Explore the vast range of titles available.

Introduction This study implemented MendelScan, a primary care rare disease case-finding tool, into a UK National Health Service population. Rare disease diagnosis is challenging due to disease complexity and low physician awareness. The 2021 UK Rare Diseases Framework highlights as a key priority the need for faster diagnosis to improve clinical outcomes. Methods and results A UK primary care locality with 68,705 patients was examined. MendelScan encodes diagnostic/screening criteria for multiple rare diseases, mapping clinical terms to appropriate SNOMED CT codes (UK primary care standardised clinical terminology) to create digital algorithms. These algorithms were applied to a pseudo-anonymised structured data extract of the electronic health records (EHR) in this locality to \"flag\" at-risk patients who may require further evaluation. All flagged patients then underwent internal clinical review (a doctor reviewing each EHR flagged by the algorithm, removing all cases with a clear diagnosis/diagnoses that explains the clinical features that led to the patient being flagged); for those that passed this review, a report was returned to their GP. 55 of 76 disease criteria flagged at least one patient. 227 (0.33%) of the total 68,705 of EHR were flagged; 18 EHR were already diagnosed with the disease (the highlighted EHR had a diagnostic code for the same RD it was screened for, e.g. Behcet’s disease algorithm identifying an EHR with a SNOMED CT code Behcet's disease). 75/227 (33%) EHR passed our internal review. Thirty-six reports were returned to the GP. Feedback was available for 28/36 of the reports sent. GP categorised nine reports as \"Reasonable possible diagnosis\" (advance for investigation), six reports as \"diagnosis has already been excluded\", ten reports as \"patient has a clear alternative aetiology\", and three reports as \"Other\" (patient left study locality, unable to re-identify accurately). All the 9 cases considered as \"reasonable possible diagnosis\" had further evaluation. Conclusions This pilot demonstrates that implementing such a tool is feasible at a population level. The case-finding tool identified credible cases which were subsequently referred for further investigation. Future work includes performance-based validation studies of diagnostic algorithms and the scalability of the tool.

Background Paroxysmal Nocturnal Haemoglobinuria (PNH) is an ultra-rare, acquired disorder that is challenging to diagnose due to varied symptoms, heterogeneous patient presentations, and lack of awareness among healthcare professionals. This leads to frequent misdiagnosis and delays in diagnosis. This study evaluated the feasibility of a machine learning model to identify undiagnosed PNH patients using structured electronic health records. Methods The study used data from the Optimum Patient Care Research Database, which contains electronic health records from general practitioner (GP) practices across the United Kingdom. PNH patients were identified by the presence, and control patients by the absence of a PNH diagnosis code in their records. Clinical features (symptoms, diagnoses, healthcare utilisation) from 131 patients in the PNH group and 593,838 patients in the control group, were inputted to a tree-based XGBoost machine learning model to classify patients as either “positive” or “negative” for PNH suspicion. The algorithm was finalised after additional exclusions and inclusions applied. Performance was assessed using positive predictive value (PPV), recall and specificity. As the sample used to develop the algorithm was not representative of the true population prevalence, PPV was additionally adjusted to reflect performance in the wider population. Results Of all the patients in the PNH group, 27% were classified as positive (recall). 99.99% of the control group were classified as negative (specificity). Of all the patients classified as positive, 60.4% had a diagnosis of PNH in their record (PPV). The PPV adjusted for the population prevalence of PNH was 19.59 suggesting nearly 1 in 5 patients flagged may warrant further PNH investigation. The key clinical features in the model were aplastic anaemia, pancytopenia, haemolytic anaemia, myelodysplastic syndrome, and Budd-Chiari syndrome. Conclusion This is the first study to combine clinical understanding of PNH with machine learning, demonstrating the ability to discriminate between PNH and control patients in retrospective electronic health records. With further investigation and validation, this algorithm could be deployed on live health data, potentially leading to earlier diagnosis for patients who currently experience long diagnostic delays or remain undiagnosed.

Abstract Context X-linked hypophosphatemia (XLH) is a rare genetic disorder causing renal phosphate wasting, which predicates musculoskeletal manifestations such as rickets. Diagnosis is often delayed. Objective To explore the recording of clinical features, and the diagnostic odyssey of children and adolescents with XLH in primary care electronic healthcare records (EHRs) in the United Kingdom. Methods Using the Optimum Patient Care Research Database, individuals aged 20 years or younger after January 1, 2000, at date of recorded XLH diagnosis were identified using Systematized Nomenclature of Medicine Clinical Terms (SNOMED)/Read codes and age-matched to 100 controls. Recording of XLH-related clinical features was summarized then compared between cases and controls using chi-squared or Fisher's exact test. Results In total, 261 XLH cases were identified; 99 met the inclusion criteria. Of these, 84/99 had at least 1 XLH-related clinical feature recorded in their primary care EHR. Clinical codes for rickets, genu varum, and low phosphate were recorded prior to XLH diagnosis in under 20% of cases (median of 1, 1, and 3 years prior, respectively). Rickets, genu varum, low phosphate, nephrocalcinosis, and growth delay were significantly more likely to be recorded in cases. Conclusion This characterization of the EHR phenotypes of children and adolescents with XLH may inform future case-finding approaches to expedite diagnosis in primary care.

Background Neuroendocrine tumours (NETs) are increasing in incidence, often diagnosed at advanced stages, and individuals may experience years of diagnostic delay, particularly when arising from the small intestine (SI). Clinical prediction models could present novel opportunities for case finding in primary care. Methods An open cohort of adults (18+ years) contributing data to the Optimum Patient Care Research Database between 1st Jan 2000 and 30th March 2023 was identified. This database collects de-identified data from general practices in the UK. Model development approaches comprised logistic regression, penalised regression, and XGBoost. Performance (discrimination and calibration) was assessed using internal-external cross-validation. Decision analysis curves compared clinical utility. Results Of 11.7 million individuals, 382 had recorded SI NET diagnoses (0.003%). The XGBoost model had the highest AUC (0.869, 95% confidence interval [CI]: 0.841–0.898) but was mildly miscalibrated (slope 1.165, 95% CI: 1.088–1.243; calibration-in-the-large 0.010, 95% CI: −0.164 to 0.185). Clinical utility was similar across all models. Discussion Multivariable prediction models may have clinical utility in identifying individuals with undiagnosed SI NETs using information in their primary care records. Further evaluation including external validation and health economics modelling may identify cost-effective strategies for case finding for this uncommon tumour.