Understanding the relationship between patient language and outcomes in internet-enabled cognitive behavioural therapy: A deep learning approach to automatic coding of session transcripts.

Objective: Understanding patient responses to psychotherapy is important in developing effective interventions. However, coding patient language is a resource-intensive exercise and difficult to perform at scale. Our aim was to develop a deep learning model to automatically identify patient utterances during text-based internet-enabled Cognitive Behavioural Therapy and to determine the association between utterances and clinical outcomes. Method: Using 340 manually annotated transcripts we trained a deep learning model to categorize patient utterances into one or more of five categories. The model was used to automatically code patient utterances from our entire data set of transcripts (∼34,000 patients), and logistic regression analyses used to determine the association between both reliable improvement and engagement, and patient responses. Results: Our model reached human-level agreement on three of the five patient categories. Regression analyses revealed that increased counter change-talk (movement away from change) was associated with lower odds of both reliable improvement and engagement, while increased change-talk (movement towards change or self-exploration) was associated with increased odds of improvement and engagement. Conclusions: Deep learning provides an effective means of automatically coding patient utterances at scale. This approach enables the development of a data-driven understanding of the relationship between therapist and patient during therapy.

Cognitive impairment in depression: a systematic review and meta-analysis.

BACKGROUND: This review aimed to address the question of whether cognitive impairment should be considered a core feature of depression that may be a valuable target for treatment. METHOD: We conducted a systematic review and meta-analysis of cognitive function, assessed with a single neuropsychological test battery, the Cambridge Neuropsychological Test Automated Battery (CANTAB), in patients with depression during symptomatic and remitted states. Inclusion of studies comparing patients remitted from depression and controls enabled us to investigate whether cognitive impairment persists beyond episodes of low mood in depression. RESULTS: Our meta-analysis revealed significant moderate cognitive deficits in executive function, memory and attention in patients with depression relative to controls (Cohen's d effect sizes ranging from -0.34 to -0.65). Significant moderate deficits in executive function and attention (Cohen's d ranging from -0.52 to -0.61) and non-significant small/moderate deficits in memory (Cohen's d ranging from -0.22 to -0.54) were found to persist in patients whose depressive symptoms had remitted, indicating that cognitive impairment occurs separately from episodes of low mood in depression. CONCLUSIONS: Both low mood and cognitive impairment are associated with poor psychosocial functioning. Therefore, we argue that remediation of cognitive impairment and alleviation of depressive symptoms each play an important role in improving outcome for patients with depression. In conclusion, this systematic review and meta-analysis demonstrates that cognitive impairment represents a core feature of depression that cannot be considered an epiphenomenon that is entirely secondary to symptoms of low mood and that may be a valuable target for future interventions.

Impulsive aggression in adults with attention-deficit/hyperactivity disorder.

OBJECTIVE: DSM-IV criteria for attention-deficit/hyperactivity disorder (ADHD) include examples of 'impulsivity'. This term can refer to various dysfunctional behaviours, including some examples of aggressive behaviour. However, impulsive aggression is not included in the DSM-IV criteria for ADHD. The associations of impulsive aggression with ADHD were investigated. METHOD: Seventy-three male adults with DSM-IV ADHD, and their informants, completed questionnaires. Impulsive aggression was assessed by ratings of two criteria for borderline personality disorder (BPD), involving hot temper and/or self-harm. RESULTS: Logistic regression indicated that features of DSM-IV ADHD were predictors of comorbid impulsive aggression. However, compared with ADHD features, verbal IQ and comorbid psychopathology were more strongly associated with impulsive aggression. CONCLUSION: The findings support the inclusion of features of impulsive aggression, such as hot temper/short fuse, in the ADHD syndrome in adults. These overlap with features of BPD. The findings inform the selection of research samples.

Reinforcement and reversal learning in first-episode psychosis.

BACKGROUND: Abnormalities in reinforcement learning and reversal learning have been reported in psychosis, possibly secondary to subcortical dopamine abnormalities. METHODS: We studied simple discrimination (SD) learning and reversal learning in a sample of 119 first-episode psychosis patients from the Cambridge early psychosis service (CAMEO) and 107 control participants. We used data on reinforcement learning and reversal learning extracted from the Cambridge Neuropsychological Test Automated Battery Intradimensional-Extradimensional shift task, which measures cognitive flexibility but also involves simple reinforcement learning (SD learning) and reversal learning stages. We also gathered diagnostic information to examine whether there were any differences between patients ultimately diagnosed with schizophrenia-spectrum disorders and those diagnosed with affective psychosis. RESULTS: Psychosis patients demonstrated deficits in simple reinforcement learning (SD learning) and in reversal learning, with no differences between affective psychosis and schizophrenia-spectrum psychosis. There was a significant modest correlation between reversal errors and negative symptoms (Spearman rho = 0.3, P = .02). CONCLUSIONS: There are reinforcement learning abnormalities in first-episode psychosis, which correlate with negative symptoms, suggesting a possible role for orbitofrontal cortex and ventral striatal pathology in the pathogenesis of motivational deficits in psychosis.

Substantia nigra/ventral tegmental reward prediction error disruption in psychosis.

