Use of mental health telemetry to enhance identification and predictive value of early changes during augmentation treatment of major depression

Machine Learning for Mental Health: Applications, Challenges, and the Clinician's Role

PURPOSE OF REVIEW

This review aims to evaluate the current psychiatric applications and limitations of machine learning (ML), defined as techniques used to train algorithms to improve performance at a task based on data. The review emphasizes the clinician's role in ensuring equitable and effective patient care and seeks to inform mental health providers about the importance of clinician involvement in these technologies.

RECENT FINDINGS

ML in psychiatry has advanced through electronic health record integration, disease phenotyping, and remote monitoring through mobile applications. However, these applications face challenges related to health equity, privacy, translation to practice, and validation. Clinicians play crucial roles in ensuring data quality, mitigating biases, promoting algorithm transparency, guiding clinical implementation, and advocating for ethical and patient-centered use of ML tools. Clinicians are essential in addressing the challenges of ML, ensuring its ethical application, and promoting equitable care, thus improving the effectiveness of ML in practice.

The Promise of Ecological Momentary Assessment to Improve Depression Management for Older Adults in Primary Care

Among older adults, depression is a common, morbid, and costly disorder. Older adults with depression are overwhelmingly treated by primary care providers with poor rates of remission and treatment response, despite attempts to improve care delivery through behavioral health integration and care management models. Given one in 10 older adults in primary care settings meet criteria for depression, there is a pressing need to improve the efficacy of depression treatment among affected individuals. Measurement-based care (i.e., the incorporation of systematic measurement of patient outcomes into treatment) for depressed older adults in primary care has had poor uptake, which at least partly underlies the limited efficacy of depression treatments. In this perspective, we discuss the proposal that ecological momentary assessment (EMA) may increase uptake of measurement-based care for depression in primary care, enhance the quality of clinical depression data, and lead to improvements in treatment efficacy without adding to providers' burden. We describe key issues related to EMA implementation and application in routine settings for depressed older adults, along with potential pitfalls and future research directions.

Grouping of mood symptoms by time series dynamics

BACKGROUND

Understanding how symptoms of mood disorders vary over time in relation to each other is potentially valuable for diagnosis and predicting episodes of illness. In this paper, we characterize the degree of similarity of time series of different mood disorder symptoms.

METHODS

We collected 32,215 mood disorder symptom questionnaires, administered twice-daily over 18 months to (n = 19) subjects with rapidly cycling bipolar disorder and (n = 20) healthy control subjects, using visual analog scales to rate 11 sets of symptom severity ratings plus a control item. We used Dynamic Time Warping to calculate similarity ratings between all within-subject pairs of severity ratings followed by Exploratory Factor Analysis (EFA) to identify latent factors of symptom time series across all subjects.

RESULTS

Two latent factors were identified: one with depression and anxiety; and a second, with concentration, energy, irritability, fatigue, appetite, euphoria/elation and overall mood. Restlessness, racing thoughts, and the control item (daily hours of daylight) did not cluster with any of the others.

LIMITATIONS

Limited sample size dictated that we pool bipolar and healthy patients and use an iterative EFA procedure.

CONCLUSION

This analysis suggests that, in a pooled sample of individuals with bipolar disorder and in healthy controls, severity ratings of overall depression and overall anxiety vary jointly as one dynamic factor, while some but not all other DSM mood symptoms vary jointly along with overall mood rating as a second dynamic factor. Further investigation may determine if these findings can simplify subjective symptom reporting in mood-monitoring studies.

Neuromodulation for major depressive disorder: innovative measures to capture efficacy and outcomes

Major depressive disorder is a common and debilitating disorder. Although most patients with this disorder benefit from established treatments, a subset of patients have symptoms that remain treatment resistant. Novel treatment approaches, such as deep brain stimulation, are urgently needed for patients with treatment-resistant major depressive disorder. These novel treatments are currently being tested in clinical trials in which success hinges on how accurately and comprehensively the primary outcome measure captures the treatment effect. In this Personal View, we argue that current measures used to assess outcomes in neurosurgical trials of major depressive disorder might be missing clinically important treatment effects. A crucial problem of continuing to use suboptimal outcome measures is that true signals of efficacy might be missed, thereby disqualifying potentially effective treatments. We argue that a re-evaluation of how outcomes are measured in these trials is much overdue and describe several novel approaches that attempt to better capture meaningful change.

