We’re delighted to announce this year’s winner is Dr Simon Williamson, Academic Clinical Fellow at the University of Warwick and core psychiatry trainee with Coventry and Warwickshire Partnership NHS Trust.

The Institute runs the annual 1,000 word essay prize competition named after psychiatrist Duncan Macmillan who helped pioneer a community-centred approach to mental health. The competition is held in partnership with The Royal College of Psychiatrists and promotes the expertise and knowledge of psychiatry trainees nationwide.

Simon’s winning entry answered the competition essay question “What’s the next big thing in psychiatry?” by exploring “Digital Phenotyping”.

Second prize in the competition was awarded to Dr Martindale, trainee psychiatrist at Devonshire Partnership NHS Trust, for her essay exploring “Teletherapy”.

Read both of the winning entries below.

FIRST PRIZE: Digital Phenotyping

By Dr Simon Williamson, Academic Clinical Fellow at the University of Warwick and core psychiatry trainee with Coventry and Warwickshire Partnership NHS Trust

Introduction

Digital devices are now an integral part of our modern lives. Interactions with smartphones, wearables, and increasingly more immersive technologies comprise a substantial portion of our waking hours. Consequently, these devices can generate large amounts of data reflecting our behaviour; whether we are active or stationary, sociable or isolative, awake or asleep. For psychiatry, this data is a rich, yet largely untapped, resource.

Digital phenotyping is the 'moment-by-moment quantification of the individual-level human phenotype, in situ, using data from personal digital devices'1. In other words, it is the use of digital data to generate a behavioural phenotype that is both continuous and ecologically valid.

Observation of behaviour is fundamental to psychiatry, insofar as behaviour manifests mental illness. Often this must be done cross-sectionally, or retrospectively, and in clinical settings outside of the patient’s normal environment. Yet mental health tends to fluctuate over time, and is largely environmentally dependent, suggesting that current practice may be limited. Digital phenotyping promises to remedy this, and moreover offers the potential for a more objective, proactive, and personalised psychiatry.

Extending the MSE

The mental state examination (MSE) is a core component of psychiatric practice. It involves the inference of mental state through careful observation. Digital phenotyping provides new means to observe behaviour, in a sense extending the sensorium available to the psychiatrist.

Data obtained from digital devices is typically differentiated into active and passive forms. Active data requires some level of engagement to obtain, for instance the completion of a questionnaire (also coined ‘ecological momentary assessment’2). Passive data, conversely, is collected without explicit user notification. Common forms of passive data include number of phone calls or text messages sent, accelerometery (to measure physical activity), and geolocation (to measure, for instance, time spent at home). With the addition of a wearable device, actigraphy, heart rate and skin conductance also become available.

There is growing evidence that these data are genuinely informative. A recent systematic review identified several studies in which within-individual variability of depressive symptoms was well captured by the data, as was response to targeted interventions3. Another systematic review noted that, across studies, features sensitive to depressive episodes were also sensitive to mania, reflecting the bipolarity of mood4.

Moreover, work continues to generate new and informative features. Speech analysis, for instance, shows great promise in quantifying the dysconnectivity inherent to thought disorder5, whilst pulse wave analysis offers a more nuanced view of the physiology captured by heart rate monitors6. The emerging picture is one of several digital biomarkers of mental health which, in combination, could be a powerful adjunct to the MSE in inferring mental state.

From Phone to Phenotype

Whilst the rapid development of new features is exciting, combining them to generate clinically useful phenotypes is easier said than done. Real-world data is noisy, patchy, and notably sizeable. Unlike in neuroimaging or genomics, there isn’t a standardized method to analyse data from digital devices7.

So how can this be achieved?

The first step is to collect and organise data on the device itself. Several applications already exist for this purpose8,9. They are also capable of automatically uploading collected data to secure servers. Once uploaded, the data are likely to require some degree of pre-processing (i.e. cleaning) before extracted features can be selected for further analysis.

From this point, the goal is to effectively model digital behaviour such that it represents, with reasonable accuracy, the individuals mental state and functioning. The better the model, the more effective it will be at detecting changes in mental state.

Barnett et al. achieved this by statistically modelling trends in digital features over time10. When new data was significantly different to what would be expected from the trend, anomalies were flagged. In a small sample of schizophrenia patients, the rate of anomalies two weeks prior to relapse was 71% higher than at other time periods.

Even more promising are machine learning models, which are highly suited to large, multi-modal data. Currently, there is marked heterogeneity between studies11 and impressive model performance should be treated with caution12. Helpfully, guidelines to standardize reporting have been proposed11. As the field matures and shared databases begin to emerge, we are likely to witness increasingly powerful digital phenotypes.

