Smart Sensing Enhanced Diagnostic Expert Systems

Terhorst, Yannik; Knauer, Johannes; Baumeister, Harald

doi:10.1007/978-3-030-98546-2_24

Cited by 15 publications

(12 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For clinical practice our results support the implementation of scalable AFI in an online video format to increase the acceptance of smart sensing in patients. Given the time- and location independent nature of such AFI, they may become a feasible and effective way to implement smart sensing at various stages before (e.g., installation and symptom tracking before treatment for a data informed decision and recommendation of psychotherapeutic modules), during (e.g., to monitor treatment progress via smart sensing), and after psychotherapy [e.g., using smart sensing to recognize re-establishing dysfunctional behavior patterns and initiate just-in-time interventions ( 3 )]. That said, the therapeutic relationship between the patient and therapist ( 49 ) represents one of the most crucial therapeutic factors in psychotherapy.…”

Section: Discussionmentioning

confidence: 99%

“…Furthermore, the technology enables more objective data collection in the natural life context of patients leading to high ecological validity and the elimination of common biases such as recall biases or social desirability, which have long posed challenges in psychotherapy ( 10 , 11 ). The gathered information can be integrated at every stage of the psychotherapeutic process: diagnosis and problem analysis, treatment planning, implementation of interventions, monitoring, and the evaluation of the treatment process ( 3 , 12 ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing the acceptance of smart sensing in psychotherapy patients: findings from a randomized controlled trial

Rottstädt,

Becker,

Wilz

et al. 2024

Front. Digit. Health

Self Cite

View full text Add to dashboard Cite

ObjectiveSmart sensing has the potential to make psychotherapeutic treatments more effective. It involves the passive analysis and collection of data generated by digital devices. However, acceptance of smart sensing among psychotherapy patients remains unclear. Based on the unified theory of acceptance and use of technology (UTAUT), this study investigated (1) the acceptance toward smart sensing in a sample of psychotherapy patients (2) the effectiveness of an acceptance facilitating intervention (AFI) and (3) the determinants of acceptance.MethodsPatients (N = 116) were randomly assigned to a control group (CG) or intervention group (IG). The IG received a video AFI on smart sensing, and the CG a control video. An online questionnaire was used to assess acceptance of smart sensing, performance expectancy, effort expectancy, facilitating conditions and social influence. The intervention effects of the AFI on acceptance were investigated. The determinants of acceptance were analyzed with structural equation modeling (SEM).ResultsThe IG showed a moderate level of acceptance (M = 3.16, SD = 0.97), while the CG showed a low level (M = 2.76, SD = 1.0). The increase in acceptance showed a moderate effect in the intervention group (p < .05, d = 0.4). For the IG, performance expectancy (M = 3.92, SD = 0.7), effort expectancy (M = 3.90, SD = 0.98) as well as facilitating conditions (M = 3.91, SD = 0.93) achieved high levels. Performance expectancy (γ = 0.63, p < .001) and effort expectancy (γ = 0.36, p < .001) were identified as the core determinants of acceptance explaining 71.1% of its variance. The fit indices supported the model's validity (CFI = .95, TLI = .93, RMSEA = .08).DiscussionThe low acceptance in the CG suggests that enhancing the acceptance should be considered, potentially increasing the use and adherence to the technology. The current AFI was effective in doing so and is thus a promising approach. The IG also showed significantly higher performance expectancy and social influence and, in general, a strong expression of the UTAUT factors. The results support the applicability of the UTAUT in the context of smart sensing in a clinical sample, as the included predictors were able to explain a great amount of the variance of acceptance.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Enhancing the acceptance of smart sensing in psychotherapy patients: findings from a randomized controlled trial

Rottstädt,

Becker,

Wilz

et al. 2024

Front. Digit. Health

Self Cite

View full text Add to dashboard Cite

show abstract

“…in smartphones, smart watches and other wearables), might be promising to further augment ML algorithms in their predictive accuracy and maximize the potential of complex data and ML. 34 , 67 – 75 However, this goes hand in hand with higher effort and costs to collect such data. In particular, the QIDS-16 might be suited to provide ML-optimized MDE predictions even without such an extension.…”

Section: Discussionmentioning

confidence: 99%

“…physicians), who have access to various sources of health records, the combination of different sources in an ML augmented expert system assisting them in the diagnosis of mental (and other) disorders could be feasible and promising. 75 …”

