No abstract

Much of the knowledge and information needed for enabling high-quality clinical research is stored in free-text format. Natural language processing (NLP) has been used to extract information from these sources at scale for several decades. This paper aims to present a comprehensive review of clinical NLP for the past 15 years in the UK to identify the community, depict its evolution, analyse methodologies and applications, and identify the main barriers. We collect a dataset of clinical NLP projects (n = 94; £ = 41.97 m) funded by UK funders or the European Union’s funding programmes. Additionally, we extract details on 9 funders, 137 organisations, 139 persons and 431 research papers. Networks are created from timestamped data interlinking all entities, and network analysis is subsequently applied to generate insights. 431 publications are identified as part of a literature review, of which 107 are eligible for final analysis. Results show, not surprisingly, clinical NLP in the UK has increased substantially in the last 15 years: the total budget in the period of 2019–2022 was 80 times that of 2007–2010. However, the effort is required to deepen areas such as disease (sub-)phenotyping and broaden application domains. There is also a need to improve links between academia and industry and enable deployments in real-world settings for the realisation of clinical NLP’s great potential in care delivery. The major barriers include research and development access to hospital data, lack of capable computational resources in the right places, the scarcity of labelled data and barriers to sharing of pretrained models.

Background and aims Individuals with schizophrenia may often experience poor sleep, self-stigma, impaired social functions, and problematic smartphone use. However, the temporal relationships between these factors have not been investigated. The present study used a longitudinal design to examine potential mediating roles of poor sleep and self-stigma in associations between problematic smartphone use and impaired social functions among individuals with schizophrenia. Methods From April 2019 to August 2021, 193 individuals with schizophrenia (mean [SD] age = 41.34 [9.01] years; 88 [45.6%] males) were recruited and asked to complete three psychometric scales: the Smartphone Application-Based Addiction Scale to assess problematic smartphone use; the Pittsburgh Sleep Quality Index to assess sleep quality; and the Self-Stigma Scale-Short Scale to assess self-stigma. Social functioning was evaluated by a psychiatrist using the Personal and Social Performance Scale. All measures were assessed five times (one baseline and four follow-ups) at three-month intervals between assessments. Results General estimating equations found that problematic smartphone use (coefficient = −0.096, SE = 0.021; P < 0.001), sleep quality (coefficient = −0.134, SE = 0.038; P < 0.001), and self-stigma (coefficient = −0.612, SE = 0.192; P = 0.001) were significant statistical predictors for social functioning. Moreover, sleep quality and self-stigma mediated associations between problematic smartphone use and social functioning. Conclusion Problematic smartphone use appears to impact social functioning longitudinally among individuals with schizophrenia via poor sleep and self-stigma concerns. Interventions aimed at reducing problematic smartphone use, improving sleep, and addressing self-stigma may help improve social functioning among individuals with schizophrenia.

Over the past two decades, smartphones have become common, and the accompanying devices have also become much more popular and easily accessible worldwide. With the development of smartphones, accompanied by internet facilities, excessive smartphone use or smartphone addiction may cause sleep disturbance and daily dysfunction. This study proposed examining the association between personality traits and smartphone addiction and its effects on sleep disturbance. Four hundred and twenty-two university participants (80 male and 342 female participants) with a mean age of 20.22 years old were recruited in this study. All participants were asked to complete the following questionnaires: Chinese Smartphone Addiction Inventory (CSPAI), Tri-dimensional personality questionnaire (TPQ), and Chinese Pittsburg Sleep Questionnaire Inventory (CPSQI). The results showed that people with a high tendency toward novelty seeking (NS) as a personality trait, compared to those with lower tendency toward NS, are more likely to become addicted to smartphone use. Moreover, those with a stronger trait of being NS and specific impulsivity factor were found to have higher total scores in the SPAI (p < 0.05). In addition, linear regression analysis showed that the individuals with higher scores for withdrawal symptoms on the SPAI and anticipatory worry factor on the TPQ tended to have higher CPSQI total scores (p < 0.05). This information may be useful for prevention in individuals with personality traits making them vulnerable to smartphone addiction and for designing intervention programs to reduce intensive smartphone use and programs to increase capability in managing smartphone use.