Closing the loop

Clinical implementation is essential if digital phenotyping is to meaningfully impact psychiatry. When a good model detects changes in mental state, the opportunity to intervene arises. Such intervention is referred to as closing the loop13, and could encompass relapse prevention, early recognition of treatment non-response, or timely delivery of a digital therapy (i.e. ecological momentary intervention14).

Digital therapies in particular are decades old, and substantial meta-analytic evidence for their efficacy has accumulated15,16. A notable example of late is the Sleepio17 app, now a NICE recommended treatment for insomnia18. For inclusion in clinical practice, a coherent overarching system linking phenotypes to interventions will be necessary. Several groups have begun this work, starting with the development of ‘clinician dashboards’; interfaces for viewing digital data in much the same way as blood test results19,20.

Importantly, clinical implementation can only proceed if digital phenotyping is acceptable to patients. The ethical issues surrounding use of personal data are apparent21, and careful collaboration with patients will be necessary to ensure individuals are empowered by their data should they choose to share it.

Conclusion

Digital phenotyping is a fast-growing field with the potential to revolutionise psychiatric practice. Initial evidence has effectively proved the concept, with the next phase of large-scale studies currently underway22. Experts from multiple fields, as well as patients, are required to actualise digital phenotyping in its entirety. Centralised repositories for the registration of studies and sharing of data have been proposed13, which will likely help to overcome the current issues facing the field, such as heterogeneity.

Technological advancement has always exerted positive and negative effects on society. When considering digital phenotyping, we as psychiatrists must be careful to avoid blind enthusiasm on the one hand, or stubborn refusal on the other. We can, however, remain hopeful that a truly 21st century psychiatry is close at hand.

References

1. Onnela, J.-P. & Rauch, S. L. Harnessing Smartphone-Based Digital Phenotyping to Enhance Behavioral and Mental Health. Neuropsychopharmacology 41, 1691–1696 (2016).
2. Stone, A. A. & Shiffman, S. Ecological momentary assessment (EMA) in behavorial medicine. Ann. Behav. Med. 16, 199–202 (1994).
3. Zarate, D., Stavropoulos, V., Ball, M., de Sena Collier, G. & Jacobson, N. C. Exploring the digital footprint of depression: a PRISMA systematic literature review of the empirical evidence. BMC Psychiatry 22, 421 (2022).
4. Maatoug, R. et al. Digital phenotype of mood disorders: A conceptual and critical review. Front. Psychiatry 13, 895860 (2022).
5. Spencer, T. J. et al. Lower speech connectedness linked to incidence of psychosis in people at clinical high risk. Schizophr. Res. 228, 493–501 (2021).
6. Williamson, S. et al. The Hybrid Excess and Decay (HED) model: an automated approach to characterising changes in the photoplethysmography pulse waveform [version 1; peer review: awaiting peer review]. Wellcome Open Res. 7, (2022).
7. Barnett, I., Torous, J., Staples, P., Keshavan, M. & Onnela, J.-P. Beyond smartphones and sensors: choosing appropriate statistical methods for the analysis of longitudinal data. J. Am. Med. Inform. Assoc. JAMIA 25, 1669–1674 (2018).
8. Torous, J. et al. Creating a Digital Health Smartphone App and Digital Phenotyping Platform for Mental Health and Diverse Healthcare Needs: an Interdisciplinary and Collaborative Approach. J. Technol. Behav. Sci. 4, 73–85 (2019).
9. Wang, R. et al. CrossCheck: toward passive sensing and detection of mental health changes in people with schizophrenia. in Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing 886–897 (ACM, 2016). doi:10.1145/2971648.2971740.
10. Barnett, I. et al. Relapse prediction in schizophrenia through digital phenotyping: a pilot study. Neuropsychopharmacology 43, 1660–1666 (2018).
11. Benoit, J., Onyeaka, H., Keshavan, M. & Torous, J. Systematic Review of Digital Phenotyping and Machine Learning in Psychosis Spectrum Illnesses. Harv. Rev. Psychiatry 28, 296–304 (2020).
12. Liu, Y., Chen, P.-H. C., Krause, J. & Peng, L. How to Read Articles That Use Machine Learning: Users’ Guides to the Medical Literature. JAMA 322, 1806–1816 (2019).
13. Huckvale, K., Venkatesh, S. & Christensen, H. Toward clinical digital phenotyping: a timely opportunity to consider purpose, quality, and safety. Npj Digit. Med. 2, 1–11 (2019).
14. Heron, K. E. & Smyth, J. M. Ecological Momentary Interventions: Incorporating Mobile Technology Into Psychosocial and Health Behavior Treatments. Br. J. Health Psychol. 15, 1–39 (2010).
15. Moshe, I. et al. Digital interventions for the treatment of depression: A meta-analytic review. Psychol. Bull. 147, 749–786 (2021).
16. Pauley, D., Cuijpers, P., Papola, D., Miguel, C. & Karyotaki, E. Two decades of digital interventions for anxiety disorders: a systematic review and meta-analysis of treatment effectiveness. Psychol. Med. 1–13 (2021) doi:10.1017/S0033291721001999.
17. sleepio.com. Sleepio. Sleepio https://www.sleepio.com.
18. Overview | Sleepio to treat insomnia and insomnia symptoms | Guidance | NICE. https://www.nice.org.uk/guidance/mtg70.
19. Wang, X. et al. HOPES: An Integrative Digital Phenotyping Platform for Data Collection, Monitoring, and Machine Learning. J. Med. Internet Res. 23, e23984 (2021).
20. Zlatintsi, A. et al. E-Prevention: Advanced Support System for Monitoring and Relapse Prevention in Patients with Psychotic Disorders Analyzing Long-Term Multimodal Data from Wearables and Video Captures. Sensors 22, 7544 (2022).
21. Birk, R., Lavis, A., Lucivero, F. & Samuel, G. For what it’s worth. Unearthing the values embedded in digital phenotyping for mental health. Big Data Soc. 8, 20539517211047320 (2021).
22. Matcham, F. et al. Remote assessment of disease and relapse in major depressive disorder (RADAR-MDD): a multi-centre prospective cohort study protocol. BMC Psychiatry 19, 72 (2019).

