Purpose: This study examines the role of online customer reviews through text mining and sentiment analysis to improve customer satisfaction across various services within the UK banking sector. Additionally, the study analyses sentiment trends over a five-year period. Design/methodology/approach: Using DistilBERT and Support Vector Machine algorithms, customer sentiments were assessed through an analysis of 20,137 Trustpilot reviews of HSBC, Santander, and Tesco Bank from 2018 to 2023. Data pre-processing steps were implemented to ensure data integrity and minimize noise. Findings: Both positive and negative sentiments provide valuable insights. The results indicate a high prevalence of negative sentiments related to customer service and communication, with HSBC and Santander receiving 90.8% and 89.7% negative feedback, respectively, compared to Tesco Bank’s 66.8%. Key areas for improvement include HSBC’s credit card services and call center efficiency, which experienced increased negative feedback during the COVID-19 pandemic. The findings also demonstrate that DistilBERT excelled in categorizing reviews, while the SVM model, when combined with customer ratings, achieved 96% accuracy in sentiment analysis. Research limitations/implications: This study focuses on UK bank consumers of HSBC, Santander, and Tesco Bank. A multi-country or cross-cultural study may further enhance our understanding of the approaches and findings. Practical implications: Online customer reviews become more informative when categorised by service sector. To enhance customer satisfaction, bank managers should pay attention to both positive and negative reviews, and track trends over time. Originality/value: The uniqueness of this study lies in its exploration of the importance of categorisation in text-mining-based sentiment analysis, its focus on the influence of both positive and negative sentiments, and its emphasis on tracking sentiment trends over time.

Finding network biomarkers from gene co-expression networks (GCNs) has attracted a lot of research interest. A network biomarker is a topological module, i.e., a group of densely connected nodes in a GCN, in which the gene expression values correlate with sample labels. Compared with biomarkers based on single genes, network biomarkers are not only more robust in separating samples from different categories, but are also able to better interpret the molecular mechanism of the disease. The previous network biomarker detection methods either employ distance based clustering methods or search for cliques in a GCN to detect topological modules. The first strategy assumes that the topological modules should be spherical in shape, and the second strategy requires all nodes to be fully connected. However, the relations between genes are complex, as a result, genes in the same biological process may not be directly, strongly connected. Therefore, the shapes of those modules could be oval or long strips. Hence, the shapes of gene functional modules and gene disease modules may not meet the aforementioned constraints in the previous methods. Thus, previous methods may break up the genes belonging to the same biological process into different topological modules due to those constraints. To address this issue, we propose a novel network biomarker detection method by using Gaussian mixture model clustering which allows more flexibility in the shapes of the topological modules. We have evaluated the performance of our method on a set of eight TCGA cancer datasets. The results show that our method can detect network modules that possess better discriminate power, and provide biological insights.

This paper investigates the role of FDI in international knowledge diffusion with a focus on the evolution of the comparative advantage of FDI-host and FDI-source countries. We use data on 99 countries, which leads to 876 country pairs, over the 2001 to 2012 period. Spatial autoregressive (SAR) models are used to investigate the impact of bilateral FDI on the similarity of the comparative advantage between the host and source countries. Empirical results show that the effect of the bilateral FDI on the evolution of the comparative advantage of the host and source countries is statistically significant. Specifically, the larger the scale of bilateral FDI, the more similar the comparative advantage between the host and source countries becomes. We also find that the impact of FDI on international knowledge diffusion is heterogeneous across country pairs and this effect varies across the development gap between the source and host countries. In the case of countries that are not very different in terms of their level of economic development, bilateral FDI has a relatively more significant effect on the similarity of the comparative advantage between countries. Moreover, we find that the similarity of the comparative advantage is spatially correlated, and FDI linkages between country pairs strengthen the spatial correlations.

