automated eligibility and randomization procedures via the SPIN Cohort platform functioned properly, except that two participants with SEMCD scores > 7 (scores of 7.2 and 7.3, respectively) were included, which was caused by a system programming error that rounded SEMCD scores. Of 26 SPIN Cohort participants offered the SPIN-SELF Program, only 9 (35%) consented to use the program. Usage logs showed that use of the SPIN-SELF Program was low: 2 of 9 users (22%) logged into the program only once (median = 3), and 4 of 9 (44%) accessed none or only 1 of the 9 program's modules (median = 2). CONCLUSIONS: The results of this study will lead to substantial changes for the planned full-scale RCT of the SPIN-SELF Program that we will incorporate into a planned additional feasibility trial with progression to a full-scale trial. These changes include transitioning to a conventional RCT design with pre-randomization consent and supplementing the online self-help with peer-facilitated videoconference-based groups to enhance engagement. TRIAL REGISTRATION: clinicaltrials.gov , NCT03914781 . Registered 16 April 2019.
RESUMO
BACKGROUND: Systemic sclerosis (scleroderma; SSc) is a rare autoimmune connective tissue disease. We completed an initial feasibility trial of an online self-administered version of the Scleroderma Patient-centered Intervention Network Self-Management (SPIN-SELF) Program using the cohort multiple randomized controlled trial (RCT) design. Due to low intervention offer uptake, we will conduct a new feasibility trial with progression to full-scale trial, using a two-arm parallel, partially nested RCT design. The SPIN-SELF Program has also been revised to include facilitator-led videoconference group sessions in addition to online material. We will test the group-based intervention delivery format, then evaluate the effect of the SPIN-SELF Program on disease management self-efficacy (primary) and patient activation, social appearance anxiety, and functional health outcomes (secondary). METHODS: This study is a feasibility trial with progression to full-scale RCT, pending meeting pre-defined criteria, of the SPIN-SELF Program. Participants will be recruited from the ongoing SPIN Cohort ( http://www.spinsclero.com/en/cohort ) and via social media and partner patient organizations. Eligible participants must have SSc and low to moderate disease management self-efficacy (Self-Efficacy for Managing Chronic Disease (SEMCD) Scale score ≤ 7.0). Participants will be randomized (1:1 allocation) to the group-based SPIN-SELF Program or usual care for 3 months. The primary outcome in the full-scale trial will be disease management self-efficacy based on SEMCD Scale scores at 3 months post-randomization. Secondary outcomes include SEMCD scores 6 months post-randomization plus patient activation, social appearance anxiety, and functional health outcomes at 3 and 6 months post-randomization. We will include 40 participants to assess feasibility. At the end of the feasibility portion, stoppage criteria will be used to determine if the trial procedures or SPIN-SELF Program need important modifications, thereby requiring a re-set for the full-scale trial. Otherwise, the full-scale RCT will proceed, and outcome data from the feasibility portion will be utilized in the full-scale trial. In the full-scale RCT, 524 participants will be recruited. DISCUSSION: The SPIN-SELF Program may improve disease management self-efficacy, patient activation, social appearance anxiety, and functional health outcomes in people with SSc. SPIN works with partner patient organizations around the world to disseminate its programs free-of-charge. TRIAL REGISTRATION: ClinicalTrials.gov NCT04246528 . Registered on 27 January 2020.
Assuntos
COVID-19 , Escleroderma Sistêmico , Autogestão , Estudos de Viabilidade , Humanos , Assistência Centrada no Paciente , Ensaios Clínicos Controlados Aleatórios como AssuntoRESUMO
BACKGROUND: Systemic sclerosis (SSc), or scleroderma, is a rare disease that often results in significant disruptions to activities of daily living and can negatively affect physical and psychological well-being. Because there is no known cure, SSc treatment focuses on reducing symptoms and disability and improving health-related quality of life (HRQoL). Self-management programs are known to increase self-efficacy for disease management in many chronic diseases. The Scleroderma Patient-centered Intervention Network (SPIN) developed a Web-based self-management program (SPIN self-management; SPIN-SELF) to increase self-efficacy for disease management and to improve HRQoL for patients with SSc. OBJECTIVE: The proposed study aims to assess the feasibility of conducting a full-scale randomized controlled trial (RCT) of the SPIN-SELF program by evaluating the trial implementation processes, required resources and management, scientific aspects, and participant acceptability and usage of the SPIN-SELF program. METHODS: The SPIN-SELF feasibility trial will be conducted via the SPIN Cohort. The SPIN Cohort was developed as a framework for embedded pragmatic trials using the cohort multiple RCT design. In total, 40 English-speaking SPIN Cohort participants with low disease management self-efficacy (Self-Efficacy for Managing Chronic Disease Scale score ≤7), who have indicated interest in using a Web-based self-management program, will be randomized with a 3:2 ratio into the SPIN-SELF program or usual care for 3 months. Feasibility outcomes include trial implementation processes, required resources and management, scientific aspects, and patient acceptability and usage of the SPIN-SELF program. RESULTS: Enrollment of the 40 participants occurred between July 5, 2019, and July 27, 2019. By November 25, 2019, data collection of trial outcomes was completed. Data analysis is underway, and results are expected to be published in 2020. CONCLUSIONS: The SPIN-SELF program is a self-help tool that may improve disease-management self-efficacy and improve HRQoL in patients with SSc. The SPIN-SELF feasibility trial will ensure that trial methodology is robust, feasible, and consistent with trial participant expectations. The results will guide adjustments that need to be implemented before undertaking a full-scale RCT of the SPIN-SELF program. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/16799.