Predictors of response to augmentation treatment in patients with treatment-resistant depression: A systematic review

BACKGROUND

Treatment-resistant depression is an important contributor to the global burden of depression. Antidepressant augmentation is a recommended treatment strategy for treatment-resistant patients, but outcomes remain poor. Identifying factors that are predictive of response to augmentation treatments may improve outcomes.

AIMS

This review aimed to synthesise the existing literature examining predictors of response to augmentation treatments in patients who had insufficiently responded to initial treatment.

METHODS

A systematic search was conducted identifying 2241 unique manuscripts. 24 examining predictors of outcome to pharmacological or psychological augmentation treatment were included in this review.

RESULTS

Atypical antipsychotics were the most frequently assessed treatment class (nine studies), closely followed by mood stabilisers (eight studies). Only one eligible psychological augmentation study was identified. Early response to treatment (week 2) was the best-supported predictor of subsequent treatment outcome, reported by six studies. Many predictor variables were only assessed by one report and others such as pre-treatment severity yielded contradictory results, both within and across treatment classes.

CONCLUSIONS

This review highlights the importance of early response as a predictor of pharmacological augmentation outcome, with implications for both the monitoring and treatment of resistant unipolar patients. Further replication is needed across specific interventions to fully assess the generalisability of this finding. However, the clear lack of consistent evidence for other predictive factors both within and across treatments, and the scarce examination of psychological augmentation, demonstrates the need for much more research of a high quality if response prediction is to improve outcomes for patients with treatment-resistant depression.

Smartphone-Based Tracking of Sleep in Depression, Anxiety, and Psychotic Disorders

PURPOSE OF REVIEW

Sleep is an important feature in mental illness. Smartphones can be used to assess and monitor sleep, yet there is little prior application of this approach in depressive, anxiety, or psychotic disorders. We review uses of smartphones and wearable devices for sleep research in patients with these conditions.

RECENT FINDINGS

To date, most studies consist of pilot evaluations demonstrating feasibility and acceptability of monitoring sleep using smartphones and wearable devices among individuals with psychiatric disorders. Promising findings show early associations between behaviors and sleep parameters and agreement between clinic-based assessments, active smartphone data capture, and passively collected data. Few studies report improvement in sleep or mental health outcomes. Success of smartphone-based sleep assessments and interventions requires emphasis on promoting long-term adherence, exploring possibilities of adaptive and personalized systems to predict risk/relapse, and determining impact of sleep monitoring on improving patients' quality of life and clinically meaningful outcomes.

Current State and Future Directions of Technology-Based Ecological Momentary Assessment and Intervention for Major Depressive Disorder: A Systematic Review

Ecological momentary assessment (EMA) and ecological momentary intervention (EMI) are alternative approaches to retrospective self-reports and face-to-face treatments, and they make it possible to repeatedly assess patients in naturalistic settings and extend psychological support into real life. The increase in smartphone applications and the availability of low-cost wearable biosensors have further improved the potential of EMA and EMI, which, however, have not yet been applied in clinical practice. Here, we conducted a systematic review, using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, to explore the state of the art of technology-based EMA and EMI for major depressive disorder (MDD). A total of 33 articles were included (EMA = 26; EMI = 7). First, we provide a detailed analysis of the included studies from technical (sampling methods, duration, prompts), clinical (fields of application, adherence rates, dropouts, intervention effectiveness), and technological (adopted devices) perspectives. Then, we identify the advantages of using information and communications technologies (ICTs) to extend the potential of these approaches to the understanding, assessment, and intervention in depression. Furthermore, we point out the relevant issues that still need to be addressed within this field, and we discuss how EMA and EMI could benefit from the use of sensors and biosensors, along with recent advances in machine learning for affective modelling.

EMOTEO: A Smartphone Application for Monitoring and Reducing Aversive Tension in Borderline Personality Disorder Patients, a Pilot Study

PURPOSE

We developed a smartphone application (App; EMOTEO: emotion-meteo [weather forecast]) to help borderline personality disorder (BPD) patients to monitor and regulate their inner tension. The App proposes targeted mindfulness-based exercises.

DESIGN AND METHODS

We assessed the usability and efficiency of this App for monitoring and reduction of aversive tension in 16 BPD participants over a 6-month period.

FINDINGS

We recorded a mean of 318.1 sessions (SD = 166.7) per participants, with a high level of satisfaction. There was a significant decrease in aversive tension (p < .05) and the App was mainly used around 10 a.m. and 9 p.m.