Background: Clinical and demographic predictors of intensive care unit (ICU) mortality risk in COVID-have been extensively characterised, yet the role of pre-admission environmental conditions in defining patient subgroups with distinct mortality risks remains unexplored. We used latent class analysis (LCA) to identify environmental subgroups among critically ill COVID-19 patients and examined how mortality risk and its clinical determinants vary across them.Methods: In this retrospective, multicentre cohort study, we analysed data from 1,166 adults admitted with PCR-confirmed COVID-19 to three Birmingham (UK) ICUs between March 2020 and February 2021. LCA was applied to pre-admission ambient temperature, relative humidity, and wind speed to derive discrete environmental profiles. Between-class mortality differences were quantified using relative risk (RR) estimation. Within each class, multivariable logistic regression examined covariate–mortality associations, adjusted for age, sex, ethnicity, deprivation, BMI, frailty, and Intensive Care National Audit Research Centre (ICNARC) Physiology Score. Findings were consistent in three sensitivity analyses addressing temporal confounding.Findings: Four environmentally distinct latent classes were identified. Relative to the reference class (moderate humidity; n=452), mortality was significantly elevated among patients admitted under warm, dry, and windy conditions (RR=1.62, 95% CI 1.14–2.29) and under mild temperatures with moderate-to-strong winds (RR=1.47, 95% CI 1.15–1.89). Associations between established clinical predictors and mortality varied significantly across classes.Interpretation: Pre-admission environmental conditions define distinct patient subgroups with systematically different mortality risks. Class-specific variation in the strength of established clinical predictors suggests that environmental context modifies how patient vulnerability translates into ICU mortality. These findings support further investigation of environmental profiling as a complementary dimension of ICU risk stratification, with potential applications in capacity planning during respiratory surges and pandemic preparedness.

Despite the global prevalence of postpartum depression (PPD), current referral uptake rates are far from satisfactory. While some qualitative studies have investigated factors affecting PPD referrals, a gap in quantitative analysis remains. Addressing this, our study utilized a discrete choice experiment (DCE) to understand the procedural elements influencing PPD referral uptake among diagnosed women. The DCE was conducted via home visits by healthcare providers and a comprehensive mobile app questionnaire. We constructed seven distinct referral attributes to explore participants’ preferences, analyzed using mixed logit models and latent class analysis. This analysis identified key determinants and revealed the heterogeneities in referral preferences. A total of 698 individuals completed the DCE questionnaire. All assessed attributes, except for Accompaniment (going to clinic with a family member), were important determinants of preference. Participants generally preferred referrals to psychiatric clinics, face-to-face consultations, lower costs, and shorter waiting times. Significantly, participants’ personal and socio-demographic characteristics also played a critical role in their referral preferences. Latent class analysis categorized participants into four distinct groups based on their preferences, with treatment cost and waiting times being the most decisive factors. In conclusion, the preference for PPD referrals is predominantly driven by convenience and access to specialist care. To enhance referral uptake, developing flexible and personalized referral programs that cater to these preferences is crucial.

Background: Coronavirus disease 2019 (COVID-19) continues to strain intensive care units (ICUs), particularly during seasonal surges and in conjunction with other respiratory infections. While clinical and demographic mortality predictors are well-established, the impact of environmental conditions remains less understood, especially at the individual level. We therefore analysed subgroups of ICU patients based on environmental conditions and evaluate differences in mortality risk. Methods: In this retrospective, multi-centre cohort study, we analysed data from 1,166 adults admitted with COVID-19 to three Birmingham (UK) ICUs between March 1, 2020, and February 28, 2021. Using latent class analysis (LCA), we grouped patients by ambient temperature, relative humidity, and wind speed preceding ICU admission. Associations between class membership and ICU mortality were assessed using multivariable logistic regression, adjusting for age, sex, ethnicity, deprivation, BMI, frailty, and ICNARC Physiology Score. Relative risk (RR) of mortality was compared across classes. Results: Four latent classes were identified. Two showed significantly increased mortality risk: one with high temperature and low humidity (RR=1.62, 95% CI: 1.14-2.29) and another with low temperature and moderate-to-high wind speed (RR=1.47, 95% CI: 1.15-1.89), compared to the reference class. Environmental and patient characteristics, particularly relative humidity, female sex, BMI, ICNARC score, and frailty, demonstrated class-specific associations with mortality. Conclusions: Environmental exposures prior to ICU admission contribute to mortality risk in critically ill COVID-19 patients. Incorporating these conditions into patient risk stratification could enhance clinical decision-making, particularly during public health emergencies.