Prodromal symptoms of rheumatoid arthritis in a primary care database: variation by ethnicity and socioeconomic status.

OBJECTIVES: To assess whether prodromal symptoms of rheumatoid arthritis (RA), as recorded in the Clinical Practice Research Datalink Aurum (CPRD) database of English primary care records, differ by ethnicity and socioeconomic status. METHODS: A cross-sectional study to determine the coding of common symptoms (≥0.1% in the sample) in the 24 months preceding RA diagnosis in CPRD Aurum, recorded between January 1st 2004 to May 1st 2022. Eligible cases were adults with a code for RA diagnosis. For each symptom, a logistic regression was performed with the symptom as dependent variable, and ethnicity and socioeconomic status as independent variables. Results were adjusted for sex, age, BMI, and smoking status. White ethnicity and the highest socioeconomic quintile were comparators. RESULTS: In total, 70115 cases were eligible for inclusion, of which 66.4% female. Twenty-one symptoms were coded in > 0.1% of cases so were included in the analysis. Patients of South Asian ethnicity had higher frequency of codes for several symptoms, with the largest difference by odds ratio being muscle cramps (OR 1.71, 1.44-2.57) and shoulder pain (1.44, 1.25-1.66). Patients of Black ethnicity had higher prevalence of several codes including unintended weight loss (2.02, 1.25-3.28) and ankle pain (1.51, 1.02-2.23). Low socioeconomic status was associated with morning stiffness (1.74, 1.08-2.80) and falls (1.37, 2.03-1.82). CONCLUSION: There are significant differences in coded symptoms between demographic groups, which must be considered in clinical practice in diverse populations and to avoid algorithmic bias in prediction tools derived from routinely collected healthcare data.

Perceptions on artificial intelligence-based decision-making for coexisting multiple long-term health conditions: protocol for a qualitative study with patients and healthcare professionals.

INTRODUCTION: Coexisting multiple health conditions is common among older people, a population that is increasing globally. The potential for polypharmacy, adverse events, drug interactions and development of additional health conditions complicates prescribing decisions for these patients. Artificial intelligence (AI)-generated decision-making tools may help guide clinical decisions in the context of multiple health conditions, by determining which of the multiple medication options is best. This study aims to explore the perceptions of healthcare professionals (HCPs) and patients on the use of AI in the management of multiple health conditions. METHODS AND ANALYSIS: A qualitative study will be conducted using semistructured interviews. Adults (≥18 years) with multiple health conditions living in the West Midlands of England and HCPs with experience in caring for patients with multiple health conditions will be eligible and purposively sampled. Patients will be identified from Clinical Practice Research Datalink (CPRD) Aurum; CPRD will contact general practitioners who will in turn, send a letter to patients inviting them to take part. Eligible HCPs will be recruited through British HCP bodies and known contacts. Up to 30 patients and 30 HCPs will be recruited, until data saturation is achieved. Interviews will be in-person or virtual, audio recorded and transcribed verbatim. The topic guide is designed to explore participants' attitudes towards AI-informed clinical decision-making to augment clinician-directed decision-making, the perceived advantages and disadvantages of both methods and attitudes towards risk management. Case vignettes comprising a common decision pathway for patients with multiple health conditions will be presented during each interview to invite participants' opinions on how their experiences compare. Data will be analysed thematically using the Framework Method. ETHICS AND DISSEMINATION: This study has been approved by the National Health Service Research Ethics Committee (Reference: 22/SC/0210). Written informed consent or verbal consent will be obtained prior to each interview. The findings from this study will be disseminated through peer-reviewed publications, conferences and lay summaries.

Artificial intelligence and health inequities in primary care: a systematic scoping review and framework.

OBJECTIVE: Artificial intelligence (AI) will have a significant impact on healthcare over the coming decade. At the same time, health inequity remains one of the biggest challenges. Primary care is both a driver and a mitigator of health inequities and with AI gaining traction in primary care, there is a need for a holistic understanding of how AI affect health inequities, through the act of providing care and through potential system effects. This paper presents a systematic scoping review of the ways AI implementation in primary care may impact health inequity. DESIGN: Following a systematic scoping review approach, we searched for literature related to AI, health inequity, and implementation challenges of AI in primary care. In addition, articles from primary exploratory searches were added, and through reference screening.The results were thematically summarised and used to produce both a narrative and conceptual model for the mechanisms by which social determinants of health and AI in primary care could interact to either improve or worsen health inequities.Two public advisors were involved in the review process. ELIGIBILITY CRITERIA: Peer-reviewed publications and grey literature in English and Scandinavian languages. INFORMATION SOURCES: PubMed, SCOPUS and JSTOR. RESULTS: A total of 1529 publications were identified, of which 86 met the inclusion criteria. The findings were summarised under six different domains, covering both positive and negative effects: (1) access, (2) trust, (3) dehumanisation, (4) agency for self-care, (5) algorithmic bias and (6) external effects. The five first domains cover aspects of the interface between the patient and the primary care system, while the last domain covers care system-wide and societal effects of AI in primary care. A graphical model has been produced to illustrate this. Community involvement throughout the whole process of designing and implementing of AI in primary care was a common suggestion to mitigate the potential negative effects of AI. CONCLUSION: AI has the potential to affect health inequities through a multitude of ways, both directly in the patient consultation and through transformative system effects. This review summarises these effects from a system tive and provides a base for future research into responsible implementation.

Predictive and prognostic properties of TB-LAM among HIV-positive patients initiating ART in Johannesburg, South Africa.

While the diagnostic properties of the TB LAM urine assay (LAM) have been well-described, little is known about its predictive and prognostic properties at ART initiation in a routine clinic setting. We describe the predictive and prognostic properties of LAM in HIV-positive patients initiating ART at an urban hospital in Johannesburg, South Africa. Retrospective study of HIV-positive adults (>18 years) who initiated standard first-line ART between February 2012 and April 2013 and had a LAM test at initiation. In HIV-positive patients with no known TB at ART initiation, we assessed the sensitivity, specificity and positive/negative likelihood ratios of LAM to predict incident TB within 6 months of ART initiation. In addition, in patients with a TB diagnosis and on TB treatment <3 months at ART initiation, we measured the CD4 response at 6 months on ART. Of the 274 patients without TB at ART initiation, 65% were female with median CD4 count of 213 cells/mm(3). Among the 14 (5.1%) patients who developed active TB, none were urine LAM +ve at baseline. LAM had poor sensitivity (0.0% 95% CI 0.00-23.2) to predict incident TB within 6 months of initiation. We analyzed 22 patients with a confirmed TB diagnosis at initiation separately. Of these, LAM +ve patients (27%) showed lower CD4 gains compared to LAM negative patients (median increase 103 vs 199 cells/mm(3); p = 0.08). LAM has limited value for accurately predicting incident TB in patients with higher CD4 counts after ART initiation. LAM may help identify TB/HIV co-infected patients at ART initiation who respond more slowly to treatment and require targeted interventions to improve treatment outcomes. Larger studies with longer patient follow-up are needed.