PRACTICE IMPLICATIONS

EMOTEO was user-friendly and efficient in reducing aversive tension in BPD patients.

There is an app for that! The current state of mobile applications (apps) for DSM-5 obsessive-compulsive disorder, posttraumatic stress disorder, anxiety and mood disorders

Mental health apps are viewed as a promising modality to extend the reach of mental health care beyond the clinic. They do so by providing a means of assessment, tracking, and treatment through a smartphone. Given that nearly 2/3 of the American population owns a smartphone, mental health apps offer the possibility of overcoming treatment barriers such as geographic location or financial barriers. Unfortunately, the excitement surrounding mental health apps may be premature as the current supporting literature regarding their efficacy is limited. The app marketplace is littered with apps claiming to treat or assess symptoms, but even those created by reputable organizations or those incorporating components of evidence-based treatments have not yet been validated in terms of their efficacy. This review aims to provide a comprehensive review of the current state of the mental health app literature by examining published reports of apps designed for DSM-5 anxiety and mood disorders, OCD, and PTSD. The breadth of apps reviewed includes those oriented around assessment, symptom tracking, and treatment as well as "multipurpose" apps, which incorporate several of these components. This review will also present some of the most popular mental health apps which may have clinical utility and could be prescribed to clients. While we discuss many potential benefits of mental health apps, we focus on a number of issues that the current state of the app literature presents. Overall there is a significant disconnect between app developers, the scientific community and health care, leaving the utility of existing apps questionable.

Mobile Mental Health: Navigating New Rules and Regulations for Digital Tools

Mobile health (mHealth) apps are becoming much more widely available. As more patients learn about and download apps, clinicians are sure to face more questions about the role these apps can play in treatment. Clinicians thus need to familiarize themselves with the clinical and legal risks that apps may introduce. Regulatory rules and organizations that oversee the safety and efficacy of mHealth apps are currently fragmentary in nature and clinicians should pay special attention to categories of apps which are currently exempt from significant regulation. Uniform HIPAA protection does not apply to personal health data that are shared with apps in many contexts which creates a number of clinically relevant privacy and security concerns. Clinicians should also consider several relatively novel potential adverse clinical outcomes and liability concerns that may be relevant to specific categories of apps, including apps that target (i) medication adherence, (ii) collection of self-reported data, (iii) collection of passive data, and (iv) generation of treatment recommendations for psychotherapeutic and behavioral interventions. Considering these potential pitfalls (and disclosing them to patients as a part of obtaining informed consent) is necessary as clinicians consider incorporating apps into treatment.

A Systematic Review of Cognitive Behavioral Therapy and Behavioral Activation Apps for Depression

Depression is a common mental health condition for which many mobile apps aim to provide support. This review aims to identify self-help apps available exclusively for people with depression and evaluate those that offer cognitive behavioural therapy (CBT) or behavioural activation (BA). One hundred and seventeen apps have been identified after searching both the scientific literature and the commercial market. 10.26% (n = 12) of these apps identified through our search offer support that seems to be consistent with evidence-based principles of CBT or BA. Taking into account the non existence of effectiveness/efficacy studies, and the low level of adherence to the core ingredients of the CBT/BA models, the utility of these CBT/BA apps are questionable. The usability of reviewed apps is highly variable and they rarely are accompanied by explicit privacy or safety policies. Despite the growing public demand, there is a concerning lack of appropiate CBT or BA apps, especially from a clinical and legal point of view. The application of superior scientific, technological, and legal knowledge is needed to improve the development, testing, and accessibility of apps for people with depression.

Using Smartphone Apps to Promote Psychiatric and Physical Well-Being

This pilot study tested the acceptability and usability of a prototype app designed to promote the physical well-being of adults with psychiatric disorders. The application under evaluation, WellWave, promoted walking as a physical exercise, and offered a variety of supportive non-physical activities, including confidential text-messaging with peer staff, and a digital library of readings and videos on recovery from psychiatric illness. Study participants engaged strongly in the app throughout the 4-week study, showing a 94 % mean daily usage rate, and a 73 % mean response rate across all electronic messages and prompts, which approximates the gold standard of 75 % for momentary ecological assessment studies. Seven of the ten study participants averaged two or more walks per week, beginning with 5-min walks and ending with walks lasting 20 min or longer. This responsiveness to the walking prompts, and the overall high rate of engagement in other app features, suggest that adults with psychiatric conditions would welcome and benefit from similar smartphone interventions that promote healthy behaviours in life domains other than exercise. Pilot study results also suggest that smartphone applications can be useful as research tools in the development and testing of theories and practical strategies for encouraging healthy lifestyles. Participants were prompted periodically to rate their own health quality, perceived control over their health, and stage-of-change in adopting a walking routine, and these electronic self-ratings showed acceptable concurrent and discriminant validity, with all participants reporting moderate to high motivation to exercise by the end of the study.