SECOND PRIZE: Teletherapy

By Dr Martindale, trainee psychiatrist at Devonshire Partnership NHS Trust

We are in the digital era. That may sound automated and remote, not exactly what you’d associate with the warm and intimate world of talking therapy, but you need only look at how COVID-19 triggered a teletherapy explosion to recognise that maybe human connection really can be as effective behind a screen, at the click of a mouse or punched out on the keyboard. As digital innovations continue to reshape our lives, psychiatry cannot afford to waste a byte.

Psychiatrists have been calling for more funding into mental health services for years; at the same time, the pandemic has seen the number of people affected by new mental health problems grow. There has also been an exacerbation of pre-existing mental health issues. The mental health care waiting list in the NHS rose to 1.2 million at the end of 2021-22, and yet talking therapy services continue to be chronically underfunded.1-3 As those responsible for these patients, psychiatrists need to show leadership and look to meet the crisis in mental health care in alternative ways.

One way could be teletherapy. The great advantage of which is its convenience: available from the palm of your hand by text, video or phone at any time.4 Therapeutic support can be accessed quickly, with minimal hassle. It makes therapy easier to access and eliminates the need to fit a commute into a busy schedule with all the traffic gridlock, road rage, public transport issues and commuting time that come with it. Avoiding a commute is also a valuable feature for those with limited mobility, physical limitations, and chronic illnesses or those who experience anxiety about leaving their familiar place to attend public places: teletherapy offers the ability to connect with a therapist from the comfort of your own home.

Whilst it’s true that teletherapy from home can mean some of the nonverbal cues are missed, nonverbal information is by no means lost altogether. Facial expressions and body stance read through a camera still give cues to what someone is feeling; a pause is just as powerful; and a sigh, an intake of breath or a quiver of the lip reverberate over the internet too. Universal human longings and pain still unravel, seeped in all their mystery and meaning, whether it is work carried out online or in person. In fact, teletherapy may bring a greater degree of intimacy by offering the therapist the added benefit of gaining insight into the patient’s home environment. This can enrichen the connection and bring greater depth and authenticity to shared transformative moments.5 For some patients, the very presence of a screen can foster greater trust, helping them open up about their personal lives and struggles.6

Alongside the elements of personal privacy and patient empowerment inherent in teletherapy, is its potential to reduce the impact of stigma as patients can access services discreetly and no one else needs know about them.7

And whilst there is always the chance that the internet may freeze at a moment of emotional intensity or on the cusp of a breakthrough, fortunately, today, our technology is generally much more reliable, secure, and realistic than that of yesterday meaning those luminous moments are seldom lost.

Teletherapy offers substantial benefits to the clinicians and service providers too. It allows clinicians to treat more patients effectively in less time with fewer resources overall than traditional therapy. Several studies have demonstrated the cost-effectiveness of teletherapy:6 In a 2012 systematic review, the authors calculated that the probability of internet-delivered cognitive behaviour therapy (CBT) being a cost-effective treatment was 57% (range 38% to 96%) relative to wait-listed controls.* One randomised control trial compared in-person group CBT with internet-delivered CBT for social anxiety. Patients were treated through a 15-module Internet-delivered program or 14 weekly group meetings and were assessed before treatment, immediately after and six months following treatment. The authors determined that the probability of Internet-delivered CBT being efficacious at a lower cost was 79.5%, if a patient is not willing to pay for the treatment. Although much of the evidence available at present relates to the translation of pre-existing programs rather than investment in the development of new programs (which is where future research needs to be focused) these data are part of a growing body of evidence to suggest a generally favourable effect of digital interventions on cost effectiveness.6

