Using digital phenotyping to classify bipolar disorder and unipolar disorder - exploratory findings using machine learning models.

The aims were to investigate 1) differences in smartphone-based data on phone usage between bipolar disorder (BD) and unipolar disorder (UD) and 2) by using machine learning models, the sensitivity, specificity, and AUC of the combined smartphone data in classifying BD and UD. Daily smartphone-based self-assessments of mood and same-time passively collected smartphone data on smartphone usage was available for six months. A total of 64 patients with BD and 74 patients with UD were included. Patients with BD during euthymic states compared with UD in euthymic states had a lower number of incoming phone calls/ day (B: -0.70, 95%CI: -1.37; -0.70, p=0.040). Patients with BD during depressive states had a lower number of incoming and outgoing phone calls/ day as compared with patients with UD in depressive states. In classification by using machine learning models, 1) overall (regardless of the affective state), patients with BD were classified with an AUC of 0.84, which reduced to 0.48 when using a leave-one-patient-out crossvalidation (LOOCV) approach; similarly 2) during a depressive state, patients with BD were classified with an AUC of 0.86, which reduced to 0.42 with LOOCV; 3) during a euthymic state, patients with BD were classified with an AUC of 0.87, which reduced to 0.46 with LOOCV. While digital phenotyping shows promise in differentiating between patients with BD and UD, it highlights the challenge of generalizing to unseen individuals. It should serve as an complement to comprehensive clinical evaluation by clinicians.

What's Up With These Conversational Health Agents? From Users' Critiques to Implications for Design.

Recent advancements in speech recognition technology in combination with increased access to smart speaker devices are expanding conversational interactions to ever-new areas of our lives - including our health and wellbeing. Prior human-computer interaction research suggests that Conversational Agents (CAs) have the potential to support a variety of health-related outcomes, due in part to their intuitive and engaging nature. Realizing this potential requires however developing a rich understanding of users' needs and experiences in relation to these still-emerging technologies. To inform the design of CAs for health and wellbeing, we analyze 2741 critical reviews of 485 Alexa health and fitness Skills using an automated topic modeling approach; identifying 15 subjects of criticism across four key areas of design (functionality, reliability, usability, pleasurability). Based on these findings, we discuss implications for the design of engaging CAs to support health and wellbeing.

Differences in mobility patterns according to machine learning models in patients with bipolar disorder and patients with unipolar disorder.

BACKGROUND: It is essential to differentiate bipolar disorder (BD) from unipolar disorder (UD) as the course of illness and treatment guidelines differ between the two disorders. Measurements of activity and mobility could assist in this discrimination. AIMS: 1) To investigate differences in smartphone-based location data between BD and UD, and 2) to investigate the sensitivity, specificity, and AUC of combined location data in classifying BD and UD. METHODS: Patients with BD and UD completed smartphone-based self-assessments of mood for six months, along with same-time passively collected smartphone data on location reflecting mobility patterns, routine and location entropy (chaos). A total of 65 patients with BD and 75 patients with UD were included. RESULTS: A total of 2594 (patients with BD) and 2088 (patients with UD) observations of smartphone-based location data were available. During a depressive state, compared with patients with UD, patients with BD had statistically significantly lower mobility (e.g., total duration of moves per day (eB 0.74, 95% CI 0.57; 0.97, p = 0.027)). In classification models during a depressive state, patients with BD versus patients with UD, there was a sensitivity of 0.70 (SD 0.07), a specificity of 0.77 (SD 0.07), and an AUC of 0.79 (SD 0.03). LIMITATIONS: The relative low symptom severity in the present study may have contributed to the magnitude of the AUC. CONCLUSION: Mobility patterns derived from mobile location data is a promising digital diagnostic marker in discriminating between patients with BD and UD.

Discriminating between patients with unipolar disorder, bipolar disorder, and healthy control individuals based on voice features collected from naturalistic smartphone calls.

BACKGROUND: It is of crucial importance to be able to discriminate unipolar disorder (UD) from bipolar disorder (BD), as treatments, as well as course of illness, differ between the two disorders. AIMS: To investigate whether voice features from naturalistic phone calls could discriminate between (1) UD, BD, and healthy control individuals (HC); (2) different states within UD. METHODS: Voice features were collected daily during naturalistic phone calls for up to 972 days. A total of 48 patients with UD, 121 patients with BD, and 38 HC were included. A total of 115,483 voice data entries were collected (UD [n = 16,454], BD [n = 78,733], and HC [n = 20,296]). Patients evaluated symptoms daily using a smartphone-based system, making it possible to define illness states within UD and BD. Data were analyzed using random forest algorithms. RESULTS: Compared with BD, UD was classified with a specificity of 0.84 (SD: 0.07)/AUC of 0.58 (SD: 0.07) and compared with HC with a sensitivity of 0.74 (SD: 0.10)/AUC = 0.74 (SD: 0.06). Compared with BD during euthymia, UD during euthymia was classified with a specificity of 0.79 (SD: 0.05)/AUC = 0.43 (SD: 0.16). Compared with BD during depression, UD during depression was classified with a specificity of 0.81 (SD: 0.09)/AUC = 0.48 (SD: 0.12). Within UD, compared with euthymia, depression was classified with a specificity of 0.70 (SD 0.31)/AUC = 0.65 (SD: 0.11). In all models, the user-dependent models outperformed the user-independent models. CONCLUSIONS: The results from the present study are promising, but as reflected by the low AUCs, does not support that voice features collected during naturalistic phone calls at the current state of art can be implemented in clinical practice as a supplementary and assisting tool. Further studies are needed.

