ABSTRACT
ObjectivesNon-attendance of scheduled hospital appointments represents a major issue affecting service effectiveness, efficiency and quality of care costing the NHS over £1billion annually. This impact is even more detrimental at a time where the NHS is experiencing record high waiting times in the peri- COVID-19 pandemic era.Rather than a reactive model of discharging patients for nonattending their appointments, we propose a proactive model identifying patients at risk of not showing up and provide them with right support at the right time. This approach is especially important for vulnerable population including young people (YP) due to the complex interplay between developmental, socio-economic factors can impact significantly on their medical care.The increasing use of electronic health record systems (EHRS) and data availability creates opportunities to develop risk scores for specific patient populations.In this study, we aim to develop a machine learning approach to develop a complex, multi-dimensional predictive model to identify YP at risk of clinic nonattendance.MethodsUniversity College London Hospital (UCLH) switched to a new EHRS in April 2019 . We extracted data on outpatient Adolescent and Young Adult Rheumatology (AYAR) between 2019 -2022.Our primary outcome was nonattendance of a scheduled appointment.Our Predictor variables were defined after literature review, consultation with clinical and operational teams. We extracted data on 67 predictors of nonattendance. These variables are broadly divided into demographics (e.g, Age, Sex, ethnicity) and index of multiple deprivation (IMD) extracted from office of national statistics (ONS) database. We also included service utilisation history (e.g., previous history of clinic non-attendance.), appointment information (month, day, time, clinic codes), and patient engagement (e.g., active in MyChart [ online patient portal]).Using data from 11602 outpatient appointments in (AYAR) clinics at UCLH, we built and assessed the performance of a predictive model as to whether a YP would not attend a scheduled outpatient appointment. We used logistic regression analysis to fit and assess the Model built. We evaluated its fit based on discrimination and calibration.ResultsWe identified a total of 1517 clinic non-attendance out of total of 11602 (13.1%) appointment.Female/male ratio was 2.03 in non attendance group as compared to 2.33 in total clinic population.In terms of age group, 10% (606/5547) of clinics booked for YP aged 14–18 were not attended as compared to 15% (651/4282 ) in those aged [19–24].Feature engineering analysis revealed that the most significant factors were IMD followed by distance, previous history of Non-attendance, age group and appointment hour.ConclusionsAiming to identify YP at risk of Non-attendance, we used a step-by-step approach to build a model that can be applied using EHR and IMD data at the point of care. High proportion of YP nonattending their appointments were from deprived areas.Accurate stratification of non-attendance risk can provide us with unique opportunity for preventative interventions, supporting to most vulnerable YP and improve the use of resources within the wider system
ABSTRACT
Introduction: There is growing recognition of the impact of societal factors on health throughout a patient's lifespan. The COVID-19 pandemic has exposed the impact of racial disparity on health outcomes. Aims: We aimed to investigate the association between ethnicity and the multidisciplinary team (MDT) interventions for young people (YP) with complex care needs. Method: This retrospective, single-centre, cross-sectional study was conducted within the department of adolescent and young adult rheumatology at University College Hospital, London, between August 2019 and August 2021. We extracted demographic, clinical and laboratory data. The index of multiple deprivation was extracted from the Office for National Statistics database. R software was used for analysis. Results: We identified 310 YP referred to the MDT with a median age of 18 years (interquartile range 17-19). The female patient to male patient ratio was 2.4. Over a third of our cohort were from deprived areas. Comparison between Black, Asian and minority ethnic (BAME) and White ethnic groups revealed significant differences in terms of referral for pain optimisation (p=0.006), social support (p<0.00001), and adherence and non-clinic attendance (p=0.0004). Conclusion: Our findings reveal the importance of quality data for early identification and support of vulnerable YP, particularly those from BAME communities.
ABSTRACT
Background/Aims Chilblain-like lesions (perniosis) have been reported frequently during COVID-19 pandemic in children and adolescents with no history of exposure to cold temperatures or underlying autoimmune conditions. Patients with these skin changes reported mild COVID-19 symptoms or previous contact with confirmed COVID-19 cases before they became symptomatic. In the majority of cases, a causal relationship between SARS-CoV-2 infection and chilblain-like lesion has not been proven. Methods Retrospective review of patients with chilblain-like lesions, possibly secondary to SARS-CoV-2 infection, presenting to a tertiary Adolescent Rheumatology service between January and August 2021. Results We identified five, male, adolescent patients (mean age, 16 years old) who presented with new onset of chilblain-like lesions affecting fingers, toes and heels in December 2020, which coincided with the peak of second wave of COVID-19 infection. One month prior to skin changes occurrence, 3 out of 5 patients experienced mild respiratory COVID-19-like symptoms and the rest of the patients were asymptomatic but were in contact with COVID-19 positive cases following outbreaks in schools. 1 of 3 symptomatic patients had a positive COVID-19 PCR test prior to skin manifestations. 2 out of 4 patients with heel lesions had deep, full thickness skin loss heel ulcers and 2 of 5 patients had superficially ulcerated lesions on a finger and toes, respectively, resulting in inability to attend school. None of the patients had any other symptoms or signs to suggest an underlying autoimmune connective tissue disorder. Demographics, clinical features and serological data are summarised in Table 1. One patient underwent a biopsy of heel ulcer which was histologically consistent with perniosis. In two patients (40%) chilblain like lesions resolved spontaneously within 2 months. Three patients (60%), with progressive ulcerated lesions, required various combinations of treatments with aspirin, calcium channel blockers (nifedipine), topical or oral steroids and hydroxychloroquine with complete resolution of symptoms within 6 months. Conclusion Chilblain-like lesions, including heel involvement associated with mildly symptomatic COVID-19 infection, have been reported before. Our mini-case series raises awareness of ulcerating chilblain like lesions possibly secondary to COVID-19 in adolescent patients, which require early recognition and instigation of treatment leading to better patient’s outcomes. P167 Table 1 Demographics, clinical, laboratory findings of patientsCaseAgeLesion locationCOVID-19 symptomsSARS-CoV-2 PCR / SARS-CoV-2 AbAutoimmune profile/ complement levelsTreatment/ skin symptoms resolution (months)116Fingers, toes, heelsNoNA/ NegativeANA positive (1:80) ENA negative anti-dsDNA normal, C3, C4 normalAspirin, prednisolone, nifedipine, hydroxychloroquine /6216fingers heels, toesNoNA/ NegativeANA negativePrednisolone, nifedipine/6318Toes, heelsrespiratoryPositive/NAANA negativeNil/1416Fingers, toesrespiratoryNegative/ NegativeANA positive (1:320) ENA negative anti- dsDNA normal C3, C4 normalNil/2516Fingers, toes, heelsrespiratoryNA/ NegativeANA negativenifedipine/6 NA: not available, PCR: polymerase chain reaction, SARS-CoV-2: severe acute respiratory syndrome coronavirus 2 Disclosure N. Gak: None. V. Choida: None. M. Leandro: None. D. Sen: None. C. Ciurtin: None. C. Fisher: None.