There is more good news too: existing studies show that virtual therapy, typically CBT, can be highly effective for improving various mental health diagnoses.6,8-10 A 2020 meta-analysis found that electronically delivered CBT might, in fact, be better than in-person CBT.11

But we still have work to do if we are to build effective talking services that do not simply endure but thrive when the current boom is no longer fresh. We need to overcome the residual obstacles associated with training, licensing, safety, privacy, payment, and evaluation.12 Studies are required to assess whether remote and in-person sessions are at least comparable in efficacy and success across the different therapy modalities in the medium and long term.13

There may be some valid critiques of teletherapy, but there can be little doubt that teletherapy allows an increasing number of people access to mental healthcare than ever before.14 This is a critical time when the latest NHS digital figures show that the number of referrals to the Improving Access to Psychological Therapies (IAPT) programme for conditions such as anxiety and depression increased by 24.5% in 2020-21 to 1.81 million in 2021-22, higher then pre-pandemic levels of 1.69 million in 2019-2020.15 With the NHS Long Term Plan’s commitment to improving the availability and quality of mental health services across England, now is the time to catalyse change and embrace all the benefits that teletherapy has to offer.16

It was the father of talk therapy Sigmund Freud who said, “Conservatism, however, is too often a welcome excuse for lazy minds, loath to adapt themselves to fast changing conditions.” The medical profession is justly conservative but as the pandemic has seen marked worsening of public mental health, the answer that psychiatrists seek may lie in the fast-changing conditions.

* Wait list control group is a group of participants who do not receive the experimental treatment, but who are put on a waiting list to receive the intervention after the active treatment group does.

References

1. Wiederbold BK. Teletherapy: the new norm? Cyberpsychology, behaviour and social networking, 2020;23(10):655-656
2. Bannister R. Underfunded mental healthcare in the NHS: the cycle of preventable distress continues. BMJ, 2021;375:n2706
3. NHS England. NHS mental health dashboard. Available at: https://www.england.nhs.uk/mental-health/taskforce/imp/mh-dashboard/ [accessed October 2022]
4. Boudin M. The Future of mental health and teletherapy. Sermo, 2020.
5. Time. Online Therapy, Booming During the Coronavirus Pandemic, May Be Here to Stay. 27 August 2020. Available at: https://time.com/5883704/teletherapy-coronavirus/ [accessed November 2022].
6. Gratzer D and Khalid-Khan F. Internet-delivered cognitive behavioural therapy in the treatment of psychiatric illness. Canadian Association Medical Journal, 2016;188(4):263-272
7. Fernbach RA and Papapetros J. Increased access to telehealth as a means of reducing stigma. NY State Psychiatric Association, 2022
8. Andersson G and Cuijpers P. Internet-based and other computerized psychological treatments for adult depression: a meta-analysis. Cogn Behav Ther, 2009;38:196–205
9. Langarizadeh M, Tabatabaei MS, Tavakol K, et al. Telemental Health Care, an Effective Alternative to Conventional Mental Care: a Systematic Review. Acta Inform Med, 2017;25(4):240-246
10. Varker T, Brand R, Ward J, et al. Efficacy of Synchronous telepsychology interventions for people with anxiety, depression, posttraumatic stress disorder, and adjustment disorder: A rapid evidence assessment. Psychological Services, 2019.16(4), 621–635
11. Giovanetti AK, Punt SEW, Nelson EL and Ilardi SS. Teletherapy Versus In-Person Psychotherapy for Depression: A Meta-Analysis of Randomized Controlled Trials. Telemed J E Health, 2022;28(8):1077-1089
12. Luo C, Sanger N, Singhal N, et al. A comparison of electronically-delivered and face to face cognitive behavioural therapies in depressive disorders: A systematic review and meta-analysis. EClinicalMedicine, 2020;24:100442
13. Taylor CB, Fitzsimmons-Craft EE and Graham AK. Digital technology can revolutionize mental health services delivery: The COVID-19 crisis as a catalyst for change. Int J Eat Disord, 2020;53(7):1155-1157
14. Markowitz JC, Milrod B, Heckman TG, et al. Psychotherapy at a distance. American Journal of Psychiatry, 2020;178(3): 240-246
15. NHS digital. 2022. Available at: https://digital.nhs.uk/news/2022/latest-nhs-digital-figures-show-21.5-rise-in-number-of-people-accessing-talking-therapies-statistical-press-release [accessed October 2022]
16. NHS. Mental health. Available at: https://www.longtermplan.nhs.uk/areas-of-work/mental-health/ [accessed October 2022]