Text mining reveals link between negative symptoms and length of hospital stays in people with schizophrenia

Research from the NIHR Maudsley Biomedical Research Centre (BRC) has found that people with schizophrenia who experience negative symptoms are more likely to be admitted to hospital, and to stay in hospital for longer.

People with schizophrenia can experience a wide range of symptoms, which broadly fall into three categories.  Negative symptoms involve disruption to normal emotions and behaviour, and include poor motivation, social and emotional withdrawal, and blunt or flattened mood.  Positive symptoms include experiences and behaviour not usually present in healthy people, including hallucinations and thought disorders. Cognitive symptoms include problems with attention or memory.

The study is the largest ever to investigate a relationship between negative symptoms and clinical outcomes, and draws from the experiences of  more than 7,500 patients.
Researchers used the Clinical Record Interactive Search (CRIS) application, a text-mining tool, to analyse anonymised patient data on negative symptoms from the South London and Maudsley NHS Foundation Trust (SLaM) Biomedical Research Centre (BRC) Case Register.

Natural Language Processing (NLP) – a technique which uses sophisticated computing techniques to process written language – was used to detect statements within the clinical records of people with schizophrenia which referred to specific negative symptoms of the illness. 10 negative symptoms were identified this way, including poor motivation, blunted or flattened mood, poor eye contact, emotional withdrawal, poor rapport, social withdrawal, poverty of speech (excessively short speech with minimal elaborations), inability to speak, apathy and concrete thinking (the inability to think in abstract terms). 

The researchers found that two out of every five (41%)  patients reported experiencing two or more negative symptoms. Negative symptoms across the sample were associated with an increased likelihood of hospital admission, longer duration of admission and an increased likelihood of re-admission following discharge from hospital. 

Patients with two or more negative symptoms were 24 per cent more likely to have been admitted to hospital. In addition, each of their admissions were, on average, an extra 21 days in duration and, when discharged, these individuals had a 58 per cent higher risk of re-admission within 12 months. 

The most frequently recorded negative symptoms were poor motivation, blunted or flattened mood, poor eye contact and emotional withdrawal.

Dr Rashmi Patel from the Department of Psychosis Studies at the Institute of Psychiatry, Psychology & Neuroscience, said: ‘Hospital admissions are the main drivers of cost in the care of patients with schizophrenia – yet they have traditionally been linked to the severity of positive psychotic symptoms.

‘Our data indicate that negative symptoms are an equally important factor, and suggest that a greater emphasis on assessing and treating these features of schizophrenia may have significant health economic benefits.

'However, as our findings are drawn from observational data, interventional clinical studies are required to determine whether an effective treatment for negative symptoms would lead to better clinical outcomes.' 

This research was funded by the National Institute for Health Research (NIHR) Biomedical Research Centre (BRC) at the South London and Maudsley NHS Foundation Trust (SLaM) and King's College London.

The research is published in BMJ Open journal.

Tags: Clinical disorders and health behaviours - Informatics - Psychosis & neuropsychiatry - Clinical and population informatics -

By NIHR Maudsley BRC at 9 Sep 2015, 16:01 PM

Back to Blog List