Section: Discussionmentioning

confidence: 99%

Optimizing the predictive power of depression screenings using machine learning

Terhorst,

Sander,

Ebert

et al. 2023

DIGITAL HEALTH

Self Cite

View full text Add to dashboard Cite

Objective Mental health self-report and clinician-rating scales with diagnoses defined by sum-score cut-offs are often used for depression screening. This study investigates whether machine learning (ML) can detect major depressive episodes (MDE) based on screening scales with higher accuracy than best-practice clinical sum-score approaches. Methods Primary data was obtained from two RCTs on the treatment of depression. Ground truth were DSM 5 MDE diagnoses based on structured clinical interviews (SCID) and PHQ-9 self-report, clinician-rated QIDS-16, and HAM-D-17 were predictors. ML models were trained using 10-fold cross-validation. Performance was compared against best-practice sum-score cut-offs. Primary outcome was the Area Under the Curve (AUC) of the Receiver Operating Characteristic curve. DeLong's test with bootstrapping was used to test for differences in AUC. Secondary outcomes were balanced accuracy, precision, recall, F1-score, and number needed to diagnose (NND). Results A total of k = 1030 diagnoses (no diagnosis: k = 775; MDE: k = 255) were included. ML models achieved an AUCQIDS-16 = 0.94, AUCHAM-D-17 = 0.88, and AUCPHQ-9 = 0.83 in the testing set. ML AUC was significantly higher than sum-score cut-offs for QIDS-16 and PHQ-9 ( ps ≤ 0.01; HAM_D-17: p = 0.847). Applying optimal prediction thresholds, QIDS-16 classifier achieved clinically relevant improvements (Δbalanced accuracy = 8%, ΔF1-score = 14%, ΔNND = 21%). Differences for PHQ_9 and HAM-D-17 were marginal. Conclusions ML augmented depression screenings could potentially make a major contribution to improving MDE diagnosis depending on questionnaire (e.g., QIDS-16). Confirmatory studies are needed before ML enhanced screening can be implemented into routine care practice.

show abstract

“…Given that data is collected from various sources through multiple channels and in diverse formats, it becomes crucial to design an interoperable framework that ensures a smooth and secure process flow before the actual manipulation by ensemble models. While accentuating the significance of reusability, automated machine learning prediction, and human decision support ( Alreshidi & Ahmad, 2019 ), it is imperative to take into account the explainability feature of these decision support systems, which empower human experts to navigate and interpret the decision-making process ( Terhorst, Knauer & Baumeister, 2023 ).…”

Section: Introductionmentioning

confidence: 99%

An adaptive data-driven architecture for mental health care applications

Sundaram,

Subramaniam,

Ab Hamid

et al. 2024

PeerJ

View full text Add to dashboard Cite

Background In the current era of rapid technological innovation, our lives are becoming more closely intertwined with digital systems. Consequently, every human action generates a valuable repository of digital data. In this context, data-driven architectures are pivotal for organizing, manipulating, and presenting data to facilitate positive computing through ensemble machine learning models. Moreover, the COVID-19 pandemic underscored a substantial need for a flexible mental health care architecture. This architecture, inclusive of machine learning predictive models, has the potential to benefit a larger population by identifying individuals at a heightened risk of developing various mental disorders. Objective Therefore, this research aims to create a flexible mental health care architecture that leverages data-driven methodologies and ensemble machine learning models. The objective is to proficiently structure, process, and present data for positive computing. The adaptive data-driven architecture facilitates customized interventions for diverse mental disorders, fostering positive computing. Consequently, improved mental health care outcomes and enhanced accessibility for individuals with varied mental health conditions are anticipated. Method Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, the researchers conducted a systematic literature review in databases indexed in Web of Science to identify the existing strengths and limitations of software architecture relevant to our adaptive design. The systematic review was registered in PROSPERO (CRD42023444661). Additionally, a mapping process was employed to derive essential paradigms serving as the foundation for the research architectural design. To validate the architecture based on its features, professional experts utilized a Likert scale. Results Through the review, the authors identified six fundamental paradigms crucial for designing architecture. Leveraging these paradigms, the authors crafted an adaptive data-driven architecture, subsequently validated by professional experts. The validation resulted in a mean score exceeding four for each evaluated feature, confirming the architecture’s effectiveness. To further assess the architecture’s practical application, a prototype architecture for predicting pandemic anxiety was developed.

show abstract

Smart Sensing Enhanced Diagnostic Expert Systems

Cited by 15 publications

References 74 publications

Enhancing the acceptance of smart sensing in psychotherapy patients: findings from a randomized controlled trial

Enhancing the acceptance of smart sensing in psychotherapy patients: findings from a randomized controlled trial

Optimizing the predictive power of depression screenings using machine learning

An adaptive data-driven architecture for mental health care applications

Contact Info

Product

Resources

About