Data science for mental health: a UK perspective on a global challenge

McIntosh, Andrew M.; Stewart, Robert; John, Ann; Smith, Daniel J.; Davis, Katrina; Sudlow, Cathie; Corvin, Aiden; Nicodemus, Kristin K.; Kingdon, David; Hassan, Lamiece; Hotopf, Matthew; Lawrie, Stephen M.; Russ, Tom C.; Geddes, John; Wolpert, Miranda; Wölbert, Eva; Porteous, David J.

doi:10.1016/s2215-0366(16)30089-x

Cited by 49 publications

(44 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although we took into account potential confounding influences of age, gender and education, more complex analyses are required to investigate the multitude of other social, clinical, lifestyle and genetic factors that are likely to contribute to cognitive risk and resilience in psychiatric and neurological disorders. It will be possible to explore these in a multivariate explanatory framework using a range of data from baseline and follow‐up assessments in UK Biobank, as well as ongoing extensions to data linkage 34.…”

Section: Discussionmentioning

confidence: 99%

The ‘cognitive footprint’ of psychiatric and neurological conditions: cross‐sectional study in the UK Biobank cohort

Cullen

Smith

Deary

et al. 2017

Acta Psychiatr Scand

View full text Add to dashboard Cite

ObjectiveWe aimed to quantify the prevalence of cognitive impairment in adults with a history of mood disorder, schizophrenia, multiple sclerosis or Parkinson's disease, within a large general population cohort.MethodCross‐sectional study using UK Biobank data (n = 502 642). Psychiatric and neurological exposure status was ascertained via self‐reported diagnoses, hospital records and questionnaires. Impairment on reasoning, reaction time and memory tests was defined with reference to a single unexposed comparison group. Results were standardised for age and gender. Sensitivity analyses examined the influence of comorbidity, education, information sources and missing data.ResultsRelative to the unexposed group, cognitive impairment was least common in major depression (standardised prevalence ratios across tests = 1.00 [95% CI 0.98, 1.02] to 1.49 [95% CI 1.24, 1.79]) and most common in schizophrenia (1.89 [95% CI 1.47, 2.42] to 3.92 [95% CI 2.34, 6.57]). Prevalence in mania/bipolar was similar to that in multiple sclerosis and Parkinson's disease. Estimated population attributable prevalence of cognitive impairment was higher for major depression (256 per 100 000 [95% CI 130, 381]) than for all other disorders.ConclusionAlthough the relative prevalence of cognitive impairment was lowest in major depression, the population attributable prevalence was highest overall for this group.

show abstract

Section: Discussionmentioning

confidence: 99%

The ‘cognitive footprint’ of psychiatric and neurological conditions: cross‐sectional study in the UK Biobank cohort

Cullen

Smith

Deary

et al. 2017

Acta Psychiatr Scand

View full text Add to dashboard Cite

show abstract

“…The application of AI in psychiatry is a field that has received relatively little attention but has great potential for innovation [11]. Some proposals found in the literature are optimisation of the delivery of momentary cognitive-behavioural interventions [21], early identification of post-traumatic stress disorder [22] and analysis of social-network information for mental health research [23].…”

Section: Prior Workmentioning

confidence: 99%

“…Use of this data at scale is expected to make a pivotal contribution to the study of many diseases [11], especially those with complex longitudinal histories such as suicide. However, the sheer volume of data and the complexity of the suicide factors-risk model have proven to be a challenge for traditional epidemiological and statistical modelling methods.…”

Section: Introduction Backgroundmentioning

confidence: 99%

Using neural networks with routine health records to identify suicide risk (Preprint)

DelPozo-Baños¹,

John²,

Petkov³

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

Background: Every year approximately 800,000 people die by suicide worldwide, accounting for 1-2 in every 100 deaths. It is always a tragic event with a huge impact on family, friends, community and professionals. Unfortunately, suicide prevention and the development of risk assessment tools have been hindered by the complexity of the underlying mechanisms and the dynamic nature of people's motivations and intent. Many of those who die by suicide have had contact with health services in the preceding year but identifying those most at risk is a challenge. Objective:To explore the feasibility of using artificial neural networks (ANNs) based on routinely collected electronic health records (EHRs) to support the identification of those at high risk of suicide when in contact with health services. Methods:Using the Secure Anonymised Information Linkage Databank UK, we extracted those who died by suicide between 2001 and 2015 and paired controls. Looking at primary (general practice: GP) and secondary (hospital admissions) EHRs, we built a binary feature vector coding the presence of risk factors at different times before the contact leading to death. Risk factors included: GP contacts and hospital admissions; diagnosis of mental health, injury and poisoning, substance misuse, maltreatment or sleep disorder; and prescription of opiates or psychotropics. We trained simple ANNs to differentiate between cases and controls and interpreted the output score as the estimated suicide risk score. We assessed system performance with 10x10 K-Folds repeated cross-valadiation and studied system performance and behaviour by representing the distribution of estimated risk across cases and controls and the distribution of factors across different estimated risks. Results:We extracted a total of 2,604 suicide cases and 20 paired controls per case. Our system obtained an error rate of 26.78% ± 1.46 (64.57% of sensitivity and 81.86% of specificity). While the distribution of controls was concentrated around estimated risks < 0.5, cases where almost uniformly distributed between 0 and 1. Prescription of psychotropics, depression and anxiety and self-harm increased the estimated risk by ~0.4. At least 95% of those presenting these factors were identified cases. Conclusions:Despite the simplicity of the implemented system, the proposed methodology obtained an accuracy similar to other published methods based on specialized questionnaire generated data. Most of the errors came from the heterogeneity of patterns shown by cases, some of which were identical to those of controls. Prescription of psychotropics, depression and anxiety and self-harm were strongly linked with higher estimated risk scores, followed by hospital admission and long-term drugs and alcohol misuse. Other risk factors such as sleep disorder and maltreatment had more complex effects.

show abstract

“…In 2014, the CRIS system was extended to four more mental health trusts (in 16 local authorities) and could be extended beyond mental health to other services. 6 …”

Section: What Data Are Available?mentioning

confidence: 99%