RESUMO
INTRODUCTION: Sentiment analysis may be a useful technique to derive a user's emotional state from free text input, allowing for more empathic automated feedback in online cognitive behavioral therapy (iCBT) interventions for psychological disorders such as depression. As guided iCBT is considered more effective than unguided iCBT, such automated feedback may help close the gap between the two. The accuracy of automated sentiment analysis is domain dependent, and it is unclear how well the technology is applicable to iCBT. This paper presents an empirical study in which automated sentiment analysis by an algorithm for the Dutch language is validated against human judgment. METHODS: A total of 493 iCBT user texts were evaluated on overall sentiment and the presence of five specific emotions by an algorithm, and by 52 psychology students who evaluated 75 randomly selected texts each, providing about eight human evaluations per text. Inter-rater agreement (IRR) between algorithm and humans, and humans among each other, was analyzed by calculating the intra-class correlation under a numerical interpretation of the data, and Cohen's kappa, and Krippendorff's alpha under a categorical interpretation. RESULTS: All analyses indicated moderate agreement between the algorithm and average human judgment with respect to evaluating overall sentiment, and low agreement for the specific emotions. Somewhat surprisingly, the same was the case for the IRR among human judges, which means that the algorithm performed about as well as a randomly selected human judge. Thus, considering average human judgment as a benchmark for the applicability of automated sentiment analysis, the technique can be considered for practical application. DISCUSSION/CONCLUSION: The low human-human agreement on the presence of emotions may be due to the nature of the texts, it may simply be difficult for humans to agree on the presence of the selected emotions, or perhaps trained therapists would have reached more consensus. Future research may focus on validating the algorithm against a more solid benchmark, on applying the algorithm in an application in which empathic feedback is provided, for example, by an embodied conversational agent, or on improving the algorithm for the iCBT domain with a bottom-up machine learning approach.
RESUMO
Recent developments in mobile technology, sensor devices, and artificial intelligence have created new opportunities for mental health care research. Enabled by large datasets collected in e-mental health research and practice, clinical researchers and members of the data mining community increasingly join forces to build predictive models for health monitoring, treatment selection, and treatment personalization. This paper aims to bridge the historical and conceptual gaps between the distant research domains involved in this new collaborative research by providing a conceptual model of common research goals. We first provide a brief overview of the data mining field and methods used for predictive modeling. Next, we propose to characterize predictive modeling research in mental health care on three dimensions: 1) time, relative to treatment (i.e., from screening to post-treatment relapse monitoring), 2) types of available data (e.g., questionnaire data, ecological momentary assessments, smartphone sensor data), and 3) type of clinical decision (i.e., whether data are used for screening purposes, treatment selection or treatment personalization). Building on these three dimensions, we introduce a framework that identifies four model types that can be used to classify existing and future research and applications. To illustrate this, we use the framework to classify and discuss published predictive modeling mental health research. Finally, in the discussion, we reflect on the next steps that are required to drive forward this promising new interdisciplinary field.
RESUMO
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.
Assuntos
Análise Custo-Benefício/métodos , Custos de Cuidados de Saúde/tendências , Aprendizado de Máquina/tendências , Feminino , Humanos , Masculino , Inquéritos e Questionários , Resultado do TratamentoRESUMO
In this paper, we explore the potential of predicting therapy success for patients in mental health care. Such predictions can eventually improve the process of matching effective therapy types to individuals. In the EU project E-COMPARED, a variety of information is gathered about patients suffering from depression. We use this data, where 276 patients received treatment as usual and 227 received blended treatment, to investigate to what extent we are able to predict therapy success. We utilize different encoding strategies for preprocessing, varying feature selection techniques, and different statistical procedures for this purpose. Significant predictive power is found with average AUC values up to 0.7628 for treatment as usual and 0.7765 for blended treatment. Adding daily assessment data for blended treatment does currently not add predictive accuracy. Cost effectiveness analysis is needed to determine the added potential for real-world applications.
RESUMO
Recent developments in the field of sensor devices provide new possibilities to measure a variety of health related aspects in a precise and fine-grained manner. Subsequently, more empirical data will be generated than ever before. While this greatly improves the opportunities for creating accurate predictive models, other types of models besides the more traditional machine learning approaches can provide insights into temporal relationships in the data. Models that express temporal relationships between states in a mathematical manner are examples of such models. However, the evaluation methods traditionally used in the field of predictive modeling are not appropriate for those models, making it difficult to distinguish them in terms of validity. Appropriate assessment methodology is therefore necessary to drive the research of mathematical modeling forward. In this paper we investigate the applicability of such a formalized method. The method takes into account important model aspects, namely descriptive and predictive capability, parameter sensitivity and model complexity. As a case study the method is applied to a mathematical model in the domain of mental health, showing that the method generates useful insights into the behavior of the model.