Clinician Perspectives on Using Computational Mental Health Insights From Patients' Social Media Activities: Design and Qualitative Evaluation of a Prototype

Effect of Integrating Patient-Generated Digital Data Into Mental Health Therapy: A Randomized Controlled Trial

OBJECTIVE

The authors sought to determine whether providing summaries of patients' social media and other digital data to patients and their clinicians improves patients' health-related quality of life (HRQoL) measured by the RAND 36-Item Short Form Health Survey (SF-36).

METHODS

The authors randomly assigned 115 adults receiving outpatient mental health therapy to usual care or to periodic sharing of summaries of their digital data with their clinician providing psychosocial therapy. The study was conducted October 2020-December 2021.

RESULTS

Patients' mean±SD age was 31.3±10.5 years, and 82% were women. At 60 days after enrollment, no statistically significant change was detected in SF-36 scores for patients randomly allocated to the intervention (mean difference=-0.39, 95% CI=-4.17, 3.39) or to usual care (mean difference=-1.98, 95% CI=-5.74, 1.77), and no significant between-arm difference was observed (between-arm difference=1.60, 95% CI=-3.67, 6.86).

CONCLUSIONS

Collecting and summarizing digital data for use in mental health treatment was feasible for patients but did not significantly improve their HRQoL or other measures of mental health.

Cross-Platform Detection of Psychiatric Hospitalization via Social Media Data: Comparison Study

BACKGROUND

Previous research has shown the feasibility of using machine learning models trained on social media data from a single platform (eg, Facebook or Twitter) to distinguish individuals either with a diagnosis of mental illness or experiencing an adverse outcome from healthy controls. However, the performance of such models on data from novel social media platforms unseen in the training data (eg, Instagram and TikTok) has not been investigated in previous literature.

OBJECTIVE

Our study examined the feasibility of building machine learning classifiers that can effectively predict an upcoming psychiatric hospitalization given social media data from platforms unseen in the classifiers' training data despite the preliminary evidence on identity fragmentation on the investigated social media platforms.

METHODS

Windowed timeline data of patients with a diagnosis of schizophrenia spectrum disorder before a known hospitalization event and healthy controls were gathered from 3 platforms: Facebook (254/268, 94.8% of participants), Twitter (51/268, 19% of participants), and Instagram (134/268, 50% of participants). We then used a 3 × 3 combinatorial binary classification design to train machine learning classifiers and evaluate their performance on testing data from all available platforms. We further compared results from models in intraplatform experiments (ie, training and testing data belonging to the same platform) to those from models in interplatform experiments (ie, training and testing data belonging to different platforms). Finally, we used Shapley Additive Explanation values to extract the top predictive features to explain and compare the underlying constructs that predict hospitalization on each platform.

RESULTS

We found that models in intraplatform experiments on average achieved an F₁-score of 0.72 (SD 0.07) in predicting a psychiatric hospitalization because of schizophrenia spectrum disorder, which is 68% higher than the average of models in interplatform experiments at an F₁-score of 0.428 (SD 0.11). When investigating the key drivers for divergence in construct validities between models, an analysis of top features for the intraplatform models showed both low predictive feature overlap between the platforms and low pairwise rank correlation (<0.1) between the platforms' top feature rankings. Furthermore, low average cosine similarity of data between platforms within participants in comparison with the same measurement on data within platforms between participants points to evidence of identity fragmentation of participants between platforms.

CONCLUSIONS

We demonstrated that models built on one platform's data to predict critical mental health treatment outcomes such as hospitalization do not generalize to another platform. In our case, this is because different social media platforms consistently reflect different segments of participants' identities. With the changing ecosystem of social media use among different demographic groups and as web-based identities continue to become fragmented across platforms, further research on holistic approaches to harnessing these diverse data sources is required.

The promise of a model-based psychiatry: building computational models of mental ill health

Computational models have great potential to revolutionise psychiatry research and clinical practice. These models are now used across multiple subfields, including computational psychiatry and precision psychiatry. Their goals vary from understanding mechanisms underlying disorders to deriving reliable classification and personalised predictions. Rapid growth of new tools and data sources (eg, digital data, gamification, and social media) requires an understanding of the constraints and advantages of different modelling approaches in psychiatry. In this Series paper, we take a critical look at the range of computational models that are used in psychiatry and evaluate their advantages and disadvantages for different purposes and data sources. We describe mechanism-driven and mechanism-agnostic computational models and discuss how interpretability of models is crucial for clinical translation. Based on these evaluations, we provide recommendations on how to build computational models that are clinically useful.