Artificial intelligence, ChatGPT, and other large language models for social determinants of health: Current state and future directions.

This perspective highlights the importance of addressing social determinants of health (SDOH) in patient health outcomes and health inequity, a global problem exacerbated by the COVID-19 pandemic. We provide a broad discussion on current developments in digital health and artificial intelligence (AI), including large language models (LLMs), as transformative tools in addressing SDOH factors, offering new capabilities for disease surveillance and patient care. Simultaneously, we bring attention to challenges, such as data standardization, infrastructure limitations, digital literacy, and algorithmic bias, that could hinder equitable access to AI benefits. For LLMs, we highlight potential unique challenges and risks including environmental impact, unfair labor practices, inadvertent disinformation or "hallucinations," proliferation of bias, and infringement of copyrights. We propose the need for a multitiered approach to digital inclusion as an SDOH and the development of ethical and responsible AI practice frameworks globally and provide suggestions on bridging the gap from development to implementation of equitable AI technologies.

COVID-19-Related Vaccine Hesitancy among Community Hospitals' Healthcare Workers in Singapore.

COVID-19 has culminated in widespread infections and increased deaths over the last 3 years. In addition, it has also resulted in collateral economic and geopolitical tensions. Vaccination remains one of the cornerstones in the fight against COVID-19. Vaccine hesitancy must be critically evaluated in individual countries to promote vaccine uptake. We describe a survey conducted in three Singapore community hospitals looking at healthcare workers' vaccine hesitancy and the barriers for its uptake. The online anonymous survey was conducted from March to July 2021 on all staff across three community hospital sites in SingHealth Singapore. The questionnaire was developed following a scoping review and was pilot tested and finalized into a 58-item instrument capturing data on demographics, contextual features, knowledge, attitudes, perceptions, and other vaccine-related factors in the vaccine hesitancy matrix. Logistic regression analysis was employed for all co-variates that are significant in univariate analysis. The response rate was 23.9%, and the vaccine hesitancy prevalence was 48.5% in the initial phase of the pandemic. On logistic regression analysis, only being female, a younger age, not having had a loved one or friend infected with COVID-19 and obtaining information from newspapers were associated with vaccine hesitancy in healthcare workers in Singapore community hospitals.

Identifying heterogeneous health profiles of primary care utilizers and their differential healthcare utilization and mortality - a retrospective cohort study.

BACKGROUND: Heterogeneity of population health needs and the resultant difficulty in health care resources planning are challenges faced by primary care systems globally. To address this challenge in population health management, it is critical to have a better understanding of primary care utilizers' heterogeneous health profiles. We aimed to segment a population of primary care utilizers into classes with unique disease patterns, and to report the 1 year follow up healthcare utilizations and all-cause mortality across the classes. METHODS: Using de-identified administrative data, we included all adult Singapore citizens or permanent residents who utilized Singapore Health Services (SingHealth) primary care services in 2012. Latent class analysis was used to identify patient subgroups having unique disease patterns in the population. The models were assessed by Bayesian Information Criterion and clinical interpretability. We compared healthcare utilizations in 2013 and one-year all-cause mortality across classes and performed regression analysis to assess predictive ability of class membership on healthcare utilizations and mortality. RESULTS: We included 100,747 patients in total. The best model (k = 6) revealed the following classes of patients: Class 1 "Relatively healthy" (n = 58,213), Class 2 "Stable metabolic disease" (n = 26,309), Class 3 "Metabolic disease with vascular complications" (n = 2964), Class 4 "High respiratory disease burden" (n = 1104), Class 5 "High metabolic disease without complication" (n = 11,122), and Class 6 "Metabolic disease with multi-organ complication" (n = 1035). The six derived classes had different disease patterns in 2012 and 1 year follow up healthcare utilizations and mortality in 2013. "Metabolic disease with multiple organ complications" class had the highest healthcare utilization (e.g. incidence rate ratio = 19.68 for hospital admissions) and highest one-year all-cause mortality (hazard ratio = 27.97). CONCLUSIONS: Primary care utilizers are heterogeneous and can be segmented by latent class analysis into classes with unique disease patterns, healthcare utilizations and all-cause mortality. This information is critical to population level health resource planning and population health policy formulation.

Association of anemia and mineral and bone disorder with health-related quality of life in Asian pre-dialysis patients.

BACKGROUND: Patients with chronic kidney disease (CKD) have poor health-related quality of life (HRQoL). The association of CKD-related complications such as anemia and mineral and bone disorders (MBD) with HRQoL in pre-dialysis patients is not well-studied. As such, this study aimed to determine the association of anemia and MBD with HRQoL in pre-dialysis patients. METHODS: This was a cross-sectional study involving 311 adult pre-dialysis patients with stage 3-5 CKD from an acute-care hospital in Singapore. Patients' HRQoL were assessed using Kidney Disease Quality of Life Short Form (KDQOL-SF™) and EuroQol 5 Dimensions-3 levels (EQ5D-3L). HRQoL between patients with and without anemia or MBD were compared by separate hierarchical multiple linear regression analyses using various HRQoL scales as dependent variables, adjusted for sociodemographic, clinical and psychosocial variables. RESULTS: After adjusting for MBD, anemia was associated with lower HRQoL scores on work status (WS), physical functioning (PF) and role physical [ß (SE): -10.9 (4.18), p = 0.010; -3.0 (1.28), p = 0.018; and -4.2 (1.40), p = 0.003, respectively]. However, significance was lost after adjustments for sociodemographic variables. Patients with MBD had poorer HRQoL with respect to burden of kidney disease, WS, PF and general health [(ß (SE): -7.9 (3.88), p = 0.042; -9.5 (3.99), p = 0.018; -3.0 (1.22) p = 0.014; -3.6 (1.48), p = 0.015, respectively]. Although these remained significant after adjusting for sociodemographic variables, significance was lost after adjusting for clinical variables, particularly pill burden. This is of clinical importance due to the high pill burden of CKD patients, especially from medications for the management of multiple comorbidities such as cardiovascular and mineral and bone diseases. CONCLUSIONS: Neither anemia nor MBD was associated with HRQoL in our pre-dialysis patients. Instead, higher total daily pill burden was associated with worse HRQoL. Medication reconciliation should therefore be routinely performed by clinicians and pharmacists to reduce total daily pill burden where possible.