Utilizing a Personal Smartphone Custom App to Assess the Patient Health Questionnaire-9 (PHQ-9) Depressive Symptoms in Patients With Major Depressive Disorder

BACKGROUND

Accurate reporting of patient symptoms is critical for diagnosis and therapeutic monitoring in psychiatry. Smartphones offer an accessible, low-cost means to collect patient symptoms in real time and aid in care.

OBJECTIVE

To investigate adherence among psychiatric outpatients diagnosed with major depressive disorder in utilizing their personal smartphones to run a custom app to monitor Patient Health Questionnaire-9 (PHQ-9) depression symptoms, as well as to examine the correlation of these scores to traditionally administered (paper-and-pencil) PHQ-9 scores.

METHODS

A total of 13 patients with major depressive disorder, referred by their clinicians, received standard outpatient treatment and, in addition, utilized their personal smartphones to run the study app to monitor their symptoms. Subjects downloaded and used the Mindful Moods app on their personal smartphone to complete up to three survey sessions per day, during which a randomized subset of PHQ-9 symptoms of major depressive disorder were assessed on a Likert scale. The study lasted 29 or 30 days without additional follow-up. Outcome measures included adherence, measured by the percentage of completed survey sessions, and estimates of daily PHQ-9 scores collected from the smartphone app, as well as from the traditionally administered PHQ-9.

RESULTS

Overall adherence was 77.78% (903/1161) and varied with time of day. PHQ-9 estimates collected from the app strongly correlated (r=.84) with traditionally administered PHQ-9 scores, but app-collected scores were 3.02 (SD 2.25) points higher on average. More subjects reported suicidal ideation using the app than they did on the traditionally administered PHQ-9.

CONCLUSIONS

Patients with major depressive disorder are able to utilize an app on their personal smartphones to self-assess their symptoms of major depressive disorder with high levels of adherence. These app-collected results correlate with the traditionally administered PHQ-9. Scores recorded from the app may potentially be more sensitive and better able to capture suicidality than the traditional PHQ-9.

Reliability, validity and sensitivity of a computerized visual analog scale measuring state anxiety

BACKGROUND AND OBJECTIVES

Assessment of state anxiety is frequently required in clinical and research settings, but its measurement using standard multi-item inventories entails practical challenges. Such inventories are increasingly complemented by paper-and-pencil, single-item visual analog scales measuring state anxiety (VAS-A), which allow rapid assessment of current anxiety states. Computerized versions of VAS-A offer additional advantages, including facilitated and accurate data collection and analysis, and applicability to computer-based protocols. Here, we establish the psychometric properties of a computerized VAS-A.

METHODS

Experiment 1 assessed the reliability, convergent validity, and discriminant validity of the computerized VAS-A in a non-selected sample. Experiment 2 assessed its sensitivity to increase in state anxiety following social stress induction, in participants with high levels of social anxiety.

RESULTS

Experiment 1 demonstrated the computerized VAS-A's test-retest reliability (r = .44, p < .001); convergent validity with the State-Trait Anxiety Inventory's state subscale (STAI-State; r = .60, p < .001); and discriminant validity as indicated by significantly lower correlations between VAS-A and different psychological measures relative to the correlation between VAS-A and STAI-State. Experiment 2 demonstrated the VAS-A's sensitivity to changes in state anxiety via a significant pre- to during-stressor rise in VAS-A scores (F(1,48) = 25.13, p < .001).

LIMITATIONS

Set-order administration of measures, absence of clinically-anxious population, and gender-unbalanced samples.

CONCLUSIONS

The adequate psychometric characteristics, combined with simple and rapid administration, make the computerized VAS-A a valuable self-rating tool for state anxiety. It may prove particularly useful for clinical and research settings where multi-item inventories are less applicable, including computer-based treatment and assessment protocols. The VAS-A is freely available: http://people.socsci.tau.ac.il/mu/anxietytrauma/visual-analog-scale/.