Voice analyses using smartphone-based data in patients with bipolar disorder, unaffected relatives and healthy control individuals, and during different affective states.

BACKGROUND: Voice features have been suggested as objective markers of bipolar disorder (BD). AIMS: To investigate whether voice features from naturalistic phone calls could discriminate between (1) BD, unaffected first-degree relatives (UR) and healthy control individuals (HC); (2) affective states within BD. METHODS: Voice features were collected daily during naturalistic phone calls for up to 972 days. A total of 121 patients with BD, 21 UR and 38 HC were included. A total of 107.033 voice data entries were collected [BD (n = 78.733), UR (n = 8004), and HC (n = 20.296)]. Daily, patients evaluated symptoms using a smartphone-based system. Affective states were defined according to these evaluations. Data were analyzed using random forest machine learning algorithms. RESULTS: Compared to HC, BD was classified with a sensitivity of 0.79 (SD 0.11)/AUC = 0.76 (SD 0.11) and UR with a sensitivity of 0.53 (SD 0.21)/AUC of 0.72 (SD 0.12). Within BD, compared to euthymia, mania was classified with a specificity of 0.75 (SD 0.16)/AUC = 0.66 (SD 0.11). Compared to euthymia, depression was classified with a specificity of 0.70 (SD 0.16)/AUC = 0.66 (SD 0.12). In all models the user dependent models outperformed the user independent models. Models combining increased mood, increased activity and insomnia compared to periods without performed best with a specificity of 0.78 (SD 0.16)/AUC = 0.67 (SD 0.11). CONCLUSIONS: Voice features from naturalistic phone calls may represent a supplementary objective marker discriminating BD from HC and a state marker within BD.

Data-Driven Learning in High-Resolution Activity Sampling From Patients With Bipolar Depression: Mixed-Methods Study.

BACKGROUND: Behavioral activation is a pen and paper-based therapy form for treating depression. The patient registers their activity hourly, and together with the therapist, they agree on a plan to change behavior. However, with the limited clinical personnel, and a growing patient population, new methods are needed to advance behavioral activation. OBJECTIVE: The objectives of this paper were to (1) automatically identify behavioral patterns through statistical analysis of the paper-based activity diaries, and (2) determine whether it is feasible to move the behavioral activation therapy format to a digital solution. METHODS: We collected activity diaries from seven patients with bipolar depression, covering in total 2,480 hours of self-reported activities. A pleasure score, on a 1-10 rating scale, was reported for each activity. The activities were digitalized into 6 activity categories, and statistical analyses were conducted. RESULTS: Across all patients, movement-related activities were associated with the highest pleasure score followed by social activities. On an individual level, through a nonparametric Wilcoxon Signed-Rank test, one patient had a statistically significant larger amount of spare time activities when feeling bad (z=-2.045, P=.041). Through a within-subject analysis of covariance, the patients were found to have a better day than the previous, if that previous day followed their diurnal rhythm (ρ=.265, P=.029). Furthermore, a second-order trend indicated that two hours of daily social activity was optimal for the patients (ß2=-0.08, t (63)=-1.22, P=.23). CONCLUSIONS: The data-driven statistical approach was able to find patterns within the behavioral traits that could assist the therapist in as well as help design future technologies for behavioral activation.

Brain-computer interface using P300 and virtual reality: a gaming approach for treating ADHD.

This paper presents a novel brain-computer interface (BCI) system aiming at the rehabilitation of attention-deficit/hyperactive disorder in children. It uses the P300 potential in a series of feedback games to improve the subjects' attention. We applied a support vector machine (SVM) using temporal and template-based features to detect these P300 responses. In an experimental setup using five subjects, an average error below 30% was achieved. To make it more challenging the BCI system has been embedded inside an immersive 3D virtual reality (VR) classroom with simulated distractions, which was created by combining a low-cost infrared camera and an "off-axis perspective projection" algorithm. This system is intended for kids by operating with four electrodes, as well as a non-intrusive VR setting. With the promising results, and considering the simplicity of the scheme, we hope to encourage future studies to adapt the techniques presented in this study.