While dopamine systems have been implicated in the pathophysiology of schizophrenia and psychosis for many years, how dopamine dysfunction generates psychotic symptoms remains unknown. Recent theoretical interest has been directed at relating the known role of midbrain dopamine neurons in reinforcement learning, motivational salience and prediction error to explain the abnormal mental experience of psychosis. However, this theoretical model has yet to be explored empirically. To examine a link between psychotic experience, reward learning and dysfunction of the dopaminergic midbrain and associated target regions, we asked a group of first episode psychosis patients suffering from active positive symptoms and a group of healthy control participants to perform an instrumental reward conditioning experiment. We characterized neural responses using functional magnetic resonance imaging. We observed that patients with psychosis exhibit abnormal physiological responses associated with reward prediction error in the dopaminergic midbrain, striatum and limbic system, and we demonstrated subtle abnormalities in the ability of psychosis patients to discriminate between motivationally salient and neutral stimuli. This study provides the first evidence linking abnormal mesolimbic activity, reward learning and psychosis.

The neuropsychology of obsessive compulsive disorder: the importance of failures in cognitive and behavioural inhibition as candidate endophenotypic markers.

Obsessive compulsive disorder (OCD) is a highly debilitating neuropsychiatric condition with estimated lifetime prevalence of 2-3%, more than twice that of schizophrenia. However, in contrast to other neuropsychiatric conditions of a comparable or lesser prevalence, relatively little is understood about the aetiology, neural substrates and cognitive profile of OCD. Despite strong evidence for OCD being familial, with risk to first-degree relatives much greater than for the background population, its genetic underpinnings have not yet been adequately delineated. Although cognitive dysfunction is evident in the everyday behaviour of OCD sufferers and is central to contemporary psychological models, theory-based studies of neurocognitive function have yet to reveal a reliable cognitive signature, and interpretation has often been confounded by failures to control for co-morbidities. The neuroimaging findings in OCD are amongst the most robust reported in the psychiatric literature, with structural and functional abnormalities frequently reported in orbitofrontal cortex, anterior cingulate cortex, and caudate nucleus. In spite of this, our relative lack of understanding of OCD neurochemical processes continues to impede progress in the development of novel pharmacological treatment approaches. Integrating the neurobiological, cognitive, and clinical findings, we propose that OCD might usefully be conceptualised in terms of lateral orbitofrontal loop dysfunction, and that failures in cognitive and behavioural inhibitory processes appear to underlie many of the symptoms and neurocognitive findings. We highlight existing limitations in the literature, and the potential utility of endophenotypes in overcoming these limitations. We propose that neurocognitive indices of inhibitory functions may represent a useful heuristic in the search for endophenotypes in OCD. This has direct implications not only for OCD but also for putative obsessive-compulsive spectrum conditions including attention deficit hyperactivity disorder, Tourette's syndrome, and trichotillomania (compulsive hair pulling).

Quality of life in Parkinson's disease: movement disorders clinic vs general medical clinic--a comparative study.

OBJECTIVES: to determine the effect of attending a movement disorders (MD) clinic on quality of life (QOL) outcomes for patients with Parkinson's disease (PD). METHODS: Postal questionnaire study of forty-two patients with Parkinson's disease attending either a movement disorders clinic or more conventional general medical clinic were selected consecutively to complete the Parkinson's Disease Quality of Life Questionnaire (PDQL). All patients were diagnosed by a consultant physician with an interest in Parkinson's disease (S.B.R.) and had attended either the movement disorders clinic or the general medical clinic on at least three occasions. Questionnaires were completed independently of the examiners and returned by post. RESULTS: Mean PDQL score was 124.1 [5.16] in the movement disorders clinic and 95.9 [5.86] in the general medical clinic. Analysis of covariance revealed that those subjects attending the MD clinic reported a significantly higher QOL than those subjects in general medical care (F(1,39)= 161.98, P < 0.001). CONCLUSION: These data indicate that the quality of life of respondents attending the movement disorders clinic is significantly higher than those attending the general medical clinic.

Heterogeneity of Parkinson's disease in the early clinical stages using a data driven approach.

OBJECTIVE: To investigate the heterogeneity of idiopathic Parkinson's disease (PD) in a data driven manner among a cohort of patients in the early clinical stages of the disease meeting established diagnostic criteria. METHODS: Data on demographic, motor, mood, and cognitive measures were collected from 120 consecutive patients in the early stages of PD (Hoehn and Yahr I-III) attending a specialist PD research clinic. Statistical cluster analysis of the data allowed the existence of the patient subgroups generated to be explored. RESULTS: The analysis revealed four main subgroups: (a) patients with a younger disease onset; (b) a tremor dominant subgroup of patients; (c) a non-tremor dominant subgroup with significant levels of cognitive impairment and mild depression; and (d) a subgroup with rapid disease progression but no cognitive impairment. CONCLUSIONS: This study complements and extends previous research by using a data driven approach to define the clinical heterogeneity of early PD. The approach adopted in this study for the identification of subgroups of patients within Parkinson's disease has important implications for generating testable hypotheses on defining the heterogeneity of this common condition and its aetiopathological basis and thus its treatment.